Diff of the two buildlogs: -- --- b1/build.log 2024-05-12 20:31:46.074137836 +0000 +++ b2/build.log 2024-05-12 21:55:58.147127364 +0000 @@ -1,6 +1,6 @@ I: pbuilder: network access will be disabled during build -I: Current time: Sat Jun 14 14:40:50 -12 2025 -I: pbuilder-time-stamp: 1749955250 +I: Current time: Mon May 13 10:31:49 +14 2024 +I: pbuilder-time-stamp: 1715545909 I: Building the build Environment I: extracting base tarball [/var/cache/pbuilder/trixie-reproducible-base.tgz] I: copying local configuration @@ -27,52 +27,84 @@ dpkg-source: info: applying auto-gitignore I: Not using root during the build. I: Installing the build-deps -I: user script /srv/workspace/pbuilder/1314568/tmp/hooks/D02_print_environment starting +I: user script /srv/workspace/pbuilder/1797627/tmp/hooks/D01_modify_environment starting +debug: Running on ionos1-amd64. +I: Changing host+domainname to test build reproducibility +I: Adding a custom variable just for the fun of it... +I: Changing /bin/sh to bash +'/bin/sh' -> '/bin/bash' +lrwxrwxrwx 1 root root 9 May 12 20:32 /bin/sh -> /bin/bash +I: Setting pbuilder2's login shell to /bin/bash +I: Setting pbuilder2's GECOS to second user,second room,second work-phone,second home-phone,second other +I: user script /srv/workspace/pbuilder/1797627/tmp/hooks/D01_modify_environment finished +I: user script /srv/workspace/pbuilder/1797627/tmp/hooks/D02_print_environment starting I: set - BUILDDIR='/build/reproducible-path' - BUILDUSERGECOS='first user,first room,first work-phone,first home-phone,first other' - BUILDUSERNAME='pbuilder1' - BUILD_ARCH='amd64' - DEBIAN_FRONTEND='noninteractive' - DEB_BUILD_OPTIONS='buildinfo=+all reproducible=+all parallel=42 ' - DISTRIBUTION='trixie' - HOME='/root' - HOST_ARCH='amd64' + BASH=/bin/sh + BASHOPTS=checkwinsize:cmdhist:complete_fullquote:extquote:force_fignore:globasciiranges:globskipdots:hostcomplete:interactive_comments:patsub_replacement:progcomp:promptvars:sourcepath + BASH_ALIASES=() + BASH_ARGC=() + BASH_ARGV=() + BASH_CMDS=() + BASH_LINENO=([0]="12" [1]="0") + BASH_LOADABLES_PATH=/usr/local/lib/bash:/usr/lib/bash:/opt/local/lib/bash:/usr/pkg/lib/bash:/opt/pkg/lib/bash:. + BASH_SOURCE=([0]="/tmp/hooks/D02_print_environment" [1]="/tmp/hooks/D02_print_environment") + BASH_VERSINFO=([0]="5" [1]="2" [2]="21" [3]="1" [4]="release" [5]="x86_64-pc-linux-gnu") + BASH_VERSION='5.2.21(1)-release' + BUILDDIR=/build/reproducible-path + BUILDUSERGECOS='second user,second room,second work-phone,second home-phone,second other' + BUILDUSERNAME=pbuilder2 + BUILD_ARCH=amd64 + DEBIAN_FRONTEND=noninteractive + DEB_BUILD_OPTIONS='buildinfo=+all reproducible=+all parallel=20 ' + DIRSTACK=() + DISTRIBUTION=trixie + EUID=0 + FUNCNAME=([0]="Echo" [1]="main") + GROUPS=() + HOME=/root + HOSTNAME=i-capture-the-hostname + HOSTTYPE=x86_64 + HOST_ARCH=amd64 IFS=' ' - INVOCATION_ID='880b57d528174da9a1f6900919dd1a4c' - LANG='C' - LANGUAGE='en_US:en' - LC_ALL='C' - MAIL='/var/mail/root' - OPTIND='1' - PATH='/usr/sbin:/usr/bin:/sbin:/bin:/usr/games' - PBCURRENTCOMMANDLINEOPERATION='build' - PBUILDER_OPERATION='build' - PBUILDER_PKGDATADIR='/usr/share/pbuilder' - PBUILDER_PKGLIBDIR='/usr/lib/pbuilder' - PBUILDER_SYSCONFDIR='/etc' - PPID='1314568' - PS1='# ' - PS2='> ' + INVOCATION_ID=09093696b88a493685b1415e225ce7eb + LANG=C + LANGUAGE=et_EE:et + LC_ALL=C + MACHTYPE=x86_64-pc-linux-gnu + MAIL=/var/mail/root + OPTERR=1 + OPTIND=1 + OSTYPE=linux-gnu + PATH=/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/i/capture/the/path + PBCURRENTCOMMANDLINEOPERATION=build + PBUILDER_OPERATION=build + PBUILDER_PKGDATADIR=/usr/share/pbuilder + PBUILDER_PKGLIBDIR=/usr/lib/pbuilder + PBUILDER_SYSCONFDIR=/etc + PIPESTATUS=([0]="0") + POSIXLY_CORRECT=y + PPID=1797627 PS4='+ ' - PWD='/' - SHELL='/bin/bash' - SHLVL='2' - SUDO_COMMAND='/usr/bin/timeout -k 18.1h 18h /usr/bin/ionice -c 3 /usr/bin/nice /usr/sbin/pbuilder --build --configfile /srv/reproducible-results/rbuild-debian/r-b-build.hIZ4oAEg/pbuilderrc_YVOu --distribution trixie --hookdir /etc/pbuilder/first-build-hooks --debbuildopts -b --basetgz /var/cache/pbuilder/trixie-reproducible-base.tgz --buildresult /srv/reproducible-results/rbuild-debian/r-b-build.hIZ4oAEg/b1 --logfile b1/build.log librsb_1.3.0.2+dfsg-6.1.dsc' - SUDO_GID='110' - SUDO_UID='105' - SUDO_USER='jenkins' - TERM='unknown' - TZ='/usr/share/zoneinfo/Etc/GMT+12' - USER='root' - _='/usr/bin/systemd-run' - http_proxy='http://213.165.73.152:3128' + PWD=/ + SHELL=/bin/bash + SHELLOPTS=braceexpand:errexit:hashall:interactive-comments:posix + SHLVL=3 + SUDO_COMMAND='/usr/bin/timeout -k 24.1h 24h /usr/bin/ionice -c 3 /usr/bin/nice -n 11 /usr/bin/unshare --uts -- /usr/sbin/pbuilder --build --configfile /srv/reproducible-results/rbuild-debian/r-b-build.hIZ4oAEg/pbuilderrc_Gp9Z --distribution trixie --hookdir /etc/pbuilder/rebuild-hooks --debbuildopts -b --basetgz /var/cache/pbuilder/trixie-reproducible-base.tgz --buildresult /srv/reproducible-results/rbuild-debian/r-b-build.hIZ4oAEg/b2 --logfile b2/build.log librsb_1.3.0.2+dfsg-6.1.dsc' + SUDO_GID=110 + SUDO_UID=105 + SUDO_USER=jenkins + TERM=unknown + TZ=/usr/share/zoneinfo/Etc/GMT-14 + UID=0 + USER=root + _='I: set' + http_proxy=http://46.16.76.132:3128 I: uname -a - Linux ionos5-amd64 6.6.13+bpo-amd64 #1 SMP PREEMPT_DYNAMIC Debian 6.6.13-1~bpo12+1 (2024-02-15) x86_64 GNU/Linux + Linux i-capture-the-hostname 6.1.0-21-amd64 #1 SMP PREEMPT_DYNAMIC Debian 6.1.90-1 (2024-05-03) x86_64 GNU/Linux I: ls -l /bin - lrwxrwxrwx 1 root root 7 Jun 13 17:46 /bin -> usr/bin -I: user script /srv/workspace/pbuilder/1314568/tmp/hooks/D02_print_environment finished + lrwxrwxrwx 1 root root 7 May 11 11:25 /bin -> usr/bin +I: user script /srv/workspace/pbuilder/1797627/tmp/hooks/D02_print_environment finished -> Attempting to satisfy build-dependencies -> Creating pbuilder-satisfydepends-dummy package Package: pbuilder-satisfydepends-dummy @@ -289,7 +321,7 @@ Get: 169 http://deb.debian.org/debian trixie/main amd64 libltdl-dev amd64 2.4.7-7+b1 [164 kB] Get: 170 http://deb.debian.org/debian trixie/main amd64 libhwloc-dev amd64 2.10.0-1+b1 [250 kB] Get: 171 http://deb.debian.org/debian trixie/main amd64 zlib1g-dev amd64 1:1.3.dfsg-3.1 [918 kB] -Fetched 358 MB in 4s (87.5 MB/s) +Fetched 358 MB in 13s (27.4 MB/s) debconf: delaying package configuration, since apt-utils is not installed Selecting previously unselected package liblocale-gettext-perl. (Reading database ... (Reading database ... 5% (Reading database ... 10% (Reading database ... 15% (Reading database ... 20% (Reading database ... 25% (Reading database ... 30% (Reading database ... 35% (Reading database ... 40% (Reading database ... 45% (Reading database ... 50% (Reading database ... 55% (Reading database ... 60% (Reading database ... 65% (Reading database ... 70% (Reading database ... 75% (Reading database ... 80% (Reading database ... 85% (Reading database ... 90% (Reading database ... 95% (Reading database ... 100% (Reading database ... 19700 files and directories currently installed.) @@ -853,8 +885,8 @@ Setting up tzdata (2024a-4) ... Current default time zone: 'Etc/UTC' -Local time is now: Sun Jun 15 02:41:52 UTC 2025. -Universal Time is now: Sun Jun 15 02:41:52 UTC 2025. +Local time is now: Sun May 12 20:35:31 UTC 2024. +Universal Time is now: Sun May 12 20:35:31 UTC 2024. Run 'dpkg-reconfigure tzdata' if you wish to change it. Setting up libfontenc1:amd64 (1:1.1.8-1) ... @@ -1021,7 +1053,11 @@ Building tag database... -> Finished parsing the build-deps I: Building the package -I: Running cd /build/reproducible-path/librsb-1.3.0.2+dfsg/ && env PATH="/usr/sbin:/usr/bin:/sbin:/bin:/usr/games" HOME="/nonexistent/first-build" dpkg-buildpackage -us -uc -b && env PATH="/usr/sbin:/usr/bin:/sbin:/bin:/usr/games" HOME="/nonexistent/first-build" dpkg-genchanges -S > ../librsb_1.3.0.2+dfsg-6.1_source.changes +I: user script /srv/workspace/pbuilder/1797627/tmp/hooks/A99_set_merged_usr starting +Not re-configuring usrmerge for trixie +I: user script /srv/workspace/pbuilder/1797627/tmp/hooks/A99_set_merged_usr finished +hostname: Name or service not known +I: Running cd /build/reproducible-path/librsb-1.3.0.2+dfsg/ && env PATH="/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/i/capture/the/path" HOME="/nonexistent/second-build" dpkg-buildpackage -us -uc -b && env PATH="/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/i/capture/the/path" HOME="/nonexistent/second-build" dpkg-genchanges -S > ../librsb_1.3.0.2+dfsg-6.1_source.changes dpkg-buildpackage: info: source package librsb dpkg-buildpackage: info: source version 1.3.0.2+dfsg-6.1 dpkg-buildpackage: info: source distribution unstable @@ -1049,62 +1085,62 @@ cp: warning: behavior of -n is non-portable and may change in future; use --update=none instead cp: warning: behavior of -n is non-portable and may change in future; use --update=none instead dh_autoreconf -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found libtoolize: putting auxiliary files in '.'. libtoolize: copying file './ltmain.sh' libtoolize: putting macros in AC_CONFIG_MACRO_DIRS, 'm4'. @@ -1146,90 +1182,90 @@ libtoolize: copying file 'm4/ltsugar.m4' libtoolize: copying file 'm4/ltversion.m4' libtoolize: copying file 'm4/lt~obsolete.m4' -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found configure.ac:66: installing './compile' configure.ac:65: installing './missing' Makefile.am: installing './depcomp' @@ -1412,7 +1448,7 @@ checking for m4... m4 checking for gmake... gmake checking for ggrep... /usr/bin/grep -checking for bash... /bin/bash +checking for bash... /bin/sh checking for gsed... /usr/bin/sed checking for cmp... cmp checking for basename... basename @@ -1529,7 +1565,7 @@ configure: It appears that Fortran programs can be linked without using the Fortran linker. configure: Using OPENMP_CFLAGS ok for linking an OpenMP program: adding it to LIBS. checking if your have a usable getrusage() ... 1 -checking for /bin/bash... /bin/bash +checking for /bin/sh... /bin/sh configure: Will not use Google Test. configure: You seem to not have GNU Octave or have disabled 'int' type. Part of the test suite will not be generated. If you want more testing capabilities, you should enable the 'int' type as well. checking that generated files are newer than configure... done @@ -1551,7 +1587,7 @@ config.status: executing depfiles commands config.status: executing libtool commands === configuring in librsbpp (/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp) -configure: running /bin/bash ./configure --disable-option-checking '--prefix=/usr' '--build=x86_64-linux-gnu' '--includedir=${prefix}/include' '--mandir=${prefix}/share/man' '--infodir=${prefix}/share/info' '--sysconfdir=/etc' '--localstatedir=/var' '--disable-silent-rules' '--libdir=${prefix}/lib/x86_64-linux-gnu' '--runstatedir=/run' '--disable-maintainer-mode' '--disable-dependency-tracking' '--with-hwloc' '--enable-matrix-types=blas' '--with-zlib=-lz' '--enable-doc-build' '--enable-fortran-module-install' '--enable-extra-patches' '--enable-pkg-config-install' '--disable-extra-patches' 'build_alias=x86_64-linux-gnu' 'CFLAGS=-g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3' 'LDFLAGS=-Wl,-z,relro' 'CPPFLAGS=-Wdate-time -D_FORTIFY_SOURCE=2' 'FCFLAGS=-g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe' 'CXXFLAGS=-g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection' 'BASH=/bin/bash' --cache-file=/dev/null --srcdir=. +configure: running /bin/sh ./configure --disable-option-checking '--prefix=/usr' '--build=x86_64-linux-gnu' '--includedir=${prefix}/include' '--mandir=${prefix}/share/man' '--infodir=${prefix}/share/info' '--sysconfdir=/etc' '--localstatedir=/var' '--disable-silent-rules' '--libdir=${prefix}/lib/x86_64-linux-gnu' '--runstatedir=/run' '--disable-maintainer-mode' '--disable-dependency-tracking' '--with-hwloc' '--enable-matrix-types=blas' '--with-zlib=-lz' '--enable-doc-build' '--enable-fortran-module-install' '--enable-extra-patches' '--enable-pkg-config-install' '--disable-extra-patches' 'build_alias=x86_64-linux-gnu' 'CFLAGS=-g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3' 'LDFLAGS=-Wl,-z,relro' 'CPPFLAGS=-Wdate-time -D_FORTIFY_SOURCE=2' 'FCFLAGS=-g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe' 'CXXFLAGS=-g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection' 'BASH=/bin/sh' --cache-file=/dev/null --srcdir=. checking for a BSD-compatible install... /usr/bin/install -c checking whether build environment is sane... yes checking for a race-free mkdir -p... /usr/bin/mkdir -p @@ -1673,7 +1709,7 @@ configure: Will not use Google Test. checking whether you have std::thread... yes checking whether you have std::mutex... yes -/bin/bash +/bin/sh checking that generated files are newer than configure... done configure: creating ./config.status config.status: creating Makefile @@ -1682,7 +1718,7 @@ config.status: executing libtool commands configure: Successfully created a Makefile. === configuring in rsblib (/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib) -configure: running /bin/bash ./configure --disable-option-checking '--prefix=/usr' '--build=x86_64-linux-gnu' '--includedir=${prefix}/include' '--mandir=${prefix}/share/man' '--infodir=${prefix}/share/info' '--sysconfdir=/etc' '--localstatedir=/var' '--disable-silent-rules' '--libdir=${prefix}/lib/x86_64-linux-gnu' '--runstatedir=/run' '--disable-maintainer-mode' '--disable-dependency-tracking' '--with-hwloc' '--enable-matrix-types=blas' '--with-zlib=-lz' '--enable-doc-build' '--enable-fortran-module-install' '--enable-extra-patches' '--enable-pkg-config-install' '--disable-extra-patches' 'build_alias=x86_64-linux-gnu' 'CFLAGS=-g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3' 'LDFLAGS=-Wl,-z,relro' 'CPPFLAGS=-Wdate-time -D_FORTIFY_SOURCE=2' 'FCFLAGS=-g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe' 'CXXFLAGS=-g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection' 'BASH=/bin/bash' --cache-file=/dev/null --srcdir=. +configure: running /bin/sh ./configure --disable-option-checking '--prefix=/usr' '--build=x86_64-linux-gnu' '--includedir=${prefix}/include' '--mandir=${prefix}/share/man' '--infodir=${prefix}/share/info' '--sysconfdir=/etc' '--localstatedir=/var' '--disable-silent-rules' '--libdir=${prefix}/lib/x86_64-linux-gnu' '--runstatedir=/run' '--disable-maintainer-mode' '--disable-dependency-tracking' '--with-hwloc' '--enable-matrix-types=blas' '--with-zlib=-lz' '--enable-doc-build' '--enable-fortran-module-install' '--enable-extra-patches' '--enable-pkg-config-install' '--disable-extra-patches' 'build_alias=x86_64-linux-gnu' 'CFLAGS=-g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3' 'LDFLAGS=-Wl,-z,relro' 'CPPFLAGS=-Wdate-time -D_FORTIFY_SOURCE=2' 'FCFLAGS=-g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe' 'CXXFLAGS=-g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection' 'BASH=/bin/sh' --cache-file=/dev/null --srcdir=. checking for a BSD-compatible install... /usr/bin/install -c checking whether build environment is sane... yes checking for a race-free mkdir -p... /usr/bin/mkdir -p @@ -1791,7 +1827,7 @@ checking for filesystem... yes checking for main in -lstdc++fs... yes configure: Assuming you are yet to build librsb.la. (set LIBS= -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la) -/bin/bash +/bin/sh checking that generated files are newer than configure... done configure: creating ./config.status config.status: creating Makefile @@ -1801,7 +1837,7 @@ config.status: executing libtool commands configure: Created a Makefile. === configuring in rsbtest (/build/reproducible-path/librsb-1.3.0.2+dfsg/rsbtest) -configure: running /bin/bash ./configure --disable-option-checking '--prefix=/usr' '--build=x86_64-linux-gnu' '--includedir=${prefix}/include' '--mandir=${prefix}/share/man' '--infodir=${prefix}/share/info' '--sysconfdir=/etc' '--localstatedir=/var' '--disable-silent-rules' '--libdir=${prefix}/lib/x86_64-linux-gnu' '--runstatedir=/run' '--disable-maintainer-mode' '--disable-dependency-tracking' '--with-hwloc' '--enable-matrix-types=blas' '--with-zlib=-lz' '--enable-doc-build' '--enable-fortran-module-install' '--enable-extra-patches' '--enable-pkg-config-install' '--disable-extra-patches' 'build_alias=x86_64-linux-gnu' 'CFLAGS=-g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3' 'LDFLAGS=-Wl,-z,relro' 'CPPFLAGS=-Wdate-time -D_FORTIFY_SOURCE=2' 'FCFLAGS=-g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe' 'CXXFLAGS=-g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection' 'BASH=/bin/bash' --cache-file=/dev/null --srcdir=. +configure: running /bin/sh ./configure --disable-option-checking '--prefix=/usr' '--build=x86_64-linux-gnu' '--includedir=${prefix}/include' '--mandir=${prefix}/share/man' '--infodir=${prefix}/share/info' '--sysconfdir=/etc' '--localstatedir=/var' '--disable-silent-rules' '--libdir=${prefix}/lib/x86_64-linux-gnu' '--runstatedir=/run' '--disable-maintainer-mode' '--disable-dependency-tracking' '--with-hwloc' '--enable-matrix-types=blas' '--with-zlib=-lz' '--enable-doc-build' '--enable-fortran-module-install' '--enable-extra-patches' '--enable-pkg-config-install' '--disable-extra-patches' 'build_alias=x86_64-linux-gnu' 'CFLAGS=-g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3' 'LDFLAGS=-Wl,-z,relro' 'CPPFLAGS=-Wdate-time -D_FORTIFY_SOURCE=2' 'FCFLAGS=-g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe' 'CXXFLAGS=-g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection' 'BASH=/bin/sh' --cache-file=/dev/null --srcdir=. checking for a BSD-compatible install... /usr/bin/install -c checking whether build environment is sane... yes checking for a race-free mkdir -p... /usr/bin/mkdir -p @@ -1912,7 +1948,7 @@ checking for filesystem... yes checking for rsb_lib_init... no checking for dd... yes -/bin/bash +/bin/sh /usr/bin/timeout checking that generated files are newer than configure... done configure: creating ./config.status @@ -1944,7 +1980,7 @@ ARFLAGS : cru M4 : m4 MAKE : gmake - BASH : /bin/bash + BASH : /bin/sh OCTAVE : false DOXYGEN : doxygen HELP2MAN : help2man @@ -1963,7 +1999,7 @@ Supported I/O functionality level : "7" vs "7" Interface Error Verbosity : "0" vs "0" Internals Error Verbosity : "0" vs "0" - Memory hierarchy info, detected : "L2:16/64/4096K,L1:8/64/32K" + Memory hierarchy info, detected : "L2:16/64/512K,L1:2/64/64K" Memory hierarchy info, selected : "" Maximum of supported threads : "128" Build Fortran examples : "yes" vs "yes" @@ -1993,31 +2029,31 @@ blhc: ignore-line-regexp: ^.*CC.*: gcc blhc: ignore-line-regexp: ^.*LD.*: /usr/bin/ld.* dh_auto_build - make -j42 + make -j20 make[2]: Entering directory '/build/reproducible-path/librsb-1.3.0.2+dfsg' gmake all-recursive gmake[3]: Entering directory '/build/reproducible-path/librsb-1.3.0.2+dfsg' Making all in librsbpp gmake[4]: Entering directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp' g++ -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -DRSBPP_HAS_RSB_H=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -DRSBPP_HAS_RSB_H=1 -c -o rsbpp.o rsbpp.cpp -/bin/bash ./libtool --tag=CXX --mode=compile g++ -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -DRSBPP_HAS_RSB_H=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -DRSBPP_HAS_RSB_H=1 -c -o rsbpp_coo.lo rsbpp_coo.cpp -/bin/bash ./libtool --tag=CXX --mode=compile g++ -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -DRSBPP_HAS_RSB_H=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -DRSBPP_HAS_RSB_H=1 -c -o rsbpp_csr.lo rsbpp_csr.cpp +/bin/sh ./libtool --tag=CXX --mode=compile g++ -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -DRSBPP_HAS_RSB_H=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -DRSBPP_HAS_RSB_H=1 -c -o rsbpp_coo.lo rsbpp_coo.cpp +/bin/sh ./libtool --tag=CXX --mode=compile g++ -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -DRSBPP_HAS_RSB_H=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -DRSBPP_HAS_RSB_H=1 -c -o rsbpp_csr.lo rsbpp_csr.cpp g++ -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -DRSBPP_HAS_RSB_H=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -DRSBPP_HAS_RSB_H=1 -c -o rsbtt.o rsbtt.cpp gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -DRSBPP_HAS_RSB_H=1 -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -c -o rsbct.o rsbct.c -libtool: compile: g++ -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -DRSBPP_HAS_RSB_H=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -DRSBPP_HAS_RSB_H=1 -c rsbpp_coo.cpp -fPIC -DPIC -o .libs/rsbpp_coo.o libtool: compile: g++ -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -DRSBPP_HAS_RSB_H=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -DRSBPP_HAS_RSB_H=1 -c rsbpp_csr.cpp -fPIC -DPIC -o .libs/rsbpp_csr.o +libtool: compile: g++ -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -DRSBPP_HAS_RSB_H=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -DRSBPP_HAS_RSB_H=1 -c rsbpp_coo.cpp -fPIC -DPIC -o .libs/rsbpp_coo.o libtool: compile: g++ -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -DRSBPP_HAS_RSB_H=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -DRSBPP_HAS_RSB_H=1 -c rsbpp_coo.cpp -o rsbpp_coo.o >/dev/null 2>&1 libtool: compile: g++ -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -DRSBPP_HAS_RSB_H=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -DRSBPP_HAS_RSB_H=1 -c rsbpp_csr.cpp -o rsbpp_csr.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CXX --mode=link g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -DRSBPP_HAS_RSB_H=1 -Wl,-z,relro -o librsbpp.la rsbpp_coo.lo rsbpp_csr.lo -lpthread -lstdc++fs +/bin/sh ./libtool --tag=CXX --mode=link g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -DRSBPP_HAS_RSB_H=1 -Wl,-z,relro -o librsbpp.la rsbpp_coo.lo rsbpp_csr.lo -lpthread -lstdc++fs libtool: link: ar cr .libs/librsbpp.a .libs/rsbpp_coo.o .libs/rsbpp_csr.o libtool: link: ranlib .libs/librsbpp.a libtool: link: ( cd ".libs" && rm -f "librsbpp.la" && ln -s "../librsbpp.la" "librsbpp.la" ) -/bin/bash ./libtool --tag=CXX --mode=link g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -DRSBPP_HAS_RSB_H=1 -Wl,-z,relro -o rsbpp rsbpp.o librsbpp.la -lpthread -lstdc++fs -/bin/bash ./libtool --tag=CXX --mode=link g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -DRSBPP_HAS_RSB_H=1 -Wl,-z,relro -o rsbtt rsbtt.o librsbpp.la -lpthread -lstdc++fs -/bin/bash ./libtool --tag=CXX --mode=link g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -DRSBPP_HAS_RSB_H=1 -Wl,-z,relro -o rsbct rsbct.o librsbpp.la -lpthread -lstdc++fs +/bin/sh ./libtool --tag=CXX --mode=link g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -DRSBPP_HAS_RSB_H=1 -Wl,-z,relro -o rsbpp rsbpp.o librsbpp.la -lpthread -lstdc++fs +/bin/sh ./libtool --tag=CXX --mode=link g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -DRSBPP_HAS_RSB_H=1 -Wl,-z,relro -o rsbtt rsbtt.o librsbpp.la -lpthread -lstdc++fs +/bin/sh ./libtool --tag=CXX --mode=link g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -DRSBPP_HAS_RSB_H=1 -Wl,-z,relro -o rsbct rsbct.o librsbpp.la -lpthread -lstdc++fs +libtool: link: g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -DRSBPP_HAS_RSB_H=1 -Wl,-z -Wl,relro -o rsbtt rsbtt.o ./.libs/librsbpp.a -lpthread -lstdc++fs -fopenmp libtool: link: g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -DRSBPP_HAS_RSB_H=1 -Wl,-z -Wl,relro -o rsbpp rsbpp.o ./.libs/librsbpp.a -lpthread -lstdc++fs -fopenmp libtool: link: g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -DRSBPP_HAS_RSB_H=1 -Wl,-z -Wl,relro -o rsbct rsbct.o ./.libs/librsbpp.a -lpthread -lstdc++fs -fopenmp -libtool: link: g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -DRSBPP_HAS_RSB_H=1 -Wl,-z -Wl,relro -o rsbtt rsbtt.o ./.libs/librsbpp.a -lpthread -lstdc++fs -fopenmp gmake all-am gmake[5]: Entering directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp' gmake[5]: Leaving directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp' @@ -2035,245 +2071,216 @@ gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o rsbench-rsb_libspblas_tests.o `test -f 'rsb_libspblas_tests.c' || echo './'`rsb_libspblas_tests.c g++ -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -c -o rsb_dummy.o rsb_dummy.cpp gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o ch2icfb-ch2icfb.o `test -f 'ch2icfb.c' || echo './'`ch2icfb.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_stropts.lo `test -f 'rsb_stropts.c' || echo './'`rsb_stropts.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_strmif.lo `test -f 'rsb_strmif.c' || echo './'`rsb_strmif.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_unroll.lo `test -f 'rsb_unroll.c' || echo './'`rsb_unroll.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_vb.lo `test -f 'rsb_krnl_vb.c' || echo './'`rsb_krnl_vb.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_lb.lo `test -f 'rsb_krnl_lb.c' || echo './'`rsb_krnl_lb.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl.lo `test -f 'rsb_krnl.c' || echo './'`rsb_krnl.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_bench.lo `test -f 'rsb_bench.c' || echo './'`rsb_bench.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_mergesort.lo `test -f 'rsb_mergesort.c' || echo './'`rsb_mergesort.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_permute.lo `test -f 'rsb_permute.c' || echo './'`rsb_permute.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_bcss_l.lo `test -f 'rsb_krnl_bcss_l.c' || echo './'`rsb_krnl_bcss_l.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_bcss_u.lo `test -f 'rsb_krnl_bcss_u.c' || echo './'`rsb_krnl_bcss_u.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_bcss_spsv_u.lo `test -f 'rsb_krnl_bcss_spsv_u.c' || echo './'`rsb_krnl_bcss_spsv_u.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_bcss_spmv_u.lo `test -f 'rsb_krnl_bcss_spmv_u.c' || echo './'`rsb_krnl_bcss_spmv_u.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_bcss_misc_u.lo `test -f 'rsb_krnl_bcss_misc_u.c' || echo './'`rsb_krnl_bcss_misc_u.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_bcoo_spmv_u.lo `test -f 'rsb_krnl_bcoo_spmv_u.c' || echo './'`rsb_krnl_bcoo_spmv_u.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_bcss.lo `test -f 'rsb_krnl_bcss.c' || echo './'`rsb_krnl_bcss.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_spmv.lo `test -f 'rsb_spmv.c' || echo './'`rsb_spmv.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_merge.lo `test -f 'rsb_merge.c' || echo './'`rsb_merge.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_ompio.lo `test -f 'rsb_ompio.c' || echo './'`rsb_ompio.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_util.lo `test -f 'rsb_util.c' || echo './'`rsb_util.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_spgemm_csr.lo `test -f 'rsb_spgemm_csr.c' || echo './'`rsb_spgemm_csr.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_spsum_misc.lo `test -f 'rsb_spsum_misc.c' || echo './'`rsb_spsum_misc.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_prec.lo `test -f 'rsb_prec.c' || echo './'`rsb_prec.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_is.lo `test -f 'rsb_is.c' || echo './'`rsb_is.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_mio.lo `test -f 'rsb_mio.c' || echo './'`rsb_mio.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_op.lo `test -f 'rsb_op.c' || echo './'`rsb_op.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_bio.lo `test -f 'rsb_bio.c' || echo './'`rsb_bio.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_get.lo `test -f 'rsb_get.c' || echo './'`rsb_get.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_set.lo `test -f 'rsb_set.c' || echo './'`rsb_set.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_coo.lo `test -f 'rsb_coo.c' || echo './'`rsb_coo.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_csr.lo `test -f 'rsb_csr.c' || echo './'`rsb_csr.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_vb.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_vb.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_stropts.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_stropts.o +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_stropts.lo `test -f 'rsb_stropts.c' || echo './'`rsb_stropts.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_strmif.lo `test -f 'rsb_strmif.c' || echo './'`rsb_strmif.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_unroll.lo `test -f 'rsb_unroll.c' || echo './'`rsb_unroll.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_vb.lo `test -f 'rsb_krnl_vb.c' || echo './'`rsb_krnl_vb.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_lb.lo `test -f 'rsb_krnl_lb.c' || echo './'`rsb_krnl_lb.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl.lo `test -f 'rsb_krnl.c' || echo './'`rsb_krnl.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_bench.lo `test -f 'rsb_bench.c' || echo './'`rsb_bench.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_mergesort.lo `test -f 'rsb_mergesort.c' || echo './'`rsb_mergesort.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_permute.lo `test -f 'rsb_permute.c' || echo './'`rsb_permute.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_strmif.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_strmif.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_unroll.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_unroll.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_bench.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_bench.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_bcss_spsv_u.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_bcss_spsv_u.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_vb.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_vb.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_permute.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_permute.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_mergesort.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_mergesort.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_bcss_spmv_u.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_bcss_spmv_u.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_bcss_l.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_bcss_l.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_strmif.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_strmif.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_util.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_util.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_merge.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_merge.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_bench.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_bench.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_lb.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_lb.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_spmv.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_spmv.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_bcss.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_bcss.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_bcoo_spmv_u.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_bcoo_spmv_u.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_bcss_misc_u.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_bcss_misc_u.o +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_bcss_l.lo `test -f 'rsb_krnl_bcss_l.c' || echo './'`rsb_krnl_bcss_l.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_mergesort.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_mergesort.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_stropts.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_stropts.o +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_bcss_u.lo `test -f 'rsb_krnl_bcss_u.c' || echo './'`rsb_krnl_bcss_u.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_bcss_l.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_bcss_l.o +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_bcss_spsv_u.lo `test -f 'rsb_krnl_bcss_spsv_u.c' || echo './'`rsb_krnl_bcss_spsv_u.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_vb.c -o librsb_nounroll_la-rsb_krnl_vb.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_bcss_u.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_bcss_u.o +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_bcss_spmv_u.lo `test -f 'rsb_krnl_bcss_spmv_u.c' || echo './'`rsb_krnl_bcss_spmv_u.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_bcss_misc_u.lo `test -f 'rsb_krnl_bcss_misc_u.c' || echo './'`rsb_krnl_bcss_misc_u.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_unroll.c -o librsb_nounroll_la-rsb_unroll.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_stropts.c -o librsb_nounroll_la-rsb_stropts.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_mergesort.c -o librsb_nounroll_la-rsb_mergesort.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_bcss_spsv_u.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_bcss_spsv_u.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_bcss_spmv_u.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_bcss_spmv_u.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_bcss_misc_u.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_bcss_misc_u.o +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_bcoo_spmv_u.lo `test -f 'rsb_krnl_bcoo_spmv_u.c' || echo './'`rsb_krnl_bcoo_spmv_u.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_strmif.c -o librsb_nounroll_la-rsb_strmif.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_lb.c -o librsb_nounroll_la-rsb_krnl_lb.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_bcss_l.c -o librsb_nounroll_la-rsb_krnl_bcss_l.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_bcss.lo `test -f 'rsb_krnl_bcss.c' || echo './'`rsb_krnl_bcss.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_bcoo_spmv_u.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_bcoo_spmv_u.o +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_spmv.lo `test -f 'rsb_spmv.c' || echo './'`rsb_spmv.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_merge.lo `test -f 'rsb_merge.c' || echo './'`rsb_merge.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_bcss_u.c -o librsb_nounroll_la-rsb_krnl_bcss_u.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_bcss.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_bcss.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_spmv.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_spmv.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_merge.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_merge.o +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_ompio.lo `test -f 'rsb_ompio.c' || echo './'`rsb_ompio.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_util.lo `test -f 'rsb_util.c' || echo './'`rsb_util.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_spgemm_csr.lo `test -f 'rsb_spgemm_csr.c' || echo './'`rsb_spgemm_csr.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_spsum_misc.lo `test -f 'rsb_spsum_misc.c' || echo './'`rsb_spsum_misc.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_nounroll_la-rsb_prec.lo `test -f 'rsb_prec.c' || echo './'`rsb_prec.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_bcss.c -o librsb_nounroll_la-rsb_krnl_bcss.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_ompio.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_ompio.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_bio.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_bio.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_util.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_util.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_spgemm_csr.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_spgemm_csr.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_op.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_op.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_coo.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_coo.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_spsum_misc.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_spsum_misc.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_prec.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_prec.o +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_is.lo `test -f 'rsb_is.c' || echo './'`rsb_is.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_ompio.c -o librsb_nounroll_la-rsb_ompio.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_is.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_is.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_csr.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_csr.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_spsum_misc.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_spsum_misc.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_get.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_get.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_permute.c -o librsb_nounroll_la-rsb_permute.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_mio.lo `test -f 'rsb_mio.c' || echo './'`rsb_mio.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_merge.c -o librsb_nounroll_la-rsb_merge.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_spgemm_csr.c -o librsb_nounroll_la-rsb_spgemm_csr.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_prec.c -o librsb_nounroll_la-rsb_prec.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_mio.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_mio.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_set.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_set.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_spmv.c -o librsb_nounroll_la-rsb_spmv.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_is.c -o librsb_base_la-rsb_is.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_op.lo `test -f 'rsb_op.c' || echo './'`rsb_op.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_spsum_misc.c -o librsb_nounroll_la-rsb_spsum_misc.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_bio.lo `test -f 'rsb_bio.c' || echo './'`rsb_bio.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_op.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_op.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_op.c -o librsb_base_la-rsb_op.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_coo_check.lo `test -f 'rsb_coo_check.c' || echo './'`rsb_coo_check.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_get.lo `test -f 'rsb_get.c' || echo './'`rsb_get.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_bio.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_bio.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_get.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_get.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_bench.c -o librsb_nounroll_la-rsb_bench.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_bio.c -o librsb_base_la-rsb_bio.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_set.lo `test -f 'rsb_set.c' || echo './'`rsb_set.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_coo.lo `test -f 'rsb_coo.c' || echo './'`rsb_coo.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_csr.lo `test -f 'rsb_csr.c' || echo './'`rsb_csr.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_coo_check.lo `test -f 'rsb_coo_check.c' || echo './'`rsb_coo_check.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_coo_symm.lo `test -f 'rsb_coo_symm.c' || echo './'`rsb_coo_symm.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_coo.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_coo.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_mio.c -o librsb_base_la-rsb_mio.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_coo_check.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_coo_check.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_coo_symm.lo `test -f 'rsb_coo_symm.c' || echo './'`rsb_coo_symm.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_idx.lo `test -f 'rsb_idx.c' || echo './'`rsb_idx.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_srt.lo `test -f 'rsb_srt.c' || echo './'`rsb_srt.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_idx.lo `test -f 'rsb_idx.c' || echo './'`rsb_idx.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_csr.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_csr.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_set.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_set.o +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_srt.lo `test -f 'rsb_srt.c' || echo './'`rsb_srt.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_coo_symm.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_coo_symm.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_mergesort.c -o librsb_nounroll_la-rsb_mergesort.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_bcss_l.c -o librsb_nounroll_la-rsb_krnl_bcss_l.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_unroll.c -o librsb_nounroll_la-rsb_unroll.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_bcss_u.c -o librsb_nounroll_la-rsb_krnl_bcss_u.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_lb.c -o librsb_nounroll_la-rsb_krnl_lb.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_bcss.c -o librsb_nounroll_la-rsb_krnl_bcss.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_vb.c -o librsb_nounroll_la-rsb_krnl_vb.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_srt.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_srt.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_idx.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_idx.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_srtp.lo `test -f 'rsb_srtp.c' || echo './'`rsb_srtp.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_bio.c -o librsb_base_la-rsb_bio.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_ompio.c -o librsb_nounroll_la-rsb_ompio.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_stropts.c -o librsb_nounroll_la-rsb_stropts.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_csr.c -o librsb_base_la-rsb_csr.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_src.lo `test -f 'rsb_src.c' || echo './'`rsb_src.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_srt.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_srt.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_srtp.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_srtp.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_src.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_src.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_coo_symm.c -o librsb_base_la-rsb_coo_symm.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_coo_check.c -o librsb_base_la-rsb_coo_check.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_is.c -o librsb_base_la-rsb_is.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_test_accuracy.lo `test -f 'rsb_test_accuracy.c' || echo './'`rsb_test_accuracy.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_clone.lo `test -f 'rsb_clone.c' || echo './'`rsb_clone.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_rec.lo `test -f 'rsb_rec.c' || echo './'`rsb_rec.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_prec.c -o librsb_nounroll_la-rsb_prec.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_render.lo `test -f 'rsb_render.c' || echo './'`rsb_render.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_eps.lo `test -f 'rsb_eps.c' || echo './'`rsb_eps.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_msort_up.lo `test -f 'rsb_msort_up.c' || echo './'`rsb_msort_up.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_sys.lo `test -f 'rsb_sys.c' || echo './'`rsb_sys.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_coo.c -o librsb_base_la-rsb_coo.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_srt.c -o librsb_base_la-rsb_srt.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_srtp.lo `test -f 'rsb_srtp.c' || echo './'`rsb_srtp.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_src.lo `test -f 'rsb_src.c' || echo './'`rsb_src.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_test_accuracy.lo `test -f 'rsb_test_accuracy.c' || echo './'`rsb_test_accuracy.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_clone.lo `test -f 'rsb_clone.c' || echo './'`rsb_clone.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_set.c -o librsb_base_la-rsb_set.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_blas_stuff.lo `test -f 'rsb_blas_stuff.c' || echo './'`rsb_blas_stuff.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_coo_symm.c -o librsb_base_la-rsb_coo_symm.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_gen.lo `test -f 'rsb_gen.c' || echo './'`rsb_gen.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_rec.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_rec.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_test_accuracy.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_test_accuracy.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_srtp.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_srtp.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_src.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_src.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_clone.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_clone.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_perf.lo `test -f 'rsb_perf.c' || echo './'`rsb_perf.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_get.c -o librsb_base_la-rsb_get.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_rec.lo `test -f 'rsb_rec.c' || echo './'`rsb_rec.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_render.lo `test -f 'rsb_render.c' || echo './'`rsb_render.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_idx.c -o librsb_base_la-rsb_idx.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_rec.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_rec.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_test_accuracy.c -o librsb_base_la-rsb_test_accuracy.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_eps.lo `test -f 'rsb_eps.c' || echo './'`rsb_eps.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_render.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_render.o +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_msort_up.lo `test -f 'rsb_msort_up.c' || echo './'`rsb_msort_up.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_srtp.c -o librsb_base_la-rsb_srtp.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_src.c -o librsb_base_la-rsb_src.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_eps.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_eps.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_rsb.lo `test -f 'rsb_rsb.c' || echo './'`rsb_rsb.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_spmv.c -o librsb_nounroll_la-rsb_spmv.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_sys.lo `test -f 'rsb_sys.c' || echo './'`rsb_sys.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_blas_stuff.lo `test -f 'rsb_blas_stuff.c' || echo './'`rsb_blas_stuff.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_msort_up.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_msort_up.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_sys.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_sys.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_strmif.c -o librsb_nounroll_la-rsb_strmif.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_coo.c -o librsb_base_la-rsb_coo.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_blas_stuff.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_blas_stuff.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_perf.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_perf.o +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_gen.lo `test -f 'rsb_gen.c' || echo './'`rsb_gen.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_msort_up.c -o librsb_base_la-rsb_msort_up.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_perf.lo `test -f 'rsb_perf.c' || echo './'`rsb_perf.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_gen.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_gen.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_blas_stuff.c -o librsb_base_la-rsb_blas_stuff.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_perf.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_perf.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_render.c -o librsb_base_la-rsb_render.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_rsb.lo `test -f 'rsb_rsb.c' || echo './'`rsb_rsb.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_err.lo `test -f 'rsb_err.c' || echo './'`rsb_err.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_rsb.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_rsb.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_merge.c -o librsb_nounroll_la-rsb_merge.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_spgemm_csr.c -o librsb_nounroll_la-rsb_spgemm_csr.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_err.lo `test -f 'rsb_err.c' || echo './'`rsb_err.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_src.c -o librsb_base_la-rsb_src.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_err.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_err.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_spsum_misc.c -o librsb_nounroll_la-rsb_spsum_misc.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_srtp.c -o librsb_base_la-rsb_srtp.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_tune.lo `test -f 'rsb_tune.c' || echo './'`rsb_tune.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_do.lo `test -f 'rsb_do.c' || echo './'`rsb_do.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_internals.lo `test -f 'rsb_internals.c' || echo './'`rsb_internals.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_mio.c -o librsb_base_la-rsb_mio.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_render.c -o librsb_base_la-rsb_render.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_sys.c -o librsb_base_la-rsb_sys.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_clone.c -o librsb_base_la-rsb_clone.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_perf.c -o librsb_base_la-rsb_perf.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_tune.lo `test -f 'rsb_tune.c' || echo './'`rsb_tune.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_do.lo `test -f 'rsb_do.c' || echo './'`rsb_do.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_internals.lo `test -f 'rsb_internals.c' || echo './'`rsb_internals.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_do.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_do.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_tune.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_tune.o +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_garbage.lo `test -f 'rsb_garbage.c' || echo './'`rsb_garbage.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_internals.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_internals.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_do.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_do.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_blas_stuff.c -o librsb_base_la-rsb_blas_stuff.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_msort_up.c -o librsb_base_la-rsb_msort_up.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_test_accuracy.c -o librsb_base_la-rsb_test_accuracy.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_garbage.lo `test -f 'rsb_garbage.c' || echo './'`rsb_garbage.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_perf.c -o librsb_base_la-rsb_perf.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_srt.c -o librsb_base_la-rsb_srt.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_mmio.lo `test -f 'rsb_mmio.c' || echo './'`rsb_mmio.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_garbage.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_garbage.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_partition.lo `test -f 'rsb_partition.c' || echo './'`rsb_partition.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_idx.c -o librsb_base_la-rsb_idx.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_mbw.lo `test -f 'rsb_mbw.c' || echo './'`rsb_mbw.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_err.c -o librsb_base_la-rsb_err.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_eps.c -o librsb_base_la-rsb_eps.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_gen.c -o librsb_base_la-rsb_gen.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_garbage.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_garbage.o +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_mmio.lo `test -f 'rsb_mmio.c' || echo './'`rsb_mmio.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_rsb.c -o librsb_base_la-rsb_rsb.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_partition.lo `test -f 'rsb_partition.c' || echo './'`rsb_partition.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_mmio.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_mmio.o +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_mbw.lo `test -f 'rsb_mbw.c' || echo './'`rsb_mbw.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_rec.c -o librsb_base_la-rsb_rec.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_partition.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_partition.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_sys.c -o librsb_base_la-rsb_sys.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_limiter.lo `test -f 'rsb_limiter.c' || echo './'`rsb_limiter.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_mmio.c -o librsb_base_la-rsb_mmio.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_mbw.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_mbw.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_fpb.lo `test -f 'rsb_fpb.c' || echo './'`rsb_fpb.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_spgemm.lo `test -f 'rsb_spgemm.c' || echo './'`rsb_spgemm.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_spsum.lo `test -f 'rsb_spsum.c' || echo './'`rsb_spsum.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_garbage.c -o librsb_base_la-rsb_garbage.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_do.c -o librsb_base_la-rsb_do.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_limiter.lo `test -f 'rsb_limiter.c' || echo './'`rsb_limiter.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_fpb.lo `test -f 'rsb_fpb.c' || echo './'`rsb_fpb.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_limiter.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_limiter.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_spsv.lo `test -f 'rsb_spsv.c' || echo './'`rsb_spsv.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_spgemm.lo `test -f 'rsb_spgemm.c' || echo './'`rsb_spgemm.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_partition.c -o librsb_base_la-rsb_partition.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_spsum.lo `test -f 'rsb_spsum.c' || echo './'`rsb_spsum.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_fpb.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_fpb.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_lock.lo `test -f 'rsb_lock.c' || echo './'`rsb_lock.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_spsv.lo `test -f 'rsb_spsv.c' || echo './'`rsb_spsv.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_spgemm.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_spgemm.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_spsum.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_spsum.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_clone.c -o librsb_base_la-rsb_clone.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_swt.lo `test -f 'rsb_swt.c' || echo './'`rsb_swt.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_init.lo `test -f 'rsb_init.c' || echo './'`rsb_init.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_dump.lo `test -f 'rsb_dump.c' || echo './'`rsb_dump.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_spsv.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_spsv.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_get.c -o librsb_base_la-rsb_get.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_lock.lo `test -f 'rsb_lock.c' || echo './'`rsb_lock.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_swt.lo `test -f 'rsb_swt.c' || echo './'`rsb_swt.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_lock.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_lock.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_cpmv.lo `test -f 'rsb_cpmv.c' || echo './'`rsb_cpmv.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_asm.lo `test -f 'rsb_asm.c' || echo './'`rsb_asm.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_limiter.c -o librsb_base_la-rsb_limiter.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_swt.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_swt.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_garbage.c -o librsb_base_la-rsb_garbage.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_dump.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_dump.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_user.lo `test -f 'rsb_user.c' || echo './'`rsb_user.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_gen.c -o librsb_base_la-rsb_gen.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_init.lo `test -f 'rsb_init.c' || echo './'`rsb_init.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_spsum.c -o librsb_base_la-rsb_spsum.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_lock.c -o librsb_base_la-rsb_lock.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_spgemm.c -o librsb_base_la-rsb_spgemm.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_dump.lo `test -f 'rsb_dump.c' || echo './'`rsb_dump.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_init.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_init.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_coo2rec.lo `test -f 'rsb_coo2rec.c' || echo './'`rsb_coo2rec.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_spsv.c -o librsb_base_la-rsb_spsv.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_dump.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_dump.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_swt.c -o librsb_base_la-rsb_swt.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_tune.c -o librsb_base_la-rsb_tune.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_fpb.c -o librsb_base_la-rsb_fpb.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_mbw.c -o librsb_base_la-rsb_mbw.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_cpmv.lo `test -f 'rsb_cpmv.c' || echo './'`rsb_cpmv.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_internals.c -o librsb_base_la-rsb_internals.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_asm.lo `test -f 'rsb_asm.c' || echo './'`rsb_asm.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_cpmv.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_cpmv.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_init.c -o librsb_base_la-rsb_init.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_user.lo `test -f 'rsb_user.c' || echo './'`rsb_user.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_asm.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_asm.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_dump.c -o librsb_base_la-rsb_dump.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_user.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_user.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_partition.c -o librsb_base_la-rsb_partition.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_mmio.c -o librsb_base_la-rsb_mmio.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_coo2rec.lo `test -f 'rsb_coo2rec.c' || echo './'`rsb_coo2rec.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_rec2coo.lo `test -f 'rsb_rec2coo.c' || echo './'`rsb_rec2coo.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_cpmv.c -o librsb_base_la-rsb_cpmv.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_rec2csr.lo `test -f 'rsb_rec2csr.c' || echo './'`rsb_rec2csr.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_coo2rec.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_coo2rec.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_permute.c -o librsb_nounroll_la-rsb_permute.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_limiter.c -o librsb_base_la-rsb_limiter.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_rec2coo.lo `test -f 'rsb_rec2coo.c' || echo './'`rsb_rec2coo.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_spsum.c -o librsb_base_la-rsb_spsum.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_rec2coo.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_rec2coo.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_rec2csr.lo `test -f 'rsb_rec2csr.c' || echo './'`rsb_rec2csr.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_do.c -o librsb_base_la-rsb_do.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_bench.c -o librsb_nounroll_la-rsb_bench.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_lock.c -o librsb_base_la-rsb_lock.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_csr2coo.lo `test -f 'rsb_csr2coo.c' || echo './'`rsb_csr2coo.c +/bin/sh ./libtool --tag=FC --mode=compile gfortran -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe -fopenmp -c -o rsb_blas_sparse.lo rsb_blas_sparse.F90 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_rec2csr.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_rec2csr.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o librsb_base_la-rsb_csr2coo.lo `test -f 'rsb_csr2coo.c' || echo './'`rsb_csr2coo.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_fpb.c -o librsb_base_la-rsb_fpb.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=FC --mode=compile gfortran -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe -fopenmp -c -o rsb_blas_sparse.lo rsb_blas_sparse.F90 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o rsb_libspblas_handle.lo rsb_libspblas_handle.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_cpmv.c -o librsb_base_la-rsb_cpmv.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_eps.c -o librsb_base_la-rsb_eps.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_swt.c -o librsb_base_la-rsb_swt.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_asm.c -o librsb_base_la-rsb_asm.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_csr2coo.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_csr2coo.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o rsb_libspblas.lo rsb_libspblas.c -gfortran -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe -fopenmp -c -o rsb_blas_sparse.o rsb_blas_sparse.F90 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_libspblas_handle.c -fPIC -DPIC -o .libs/rsb_libspblas_handle.o libtool: compile: gfortran -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe -fopenmp -c rsb_blas_sparse.F90 -fPIC -o .libs/rsb_blas_sparse.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_dump.c -o librsb_base_la-rsb_dump.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=link gcc -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -no-undefined -version-info 0:0:0 -Wl,-z,relro -o ch2icfb ch2icfb-ch2icfb.o -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_rec.c -o librsb_base_la-rsb_rec.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_user.c -o librsb_base_la-rsb_user.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_libspblas.c -fPIC -DPIC -o .libs/rsb_libspblas.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_init.c -o librsb_base_la-rsb_init.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_spsv.c -o librsb_base_la-rsb_spsv.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_spgemm.c -o librsb_base_la-rsb_spgemm.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_rec2csr.c -o librsb_base_la-rsb_rec2csr.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o rsb_libspblas_handle.lo rsb_libspblas_handle.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_rec2coo.c -o librsb_base_la-rsb_rec2coo.o >/dev/null 2>&1 -libtool: warning: '-version-info' is ignored for programs -libtool: link: gcc -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -Wl,-z -Wl,relro -o ch2icfb ch2icfb-ch2icfb.o -fopenmp -lhwloc -lz -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath -fopenmp -if test -f ./rsb_types.h -a ! -f ./rsb_types.h ; then cp -pv ./rsb_types.h ./rsb_types.h ; fi # out-of-dir behaviour varies between installations -if test -f ch2icfb ; then if SED=/usr/bin/sed GREP=/usr/bin/grep /bin/bash ./scripts/rsb_h_to_rsb_fi.sh . /build/reproducible-path/librsb-1.3.0.2+dfsg > rsb.F90 ; then true; else rm "rsb.F90"; echo "Failure generating rsb.F90!" ; exit ; fi ; else echo "Warning: Your system did not build ch2icfb for some reason --- skipping rebuild of "rsb.F90 ;true ; fi -/bin/bash ./libtool --tag=FC --mode=compile gfortran -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe -fopenmp -c -o rsb.lo rsb.F90 -gfortran -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe -fopenmp -c -o rsb.o rsb.F90 -libtool: compile: gfortran -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe -fopenmp -c rsb.F90 -fPIC -o .libs/rsb.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_mbw.c -o librsb_base_la-rsb_mbw.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_csr2coo.c -o librsb_base_la-rsb_csr2coo.o >/dev/null 2>&1 -libtool: compile: gfortran -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe -fopenmp -c rsb.F90 -o rsb.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_internals.c -o librsb_base_la-rsb_internals.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_tune.c -o librsb_base_la-rsb_tune.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_coo2rec.c -o librsb_base_la-rsb_coo2rec.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_libspblas_handle.c -o rsb_libspblas_handle.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_libspblas.c -o rsb_libspblas.o >/dev/null 2>&1 -libtool: compile: gfortran -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe -fopenmp -c rsb_blas_sparse.F90 -o rsb_blas_sparse.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=link gcc -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -no-undefined -version-info 0:0:0 -Wl,-z,relro -o librsb_spblas.la rsb_libspblas_handle.lo rsb_libspblas.lo -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath -libtool: warning: '-version-info/-version-number' is ignored for convenience libraries -/bin/bash ./libtool --tag=CC --mode=link gcc -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -no-undefined -version-info 0:0:0 -Wl,-z,relro -o librsb_base.la librsb_base_la-rsb_is.lo librsb_base_la-rsb_mio.lo librsb_base_la-rsb_op.lo librsb_base_la-rsb_bio.lo librsb_base_la-rsb_get.lo librsb_base_la-rsb_set.lo librsb_base_la-rsb_coo.lo librsb_base_la-rsb_csr.lo librsb_base_la-rsb_coo_check.lo librsb_base_la-rsb_coo_symm.lo librsb_base_la-rsb_idx.lo librsb_base_la-rsb_srt.lo librsb_base_la-rsb_srtp.lo librsb_base_la-rsb_src.lo librsb_base_la-rsb_test_accuracy.lo librsb_base_la-rsb_clone.lo librsb_base_la-rsb_rec.lo librsb_base_la-rsb_render.lo librsb_base_la-rsb_eps.lo librsb_base_la-rsb_msort_up.lo librsb_base_la-rsb_sys.lo librsb_base_la-rsb_blas_stuff.lo librsb_base_la-rsb_gen.lo librsb_base_la-rsb_perf.lo librsb_base_la-rsb_rsb.lo librsb_base_la-rsb_err.lo librsb_base_la-rsb_tune.lo librsb_base_la-rsb_do.lo librsb_base_la-rsb_internals.lo librsb_base_la-rsb_garbage.lo librsb_base_la-rsb_mmio.lo librsb_base_la-rsb_partition.lo librsb_base_la-rsb_mbw.lo librsb_base_la-rsb_limiter.lo librsb_base_la-rsb_fpb.lo librsb_base_la-rsb_spgemm.lo librsb_base_la-rsb_spsum.lo librsb_base_la-rsb_spsv.lo librsb_base_la-rsb_lock.lo librsb_base_la-rsb_swt.lo librsb_base_la-rsb_init.lo librsb_base_la-rsb_dump.lo librsb_base_la-rsb_cpmv.lo librsb_base_la-rsb_asm.lo librsb_base_la-rsb_user.lo librsb_base_la-rsb_coo2rec.lo librsb_base_la-rsb_rec2coo.lo librsb_base_la-rsb_rec2csr.lo librsb_base_la-rsb_csr2coo.lo rsb_blas_sparse.lo -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath -libtool: link: ar cr .libs/librsb_spblas.a .libs/rsb_libspblas_handle.o .libs/rsb_libspblas.o -libtool: link: ranlib .libs/librsb_spblas.a -libtool: link: ( cd ".libs" && rm -f "librsb_spblas.la" && ln -s "../librsb_spblas.la" "librsb_spblas.la" ) -libtool: warning: '-version-info/-version-number' is ignored for convenience libraries -libtool: link: ar cr .libs/librsb_base.a .libs/librsb_base_la-rsb_is.o .libs/librsb_base_la-rsb_mio.o .libs/librsb_base_la-rsb_op.o .libs/librsb_base_la-rsb_bio.o .libs/librsb_base_la-rsb_get.o .libs/librsb_base_la-rsb_set.o .libs/librsb_base_la-rsb_coo.o .libs/librsb_base_la-rsb_csr.o .libs/librsb_base_la-rsb_coo_check.o .libs/librsb_base_la-rsb_coo_symm.o .libs/librsb_base_la-rsb_idx.o .libs/librsb_base_la-rsb_srt.o .libs/librsb_base_la-rsb_srtp.o .libs/librsb_base_la-rsb_src.o .libs/librsb_base_la-rsb_test_accuracy.o .libs/librsb_base_la-rsb_clone.o .libs/librsb_base_la-rsb_rec.o .libs/librsb_base_la-rsb_render.o .libs/librsb_base_la-rsb_eps.o .libs/librsb_base_la-rsb_msort_up.o .libs/librsb_base_la-rsb_sys.o .libs/librsb_base_la-rsb_blas_stuff.o .libs/librsb_base_la-rsb_gen.o .libs/librsb_base_la-rsb_perf.o .libs/librsb_base_la-rsb_rsb.o .libs/librsb_base_la-rsb_err.o .libs/librsb_base_la-rsb_tune.o .libs/librsb_base_la-rsb_do.o .libs/librsb_base_la-rsb_internals.o .libs/librsb_base_la-rsb_garbage.o .libs/librsb_base_la-rsb_mmio.o .libs/librsb_base_la-rsb_partition.o .libs/librsb_base_la-rsb_mbw.o .libs/librsb_base_la-rsb_limiter.o .libs/librsb_base_la-rsb_fpb.o .libs/librsb_base_la-rsb_spgemm.o .libs/librsb_base_la-rsb_spsum.o .libs/librsb_base_la-rsb_spsv.o .libs/librsb_base_la-rsb_lock.o .libs/librsb_base_la-rsb_swt.o .libs/librsb_base_la-rsb_init.o .libs/librsb_base_la-rsb_dump.o .libs/librsb_base_la-rsb_cpmv.o .libs/librsb_base_la-rsb_asm.o .libs/librsb_base_la-rsb_user.o .libs/librsb_base_la-rsb_coo2rec.o .libs/librsb_base_la-rsb_rec2coo.o .libs/librsb_base_la-rsb_rec2csr.o .libs/librsb_base_la-rsb_csr2coo.o .libs/rsb_blas_sparse.o -libtool: link: ranlib .libs/librsb_base.a -libtool: link: ( cd ".libs" && rm -f "librsb_base.la" && ln -s "../librsb_base.la" "librsb_base.la" ) +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_rec2csr.c -o librsb_base_la-rsb_rec2csr.o >/dev/null 2>&1 rsb_test_matops.c: In function 'rsb__main_block_partitioned_spmv_sxsa': rsb_test_matops.c:214:41: warning: '%s' directive writing up to 2047 bytes into a region of size 1011 [-Wformat-overflow=] 214 | rsb__sprintf(dst,"%s%s_%s_%.0lf_%s%s" "%s%s%s" "%s%s" "%s",pp?pp:"",h,rsb__getenv_nnr("HOSTNAME"),rsb_time(),buf,ap?ap:"", @@ -2292,7 +2299,36 @@ | ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 32 | __va_arg_pack ()); | ~~~~~~~~~~~~~~~~~ +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c -o rsb_libspblas.lo rsb_libspblas.c +gfortran -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe -fopenmp -c -o rsb_blas_sparse.o rsb_blas_sparse.F90 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_user.c -o librsb_base_la-rsb_user.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_libspblas_handle.c -fPIC -DPIC -o .libs/rsb_libspblas_handle.o +/bin/sh ./libtool --tag=CC --mode=link gcc -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -no-undefined -version-info 0:0:0 -Wl,-z,relro -o ch2icfb ch2icfb-ch2icfb.o -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_csr2coo.c -o librsb_base_la-rsb_csr2coo.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_libspblas.c -fPIC -DPIC -o .libs/rsb_libspblas.o +libtool: warning: '-version-info' is ignored for programs +libtool: link: gcc -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -Wl,-z -Wl,relro -o ch2icfb ch2icfb-ch2icfb.o -fopenmp -lhwloc -lz -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath -fopenmp +if test -f ./rsb_types.h -a ! -f ./rsb_types.h ; then cp -pv ./rsb_types.h ./rsb_types.h ; fi # out-of-dir behaviour varies between installations +if test -f ch2icfb ; then if SED=/usr/bin/sed GREP=/usr/bin/grep /bin/sh ./scripts/rsb_h_to_rsb_fi.sh . /build/reproducible-path/librsb-1.3.0.2+dfsg > rsb.F90 ; then true; else rm "rsb.F90"; echo "Failure generating rsb.F90!" ; exit ; fi ; else echo "Warning: Your system did not build ch2icfb for some reason --- skipping rebuild of "rsb.F90 ;true ; fi +/bin/sh ./libtool --tag=FC --mode=compile gfortran -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe -fopenmp -c -o rsb.lo rsb.F90 +gfortran -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe -fopenmp -c -o rsb.o rsb.F90 +libtool: compile: gfortran -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe -fopenmp -c rsb.F90 -fPIC -o .libs/rsb.o +libtool: compile: gfortran -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe -fopenmp -c rsb.F90 -o rsb.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_libspblas_handle.c -o rsb_libspblas_handle.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_coo2rec.c -o librsb_base_la-rsb_coo2rec.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_bcss_spsv_u.c -o librsb_nounroll_la-rsb_krnl_bcss_spsv_u.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_libspblas.c -o rsb_libspblas.o >/dev/null 2>&1 +libtool: compile: gfortran -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe -fopenmp -c rsb_blas_sparse.F90 -o rsb_blas_sparse.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=link gcc -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -no-undefined -version-info 0:0:0 -Wl,-z,relro -o librsb_base.la librsb_base_la-rsb_is.lo librsb_base_la-rsb_mio.lo librsb_base_la-rsb_op.lo librsb_base_la-rsb_bio.lo librsb_base_la-rsb_get.lo librsb_base_la-rsb_set.lo librsb_base_la-rsb_coo.lo librsb_base_la-rsb_csr.lo librsb_base_la-rsb_coo_check.lo librsb_base_la-rsb_coo_symm.lo librsb_base_la-rsb_idx.lo librsb_base_la-rsb_srt.lo librsb_base_la-rsb_srtp.lo librsb_base_la-rsb_src.lo librsb_base_la-rsb_test_accuracy.lo librsb_base_la-rsb_clone.lo librsb_base_la-rsb_rec.lo librsb_base_la-rsb_render.lo librsb_base_la-rsb_eps.lo librsb_base_la-rsb_msort_up.lo librsb_base_la-rsb_sys.lo librsb_base_la-rsb_blas_stuff.lo librsb_base_la-rsb_gen.lo librsb_base_la-rsb_perf.lo librsb_base_la-rsb_rsb.lo librsb_base_la-rsb_err.lo librsb_base_la-rsb_tune.lo librsb_base_la-rsb_do.lo librsb_base_la-rsb_internals.lo librsb_base_la-rsb_garbage.lo librsb_base_la-rsb_mmio.lo librsb_base_la-rsb_partition.lo librsb_base_la-rsb_mbw.lo librsb_base_la-rsb_limiter.lo librsb_base_la-rsb_fpb.lo librsb_base_la-rsb_spgemm.lo librsb_base_la-rsb_spsum.lo librsb_base_la-rsb_spsv.lo librsb_base_la-rsb_lock.lo librsb_base_la-rsb_swt.lo librsb_base_la-rsb_init.lo librsb_base_la-rsb_dump.lo librsb_base_la-rsb_cpmv.lo librsb_base_la-rsb_asm.lo librsb_base_la-rsb_user.lo librsb_base_la-rsb_coo2rec.lo librsb_base_la-rsb_rec2coo.lo librsb_base_la-rsb_rec2csr.lo librsb_base_la-rsb_csr2coo.lo rsb_blas_sparse.lo -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath +/bin/sh ./libtool --tag=CC --mode=link gcc -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -no-undefined -version-info 0:0:0 -Wl,-z,relro -o librsb_spblas.la rsb_libspblas_handle.lo rsb_libspblas.lo -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath +libtool: warning: '-version-info/-version-number' is ignored for convenience libraries +libtool: warning: '-version-info/-version-number' is ignored for convenience libraries +libtool: link: ar cr .libs/librsb_spblas.a .libs/rsb_libspblas_handle.o .libs/rsb_libspblas.o +libtool: link: ranlib .libs/librsb_spblas.a +libtool: link: ( cd ".libs" && rm -f "librsb_spblas.la" && ln -s "../librsb_spblas.la" "librsb_spblas.la" ) +libtool: link: ar cr .libs/librsb_base.a .libs/librsb_base_la-rsb_is.o .libs/librsb_base_la-rsb_mio.o .libs/librsb_base_la-rsb_op.o .libs/librsb_base_la-rsb_bio.o .libs/librsb_base_la-rsb_get.o .libs/librsb_base_la-rsb_set.o .libs/librsb_base_la-rsb_coo.o .libs/librsb_base_la-rsb_csr.o .libs/librsb_base_la-rsb_coo_check.o .libs/librsb_base_la-rsb_coo_symm.o .libs/librsb_base_la-rsb_idx.o .libs/librsb_base_la-rsb_srt.o .libs/librsb_base_la-rsb_srtp.o .libs/librsb_base_la-rsb_src.o .libs/librsb_base_la-rsb_test_accuracy.o .libs/librsb_base_la-rsb_clone.o .libs/librsb_base_la-rsb_rec.o .libs/librsb_base_la-rsb_render.o .libs/librsb_base_la-rsb_eps.o .libs/librsb_base_la-rsb_msort_up.o .libs/librsb_base_la-rsb_sys.o .libs/librsb_base_la-rsb_blas_stuff.o .libs/librsb_base_la-rsb_gen.o .libs/librsb_base_la-rsb_perf.o .libs/librsb_base_la-rsb_rsb.o .libs/librsb_base_la-rsb_err.o .libs/librsb_base_la-rsb_tune.o .libs/librsb_base_la-rsb_do.o .libs/librsb_base_la-rsb_internals.o .libs/librsb_base_la-rsb_garbage.o .libs/librsb_base_la-rsb_mmio.o .libs/librsb_base_la-rsb_partition.o .libs/librsb_base_la-rsb_mbw.o .libs/librsb_base_la-rsb_limiter.o .libs/librsb_base_la-rsb_fpb.o .libs/librsb_base_la-rsb_spgemm.o .libs/librsb_base_la-rsb_spsum.o .libs/librsb_base_la-rsb_spsv.o .libs/librsb_base_la-rsb_lock.o .libs/librsb_base_la-rsb_swt.o .libs/librsb_base_la-rsb_init.o .libs/librsb_base_la-rsb_dump.o .libs/librsb_base_la-rsb_cpmv.o .libs/librsb_base_la-rsb_asm.o .libs/librsb_base_la-rsb_user.o .libs/librsb_base_la-rsb_coo2rec.o .libs/librsb_base_la-rsb_rec2coo.o .libs/librsb_base_la-rsb_rec2csr.o .libs/librsb_base_la-rsb_csr2coo.o .libs/rsb_blas_sparse.o +libtool: link: ranlib .libs/librsb_base.a +libtool: link: ( cd ".libs" && rm -f "librsb_base.la" && ln -s "../librsb_base.la" "librsb_base.la" ) libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_util.c -o librsb_nounroll_la-rsb_util.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl.c -o librsb_nounroll_la-rsb_krnl.o >/dev/null 2>&1 rsb_test_matops.c: In function 'rsb__main_block_partitioned_spsv_sxsx': @@ -2326,12 +2362,12 @@ | ~~~~~~~~~~~~~~~~~ libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_bcss_spmv_u.c -o librsb_nounroll_la-rsb_krnl_bcss_spmv_u.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -c rsb_krnl_bcoo_spmv_u.c -o librsb_nounroll_la-rsb_krnl_bcoo_spmv_u.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=link gcc -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -no-undefined -version-info 0:0:0 -Wl,-z,relro -o librsb_nounroll.la librsb_nounroll_la-rsb_stropts.lo librsb_nounroll_la-rsb_strmif.lo librsb_nounroll_la-rsb_unroll.lo librsb_nounroll_la-rsb_krnl_vb.lo librsb_nounroll_la-rsb_krnl_lb.lo librsb_nounroll_la-rsb_krnl.lo librsb_nounroll_la-rsb_bench.lo librsb_nounroll_la-rsb_mergesort.lo librsb_nounroll_la-rsb_permute.lo librsb_nounroll_la-rsb_krnl_bcss_l.lo librsb_nounroll_la-rsb_krnl_bcss_u.lo librsb_nounroll_la-rsb_krnl_bcss_spsv_u.lo librsb_nounroll_la-rsb_krnl_bcss_spmv_u.lo librsb_nounroll_la-rsb_krnl_bcss_misc_u.lo librsb_nounroll_la-rsb_krnl_bcoo_spmv_u.lo librsb_nounroll_la-rsb_krnl_bcss.lo librsb_nounroll_la-rsb_spmv.lo librsb_nounroll_la-rsb_merge.lo librsb_nounroll_la-rsb_ompio.lo librsb_nounroll_la-rsb_util.lo librsb_nounroll_la-rsb_spgemm_csr.lo librsb_nounroll_la-rsb_spsum_misc.lo librsb_nounroll_la-rsb_prec.lo -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath +/bin/sh ./libtool --tag=CC --mode=link gcc -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -no-undefined -version-info 0:0:0 -Wl,-z,relro -o librsb_nounroll.la librsb_nounroll_la-rsb_stropts.lo librsb_nounroll_la-rsb_strmif.lo librsb_nounroll_la-rsb_unroll.lo librsb_nounroll_la-rsb_krnl_vb.lo librsb_nounroll_la-rsb_krnl_lb.lo librsb_nounroll_la-rsb_krnl.lo librsb_nounroll_la-rsb_bench.lo librsb_nounroll_la-rsb_mergesort.lo librsb_nounroll_la-rsb_permute.lo librsb_nounroll_la-rsb_krnl_bcss_l.lo librsb_nounroll_la-rsb_krnl_bcss_u.lo librsb_nounroll_la-rsb_krnl_bcss_spsv_u.lo librsb_nounroll_la-rsb_krnl_bcss_spmv_u.lo librsb_nounroll_la-rsb_krnl_bcss_misc_u.lo librsb_nounroll_la-rsb_krnl_bcoo_spmv_u.lo librsb_nounroll_la-rsb_krnl_bcss.lo librsb_nounroll_la-rsb_spmv.lo librsb_nounroll_la-rsb_merge.lo librsb_nounroll_la-rsb_ompio.lo librsb_nounroll_la-rsb_util.lo librsb_nounroll_la-rsb_spgemm_csr.lo librsb_nounroll_la-rsb_spsum_misc.lo librsb_nounroll_la-rsb_prec.lo -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath libtool: warning: '-version-info/-version-number' is ignored for convenience libraries libtool: link: ar cr .libs/librsb_nounroll.a .libs/librsb_nounroll_la-rsb_stropts.o .libs/librsb_nounroll_la-rsb_strmif.o .libs/librsb_nounroll_la-rsb_unroll.o .libs/librsb_nounroll_la-rsb_krnl_vb.o .libs/librsb_nounroll_la-rsb_krnl_lb.o .libs/librsb_nounroll_la-rsb_krnl.o .libs/librsb_nounroll_la-rsb_bench.o .libs/librsb_nounroll_la-rsb_mergesort.o .libs/librsb_nounroll_la-rsb_permute.o .libs/librsb_nounroll_la-rsb_krnl_bcss_l.o .libs/librsb_nounroll_la-rsb_krnl_bcss_u.o .libs/librsb_nounroll_la-rsb_krnl_bcss_spsv_u.o .libs/librsb_nounroll_la-rsb_krnl_bcss_spmv_u.o .libs/librsb_nounroll_la-rsb_krnl_bcss_misc_u.o .libs/librsb_nounroll_la-rsb_krnl_bcoo_spmv_u.o .libs/librsb_nounroll_la-rsb_krnl_bcss.o .libs/librsb_nounroll_la-rsb_spmv.o .libs/librsb_nounroll_la-rsb_merge.o .libs/librsb_nounroll_la-rsb_ompio.o .libs/librsb_nounroll_la-rsb_util.o .libs/librsb_nounroll_la-rsb_spgemm_csr.o .libs/librsb_nounroll_la-rsb_spsum_misc.o .libs/librsb_nounroll_la-rsb_prec.o libtool: link: ranlib .libs/librsb_nounroll.a libtool: link: ( cd ".libs" && rm -f "librsb_nounroll.la" && ln -s "../librsb_nounroll.la" "librsb_nounroll.la" ) -/bin/bash ./libtool --tag=CC --mode=link gcc -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -no-undefined -version-info 0:0:0 -Wl,-z,relro -o librsb.la -rpath /usr/lib/x86_64-linux-gnu rsb.lo librsb_nounroll.la librsb_base.la librsb_spblas.la /build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp/librsbpp.la -lstdc++ -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath +/bin/sh ./libtool --tag=CC --mode=link gcc -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -no-undefined -version-info 0:0:0 -Wl,-z,relro -o librsb.la -rpath /usr/lib/x86_64-linux-gnu rsb.lo librsb_nounroll.la librsb_base.la librsb_spblas.la /build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp/librsbpp.la -lstdc++ -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath libtool: link: gcc -shared -fPIC -DPIC .libs/rsb.o -Wl,--whole-archive ./.libs/librsb_nounroll.a ./.libs/librsb_base.a ./.libs/librsb_spblas.a /build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp/.libs/librsbpp.a -Wl,--no-whole-archive -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lpthread -lstdc++fs -lstdc++ -lhwloc -lz -lgfortran -lm -lquadmath -g -O2 -fstack-protector-strong -O3 -Wl,-z -Wl,relro -fopenmp -fopenmp -Wl,-soname -Wl,librsb.so.0 -o .libs/librsb.so.0.0.0 libtool: link: (cd ".libs" && rm -f "librsb.so.0" && ln -s "librsb.so.0.0.0" "librsb.so.0") libtool: link: (cd ".libs" && rm -f "librsb.so" && ln -s "librsb.so.0.0.0" "librsb.so") @@ -2343,7 +2379,7 @@ libtool: link: ranlib .libs/librsb.a libtool: link: rm -fr .libs/librsb.lax libtool: link: ( cd ".libs" && rm -f "librsb.la" && ln -s "../librsb.la" "librsb.la" ) -/bin/bash ./libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -no-undefined -version-info 0:0:0 -Wl,-z,relro -o rsbench rsbench-rsbench.o rsbench-rsb_test_matops.o rsbench-rsb_mkl.o rsbench-rsb_genmm.o rsbench-rsb_mmls.o rsbench-rsb_pr.o rsbench-rsb_pcnt.o rsbench-rsb_failure_tests.o rsbench-rsb_libspblas_tests.o rsb_dummy.o librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath +/bin/sh ./libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -no-undefined -version-info 0:0:0 -Wl,-z,relro -o rsbench rsbench-rsbench.o rsbench-rsb_test_matops.o rsbench-rsb_mkl.o rsbench-rsb_genmm.o rsbench-rsb_mmls.o rsbench-rsb_pr.o rsbench-rsb_pcnt.o rsbench-rsb_failure_tests.o rsbench-rsb_libspblas_tests.o rsb_dummy.o librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath libtool: warning: '-version-info' is ignored for programs libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z -Wl,relro -o .libs/rsbench rsbench-rsbench.o rsbench-rsb_test_matops.o rsbench-rsb_mkl.o rsbench-rsb_genmm.o rsbench-rsb_mmls.o rsbench-rsb_pr.o rsbench-rsb_pcnt.o rsbench-rsb_failure_tests.o rsbench-rsb_libspblas_tests.o rsb_dummy.o -fopenmp ./.libs/librsb.so -lhwloc -lz -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath -fopenmp gmake[4]: Leaving directory '/build/reproducible-path/librsb-1.3.0.2+dfsg' @@ -2360,27 +2396,27 @@ gfortran -DHAVE_CONFIG_H -I. -I.. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -I.. -I.. -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe -fopenmp -c -o fortran.o fortran.F90 gfortran -DHAVE_CONFIG_H -I. -I.. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -I.. -I.. -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -fcf-protection -pipe -fopenmp -c -o fortran_rsb_fi.o fortran_rsb_fi.F90 g++ -DHAVE_CONFIG_H -I. -I.. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -c -o cplusplus.o cplusplus.cpp -/bin/bash ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z,relro -o io-spblas io-spblas.o -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath -/bin/bash ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z,relro -o transpose transpose.o -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath -/bin/bash ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z,relro -o hello hello.o -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath -/bin/bash ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z,relro -o hello-spblas hello-spblas.o -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath -/bin/bash ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z,relro -o backsolve backsolve.o -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath -/bin/bash ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z,relro -o power power.o -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath -/bin/bash ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z,relro -o fortran_rsb_fi fortran_rsb_fi.o -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath -/bin/bash ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z,relro -o autotune autotune.o -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z,relro -o power power.o -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z,relro -o hello hello.o -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z,relro -o transpose transpose.o -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z,relro -o io-spblas io-spblas.o -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z,relro -o backsolve backsolve.o -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z,relro -o hello-spblas hello-spblas.o -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z,relro -o fortran_rsb_fi fortran_rsb_fi.o -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z,relro -o fortran fortran.o -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z,relro -o autotune autotune.o -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z -Wl,relro -o .libs/io-spblas io-spblas.o -fopenmp -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -lhwloc -lz -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath -fopenmp libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z -Wl,relro -o .libs/hello hello.o -fopenmp -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -lhwloc -lz -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath -fopenmp +libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z -Wl,relro -o .libs/power power.o -fopenmp -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -lhwloc -lz -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath -fopenmp +libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z -Wl,relro -o .libs/backsolve backsolve.o -fopenmp -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -lhwloc -lz -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath -fopenmp libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z -Wl,relro -o .libs/transpose transpose.o -fopenmp -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -lhwloc -lz -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath -fopenmp +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z,relro -o snippets snippets.o -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z -Wl,relro -o .libs/hello-spblas hello-spblas.o -fopenmp -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -lhwloc -lz -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath -fopenmp -libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z -Wl,relro -o .libs/backsolve backsolve.o -fopenmp -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -lhwloc -lz -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath -fopenmp -/bin/bash ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z,relro -o fortran fortran.o -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath -libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z -Wl,relro -o .libs/power power.o -fopenmp -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -lhwloc -lz -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath -fopenmp +libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z -Wl,relro -o .libs/fortran fortran.o -fopenmp -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -lhwloc -lz -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath -fopenmp libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z -Wl,relro -o .libs/fortran_rsb_fi fortran_rsb_fi.o -fopenmp -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -lhwloc -lz -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath -fopenmp libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z -Wl,relro -o .libs/autotune autotune.o -fopenmp -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -lhwloc -lz -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath -fopenmp -/bin/bash ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z,relro -o snippets snippets.o -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath -libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z -Wl,relro -o .libs/fortran fortran.o -fopenmp -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -lhwloc -lz -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath -fopenmp libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z -Wl,relro -o .libs/snippets snippets.o -fopenmp -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -lhwloc -lz -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath -fopenmp -/bin/bash ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z,relro -o cplusplus cplusplus.o -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z,relro -o cplusplus cplusplus.o -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp -Wl,-z -Wl,relro -o .libs/cplusplus cplusplus.o -fopenmp -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -lhwloc -lz -L/usr/lib/gcc/x86_64-linux-gnu/13 -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../x86_64-linux-gnu -L/usr/lib/gcc/x86_64-linux-gnu/13/../../../../lib -L/lib/x86_64-linux-gnu -L/lib/../lib -L/usr/lib/x86_64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/x86_64-linux-gnu/13/../../.. -lgfortran -lm -lquadmath -fopenmp gmake[4]: Leaving directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/examples' Making all in scripts @@ -2398,12 +2434,12 @@ Making all in doc gmake[4]: Entering directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/doc' /usr/bin/mkdir -p man -/usr/bin/mkdir -p man -gmake makedox -SOURCE_DATE_EPOCH=1735736461 \ +SOURCE_DATE_EPOCH=1704020461 \ help2man --name="benchmark and test for librsb" --no-info ../rsbench | /usr/bin/sed 's/January //g' > man/rsbench.1 -SOURCE_DATE_EPOCH=1735736461 \ +/usr/bin/mkdir -p man +SOURCE_DATE_EPOCH=1704020461 \ help2man --name="provide configuration information for librsb" --no-info /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb-config | /usr/bin/sed 's/January //g' > man/librsb-config.1 +gmake makedox gmake[5]: Entering directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/doc' DOXYGEN_PROJECT_NUMBER=1.3.0.2 doxygen Doxyfile || echo "are you sure you have doxygen installed ?" warning: Tag 'HTML_TIMESTAMP' at line 1513 of file 'Doxyfile' has become obsolete. @@ -3114,13 +3150,13 @@ g++ -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -c -o rgt-rgt.o `test -f 'rgt.cpp' || echo './'`rgt.cpp g++ -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -DRSBP_NOTHROW=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -c -o rgt_ne-rgt.o `test -f 'rgt.cpp' || echo './'`rgt.cpp g++ -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -DRSBP_NOTHROW=1 -DRSBP_WANT_REV=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -c -o rgt_rv-rgt.o `test -f 'rgt.cpp' || echo './'`rgt.cpp -/bin/bash ./libtool --tag=CXX --mode=link g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o rgt rgt-rgt.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -/bin/bash ./libtool --tag=CXX --mode=link g++ -DRSBP_NOTHROW=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o rgt_ne rgt_ne-rgt.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -/bin/bash ./libtool --tag=CXX --mode=link g++ -DRSBP_NOTHROW=1 -DRSBP_WANT_REV=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o rgt_rv rgt_rv-rgt.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -libtool: link: g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z -Wl,relro -o .libs/rgt rgt-rgt.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp +/bin/sh ./libtool --tag=CXX --mode=link g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o rgt rgt-rgt.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la +/bin/sh ./libtool --tag=CXX --mode=link g++ -DRSBP_NOTHROW=1 -DRSBP_WANT_REV=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o rgt_rv rgt_rv-rgt.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la +/bin/sh ./libtool --tag=CXX --mode=link g++ -DRSBP_NOTHROW=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o rgt_ne rgt_ne-rgt.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la libtool: link: g++ -DRSBP_NOTHROW=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z -Wl,relro -o .libs/rgt_ne rgt_ne-rgt.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp +libtool: link: g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z -Wl,relro -o .libs/rgt rgt-rgt.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp libtool: link: g++ -DRSBP_NOTHROW=1 -DRSBP_WANT_REV=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z -Wl,relro -o .libs/rgt_rv rgt_rv-rgt.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp -/bin/bash ./libtool --tag=CXX --mode=link g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o rsb rsb.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la +/bin/sh ./libtool --tag=CXX --mode=link g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o rsb rsb.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la libtool: link: g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z -Wl,relro -o .libs/rsb rsb.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp gmake[6]: Leaving directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib' Making all in examples @@ -3135,25 +3171,25 @@ g++ -DHAVE_CONFIG_H -I.. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -c -o mtx2bin.o mtx2bin.cpp g++ -DHAVE_CONFIG_H -I.. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -c -o render.o render.cpp g++ -DHAVE_CONFIG_H -I.. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -c -o span.o span.cpp -/bin/bash ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o span span.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -/bin/bash ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o assemble assemble.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -libtool: link: g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z -Wl,relro -o .libs/span span.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp -/bin/bash ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o render render.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -/bin/bash ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o example example.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la +/bin/sh ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o assemble assemble.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la +/bin/sh ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o render render.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la +/bin/sh ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o span span.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la libtool: link: g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z -Wl,relro -o .libs/assemble assemble.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp libtool: link: g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z -Wl,relro -o .libs/render render.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp -libtool: link: g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z -Wl,relro -o .libs/example example.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp -/bin/bash ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o misc misc.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la +/bin/sh ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o misc misc.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la +/bin/sh ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o example example.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la +libtool: link: g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z -Wl,relro -o .libs/span span.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp libtool: link: g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z -Wl,relro -o .libs/misc misc.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp -/bin/bash ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o build build.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la +libtool: link: g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z -Wl,relro -o .libs/example example.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp +/bin/sh ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o build build.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la libtool: link: g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z -Wl,relro -o .libs/build build.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp -/bin/bash ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o twonnz twonnz.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -/bin/bash ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o mtx2bin mtx2bin.o -lstdc++fs -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -libtool: link: g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z -Wl,relro -o .libs/twonnz twonnz.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp +/bin/sh ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o mtx2bin mtx2bin.o -lstdc++fs -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la libtool: link: g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z -Wl,relro -o .libs/mtx2bin mtx2bin.o -lstdc++fs -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp -/bin/bash ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o autotune autotune.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la +/bin/sh ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o twonnz twonnz.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la +libtool: link: g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z -Wl,relro -o .libs/twonnz twonnz.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp +/bin/sh ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o autotune autotune.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la +/bin/sh ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o bench bench.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la libtool: link: g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z -Wl,relro -o .libs/autotune autotune.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp -/bin/bash ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o bench bench.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la libtool: link: g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z -Wl,relro -o .libs/bench bench.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp gmake[6]: Leaving directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib/examples' gmake[5]: Leaving directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib' @@ -3163,7 +3199,7 @@ gmake all-am gmake[5]: Entering directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/rsbtest' g++ -DHAVE_CONFIG_H -I. -I/build/reproducible-path/librsb-1.3.0.2+dfsg -Wdate-time -D_FORTIFY_SOURCE=2 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -c -o rsbtest.o rsbtest.cpp -/bin/bash ./libtool --tag=CXX --mode=link g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o rsbtest rsbtest.o /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lstdc++fs -lstdc++fs +/bin/sh ./libtool --tag=CXX --mode=link g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z,relro -o rsbtest rsbtest.o /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lstdc++fs -lstdc++fs libtool: link: g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -Wl,-z -Wl,relro -o .libs/rsbtest rsbtest.o /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -lstdc++fs -fopenmp gmake[5]: Leaving directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/rsbtest' gmake[4]: Leaving directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/rsbtest' @@ -3239,7 +3275,7 @@ gmake[3]: Leaving directory '/build/reproducible-path/librsb-1.3.0.2+dfsg' gmake mtests -C . gmake[3]: Entering directory '/build/reproducible-path/librsb-1.3.0.2+dfsg' -srcdir="/build/reproducible-path/librsb-1.3.0.2+dfsg" /bin/bash -ex ./scripts/readme-tests.sh +srcdir="/build/reproducible-path/librsb-1.3.0.2+dfsg" /bin/sh -ex ./scripts/readme-tests.sh + test x/build/reproducible-path/librsb-1.3.0.2+dfsg = x + ./rsbench -oa -Ob --bench -f /build/reproducible-path/librsb-1.3.0.2+dfsg/A.mtx -qH -R -n1,4 -T z --verbose --nrhs 1,2 --by-rows # --bench option implies -qH -R --write-performance-record --want-mkl-autotune --mkl-benchmark --types : --split-experimental 6 --merge-experimental 6 --also-transpose --sort-filenames-list --want-memory-benchmark @@ -3249,15 +3285,15 @@ Adding matrix file: /build/reproducible-path/librsb-1.3.0.2+dfsg/A.mtx # Sorting matrices list (use --no-sort-filenames-list to prevent this) # Using matrices: A.mtx -# beginning run at 1749955878 +# beginning run at 1715548768 # /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/rsbench -oa -Ob --bench -f /build/reproducible-path/librsb-1.3.0.2+dfsg/A.mtx -qH -R -n1,4 -T z --verbose --nrhs 1,2 --by-rows # compiled with: CC=gcc CFLAGS=-g -O2 -Werror=implicit-function-declaration -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -# average timer granularity: 3.32e-08 s -# Will write a final performance record to file rsbench_pr__1749955878_gcc-13.2-1,4th.rpr and periodic checkpoints to rsbench_pr__1749955878_gcc-13.2-1,4th.rpr.tmp +# average timer granularity: 7.82e-07 s +# Will write a final performance record to file rsbench_pr__1715548768_gcc-13.2-1,4th.rpr and periodic checkpoints to rsbench_pr__1715548768_gcc-13.2-1,4th.rpr.tmp # will NOT perform ancillary tests. # will flush cache memory: between each operation measurement series, and NOT between each operation. # will keep any zero encountered in the matrix. -# env: export PATH=/usr/sbin:/usr/bin:/sbin:/bin:/usr/games +# env: export PATH=/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/i/capture/the/path # env: export LD_LIBRARY_PATH=/build/reproducible-path/librsb-1.3.0.2+dfsg/.libs # env: HOSTNAME is not set # env: KMP_AFFINITY is not set @@ -3296,67 +3332,67 @@ # env: SLURM_NTASKS is not set # env: SLURM_STEP_TASKS_PER_NODE is not set # env: SLURM_TASKS_PER_NODE is not set -# detected hostname: ionos5-amd64 +# detected hostname: i-capture-the-hostname # user specified a verbosity level of 1 (each --verbose occurrence counts +1) # This test will measure times in scanning arrays sized and aligned to fit in caches. # 2 cache levels detected Will fill struct with 40 samples... -# Memory benchmark took 6.174s +# Memory benchmark took 5.352s # auto-tuning oriented output implies times==0 iterations and sort-after-load. #pr: allocated a performance record for 8 samples (2240 bytes). -# Cache block size total 4194304 bytes, per-thread 99864 bytes -# so far, program took 6.176s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.000s/0.000s . +# Cache block size total 524288 bytes, per-thread 26214 bytes +# so far, program took 5.388s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.000s/0.000s . # Using 1 threads # reading A.mtx (184 bytes / 1 MiB / 6 nnz / 3 rows / 3 columns / 1 MiB COO) as type Z... -# file input of A.mtx took 0.00 s (6 nnz, 53544 nnz/s ) (1.64 MB/s ) -#pre-sorting (6 elements) took 0.00454903 s -#weeding duplicates (to 6 elements) took 2.14577e-06 s (and check, 1.90735e-06 s ) +# file input of A.mtx took 0.00 s (6 nnz, 32940 nnz/s ) (1.01 MB/s ) +#pre-sorting (6 elements) took 0.0515988 s +#weeding duplicates (to 6 elements) took 5.00679e-06 s (and check, 4.05312e-06 s ) # multi-nrhs benchmarking (1,2) -- now using nrhs 1. # Using alpha=1 beta=1 order=rows for rsb_spmv/rsb_spsv/rsb_spmm/rsb_spsm. # multi-transpose benchmarking -- now using transA = N. # will use input matrix flags: RSB_FLAG_USE_HALFWORD_INDICES, RSB_FLAG_SORTED_INPUT, RSB_FLAG_QUAD_PARTITIONING, RSB_FLAG_SYMMETRIC, RSB_FLAG_OWN_PARTITIONING_ARRAYS # Using 1 threads -# Constructed matrix (took 0.020s): (3 x 3)[0x55925305fa20]{Z} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x2442186 (coo:1, csr:0, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'S' +# Constructed matrix (took 0.192s): (3 x 3)[0x55764ce149d0]{Z} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x2442186 (coo:1, csr:0, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'S' # matrix consistency check took 0.000s (ok) RSB Sparse Blocks Autotuner invoked requesting max 6 splits and max 6 merges in 1 rounds, threads spec.0 (specify negative values to enable threads tuning). Will autotune matrix: 3 x 3, type Z, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:3 -3 iterations (1 th.) took 0.01312s; avg 0.004374s ( +/- 15.32/ 28.19 %); best 0.003704s; worst 0.005607s; std dev. 0.000873 (taking best). -Reference operation time is 0.00370407 s (0.02592 Mflops) with 1 threads. -Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=rows) (max 6 steps, inclusive 3 grace steps) on: 3 x 3, type Z, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz (tpop: 0.003704 Mflops: 0.026) -Merge (3 -> 1 leaves) took w.c.t. of 2.694e-05s, ~8.106e-06s of computing time (of which 1.907e-06s sorting, 2.861e-06s analysis) -3 iterations (1 th.) took 2.599e-05s; avg 8.663e-06s ( +/- 99.62/186.24 %); best 3.32e-08s; worst 2.48e-05s; std dev. 1.142e-05 (taking best). -Reference operation time is 3.31998e-08 s (2892 Mflops) with 1 threads. -After merge step 1: tpop: 3.32e-08 s ~Mflops: 2891.585 nsubm:1 otn:1 -Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 111569.120x: 0.003704s -> 3.32e-08s, so taking this instance. +3 iterations (1 th.) took 0.104s; avg 0.03465s ( +/- 42.29/ 49.99 %); best 0.02s; worst 0.05198s; std dev. 0.01319 (taking best). +Reference operation time is 0.0199978 s (0.004801 Mflops) with 1 threads. +Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=rows) (max 6 steps, inclusive 3 grace steps) on: 3 x 3, type Z, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz (tpop: 0.02 Mflops: 0.005) +Merge (3 -> 1 leaves) took w.c.t. of 4.816e-05s, ~1.693e-05s of computing time (of which 3.099e-06s sorting, 8.821e-06s analysis) +3 iterations (1 th.) took 5.412e-05s; avg 1.804e-05s ( +/- 94.71/189.43 %); best 9.537e-07s; worst 5.221e-05s; std dev. 2.416e-05 (taking best). +Reference operation time is 9.53674e-07 s (100.7 Mflops) with 1 threads. +After merge step 1: tpop: 9.537e-07 s ~Mflops: 100.663 nsubm:1 otn:1 +Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 20969.250x: 0.02s -> 9.537e-07s, so taking this instance. Merged all the matrix leaves: no reason to continue merging. -A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.00956s (of which 3.099e-05s partitioning, 0s I/O); computing times: 8.106e-06s in par. loops, 1.907e-06s sorting, 2.861e-06s analyzing) -Total merge + benchmarking process took 0.00956s, equivalent to 287956.9/2.6 new/old ops (0.02059s for 2 clones -- as 620035.9/5.6 ops, or 310018.0/2.8 ops per clone), SPEEDUP of 111569.120x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 111569.120x (0.003704s -> 3.32e-08s), will amortize in 2.6 ops by saving 0.003704s per op. -In 1 tuning rounds (tot. 0.034s, 0.021s for constructor, 2 clones) obtained a SPEEDUP of 11156812.0% (1.116e+05x) (from 0.02592 to 2892 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.08358s (of which 5.388e-05s partitioning, 0s I/O); computing times: 1.693e-05s in par. loops, 3.099e-06s sorting, 8.821e-06s analyzing) +Total merge + benchmarking process took 0.08358s, equivalent to 87638.8/4.2 new/old ops (0.1833s for 2 clones -- as 192190.5/9.2 ops, or 96095.2/4.6 ops per clone), SPEEDUP of 20969.250x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 20969.250x (0.02s -> 9.537e-07s), will amortize in 4.2 ops by saving 0.02s per op. +In 1 tuning rounds (tot. 0.29s, 0.18s for constructor, 2 clones) obtained a SPEEDUP of 2096825.0% (2.097e+04x) (from 0.004801 to 100.7 Mflops). #pr: updating sample at index 1 (0^th of 8), 0^th touch for (0,0,0,0,0,0,0). -First run of RSB Autotuner took 0.033864 s (3.704e-03 s -> 3.320e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.287576 s (2.000e-02 s -> 9.537e-07 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). RSB Sparse Blocks Autotuner invoked requesting max 0 splits and max 0 merges in 1 rounds, auto threads spec. -Second run of RSB Autotuner took 0.187175 s and estimated a speedup of 1.000000 x (3.320e-08 s -> 3.320e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 1.71234 s and estimated a speedup of 1.000000 x (9.537e-07 s -> 9.537e-07 s per op) in same matrix (1 -> 1 lsubm) #min:1 0 #max:1 0 #sum:3 0 #norm:1.7320508075688772 0 #used index storage compared to COO:28 vs 48 bytes (58.33%) ; compared to CSR:28 vs 40 bytes (77.78%) #%:CONSTRUCTOR_*:SORT SCAN INSERT SCAN+INSERT -%:CONSTRUCTOR_TIMES:A.mtx S N 1 3 3 6 0.000000 0.005394 0.007545 0.012939 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 1 3 3 6 0.012939 -%:RSB_SUBDIVISION_TIME:A.mtx S N 1 3 3 6 0.005394 -%:RSB_SHUFFLE_TIME:A.mtx S N 1 3 3 6 0.007545 -%:ROW_MAJOR_SORT_TIME:A.mtx S N 1 3 3 6 0.000000 -%:ROW_MAJOR_SORT_SCALING:A.mtx S N 1 3 3 6 -nan -%:SORTEDCOO2RSB_TIME:A.mtx S N 1 3 3 6 0.012939 +%:CONSTRUCTOR_TIMES:A.mtx S N 1 3 3 6 0.000001 0.047807 0.071980 0.119787 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 1 3 3 6 0.119788 +%:RSB_SUBDIVISION_TIME:A.mtx S N 1 3 3 6 0.047807 +%:RSB_SHUFFLE_TIME:A.mtx S N 1 3 3 6 0.071980 +%:ROW_MAJOR_SORT_TIME:A.mtx S N 1 3 3 6 0.000001 +%:ROW_MAJOR_SORT_SCALING:A.mtx S N 1 3 3 6 1.000 +%:SORTEDCOO2RSB_TIME:A.mtx S N 1 3 3 6 0.119787 %:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 1 3 3 6 0.000 %:UNSORTEDCOO2RSB_SCALING:A.mtx S N 1 3 3 6 1.00 %:SORTEDCOO2RSB_SCALING:A.mtx S N 1 3 3 6 1.00 %:RSB_SUBDIVISION_SCALING:A.mtx S N 1 3 3 6 1.00 %:RSB_SHUFFLE_SCALING:A.mtx S N 1 3 3 6 1.00 -%:CONSTRUCTOR_SCALING:A.mtx S N 1 3 3 6 -nan 1.00 1.00 1.00 +%:CONSTRUCTOR_SCALING:A.mtx S N 1 3 3 6 1.00 1.00 1.00 1.00 #%:SM_COUNTS: Tot HalfwordCsr FullwordCsr HalfwordCoo FullwordCoo %:SM_COUNTS:A.mtx S N 1 3 3 6 1 1 0 0 0 %:SM_IDXOCCUPATIONRSBVSCOOANDCSR:A.mtx S N 1 3 3 6 28 48 36 @@ -3365,47 +3401,47 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 1 3 3 6 6 6 6 # # Using 4 threads -# Constructed matrix (took 0.024s): (3 x 3)[0x55925305fa20]{Z} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x2442186 (coo:1, csr:0, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'S' +# Constructed matrix (took 0.236s): (3 x 3)[0x55764ce149d0]{Z} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x2442186 (coo:1, csr:0, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'S' # matrix consistency check took 0.000s (ok) RSB Sparse Blocks Autotuner invoked requesting max 6 splits and max 6 merges in 1 rounds, threads spec.1 (specify negative values to enable threads tuning). Will autotune matrix: 3 x 3, type Z, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:3 -3 iterations (4 th.) took 0.01085s; avg 0.003618s ( +/- 7.29/ 4.19 %); best 0.003354s; worst 0.003769s; std dev. 0.0001873 (taking best). -Reference operation time is 0.00335383 s (0.02862 Mflops) with 4 threads. -Starting merge (user-supplied threads) based auto-tuning procedure (transA=N, nrhs=1, order=rows) (max 6 steps, inclusive 3 grace steps) on: 3 x 3, type Z, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz (tpop: 0.003354 Mflops: 0.029) -Merge (3 -> 1 leaves) took w.c.t. of 1.001e-05s, ~4.053e-06s of computing time (of which 1.192e-06s sorting, 2.146e-06s analysis) -3 iterations (4 th.) took 2.861e-06s; avg 9.537e-07s ( +/- 96.52/100.00 %); best 3.32e-08s; worst 1.907e-06s; std dev. 7.787e-07 (taking best). -Reference operation time is 3.31998e-08 s (2892 Mflops) with 4 threads. -After merge step 1: tpop: 3.32e-08 s ~Mflops: 2891.585 nsubm:1 otn:1 -Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 101019.749x: 0.003354s -> 3.32e-08s, so taking this instance. +3 iterations (4 th.) took 0.104s; avg 0.03467s ( +/- 7.68/ 3.87 %); best 0.032s; worst 0.03601s; std dev. 0.001883 (taking best). +Reference operation time is 0.0320041 s (0.003 Mflops) with 4 threads. +Starting merge (user-supplied threads) based auto-tuning procedure (transA=N, nrhs=1, order=rows) (max 6 steps, inclusive 3 grace steps) on: 3 x 3, type Z, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz (tpop: 0.032 Mflops: 0.003) +Merge (3 -> 1 leaves) took w.c.t. of 3.29e-05s, ~1.097e-05s of computing time (of which 2.861e-06s sorting, 5.96e-06s analysis) +3 iterations (4 th.) took 1.001e-05s; avg 3.338e-06s ( +/- 71.43/135.71 %); best 9.537e-07s; worst 7.868e-06s; std dev. 3.205e-06 (taking best). +Reference operation time is 9.53674e-07 s (100.7 Mflops) with 4 threads. +After merge step 1: tpop: 9.537e-07 s ~Mflops: 100.663 nsubm:1 otn:1 +Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 33558.750x: 0.032s -> 9.537e-07s, so taking this instance. Merged all the matrix leaves: no reason to continue merging. -A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.01131s (of which 1.311e-05s partitioning, 0s I/O); computing times: 4.053e-06s in par. loops, 1.192e-06s sorting, 2.146e-06s analyzing) -Total merge + benchmarking process took 0.01131s, equivalent to 340789.9/3.4 new/old ops (0.02254s for 2 clones -- as 678879.7/6.7 ops, or 339439.9/3.4 ops per clone), SPEEDUP of 101019.749x -Applying multi-merge (3 -> 1 leaves, 1 steps, 1 -> 1 th.sp.) yielded SPEEDUP of 101019.749x (0.003354s -> 3.32e-08s), will amortize in 3.4 ops by saving 0.003354s per op. -In 1 tuning rounds (tot. 0.033s, 0.023s for constructor, 2 clones) obtained a SPEEDUP of 10101874.9% (1.01e+05x) (from 0.02862 to 2892 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.08412s (of which 3.791e-05s partitioning, 0s I/O); computing times: 1.097e-05s in par. loops, 2.861e-06s sorting, 5.96e-06s analyzing) +Total merge + benchmarking process took 0.08412s, equivalent to 88206.2/2.6 new/old ops (0.168s for 2 clones -- as 176112.8/5.2 ops, or 88056.4/2.6 ops per clone), SPEEDUP of 33558.750x +Applying multi-merge (3 -> 1 leaves, 1 steps, 1 -> 1 th.sp.) yielded SPEEDUP of 33558.750x (0.032s -> 9.537e-07s), will amortize in 2.6 ops by saving 0.032s per op. +In 1 tuning rounds (tot. 0.27s, 0.17s for constructor, 2 clones) obtained a SPEEDUP of 3355775.0% (3.356e+04x) (from 0.003 to 100.7 Mflops). #pr: updating sample at index 5 (1^th of 8), 0^th touch for (0,1,0,0,0,0,0). -First run of RSB Autotuner took 0.0334649 s (3.354e-03 s -> 3.320e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.272152 s (3.200e-02 s -> 9.537e-07 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). RSB Sparse Blocks Autotuner invoked requesting max 0 splits and max 0 merges in 1 rounds, auto threads spec. -Second run of RSB Autotuner took 0.188847 s and estimated a speedup of 1.000000 x (3.320e-08 s -> 3.320e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 1.62781 s and estimated a speedup of 1.000000 x (9.537e-07 s -> 9.537e-07 s per op) in same matrix (1 -> 1 lsubm) #min:1 0 #max:1 0 #sum:3 0 #norm:1.7320508075688772 0 #used index storage compared to COO:28 vs 48 bytes (58.33%) ; compared to CSR:28 vs 40 bytes (77.78%) #%:CONSTRUCTOR_*:SORT SCAN INSERT SCAN+INSERT -%:CONSTRUCTOR_TIMES:A.mtx S N 4 3 3 6 0.000000 0.007210 0.009037 0.016247 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 4 3 3 6 0.016247 -%:RSB_SUBDIVISION_TIME:A.mtx S N 4 3 3 6 0.007210 -%:RSB_SHUFFLE_TIME:A.mtx S N 4 3 3 6 0.009037 -%:ROW_MAJOR_SORT_TIME:A.mtx S N 4 3 3 6 0.000000 -%:ROW_MAJOR_SORT_SCALING:A.mtx S N 4 3 3 6 -nan -%:SORTEDCOO2RSB_TIME:A.mtx S N 4 3 3 6 0.016247 +%:CONSTRUCTOR_TIMES:A.mtx S N 4 3 3 6 0.000001 0.063720 0.119897 0.183617 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 4 3 3 6 0.183618 +%:RSB_SUBDIVISION_TIME:A.mtx S N 4 3 3 6 0.063720 +%:RSB_SHUFFLE_TIME:A.mtx S N 4 3 3 6 0.119897 +%:ROW_MAJOR_SORT_TIME:A.mtx S N 4 3 3 6 0.000001 +%:ROW_MAJOR_SORT_SCALING:A.mtx S N 4 3 3 6 1.000 +%:SORTEDCOO2RSB_TIME:A.mtx S N 4 3 3 6 0.183617 %:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 4 3 3 6 0.000 -%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 4 3 3 6 0.80 -%:SORTEDCOO2RSB_SCALING:A.mtx S N 4 3 3 6 0.80 +%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 4 3 3 6 0.65 +%:SORTEDCOO2RSB_SCALING:A.mtx S N 4 3 3 6 0.65 %:RSB_SUBDIVISION_SCALING:A.mtx S N 4 3 3 6 0.75 -%:RSB_SHUFFLE_SCALING:A.mtx S N 4 3 3 6 0.83 -%:CONSTRUCTOR_SCALING:A.mtx S N 4 3 3 6 -nan 0.75 0.83 0.80 +%:RSB_SHUFFLE_SCALING:A.mtx S N 4 3 3 6 0.60 +%:CONSTRUCTOR_SCALING:A.mtx S N 4 3 3 6 1.00 0.75 0.60 0.65 #%:SM_COUNTS: Tot HalfwordCsr FullwordCsr HalfwordCoo FullwordCoo %:SM_COUNTS:A.mtx S N 4 3 3 6 1 1 0 0 0 %:SM_IDXOCCUPATIONRSBVSCOOANDCSR:A.mtx S N 4 3 3 6 28 48 36 @@ -3414,50 +3450,50 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 4 3 3 6 6 6 6 # %operation:matrix CONSTRUCTOR[1] SPMV[1] SPMV[4] -%operation:A.mtx 0.0203981 1e+09 1e+09 +%operation:A.mtx 0.191805 1e+09 1e+09 %constructor:matrix SORT[1] SCAN[1] SHUFFLE[1] INSERT[1] -%constructor:A.mtx 0 0.00539398 0 0.00754499 +%constructor:A.mtx 9.53674e-07 0.047807 0 0.07198 # symmetric matrix --- skipping transposed benchmarking # multi-nrhs benchmarking (1,2) -- now using nrhs 2. # Using alpha=1 beta=1 order=rows for rsb_spmv/rsb_spsv/rsb_spmm/rsb_spsm. # multi-transpose benchmarking -- now using transA = N. # will use input matrix flags: RSB_FLAG_USE_HALFWORD_INDICES, RSB_FLAG_SORTED_INPUT, RSB_FLAG_QUAD_PARTITIONING, RSB_FLAG_SYMMETRIC, RSB_FLAG_OWN_PARTITIONING_ARRAYS # Using 1 threads -# Constructed matrix (took 0.020s): (3 x 3)[0x55925305fa20]{Z} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x2442186 (coo:1, csr:0, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'S' +# Constructed matrix (took 0.208s): (3 x 3)[0x55764ce149d0]{Z} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x2442186 (coo:1, csr:0, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'S' # matrix consistency check took 0.000s (ok) RSB Sparse Blocks Autotuner invoked requesting max 6 splits and max 6 merges in 1 rounds, threads spec.0 (specify negative values to enable threads tuning). Will autotune matrix: 3 x 3, type Z, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:3 -3 iterations (1 th.) took 0.01113s; avg 0.00371s ( +/- 1.41/ 0.83 %); best 0.003658s; worst 0.003741s; std dev. 3.716e-05 (taking best). -Reference operation time is 0.00365806 s (0.05249 Mflops) with 1 threads. -Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=2, order=rows) (max 6 steps, inclusive 3 grace steps) on: 3 x 3, type Z, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz (tpop: 0.003658 Mflops: 0.052) -Merge (3 -> 1 leaves) took w.c.t. of 7.868e-06s, ~2.861e-06s of computing time (of which 9.537e-07s sorting, 1.907e-06s analysis) -3 iterations (1 th.) took 1.407e-05s; avg 4.689e-06s ( +/- 99.29/179.66 %); best 3.32e-08s; worst 1.311e-05s; std dev. 5.969e-06 (taking best). -Reference operation time is 3.31998e-08 s (5783 Mflops) with 1 threads. -After merge step 1: tpop: 3.32e-08 s ~Mflops: 5783.170 nsubm:1 otn:1 -Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 110183.124x: 0.003658s -> 3.32e-08s, so taking this instance. +3 iterations (1 th.) took 0.104s; avg 0.03466s ( +/- 7.90/ 4.01 %); best 0.03192s; worst 0.03605s; std dev. 0.001937 (taking best). +Reference operation time is 0.031924 s (0.006014 Mflops) with 1 threads. +Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=2, order=rows) (max 6 steps, inclusive 3 grace steps) on: 3 x 3, type Z, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz (tpop: 0.03192 Mflops: 0.006) +Merge (3 -> 1 leaves) took w.c.t. of 3.505e-05s, ~1.216e-05s of computing time (of which 2.146e-06s sorting, 6.914e-06s analysis) +3 iterations (1 th.) took 1.311e-05s; avg 4.371e-06s ( +/- 78.18/129.09 %); best 9.537e-07s; worst 1.001e-05s; std dev. 4.019e-06 (taking best). +Reference operation time is 9.53674e-07 s (201.3 Mflops) with 1 threads. +After merge step 1: tpop: 9.537e-07 s ~Mflops: 201.327 nsubm:1 otn:1 +Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 33474.750x: 0.03192s -> 9.537e-07s, so taking this instance. Merged all the matrix leaves: no reason to continue merging. -A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.01115s (of which 1.192e-05s partitioning, 0s I/O); computing times: 2.861e-06s in par. loops, 9.537e-07s sorting, 1.907e-06s analyzing) -Total merge + benchmarking process took 0.01115s, equivalent to 335755.8/3.0 new/old ops (0.02228s for 2 clones -- as 670965.9/6.1 ops, or 335482.9/3.0 ops per clone), SPEEDUP of 110183.124x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 110183.124x (0.003658s -> 3.32e-08s), will amortize in 3.0 ops by saving 0.003658s per op. -In 1 tuning rounds (tot. 0.033s, 0.022s for constructor, 2 clones) obtained a SPEEDUP of 11018212.4% (1.102e+05x) (from 0.05249 to 5783 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.08397s (of which 4.792e-05s partitioning, 0s I/O); computing times: 1.216e-05s in par. loops, 2.146e-06s sorting, 6.914e-06s analyzing) +Total merge + benchmarking process took 0.08397s, equivalent to 88043.8/2.6 new/old ops (0.1838s for 2 clones -- as 192704.2/5.8 ops, or 96352.1/2.9 ops per clone), SPEEDUP of 33474.750x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 33474.750x (0.03192s -> 9.537e-07s), will amortize in 2.6 ops by saving 0.03192s per op. +In 1 tuning rounds (tot. 0.29s, 0.18s for constructor, 2 clones) obtained a SPEEDUP of 3347375.0% (3.347e+04x) (from 0.006014 to 201.3 Mflops). #pr: updating sample at index 3 (2^th of 8), 0^th touch for (0,0,0,0,1,0,0). -First run of RSB Autotuner took 0.0334868 s (3.658e-03 s -> 3.320e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.28797 s (3.192e-02 s -> 9.537e-07 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). RSB Sparse Blocks Autotuner invoked requesting max 0 splits and max 0 merges in 1 rounds, auto threads spec. -Second run of RSB Autotuner took 0.0416501 s and estimated a speedup of 1.000000 x (3.320e-08 s -> 3.320e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 1.61602 s and estimated a speedup of 1.000000 x (1.192e-06 s -> 1.192e-06 s per op) in same matrix (1 -> 1 lsubm) #min:1 0 #max:1 0 #sum:3 0 #norm:1.7320508075688772 0 #used index storage compared to COO:28 vs 48 bytes (58.33%) ; compared to CSR:28 vs 40 bytes (77.78%) #%:CONSTRUCTOR_*:SORT SCAN INSERT SCAN+INSERT -%:CONSTRUCTOR_TIMES:A.mtx S N 1 3 3 6 0.000000 0.005397 0.007445 0.012842 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 1 3 3 6 0.012842 -%:RSB_SUBDIVISION_TIME:A.mtx S N 1 3 3 6 0.005397 -%:RSB_SHUFFLE_TIME:A.mtx S N 1 3 3 6 0.007445 +%:CONSTRUCTOR_TIMES:A.mtx S N 1 3 3 6 0.000000 0.051752 0.067989 0.119741 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 1 3 3 6 0.119741 +%:RSB_SUBDIVISION_TIME:A.mtx S N 1 3 3 6 0.051752 +%:RSB_SHUFFLE_TIME:A.mtx S N 1 3 3 6 0.067989 %:ROW_MAJOR_SORT_TIME:A.mtx S N 1 3 3 6 0.000000 %:ROW_MAJOR_SORT_SCALING:A.mtx S N 1 3 3 6 -nan -%:SORTEDCOO2RSB_TIME:A.mtx S N 1 3 3 6 0.012842 +%:SORTEDCOO2RSB_TIME:A.mtx S N 1 3 3 6 0.119741 %:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 1 3 3 6 0.000 %:UNSORTEDCOO2RSB_SCALING:A.mtx S N 1 3 3 6 1.00 %:SORTEDCOO2RSB_SCALING:A.mtx S N 1 3 3 6 1.00 @@ -3472,47 +3508,47 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 1 3 3 6 6 6 6 # # Using 4 threads -# Constructed matrix (took 0.010s): (3 x 3)[0x55925305fa20]{Z} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x2442186 (coo:1, csr:0, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'S' +# Constructed matrix (took 0.255s): (3 x 3)[0x55764ce149d0]{Z} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x2442186 (coo:1, csr:0, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'S' # matrix consistency check took 0.000s (ok) RSB Sparse Blocks Autotuner invoked requesting max 6 splits and max 6 merges in 1 rounds, threads spec.1 (specify negative values to enable threads tuning). Will autotune matrix: 3 x 3, type Z, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:3 -3 iterations (4 th.) took 7.796e-05s; avg 2.599e-05s ( +/- 3.67/ 7.34 %); best 2.503e-05s; worst 2.789e-05s; std dev. 1.349e-06 (taking best). -Reference operation time is 2.5034e-05 s (7.67 Mflops) with 4 threads. -Starting merge (user-supplied threads) based auto-tuning procedure (transA=N, nrhs=2, order=rows) (max 6 steps, inclusive 3 grace steps) on: 3 x 3, type Z, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz (tpop: 2.503e-05 Mflops: 7.670) -Merge (3 -> 1 leaves) took w.c.t. of 7.153e-06s, ~1.907e-06s of computing time (of which 9.537e-07s sorting, 2.146e-06s analysis) -3 iterations (4 th.) took 2.146e-06s; avg 7.153e-07s ( +/- 95.36/ 66.67 %); best 3.32e-08s; worst 1.192e-06s; std dev. 5.15e-07 (taking best). -Reference operation time is 3.31998e-08 s (5783 Mflops) with 4 threads. -After merge step 1: tpop: 3.32e-08 s ~Mflops: 5783.170 nsubm:1 otn:1 -Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 754.039x: 2.503e-05s -> 3.32e-08s, so taking this instance. +3 iterations (4 th.) took 0.09948s; avg 0.03316s ( +/- 5.28/ 8.72 %); best 0.03141s; worst 0.03605s; std dev. 0.002059 (taking best). +Reference operation time is 0.031409 s (0.006113 Mflops) with 4 threads. +Starting merge (user-supplied threads) based auto-tuning procedure (transA=N, nrhs=2, order=rows) (max 6 steps, inclusive 3 grace steps) on: 3 x 3, type Z, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz (tpop: 0.03141 Mflops: 0.006) +Merge (3 -> 1 leaves) took w.c.t. of 3.29e-05s, ~1.192e-05s of computing time (of which 1.907e-06s sorting, 5.96e-06s analysis) +3 iterations (4 th.) took 1.192e-05s; avg 3.974e-06s ( +/- 76.00/152.00 %); best 9.537e-07s; worst 1.001e-05s; std dev. 4.271e-06 (taking best). +Reference operation time is 9.53674e-07 s (201.3 Mflops) with 4 threads. +After merge step 1: tpop: 9.537e-07 s ~Mflops: 201.327 nsubm:1 otn:1 +Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 32934.750x: 0.03141s -> 9.537e-07s, so taking this instance. Merged all the matrix leaves: no reason to continue merging. -A total of 1 merge steps (of max 6) (3 -> 1 subms) took 7.2e-05s (of which 9.06e-06s partitioning, 0s I/O); computing times: 1.907e-06s in par. loops, 9.537e-07s sorting, 2.146e-06s analyzing) -Total merge + benchmarking process took 7.2e-05s, equivalent to 2168.8/2.9 new/old ops (8.798e-05s for 2 clones -- as 2649.9/3.5 ops, or 1325.0/1.8 ops per clone), SPEEDUP of 754.039x -Applying multi-merge (3 -> 1 leaves, 1 steps, 1 -> 1 th.sp.) yielded SPEEDUP of 754.039x (2.503e-05s -> 3.32e-08s), will amortize in 2.9 ops by saving 2.5e-05s per op. -In 1 tuning rounds (tot. 0.00021s, 8.8e-05s for constructor, 2 clones) obtained a SPEEDUP of 75303.9% (754x) (from 7.67 to 5783 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.09996s (of which 3.791e-05s partitioning, 0s I/O); computing times: 1.192e-05s in par. loops, 1.907e-06s sorting, 5.96e-06s analyzing) +Total merge + benchmarking process took 0.09996s, equivalent to 104820.0/3.2 new/old ops (0.1883s for 2 clones -- as 197474.0/6.0 ops, or 98737.0/3.0 ops per clone), SPEEDUP of 32934.750x +Applying multi-merge (3 -> 1 leaves, 1 steps, 1 -> 1 th.sp.) yielded SPEEDUP of 32934.750x (0.03141s -> 9.537e-07s), will amortize in 3.2 ops by saving 0.03141s per op. +In 1 tuning rounds (tot. 0.29s, 0.19s for constructor, 2 clones) obtained a SPEEDUP of 3293375.0% (3.293e+04x) (from 0.006113 to 201.3 Mflops). #pr: updating sample at index 7 (3^th of 8), 0^th touch for (0,1,0,0,1,0,0). -First run of RSB Autotuner took 0.000224829 s (2.503e-05 s -> 3.320e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.28801 s (3.141e-02 s -> 9.537e-07 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). RSB Sparse Blocks Autotuner invoked requesting max 0 splits and max 0 merges in 1 rounds, auto threads spec. -Second run of RSB Autotuner took 0.00103807 s and estimated a speedup of 1.000000 x (3.320e-08 s -> 3.320e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 1.49993 s and estimated a speedup of 1.000000 x (9.537e-07 s -> 9.537e-07 s per op) in same matrix (1 -> 1 lsubm) #min:1 0 #max:1 0 #sum:3 0 #norm:1.7320508075688772 0 #used index storage compared to COO:28 vs 48 bytes (58.33%) ; compared to CSR:28 vs 40 bytes (77.78%) #%:CONSTRUCTOR_*:SORT SCAN INSERT SCAN+INSERT -%:CONSTRUCTOR_TIMES:A.mtx S N 4 3 3 6 0.000000 0.001893 0.007897 0.009790 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 4 3 3 6 0.009790 -%:RSB_SUBDIVISION_TIME:A.mtx S N 4 3 3 6 0.001893 -%:RSB_SHUFFLE_TIME:A.mtx S N 4 3 3 6 0.007897 -%:ROW_MAJOR_SORT_TIME:A.mtx S N 4 3 3 6 0.000000 -%:ROW_MAJOR_SORT_SCALING:A.mtx S N 4 3 3 6 -nan -%:SORTEDCOO2RSB_TIME:A.mtx S N 4 3 3 6 0.009790 +%:CONSTRUCTOR_TIMES:A.mtx S N 4 3 3 6 0.000001 0.075440 0.115985 0.191425 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 4 3 3 6 0.191426 +%:RSB_SUBDIVISION_TIME:A.mtx S N 4 3 3 6 0.075440 +%:RSB_SHUFFLE_TIME:A.mtx S N 4 3 3 6 0.115985 +%:ROW_MAJOR_SORT_TIME:A.mtx S N 4 3 3 6 0.000001 +%:ROW_MAJOR_SORT_SCALING:A.mtx S N 4 3 3 6 0.000 +%:SORTEDCOO2RSB_TIME:A.mtx S N 4 3 3 6 0.191425 %:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 4 3 3 6 0.000 -%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 4 3 3 6 1.31 -%:SORTEDCOO2RSB_SCALING:A.mtx S N 4 3 3 6 1.31 -%:RSB_SUBDIVISION_SCALING:A.mtx S N 4 3 3 6 2.85 -%:RSB_SHUFFLE_SCALING:A.mtx S N 4 3 3 6 0.94 -%:CONSTRUCTOR_SCALING:A.mtx S N 4 3 3 6 -nan 2.85 0.94 1.31 +%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 4 3 3 6 0.63 +%:SORTEDCOO2RSB_SCALING:A.mtx S N 4 3 3 6 0.63 +%:RSB_SUBDIVISION_SCALING:A.mtx S N 4 3 3 6 0.69 +%:RSB_SHUFFLE_SCALING:A.mtx S N 4 3 3 6 0.59 +%:CONSTRUCTOR_SCALING:A.mtx S N 4 3 3 6 0.00 0.69 0.59 0.63 #%:SM_COUNTS: Tot HalfwordCsr FullwordCsr HalfwordCoo FullwordCoo %:SM_COUNTS:A.mtx S N 4 3 3 6 1 1 0 0 0 %:SM_IDXOCCUPATIONRSBVSCOOANDCSR:A.mtx S N 4 3 3 6 28 48 36 @@ -3521,184 +3557,184 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 4 3 3 6 6 6 6 # %operation:matrix CONSTRUCTOR[1] SPMV[1] SPMV[4] -%operation:A.mtx 0.020344 1e+09 1e+09 +%operation:A.mtx 0.207772 1e+09 1e+09 %constructor:matrix SORT[1] SCAN[1] SHUFFLE[1] INSERT[1] -%constructor:A.mtx 0 0.00539684 0 0.0074451 +%constructor:A.mtx 0 0.0517519 0 0.0679889 # symmetric matrix --- skipping transposed benchmarking -# so far, program took 6.849s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.520s/0.000s . +# so far, program took 14.516s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 7.592s/0.000s . getrusage() stats: -ru_maxrss: 26 (maximum resident set size -- MB) -ru_stime : 0.2713s (system CPU time used) -ru_utime : 32.24s (user CPU time used) +ru_maxrss: 7 (maximum resident set size -- MB) +ru_stime : 0.145s (system CPU time used) +ru_utime : 58.89s (user CPU time used) # benchmarking terminated --- finalizing run. # ====== BEGIN Total summary record. #pr: ======== Limiting to nrhs=1: #pr: 2 samples (out of 4) matched the dump limiting criteria. #pr: Dump from a base of 4 samples (of max 8) ordered by (1,2,1,1,2,1,2) = (filename x cores x incX x incY x nrhs x typecode x transA). pr: BESTCODE MTX NR NC NNZ NRHS TYPE SYM TRANS NT AT-NT AT-MKL-NT BPNZ AT-BPNZ NSUBM AT-SUBM RSBBEST-MFLOPS OPTIME MKL-OPTIME AT-OPTIME AT-MKL-OPTIME AT-TIME RWminBW-GBps CB-bpf AT-MS CMFLOPS -pr: 1:R_R A 3 3 6 1 Z S N 1 1 0 4.0000 4.6667 3 1 2891.58 3.704e-03 0.000e+00 3.320e-08 0.000e+00 3.386e-02 8.07e+00 2.29e+00 1 9.60e-05 -pr: 5:R_R A 3 3 6 1 Z S N 4 1 0 4.0000 4.6667 3 1 2891.58 3.354e-03 0.000e+00 3.320e-08 0.000e+00 3.346e-02 8.07e+00 2.29e+00 1 9.60e-05 +pr: 1:R_R A 3 3 6 1 Z S N 1 1 0 4.0000 4.6667 3 1 100.66 2.000e-02 0.000e+00 9.537e-07 0.000e+00 2.876e-01 2.81e-01 2.29e+00 1 9.60e-05 +pr: 5:R_R A 3 3 6 1 Z S N 4 1 0 4.0000 4.6667 3 1 100.66 3.200e-02 0.000e+00 9.537e-07 0.000e+00 2.722e-01 2.81e-01 2.29e+00 1 9.60e-05 #pr: 2 samples (out of 4) matched the dump limiting criteria. #pr: below, we define 'successful' autotuning when speedup of 1.010000x is exceeded, and 'tuned' results even the ones which are same as untuned #pr: rsb autotuning was successful in 2 cases (100.00 %) and unsuccessful in 0 cases (0.00 %) -#pr: (in succ. cases rsb autotuning gave avg. 10629343.4 % faster, avg. sp. ratio 106294.434x, max sp. ratio 111569.120x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 1013996.4/1007985.6/1020007.2/2027992.8 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 9.6/ 9.1/ 10.0/ 19.1 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 9.6, min. 9.1, max. 10.0 ops) +#pr: (in succ. cases rsb autotuning gave avg. 2726300.0 % faster, avg. sp. ratio 27264.000x, max sp. ratio 33558.750x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 293458.8/285372.2/301545.2/586917.5 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 11.4/ 8.5/ 14.4/ 22.9 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 11.4, min. 8.5, max. 14.4 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 32/ 32/ 32) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 96/ 96/ 96) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 6.627/ 6.627/ 6.627,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 16.145/ 8.072/ 8.072,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 0.231/ 0.231/ 0.231,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 0.562/ 0.281/ 0.281,GBps) #pr: (avg/min/max code balance (bytes read at least once per flop) 2.292/ 2.292/ 2.292) #pr: (avg/min/max (avg) bytes per nnz after successful tuning were 4.667/ 4.667/ 4.667) #pr: (matrix has been subdivided more/less/same in resp. 0 / 2 /0 cases) #pr: (matrix has used more/less/same threads in resp. 0 / 1 /1 cases) #pr: no unsuccessful rsb autotuning attempt (according to 1.01x threshold) -#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.03 s, min 0.03 s, max 0.03 s, tot 0.07 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.03 s, min 0.03 s, max 0.03 s, tot 0.07 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 2.892e+03, min 2.892e+03, max 2.892e+03 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 2.727e-02, min 2.592e-02, max 2.862e-02 (2 samples) -#pr: best tun. rsb operation time was: on avg. 3.320e-08s, min 3.320e-08s, max 3.320e-08s, tot 6.640e-08s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 3.529e-03s, min 3.354e-03s, max 3.704e-03s, tot 7.058e-03s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 3.320e+00 3.320e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 4.045e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.28 s, min 0.27 s, max 0.29 s, tot 0.56 s (2 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.28 s, min 0.27 s, max 0.29 s, tot 0.56 s (2 samples) +#pr: best tun. rsb canon. mflops were: on avg. 1.007e+02, min 1.007e+02, max 1.007e+02 (2 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 3.900e-03, min 3.000e-03, max 4.801e-03 (2 samples) +#pr: best tun. rsb operation time was: on avg. 9.537e-07s, min 9.537e-07s, max 9.537e-07s, tot 1.907e-06s (2 samples) +#pr: ref. unt. rsb operation time was: on avg. 2.600e-02s, min 2.000e-02s, max 3.200e-02s, tot 5.200e-02s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.121e+01 1.121e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 2.353e+00 #pr: ======== Limiting to nrhs=2: #pr: 2 samples (out of 4) matched the dump limiting criteria. #pr: Dump from a base of 4 samples (of max 8) ordered by (1,2,1,1,2,1,2) = (filename x cores x incX x incY x nrhs x typecode x transA). pr: BESTCODE MTX NR NC NNZ NRHS TYPE SYM TRANS NT AT-NT AT-MKL-NT BPNZ AT-BPNZ NSUBM AT-SUBM RSBBEST-MFLOPS OPTIME MKL-OPTIME AT-OPTIME AT-MKL-OPTIME AT-TIME RWminBW-GBps CB-bpf AT-MS CMFLOPS -pr: 3:R_R A 3 3 6 2 Z S N 1 1 0 4.0000 4.6667 3 1 5783.17 3.658e-03 0.000e+00 3.320e-08 0.000e+00 3.349e-02 1.24e+01 1.65e+00 1 1.92e-04 -pr: 7:R_R A 3 3 6 2 Z S N 4 1 0 4.0000 4.6667 3 1 5783.17 2.503e-05 0.000e+00 3.320e-08 0.000e+00 2.248e-04 1.24e+01 1.65e+00 1 1.92e-04 +pr: 3:R_R A 3 3 6 2 Z S N 1 1 0 4.0000 4.6667 3 1 201.33 3.192e-02 0.000e+00 9.537e-07 0.000e+00 2.880e-01 4.32e-01 1.65e+00 1 1.92e-04 +pr: 7:R_R A 3 3 6 2 Z S N 4 1 0 4.0000 4.6667 3 1 201.33 3.141e-02 0.000e+00 9.537e-07 0.000e+00 2.880e-01 4.32e-01 1.65e+00 1 1.92e-04 #pr: 2 samples (out of 4) matched the dump limiting criteria. #pr: below, we define 'successful' autotuning when speedup of 1.010000x is exceeded, and 'tuned' results even the ones which are same as untuned #pr: rsb autotuning was successful in 2 cases (100.00 %) and unsuccessful in 0 cases (0.00 %) -#pr: (in succ. cases rsb autotuning gave avg. 5546758.2 % faster, avg. sp. ratio 55468.582x, max sp. ratio 110183.124x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 507709.2/6772.0/1008646.3/1015418.3 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 9.1/ 9.0/ 9.2/ 18.1 untuned ops) +#pr: (in succ. cases rsb autotuning gave avg. 3320375.0 % faster, avg. sp. ratio 33204.750x, max sp. ratio 33474.750x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 301979.4/301958.5/302000.2/603958.8 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 9.1/ 9.0/ 9.2/ 18.2 untuned ops) #pr: (and amortizes from untuned rsb in avg. 9.1, min. 9.0, max. 9.2 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 32/ 32/ 32) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 96/ 96/ 96) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 9.518/ 9.518/ 9.518,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 24.819/ 12.410/ 12.410,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 0.331/ 0.331/ 0.331,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 0.864/ 0.432/ 0.432,GBps) #pr: (avg/min/max code balance (bytes read at least once per flop) 1.646/ 1.646/ 1.646) #pr: (avg/min/max (avg) bytes per nnz after successful tuning were 4.667/ 4.667/ 4.667) #pr: (matrix has been subdivided more/less/same in resp. 0 / 2 /0 cases) #pr: (matrix has used more/less/same threads in resp. 0 / 1 /1 cases) #pr: no unsuccessful rsb autotuning attempt (according to 1.01x threshold) -#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.02 s, min 0.00 s, max 0.03 s, tot 0.03 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.02 s, min 0.00 s, max 0.03 s, tot 0.03 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 5.783e+03, min 5.783e+03, max 5.783e+03 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 3.861e+00, min 5.249e-02, max 7.670e+00 (2 samples) -#pr: best tun. rsb operation time was: on avg. 3.320e-08s, min 3.320e-08s, max 3.320e-08s, tot 6.640e-08s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 1.842e-03s, min 2.503e-05s, max 3.658e-03s, tot 3.683e-03s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 2.312e+00 2.312e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 4.045e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.29 s, min 0.29 s, max 0.29 s, tot 0.58 s (2 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.29 s, min 0.29 s, max 0.29 s, tot 0.58 s (2 samples) +#pr: best tun. rsb canon. mflops were: on avg. 2.013e+02, min 2.013e+02, max 2.013e+02 (2 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 6.064e-03, min 6.014e-03, max 6.113e-03 (2 samples) +#pr: best tun. rsb operation time was: on avg. 9.537e-07s, min 9.537e-07s, max 9.537e-07s, tot 1.907e-06s (2 samples) +#pr: ref. unt. rsb operation time was: on avg. 3.167e-02s, min 3.141e-02s, max 3.192e-02s, tot 6.333e-02s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 7.807e+00 7.807e+00 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 2.353e+00 #pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 2.000e+00 x, min 2.000e+00 x, max 2.000e+00 x (2 samples, the non-min-nrhs ones) #pr: ======== Limiting to transA=N: #pr: Dump from a base of 4 samples (of max 8) ordered by (1,2,1,1,2,1,2) = (filename x cores x incX x incY x nrhs x typecode x transA). pr: BESTCODE MTX NR NC NNZ NRHS TYPE SYM TRANS NT AT-NT AT-MKL-NT BPNZ AT-BPNZ NSUBM AT-SUBM RSBBEST-MFLOPS OPTIME MKL-OPTIME AT-OPTIME AT-MKL-OPTIME AT-TIME RWminBW-GBps CB-bpf AT-MS CMFLOPS -pr: 1:R_R A 3 3 6 1 Z S N 1 1 0 4.0000 4.6667 3 1 2891.58 3.704e-03 0.000e+00 3.320e-08 0.000e+00 3.386e-02 8.07e+00 2.29e+00 1 9.60e-05 -pr: 3:R_R A 3 3 6 2 Z S N 1 1 0 4.0000 4.6667 3 1 5783.17 3.658e-03 0.000e+00 3.320e-08 0.000e+00 3.349e-02 1.24e+01 1.65e+00 1 1.92e-04 -pr: 5:R_R A 3 3 6 1 Z S N 4 1 0 4.0000 4.6667 3 1 2891.58 3.354e-03 0.000e+00 3.320e-08 0.000e+00 3.346e-02 8.07e+00 2.29e+00 1 9.60e-05 -pr: 7:R_R A 3 3 6 2 Z S N 4 1 0 4.0000 4.6667 3 1 5783.17 2.503e-05 0.000e+00 3.320e-08 0.000e+00 2.248e-04 1.24e+01 1.65e+00 1 1.92e-04 +pr: 1:R_R A 3 3 6 1 Z S N 1 1 0 4.0000 4.6667 3 1 100.66 2.000e-02 0.000e+00 9.537e-07 0.000e+00 2.876e-01 2.81e-01 2.29e+00 1 9.60e-05 +pr: 3:R_R A 3 3 6 2 Z S N 1 1 0 4.0000 4.6667 3 1 201.33 3.192e-02 0.000e+00 9.537e-07 0.000e+00 2.880e-01 4.32e-01 1.65e+00 1 1.92e-04 +pr: 5:R_R A 3 3 6 1 Z S N 4 1 0 4.0000 4.6667 3 1 100.66 3.200e-02 0.000e+00 9.537e-07 0.000e+00 2.722e-01 2.81e-01 2.29e+00 1 9.60e-05 +pr: 7:R_R A 3 3 6 2 Z S N 4 1 0 4.0000 4.6667 3 1 201.33 3.141e-02 0.000e+00 9.537e-07 0.000e+00 2.880e-01 4.32e-01 1.65e+00 1 1.92e-04 #pr: below, we define 'successful' autotuning when speedup of 1.010000x is exceeded, and 'tuned' results even the ones which are same as untuned #pr: rsb autotuning was successful in 4 cases (100.00 %) and unsuccessful in 0 cases (0.00 %) -#pr: (in succ. cases rsb autotuning gave avg. 8088050.8 % faster, avg. sp. ratio 80881.508x, max sp. ratio 111569.120x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 760852.8/6772.0/1020007.2/3043411.1 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 9.3/ 9.0/ 10.0/ 37.3 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 9.3, min. 9.0, max. 10.0 ops) +#pr: (in succ. cases rsb autotuning gave avg. 3023337.5 % faster, avg. sp. ratio 30234.375x, max sp. ratio 33558.750x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 297719.1/285372.2/302000.2/1190876.2 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 10.3/ 8.5/ 14.4/ 41.1 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 10.3, min. 8.5, max. 14.4 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 32/ 32/ 32) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 96/ 96/ 96) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 8.072/ 6.627/ 9.518,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 40.964/ 8.072/ 12.410,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 0.281/ 0.231/ 0.331,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 1.426/ 0.281/ 0.432,GBps) #pr: (avg/min/max code balance (bytes read at least once per flop) 1.969/ 1.646/ 2.292) #pr: (avg/min/max (avg) bytes per nnz after successful tuning were 4.667/ 4.667/ 4.667) #pr: (matrix has been subdivided more/less/same in resp. 0 / 4 /0 cases) #pr: (matrix has used more/less/same threads in resp. 0 / 2 /2 cases) #pr: no unsuccessful rsb autotuning attempt (according to 1.01x threshold) -#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.03 s, min 0.00 s, max 0.03 s, tot 0.10 s (4 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.03 s, min 0.00 s, max 0.03 s, tot 0.10 s (4 samples) -#pr: best tun. rsb canon. mflops were: on avg. 4.337e+03, min 2.892e+03, max 5.783e+03 (4 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 1.944e+00, min 2.592e-02, max 7.670e+00 (4 samples) -#pr: best tun. rsb operation time was: on avg. 3.320e-08s, min 3.320e-08s, max 3.320e-08s, tot 1.328e-07s (4 samples) -#pr: ref. unt. rsb operation time was: on avg. 2.685e-03s, min 2.503e-05s, max 3.704e-03s, tot 1.074e-02s (4 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 2.312e+00 3.320e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 4.045e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.28 s, min 0.27 s, max 0.29 s, tot 1.14 s (4 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.28 s, min 0.27 s, max 0.29 s, tot 1.14 s (4 samples) +#pr: best tun. rsb canon. mflops were: on avg. 1.510e+02, min 1.007e+02, max 2.013e+02 (4 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 4.982e-03, min 3.000e-03, max 6.113e-03 (4 samples) +#pr: best tun. rsb operation time was: on avg. 9.537e-07s, min 9.537e-07s, max 9.537e-07s, tot 3.815e-06s (4 samples) +#pr: ref. unt. rsb operation time was: on avg. 2.883e-02s, min 2.000e-02s, max 3.200e-02s, tot 1.153e-01s (4 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 7.807e+00 1.121e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 2.353e+00 #pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 2.000e+00 x, min 2.000e+00 x, max 2.000e+00 x (2 samples, the non-min-nrhs ones) #pr: ======== Limiting to both transA=N and nrhs=1: #pr: 2 samples (out of 4) matched the dump limiting criteria. #pr: Dump from a base of 4 samples (of max 8) ordered by (1,2,1,1,2,1,2) = (filename x cores x incX x incY x nrhs x typecode x transA). pr: BESTCODE MTX NR NC NNZ NRHS TYPE SYM TRANS NT AT-NT AT-MKL-NT BPNZ AT-BPNZ NSUBM AT-SUBM RSBBEST-MFLOPS OPTIME MKL-OPTIME AT-OPTIME AT-MKL-OPTIME AT-TIME RWminBW-GBps CB-bpf AT-MS CMFLOPS -pr: 1:R_R A 3 3 6 1 Z S N 1 1 0 4.0000 4.6667 3 1 2891.58 3.704e-03 0.000e+00 3.320e-08 0.000e+00 3.386e-02 8.07e+00 2.29e+00 1 9.60e-05 -pr: 5:R_R A 3 3 6 1 Z S N 4 1 0 4.0000 4.6667 3 1 2891.58 3.354e-03 0.000e+00 3.320e-08 0.000e+00 3.346e-02 8.07e+00 2.29e+00 1 9.60e-05 +pr: 1:R_R A 3 3 6 1 Z S N 1 1 0 4.0000 4.6667 3 1 100.66 2.000e-02 0.000e+00 9.537e-07 0.000e+00 2.876e-01 2.81e-01 2.29e+00 1 9.60e-05 +pr: 5:R_R A 3 3 6 1 Z S N 4 1 0 4.0000 4.6667 3 1 100.66 3.200e-02 0.000e+00 9.537e-07 0.000e+00 2.722e-01 2.81e-01 2.29e+00 1 9.60e-05 #pr: 2 samples (out of 4) matched the dump limiting criteria. #pr: below, we define 'successful' autotuning when speedup of 1.010000x is exceeded, and 'tuned' results even the ones which are same as untuned #pr: rsb autotuning was successful in 2 cases (100.00 %) and unsuccessful in 0 cases (0.00 %) -#pr: (in succ. cases rsb autotuning gave avg. 10629343.4 % faster, avg. sp. ratio 106294.434x, max sp. ratio 111569.120x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 1013996.4/1007985.6/1020007.2/2027992.8 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 9.6/ 9.1/ 10.0/ 19.1 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 9.6, min. 9.1, max. 10.0 ops) +#pr: (in succ. cases rsb autotuning gave avg. 2726300.0 % faster, avg. sp. ratio 27264.000x, max sp. ratio 33558.750x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 293458.8/285372.2/301545.2/586917.5 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 11.4/ 8.5/ 14.4/ 22.9 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 11.4, min. 8.5, max. 14.4 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 32/ 32/ 32) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 96/ 96/ 96) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 6.627/ 6.627/ 6.627,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 16.145/ 8.072/ 8.072,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 0.231/ 0.231/ 0.231,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 0.562/ 0.281/ 0.281,GBps) #pr: (avg/min/max code balance (bytes read at least once per flop) 2.292/ 2.292/ 2.292) #pr: (avg/min/max (avg) bytes per nnz after successful tuning were 4.667/ 4.667/ 4.667) #pr: (matrix has been subdivided more/less/same in resp. 0 / 2 /0 cases) #pr: (matrix has used more/less/same threads in resp. 0 / 1 /1 cases) #pr: no unsuccessful rsb autotuning attempt (according to 1.01x threshold) -#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.03 s, min 0.03 s, max 0.03 s, tot 0.07 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.03 s, min 0.03 s, max 0.03 s, tot 0.07 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 2.892e+03, min 2.892e+03, max 2.892e+03 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 2.727e-02, min 2.592e-02, max 2.862e-02 (2 samples) -#pr: best tun. rsb operation time was: on avg. 3.320e-08s, min 3.320e-08s, max 3.320e-08s, tot 6.640e-08s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 3.529e-03s, min 3.354e-03s, max 3.704e-03s, tot 7.058e-03s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 3.320e+00 3.320e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 4.045e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.28 s, min 0.27 s, max 0.29 s, tot 0.56 s (2 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.28 s, min 0.27 s, max 0.29 s, tot 0.56 s (2 samples) +#pr: best tun. rsb canon. mflops were: on avg. 1.007e+02, min 1.007e+02, max 1.007e+02 (2 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 3.900e-03, min 3.000e-03, max 4.801e-03 (2 samples) +#pr: best tun. rsb operation time was: on avg. 9.537e-07s, min 9.537e-07s, max 9.537e-07s, tot 1.907e-06s (2 samples) +#pr: ref. unt. rsb operation time was: on avg. 2.600e-02s, min 2.000e-02s, max 3.200e-02s, tot 5.200e-02s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.121e+01 1.121e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 2.353e+00 #pr: ======== Limiting to both transA=N and nrhs=2: #pr: 2 samples (out of 4) matched the dump limiting criteria. #pr: Dump from a base of 4 samples (of max 8) ordered by (1,2,1,1,2,1,2) = (filename x cores x incX x incY x nrhs x typecode x transA). pr: BESTCODE MTX NR NC NNZ NRHS TYPE SYM TRANS NT AT-NT AT-MKL-NT BPNZ AT-BPNZ NSUBM AT-SUBM RSBBEST-MFLOPS OPTIME MKL-OPTIME AT-OPTIME AT-MKL-OPTIME AT-TIME RWminBW-GBps CB-bpf AT-MS CMFLOPS -pr: 3:R_R A 3 3 6 2 Z S N 1 1 0 4.0000 4.6667 3 1 5783.17 3.658e-03 0.000e+00 3.320e-08 0.000e+00 3.349e-02 1.24e+01 1.65e+00 1 1.92e-04 -pr: 7:R_R A 3 3 6 2 Z S N 4 1 0 4.0000 4.6667 3 1 5783.17 2.503e-05 0.000e+00 3.320e-08 0.000e+00 2.248e-04 1.24e+01 1.65e+00 1 1.92e-04 +pr: 3:R_R A 3 3 6 2 Z S N 1 1 0 4.0000 4.6667 3 1 201.33 3.192e-02 0.000e+00 9.537e-07 0.000e+00 2.880e-01 4.32e-01 1.65e+00 1 1.92e-04 +pr: 7:R_R A 3 3 6 2 Z S N 4 1 0 4.0000 4.6667 3 1 201.33 3.141e-02 0.000e+00 9.537e-07 0.000e+00 2.880e-01 4.32e-01 1.65e+00 1 1.92e-04 #pr: 2 samples (out of 4) matched the dump limiting criteria. #pr: below, we define 'successful' autotuning when speedup of 1.010000x is exceeded, and 'tuned' results even the ones which are same as untuned #pr: rsb autotuning was successful in 2 cases (100.00 %) and unsuccessful in 0 cases (0.00 %) -#pr: (in succ. cases rsb autotuning gave avg. 5546758.2 % faster, avg. sp. ratio 55468.582x, max sp. ratio 110183.124x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 507709.2/6772.0/1008646.3/1015418.3 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 9.1/ 9.0/ 9.2/ 18.1 untuned ops) +#pr: (in succ. cases rsb autotuning gave avg. 3320375.0 % faster, avg. sp. ratio 33204.750x, max sp. ratio 33474.750x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 301979.4/301958.5/302000.2/603958.8 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 9.1/ 9.0/ 9.2/ 18.2 untuned ops) #pr: (and amortizes from untuned rsb in avg. 9.1, min. 9.0, max. 9.2 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 32/ 32/ 32) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 96/ 96/ 96) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 9.518/ 9.518/ 9.518,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 24.819/ 12.410/ 12.410,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 0.331/ 0.331/ 0.331,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 0.864/ 0.432/ 0.432,GBps) #pr: (avg/min/max code balance (bytes read at least once per flop) 1.646/ 1.646/ 1.646) #pr: (avg/min/max (avg) bytes per nnz after successful tuning were 4.667/ 4.667/ 4.667) #pr: (matrix has been subdivided more/less/same in resp. 0 / 2 /0 cases) #pr: (matrix has used more/less/same threads in resp. 0 / 1 /1 cases) #pr: no unsuccessful rsb autotuning attempt (according to 1.01x threshold) -#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.02 s, min 0.00 s, max 0.03 s, tot 0.03 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.02 s, min 0.00 s, max 0.03 s, tot 0.03 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 5.783e+03, min 5.783e+03, max 5.783e+03 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 3.861e+00, min 5.249e-02, max 7.670e+00 (2 samples) -#pr: best tun. rsb operation time was: on avg. 3.320e-08s, min 3.320e-08s, max 3.320e-08s, tot 6.640e-08s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 1.842e-03s, min 2.503e-05s, max 3.658e-03s, tot 3.683e-03s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 2.312e+00 2.312e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 4.045e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.29 s, min 0.29 s, max 0.29 s, tot 0.58 s (2 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.29 s, min 0.29 s, max 0.29 s, tot 0.58 s (2 samples) +#pr: best tun. rsb canon. mflops were: on avg. 2.013e+02, min 2.013e+02, max 2.013e+02 (2 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 6.064e-03, min 6.014e-03, max 6.113e-03 (2 samples) +#pr: best tun. rsb operation time was: on avg. 9.537e-07s, min 9.537e-07s, max 9.537e-07s, tot 1.907e-06s (2 samples) +#pr: ref. unt. rsb operation time was: on avg. 3.167e-02s, min 3.141e-02s, max 3.192e-02s, tot 6.333e-02s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 7.807e+00 7.807e+00 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 2.353e+00 #pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 2.000e+00 x, min 2.000e+00 x, max 2.000e+00 x (2 samples, the non-min-nrhs ones) #pr: ======== Limiting to transA=T: #pr: No sample (out of 4) matched the dump criteria -- skipping dump round. @@ -3709,44 +3745,44 @@ #pr: ======== All results (not limiting) #pr: Dump from a base of 4 samples (of max 8) ordered by (1,2,1,1,2,1,2) = (filename x cores x incX x incY x nrhs x typecode x transA). pr: BESTCODE MTX NR NC NNZ NRHS TYPE SYM TRANS NT AT-NT AT-MKL-NT BPNZ AT-BPNZ NSUBM AT-SUBM RSBBEST-MFLOPS OPTIME MKL-OPTIME AT-OPTIME AT-MKL-OPTIME AT-TIME RWminBW-GBps CB-bpf AT-MS CMFLOPS -pr: 1:R_R A 3 3 6 1 Z S N 1 1 0 4.0000 4.6667 3 1 2891.58 3.704e-03 0.000e+00 3.320e-08 0.000e+00 3.386e-02 8.07e+00 2.29e+00 1 9.60e-05 -pr: 3:R_R A 3 3 6 2 Z S N 1 1 0 4.0000 4.6667 3 1 5783.17 3.658e-03 0.000e+00 3.320e-08 0.000e+00 3.349e-02 1.24e+01 1.65e+00 1 1.92e-04 -pr: 5:R_R A 3 3 6 1 Z S N 4 1 0 4.0000 4.6667 3 1 2891.58 3.354e-03 0.000e+00 3.320e-08 0.000e+00 3.346e-02 8.07e+00 2.29e+00 1 9.60e-05 -pr: 7:R_R A 3 3 6 2 Z S N 4 1 0 4.0000 4.6667 3 1 5783.17 2.503e-05 0.000e+00 3.320e-08 0.000e+00 2.248e-04 1.24e+01 1.65e+00 1 1.92e-04 +pr: 1:R_R A 3 3 6 1 Z S N 1 1 0 4.0000 4.6667 3 1 100.66 2.000e-02 0.000e+00 9.537e-07 0.000e+00 2.876e-01 2.81e-01 2.29e+00 1 9.60e-05 +pr: 3:R_R A 3 3 6 2 Z S N 1 1 0 4.0000 4.6667 3 1 201.33 3.192e-02 0.000e+00 9.537e-07 0.000e+00 2.880e-01 4.32e-01 1.65e+00 1 1.92e-04 +pr: 5:R_R A 3 3 6 1 Z S N 4 1 0 4.0000 4.6667 3 1 100.66 3.200e-02 0.000e+00 9.537e-07 0.000e+00 2.722e-01 2.81e-01 2.29e+00 1 9.60e-05 +pr: 7:R_R A 3 3 6 2 Z S N 4 1 0 4.0000 4.6667 3 1 201.33 3.141e-02 0.000e+00 9.537e-07 0.000e+00 2.880e-01 4.32e-01 1.65e+00 1 1.92e-04 #pr: below, we define 'successful' autotuning when speedup of 1.010000x is exceeded, and 'tuned' results even the ones which are same as untuned #pr: rsb autotuning was successful in 4 cases (100.00 %) and unsuccessful in 0 cases (0.00 %) -#pr: (in succ. cases rsb autotuning gave avg. 8088050.8 % faster, avg. sp. ratio 80881.508x, max sp. ratio 111569.120x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 760852.8/6772.0/1020007.2/3043411.1 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 9.3/ 9.0/ 10.0/ 37.3 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 9.3, min. 9.0, max. 10.0 ops) +#pr: (in succ. cases rsb autotuning gave avg. 3023337.5 % faster, avg. sp. ratio 30234.375x, max sp. ratio 33558.750x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 297719.1/285372.2/302000.2/1190876.2 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 10.3/ 8.5/ 14.4/ 41.1 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 10.3, min. 8.5, max. 14.4 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 32/ 32/ 32) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 96/ 96/ 96) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 8.072/ 6.627/ 9.518,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 40.964/ 8.072/ 12.410,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 0.281/ 0.231/ 0.331,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 1.426/ 0.281/ 0.432,GBps) #pr: (avg/min/max code balance (bytes read at least once per flop) 1.969/ 1.646/ 2.292) #pr: (avg/min/max (avg) bytes per nnz after successful tuning were 4.667/ 4.667/ 4.667) #pr: (matrix has been subdivided more/less/same in resp. 0 / 4 /0 cases) #pr: (matrix has used more/less/same threads in resp. 0 / 2 /2 cases) #pr: no unsuccessful rsb autotuning attempt (according to 1.01x threshold) -#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.03 s, min 0.00 s, max 0.03 s, tot 0.10 s (4 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.03 s, min 0.00 s, max 0.03 s, tot 0.10 s (4 samples) -#pr: best tun. rsb canon. mflops were: on avg. 4.337e+03, min 2.892e+03, max 5.783e+03 (4 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 1.944e+00, min 2.592e-02, max 7.670e+00 (4 samples) -#pr: best tun. rsb operation time was: on avg. 3.320e-08s, min 3.320e-08s, max 3.320e-08s, tot 1.328e-07s (4 samples) -#pr: ref. unt. rsb operation time was: on avg. 2.685e-03s, min 2.503e-05s, max 3.704e-03s, tot 1.074e-02s (4 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 2.312e+00 3.320e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 4.045e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.28 s, min 0.27 s, max 0.29 s, tot 1.14 s (4 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.28 s, min 0.27 s, max 0.29 s, tot 1.14 s (4 samples) +#pr: best tun. rsb canon. mflops were: on avg. 1.510e+02, min 1.007e+02, max 2.013e+02 (4 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 4.982e-03, min 3.000e-03, max 6.113e-03 (4 samples) +#pr: best tun. rsb operation time was: on avg. 9.537e-07s, min 9.537e-07s, max 9.537e-07s, tot 3.815e-06s (4 samples) +#pr: ref. unt. rsb operation time was: on avg. 2.883e-02s, min 2.000e-02s, max 3.200e-02s, tot 1.153e-01s (4 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 7.807e+00 1.121e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 2.353e+00 #pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 2.000e+00 x, min 2.000e+00 x, max 2.000e+00 x (2 samples, the non-min-nrhs ones) -#pr: Record collection took 0.66 s. +#pr: Record collection took 7.49 s. #pr: Record comprises 40 memory benchmark samples (prepend RSB_PR_MBW=1 to dump this). -#pr: Record comprises 100 environment variables in 4266 bytes (prepend RSB_PR_ENV=1 to dump this). +#pr: Record comprises 100 environment variables in 4321 bytes (prepend RSB_PR_ENV=1 to dump this). # ====== END Total summary record. -#pr: ======== Saved a performance record of 8 samples to rsbench_pr__1749955878_gcc-13.2-1,4th.rpr -# Removing the temporary record file rsbench_pr__1749955878_gcc-13.2-1,4th.rpr.tmp. -# terminating run at 1749955884 (after 6.8s of w.c.t.) +#pr: ======== Saved a performance record of 8 samples to rsbench_pr__1715548768_gcc-13.2-1,4th.rpr +# Removing the temporary record file rsbench_pr__1715548768_gcc-13.2-1,4th.rpr.tmp. +# terminating run at 1715548783 (after 14.5s of w.c.t.) + ./rsbench -oa -Ob --help /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/rsbench is a swiss army knife for testing the library functionality and performance. You can use it to perform sparse matrix - unitary vector multiplication, specifying the blocking parameters, the times to perform multiplication. @@ -4000,67 +4036,45 @@ Written by michelemartone_AT_users_DOT_sourceforge_DOT_net. + ./rsbench -I -cache block size : 99864 -hwloc size of cache level 1: 32768 -hwloc size of cache level 2: 4194304 -detected max available cores/threads : 42 -detected max OpenMP procs : 42 -detected max OpenMP procs : 42 -detected max OpenMP procs : 42 -detected max OpenMP procs : 42 -detected max OpenMP procs : 42 -detected max OpenMP procs : 42 -detected max OpenMP procs : 42 -detected max OpenMP procs : 42 -detected max OpenMP procs : 42 -detected max OpenMP procs : 42 -detected max OpenMP procs : 42 -detected max OpenMP procs : 42 -detected max OpenMP procs : 42 -detected max OpenMP procs : 42 -detected max OpenMP procs : 42 -detected max OpenMP procs : 42 -detected max OpenMP procs : 42 -detected max OpenMP procs : 42 -detected max OpenMP procs : 42 -detected max OpenMP procs : 42 -detected max OpenMP procs : 42 -detected max OpenMP procs : 42 -detected max OpenMP procs : 42 -detected max OpenMP procs : 42 -detected max OpenMP procs : 42 -detected max OpenMP procs : 42 -detected max OpenMP procs : 42 -detected max OpenMP procs : 42 -detected max OpenMP procs : 42 -detected max OpenMP procs : 42 -detected max OpenMP procs : 42 -detected max OpenMP procs : 42 -detected max OpenMP procs : 42 -detected max OpenMP procs : 42 -detected max OpenMP procs : 42 -detected max OpenMP procs : 42 -detected max OpenMP procs : 42 -detected max OpenMP procs : 42 -detected max OpenMP procs : 42 -detected max OpenMP procs : 42 -detected max OpenMP procs : 42 -detected max OpenMP procs : 42 +cache block size : 26214 +hwloc size of cache level 1: 65536 +hwloc size of cache level 2: 524288 +detected max available cores/threads : 20 +detected max OpenMP procs : 20 +detected max OpenMP procs : 20 +detected max OpenMP procs : 20 +detected max OpenMP procs : 20 +detected max OpenMP procs : 20 +detected max OpenMP procs : 20 +detected max OpenMP procs : 20 +detected max OpenMP procs : 20 +detected max OpenMP procs : 20 +detected max OpenMP procs : 20 +detected max OpenMP procs : 20 +detected max OpenMP procs : 20 +detected max OpenMP procs : 20 +detected max OpenMP procs : 20 +detected max OpenMP procs : 20 +detected max OpenMP procs : 20 +detected max OpenMP procs : 20 +detected max OpenMP procs : 20 +detected max OpenMP procs : 20 +detected max OpenMP procs : 20 detected 2 levels of cache -L1 size: 32768 -L2 size: 4194304 +L1 size: 65536 +L2 size: 524288 sysconf() : 4096 bytes per pagesize -sysconf() : 20584023 physical pages -sysconf() : 84312158208 bytes (80406 MB) of physical memory -sysconf() : 13240291 available (free) physical pages -sysconf() : 54232231936 available (free) physical memory -sysconf() , processors : 128 -sysconf() , processors online : 42 -sysconf() : level 1 cache size 32768 -sysconf() : level 1 cache associativity 8 +sysconf() : 20652059 physical pages +sysconf() : 84590833664 bytes (80672 MB) of physical memory +sysconf() : 8984381 available (free) physical pages +sysconf() : 36800024576 available (free) physical memory +sysconf() , processors : 64 +sysconf() , processors online : 20 +sysconf() : level 1 cache size 65536 +sysconf() : level 1 cache associativity 2 sysconf() : level 1 cache line size 64 -sysconf() : level 2 cache size 2097152 -sysconf() : level 2 cache associativity 8 +sysconf() : level 2 cache size 524288 +sysconf() : level 2 cache associativity 16 sysconf() : level 2 cache line size 64 sysconf() : no level 3 cache sysconf() : no level 4 cache @@ -4082,33 +4096,30 @@ RSB_SUBM_IDX_MARKER : 2147483647 RSB_MAX_ALLOCATABLE_MEMORY_CHUNK: 18446744073709551615 timing min delta (if negative, don't complain with us) : 0 s -timing granularity : 3.31998e-08 s +timing granularity : 1.20755e-06 s CFLAGS : -g -O2 -Werror=implicit-function-declaration -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 CXXFLAGS : -g -O2 -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -fopenmp CC : gcc -memhinfo : L2:16/64/4M,L1:8/64/32K -detected free memory : 54232231936 -detected total memory : 84312158208 -for array sized 4194304 elems, took 0.00145388 s for linear search and 0 s for binary search for element 4194303, in 68 tries, for a total of 0.100691 s (ignore this:570425208) -for array sized 4194304 elems, took 0.000726938 s for linear search and 0 s for binary search for element 2097151, in 136 tries, for a total of 0.100343 s (ignore this:1140850280) -for array sized 4194304 elems, took 0.000362873 s for linear search and 0 s for binary search for element 1048575, in 273 tries, for a total of 0.100125 s (ignore this:1713372230) -for array sized 4194304 elems, took 0.00018096 s for linear search and 0 s for binary search for element 524287, in 541 tries, for a total of 0.100049 s (ignore this:-2014316532) -for array sized 4194304 elems, took 8.98838e-05 s for linear search and 0 s for binary search for element 262143, in 1090 tries, for a total of 0.100061 s (ignore this:-1442844792) -for array sized 4194304 elems, took 4.48227e-05 s for linear search and 0 s for binary search for element 131071, in 2166 tries, for a total of 0.100002 s (ignore this:-875045220) -for array sized 4194304 elems, took 2.19345e-05 s for linear search and 0 s for binary search for element 65535, in 4330 tries, for a total of 0.100017 s (ignore this:-307512120) -for array sized 4194304 elems, took 1.09673e-05 s for linear search and 0 s for binary search for element 32767, in 8471 tries, for a total of 0.100007 s (ignore this:247626394) -for array sized 4194304 elems, took 4.76837e-06 s for linear search and 0 s for binary search for element 16383, in 17126 tries, for a total of 0.100001 s (ignore this:808776910) -for array sized 4194304 elems, took 1.90735e-06 s for linear search and 0 s for binary search for element 8191, in 33435 tries, for a total of 0.100001 s (ignore this:1356509080) -for array sized 4194304 elems, took 9.53674e-07 s for linear search and 0 s for binary search for element 4095, in 65387 tries, for a total of 0.100000 s (ignore this:1892028610) -for array sized 4194304 elems, took 0 s for linear search and 0 s for binary search for element 2047, in 121291 tries, for a total of 0.100000 s (ignore this:-1906373332) -for array sized 4194304 elems, took 0 s for linear search and 0 s for binary search for element 1023, in 217428 tries, for a total of 0.100001 s (ignore this:-1461515644) -for array sized 4194304 elems, took 0 s for linear search and 0 s for binary search for element 511, in 350156 tries, for a total of 0.100001 s (ignore this:-1103656212) -for array sized 4194304 elems, took 0 s for linear search and 0 s for binary search for element 255, in 514869 tries, for a total of 0.100000 s (ignore this:-841073022) -for array sized 4194304 elems, took 0 s for linear search and 0 s for binary search for element 127, in 673256 tries, for a total of 0.100001 s (ignore this:-670065998) -for array sized 4194304 elems, took 0 s for linear search and 0 s for binary search for element 63, in 839876 tries, for a total of 0.100000 s (ignore this:-564241622) -for array sized 4194304 elems, took 0 s for linear search and 0 s for binary search for element 31, in 961916 tries, for a total of 0.100001 s (ignore this:-504602830) -for array sized 4194304 elems, took 0 s for linear search and 0 s for binary search for element 15, in 1016275 tries, for a total of 0.100000 s (ignore this:-474114580) -for array sized 4194304 elems, took 0 s for linear search and 0 s for binary search for element 7, in 1048735 tries, for a total of 0.100000 s (ignore this:-459432290) +memhinfo : L2:16/64/512K,L1:2/64/64K +detected free memory : 36800024576 +detected total memory : 84590833664 +for array sized 524288 elems, took 0.000602007 s for linear search and 0 s for binary search for element 524287, in 53 tries, for a total of 0.100239 s (ignore this:55574422) +for array sized 524288 elems, took 0.000256062 s for linear search and 0 s for binary search for element 262143, in 111 tries, for a total of 0.104674 s (ignore this:113770168) +for array sized 524288 elems, took 7.60555e-05 s for linear search and 0 s for binary search for element 131071, in 242 tries, for a total of 0.107628 s (ignore this:177208532) +for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 65535, in 440 tries, for a total of 0.100011 s (ignore this:234879332) +for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 32767, in 1028 tries, for a total of 0.100104 s (ignore this:302248284) +for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 16383, in 3736 tries, for a total of 0.100052 s (ignore this:424662060) +for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 8191, in 5212 tries, for a total of 0.100001 s (ignore this:510045044) +for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 4095, in 6108 tries, for a total of 0.101086 s (ignore this:560069564) +for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 2047, in 10558 tries, for a total of 0.100001 s (ignore this:603294016) +for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 1023, in 16946 tries, for a total of 0.100001 s (ignore this:637965532) +for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 511, in 24685 tries, for a total of 0.105229 s (ignore this:663193602) +for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 255, in 31455 tries, for a total of 0.106920 s (ignore this:679235652) +for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 127, in 58668 tries, for a total of 0.100002 s (ignore this:694137324) +for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 63, in 78743 tries, for a total of 0.100000 s (ignore this:704058942) +for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 31, in 72466 tries, for a total of 0.100001 s (ignore this:708551834) +for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 15, in 46233 tries, for a total of 0.103278 s (ignore this:709938824) +for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 7, in 51693 tries, for a total of 0.100002 s (ignore this:710662526) + ./rsbench -C /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/rsbench version: 1.3.0 format switches:br @@ -4135,7 +4146,7 @@ RSB_CONST_MAX_SUPPORTED_CORES:128 RSB_BLAS_MATRICES_MAX:2147482623 RSB_CONST_MIN_NNZ_PER_ROW_FOR_COO_SWITCH:2 -RSB_USER_SET_MEM_HIERARCHY_INFO:L2:16/64/4096K,L1:8/64/32K +RSB_USER_SET_MEM_HIERARCHY_INFO:L2:16/64/512K,L1:2/64/64K RSB_MAX_VALUE_FOR_TYPE(rsb_half_idx_t):65535 RSB_IOLEVEL:7 LIBRSBPP support: on. @@ -4155,17 +4166,17 @@ Adding matrix file: /build/reproducible-path/librsb-1.3.0.2+dfsg/A.mtx # Sorting matrices list (use --no-sort-filenames-list to prevent this) # Using matrices: A.mtx -# beginning run at 1749955887 +# beginning run at 1715548787 # /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/rsbench -oa -Ob --bench -f /build/reproducible-path/librsb-1.3.0.2+dfsg/A.mtx --verbose --nrhs 1,4 --by-rows # compiled with: CC=gcc CFLAGS=-g -O2 -Werror=implicit-function-declaration -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -# User did not specify threads; assuming 1. Environment provides max 42 threads; this build supports max 128. -# User did not specify threads; assuming 1. Environment provides max 42 threads; this build supports max 128. -# average timer granularity: 3.32e-08 s -# Will write a final performance record to file rsbench_pr__1749955887_gcc-13.2.rpr and periodic checkpoints to rsbench_pr__1749955887_gcc-13.2.rpr.tmp +# User did not specify threads; assuming 1. Environment provides max 20 threads; this build supports max 128. +# User did not specify threads; assuming 1. Environment provides max 20 threads; this build supports max 128. +# average timer granularity: 4.51e-07 s +# Will write a final performance record to file rsbench_pr__1715548787_gcc-13.2.rpr and periodic checkpoints to rsbench_pr__1715548787_gcc-13.2.rpr.tmp # will NOT perform ancillary tests. # will flush cache memory: between each operation measurement series, and NOT between each operation. # will keep any zero encountered in the matrix. -# env: export PATH=/usr/sbin:/usr/bin:/sbin:/bin:/usr/games +# env: export PATH=/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/i/capture/the/path # env: export LD_LIBRARY_PATH=/build/reproducible-path/librsb-1.3.0.2+dfsg/.libs # env: HOSTNAME is not set # env: KMP_AFFINITY is not set @@ -4204,835 +4215,835 @@ # env: SLURM_NTASKS is not set # env: SLURM_STEP_TASKS_PER_NODE is not set # env: SLURM_TASKS_PER_NODE is not set -# detected hostname: ionos5-amd64 +# detected hostname: i-capture-the-hostname # user specified a verbosity level of 1 (each --verbose occurrence counts +1) # This test will measure times in scanning arrays sized and aligned to fit in caches. # 2 cache levels detected Will fill struct with 40 samples... -# Memory benchmark took 6.171s +# Memory benchmark took 6.843s # auto-tuning oriented output implies times==0 iterations and sort-after-load. #pr: allocated a performance record for 16 samples (4480 bytes). # multi-type benchmarking (DSCZ) -- now using typecode D (last was D). -# Cache block size total 4194304 bytes, per-thread 99864 bytes -# so far, program took 6.172s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.000s/0.000s . +# Cache block size total 524288 bytes, per-thread 26214 bytes +# so far, program took 6.862s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.000s/0.000s . # reading A.mtx (184 bytes / 1 MiB / 6 nnz / 3 rows / 3 columns / 1 MiB COO) as type D... -# file input of A.mtx took 0.00 s (6 nnz, 58799 nnz/s ) (1.80 MB/s ) -#pre-sorting (6 elements) took 0.00426102 s -#weeding duplicates (to 6 elements) took 2.14577e-06 s (and check, 1.90735e-06 s ) +# file input of A.mtx took 0.00 s (6 nnz, 33157 nnz/s ) (1.02 MB/s ) +#pre-sorting (6 elements) took 0.055532 s +#weeding duplicates (to 6 elements) took 5.96046e-06 s (and check, 3.09944e-06 s ) # multi-nrhs benchmarking (1,4) -- now using nrhs 1. # Using alpha=1 beta=1 order=rows for rsb_spmv/rsb_spsv/rsb_spmm/rsb_spsm. # multi-transpose benchmarking -- now using transA = N. # will use input matrix flags: RSB_FLAG_USE_HALFWORD_INDICES, RSB_FLAG_SORTED_INPUT, RSB_FLAG_QUAD_PARTITIONING, RSB_FLAG_SYMMETRIC, RSB_FLAG_OWN_PARTITIONING_ARRAYS -# Using 42 threads -# Constructed matrix (took 0.024s): (3 x 3)[0x555d69ddb2a0]{D} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x2442186 (coo:1, csr:0, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'S' +# Using 20 threads +# Constructed matrix (took 0.262s): (3 x 3)[0x562f6a5ee1d0]{D} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x2442186 (coo:1, csr:0, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'S' # matrix consistency check took 0.000s (ok) RSB Sparse Blocks Autotuner invoked requesting max 6 splits and max 6 merges in 1 rounds, threads spec.0 (specify negative values to enable threads tuning). Will autotune matrix: 3 x 3, type D, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:3 -3 iterations (42 th.) took 0.01132s; avg 0.003773s ( +/- 0.72/ 1.29 %); best 0.003746s; worst 0.003822s; std dev. 3.442e-05 (taking best). -Reference operation time is 0.00374603 s (0.006407 Mflops) with 42 threads. -Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=rows) (max 6 steps, inclusive 3 grace steps) on: 3 x 3, type D, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz (tpop: 0.003746 Mflops: 0.006) -Merge (3 -> 1 leaves) took w.c.t. of 1.907e-05s, ~7.153e-06s of computing time (of which 9.537e-07s sorting, 3.099e-06s analysis) -3 iterations (42 th.) took 5.579e-05s; avg 1.86e-05s ( +/- 99.82/194.87 %); best 3.411e-08s; worst 5.484e-05s; std dev. 2.563e-05 (taking best). -Reference operation time is 3.41058e-08 s (703.7 Mflops) with 42 threads. -After merge step 1: tpop: 3.411e-08 s ~Mflops: 703.693 nsubm:1 otn:42 -Applying merge (3 -> 1 leaves, 42 th.) yielded SPEEDUP of 109835.722x: 0.003746s -> 3.411e-08s, so taking this instance. +3 iterations (20 th.) took 0.09199s; avg 0.03066s ( +/- 34.75/ 43.44 %); best 0.02001s; worst 0.04398s; std dev. 0.009968 (taking best). +Reference operation time is 0.0200081 s (0.0012 Mflops) with 20 threads. +Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=rows) (max 6 steps, inclusive 3 grace steps) on: 3 x 3, type D, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz (tpop: 0.02001 Mflops: 0.001) +Merge (3 -> 1 leaves) took w.c.t. of 5.102e-05s, ~1.693e-05s of computing time (of which 2.861e-06s sorting, 1.097e-05s analysis) +3 iterations (20 th.) took 4.101e-05s; avg 1.367e-05s ( +/- 93.02/184.30 %); best 9.537e-07s; worst 3.886e-05s; std dev. 1.781e-05 (taking best). +Reference operation time is 9.53674e-07 s (25.17 Mflops) with 20 threads. +After merge step 1: tpop: 9.537e-07 s ~Mflops: 25.166 nsubm:1 otn:20 +Applying merge (3 -> 1 leaves, 20 th.) yielded SPEEDUP of 20980.000x: 0.02001s -> 9.537e-07s, so taking this instance. Merged all the matrix leaves: no reason to continue merging. -A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.01134s (of which 2.289e-05s partitioning, 0s I/O); computing times: 7.153e-06s in par. loops, 9.537e-07s sorting, 3.099e-06s analyzing) -Total merge + benchmarking process took 0.01134s, equivalent to 332492.1/3.0 new/old ops (0.02258s for 2 clones -- as 661915.4/6.0 ops, or 330957.7/3.0 ops per clone), SPEEDUP of 109835.722x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 42 th.sp.) yielded SPEEDUP of 109835.722x (0.003746s -> 3.411e-08s), will amortize in 3.0 ops by saving 0.003746s per op. -In 1 tuning rounds (tot. 0.034s, 0.023s for constructor, 2 clones) obtained a SPEEDUP of 10983472.2% (1.098e+05x) (from 0.006407 to 703.7 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.116s (of which 5.817e-05s partitioning, 0s I/O); computing times: 1.693e-05s in par. loops, 2.861e-06s sorting, 1.097e-05s analyzing) +Total merge + benchmarking process took 0.116s, equivalent to 121605.5/5.8 new/old ops (0.2556s for 2 clones -- as 268013.8/12.8 ops, or 134006.9/6.4 ops per clone), SPEEDUP of 20980.000x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 20 th.sp.) yielded SPEEDUP of 20980.000x (0.02001s -> 9.537e-07s), will amortize in 5.8 ops by saving 0.02001s per op. +In 1 tuning rounds (tot. 0.35s, 0.26s for constructor, 2 clones) obtained a SPEEDUP of 2097900.0% (2.098e+04x) (from 0.0012 to 25.17 Mflops). #pr: updating sample at index 1 (0^th of 16), 0^th touch for (0,0,0,0,0,0,0). -First run of RSB Autotuner took 0.0340579 s (3.746e-03 s -> 3.411e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.347948 s (2.001e-02 s -> 9.537e-07 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). RSB Sparse Blocks Autotuner invoked requesting max 0 splits and max 0 merges in 1 rounds, auto threads spec. -Second run of RSB Autotuner took 0.191144 s and estimated a speedup of 1.000000 x (3.411e-08 s -> 3.411e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 1.58393 s and estimated a speedup of 1.000000 x (9.537e-07 s -> 9.537e-07 s per op) in same matrix (1 -> 1 lsubm) #min:1 #max:1 #sum:3 #norm:1.7320508075688772 #used index storage compared to COO:28 vs 48 bytes (58.33%) ; compared to CSR:28 vs 40 bytes (77.78%) #%:CONSTRUCTOR_*:SORT SCAN INSERT SCAN+INSERT -%:CONSTRUCTOR_TIMES:A.mtx S N 42 3 3 6 0.000000 0.009229 0.007538 0.016767 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 42 3 3 6 0.016767 -%:RSB_SUBDIVISION_TIME:A.mtx S N 42 3 3 6 0.009229 -%:RSB_SHUFFLE_TIME:A.mtx S N 42 3 3 6 0.007538 -%:ROW_MAJOR_SORT_TIME:A.mtx S N 42 3 3 6 0.000000 -%:ROW_MAJOR_SORT_SCALING:A.mtx S N 42 3 3 6 -nan -%:SORTEDCOO2RSB_TIME:A.mtx S N 42 3 3 6 0.016767 -%:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 42 3 3 6 0.000 -%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 42 3 3 6 1.00 -%:SORTEDCOO2RSB_SCALING:A.mtx S N 42 3 3 6 1.00 -%:RSB_SUBDIVISION_SCALING:A.mtx S N 42 3 3 6 1.00 -%:RSB_SHUFFLE_SCALING:A.mtx S N 42 3 3 6 1.00 -%:CONSTRUCTOR_SCALING:A.mtx S N 42 3 3 6 -nan 1.00 1.00 1.00 +%:CONSTRUCTOR_TIMES:A.mtx S N 20 3 3 6 0.000001 0.110027 0.087688 0.197715 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 20 3 3 6 0.197716 +%:RSB_SUBDIVISION_TIME:A.mtx S N 20 3 3 6 0.110027 +%:RSB_SHUFFLE_TIME:A.mtx S N 20 3 3 6 0.087688 +%:ROW_MAJOR_SORT_TIME:A.mtx S N 20 3 3 6 0.000001 +%:ROW_MAJOR_SORT_SCALING:A.mtx S N 20 3 3 6 1.000 +%:SORTEDCOO2RSB_TIME:A.mtx S N 20 3 3 6 0.197715 +%:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 20 3 3 6 0.000 +%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 20 3 3 6 1.00 +%:SORTEDCOO2RSB_SCALING:A.mtx S N 20 3 3 6 1.00 +%:RSB_SUBDIVISION_SCALING:A.mtx S N 20 3 3 6 1.00 +%:RSB_SHUFFLE_SCALING:A.mtx S N 20 3 3 6 1.00 +%:CONSTRUCTOR_SCALING:A.mtx S N 20 3 3 6 1.00 1.00 1.00 1.00 #%:SM_COUNTS: Tot HalfwordCsr FullwordCsr HalfwordCoo FullwordCoo -%:SM_COUNTS:A.mtx S N 42 3 3 6 1 1 0 0 0 -%:SM_IDXOCCUPATIONRSBVSCOOANDCSR:A.mtx S N 42 3 3 6 28 48 36 -%:SM_IDXOCCUPATION:A.mtx S N 42 3 3 6 28 -%:SM_MEMTRAFFIC:A.mtx S N 42 3 3 6 156 -%:SM_MINMAXAVGNNZ:A.mtx S N 42 3 3 6 6 6 6 +%:SM_COUNTS:A.mtx S N 20 3 3 6 1 1 0 0 0 +%:SM_IDXOCCUPATIONRSBVSCOOANDCSR:A.mtx S N 20 3 3 6 28 48 36 +%:SM_IDXOCCUPATION:A.mtx S N 20 3 3 6 28 +%:SM_MEMTRAFFIC:A.mtx S N 20 3 3 6 156 +%:SM_MINMAXAVGNNZ:A.mtx S N 20 3 3 6 6 6 6 # -%operation:matrix CONSTRUCTOR[42] SPMV[42] SPMV[42] -%operation:A.mtx 0.024255 1e+09 1e+09 -%constructor:matrix SORT[42] SCAN[42] SHUFFLE[42] INSERT[42] -%constructor:A.mtx 0 0.00922894 0 0.00753808 +%operation:matrix CONSTRUCTOR[20] SPMV[20] SPMV[20] +%operation:A.mtx 0.261781 1e+09 1e+09 +%constructor:matrix SORT[20] SCAN[20] SHUFFLE[20] INSERT[20] +%constructor:A.mtx 9.53674e-07 0.110027 0 0.087688 # symmetric matrix --- skipping transposed benchmarking # multi-nrhs benchmarking (1,4) -- now using nrhs 4. # Using alpha=1 beta=1 order=rows for rsb_spmv/rsb_spsv/rsb_spmm/rsb_spsm. # multi-transpose benchmarking -- now using transA = N. # will use input matrix flags: RSB_FLAG_USE_HALFWORD_INDICES, RSB_FLAG_SORTED_INPUT, RSB_FLAG_QUAD_PARTITIONING, RSB_FLAG_SYMMETRIC, RSB_FLAG_OWN_PARTITIONING_ARRAYS -# Using 42 threads -# Constructed matrix (took 0.024s): (3 x 3)[0x555d69ddb2a0]{D} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x2442186 (coo:1, csr:0, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'S' +# Using 20 threads +# Constructed matrix (took 0.205s): (3 x 3)[0x562f6a5ee1d0]{D} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x2442186 (coo:1, csr:0, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'S' # matrix consistency check took 0.000s (ok) RSB Sparse Blocks Autotuner invoked requesting max 6 splits and max 6 merges in 1 rounds, threads spec.0 (specify negative values to enable threads tuning). Will autotune matrix: 3 x 3, type D, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:3 -3 iterations (42 th.) took 0.01289s; avg 0.004298s ( +/- 13.18/ 18.55 %); best 0.003731s; worst 0.005095s; std dev. 0.0005803 (taking best). -Reference operation time is 0.00373101 s (0.02573 Mflops) with 42 threads. -Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=4, order=rows) (max 6 steps, inclusive 3 grace steps) on: 3 x 3, type D, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz (tpop: 0.003731 Mflops: 0.026) -Merge (3 -> 1 leaves) took w.c.t. of 1.192e-05s, ~4.053e-06s of computing time (of which 2.146e-06s sorting, 1.907e-06s analysis) -3 iterations (42 th.) took 2.193e-05s; avg 7.312e-06s ( +/- 99.53/186.96 %); best 3.411e-08s; worst 2.098e-05s; std dev. 9.674e-06 (taking best). -Reference operation time is 3.41058e-08 s (2815 Mflops) with 42 threads. -After merge step 1: tpop: 3.411e-08 s ~Mflops: 2814.772 nsubm:1 otn:42 -Applying merge (3 -> 1 leaves, 42 th.) yielded SPEEDUP of 109395.316x: 0.003731s -> 3.411e-08s, so taking this instance. +3 iterations (20 th.) took 0.0893s; avg 0.02977s ( +/- 10.51/ 13.57 %); best 0.02664s; worst 0.03381s; std dev. 0.002997 (taking best). +Reference operation time is 0.0266371 s (0.003604 Mflops) with 20 threads. +Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=4, order=rows) (max 6 steps, inclusive 3 grace steps) on: 3 x 3, type D, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz (tpop: 0.02664 Mflops: 0.004) +Merge (3 -> 1 leaves) took w.c.t. of 3.386e-05s, ~1.097e-05s of computing time (of which 2.861e-06s sorting, 6.914e-06s analysis) +3 iterations (20 th.) took 2.885e-05s; avg 9.616e-06s ( +/- 90.08/180.17 %); best 9.537e-07s; worst 2.694e-05s; std dev. 1.225e-05 (taking best). +Reference operation time is 9.53674e-07 s (100.7 Mflops) with 20 threads. +After merge step 1: tpop: 9.537e-07 s ~Mflops: 100.663 nsubm:1 otn:20 +Applying merge (3 -> 1 leaves, 20 th.) yielded SPEEDUP of 27931.000x: 0.02664s -> 9.537e-07s, so taking this instance. Merged all the matrix leaves: no reason to continue merging. -A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.01142s (of which 1.502e-05s partitioning, 0s I/O); computing times: 4.053e-06s in par. loops, 2.146e-06s sorting, 1.907e-06s analyzing) -Total merge + benchmarking process took 0.01142s, equivalent to 334806.0/3.1 new/old ops (0.02264s for 2 clones -- as 663726.0/6.1 ops, or 331863.0/3.0 ops per clone), SPEEDUP of 109395.316x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 42 th.sp.) yielded SPEEDUP of 109395.316x (0.003731s -> 3.411e-08s), will amortize in 3.1 ops by saving 0.003731s per op. -In 1 tuning rounds (tot. 0.036s, 0.023s for constructor, 2 clones) obtained a SPEEDUP of 10939431.6% (1.094e+05x) (from 0.02573 to 2815 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.09112s (of which 3.791e-05s partitioning, 0s I/O); computing times: 1.097e-05s in par. loops, 2.861e-06s sorting, 6.914e-06s analyzing) +Total merge + benchmarking process took 0.09112s, equivalent to 95549.5/3.4 new/old ops (0.1783s for 2 clones -- as 186985.2/6.7 ops, or 93492.6/3.3 ops per clone), SPEEDUP of 27931.000x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 20 th.sp.) yielded SPEEDUP of 27931.000x (0.02664s -> 9.537e-07s), will amortize in 3.4 ops by saving 0.02664s per op. +In 1 tuning rounds (tot. 0.27s, 0.18s for constructor, 2 clones) obtained a SPEEDUP of 2793000.0% (2.793e+04x) (from 0.003604 to 100.7 Mflops). #pr: updating sample at index 9 (1^th of 16), 0^th touch for (0,0,0,0,1,0,0). -First run of RSB Autotuner took 0.0356309 s (3.731e-03 s -> 3.411e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.267844 s (2.664e-02 s -> 9.537e-07 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). RSB Sparse Blocks Autotuner invoked requesting max 0 splits and max 0 merges in 1 rounds, auto threads spec. -Second run of RSB Autotuner took 0.190078 s and estimated a speedup of 1.000000 x (3.411e-08 s -> 3.411e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 1.43191 s and estimated a speedup of 1.000000 x (9.537e-07 s -> 9.537e-07 s per op) in same matrix (1 -> 1 lsubm) #min:1 #max:1 #sum:3 #norm:1.7320508075688772 #used index storage compared to COO:28 vs 48 bytes (58.33%) ; compared to CSR:28 vs 40 bytes (77.78%) #%:CONSTRUCTOR_*:SORT SCAN INSERT SCAN+INSERT -%:CONSTRUCTOR_TIMES:A.mtx S N 42 3 3 6 0.000000 0.009127 0.007505 0.016632 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 42 3 3 6 0.016632 -%:RSB_SUBDIVISION_TIME:A.mtx S N 42 3 3 6 0.009127 -%:RSB_SHUFFLE_TIME:A.mtx S N 42 3 3 6 0.007505 -%:ROW_MAJOR_SORT_TIME:A.mtx S N 42 3 3 6 0.000000 -%:ROW_MAJOR_SORT_SCALING:A.mtx S N 42 3 3 6 -nan -%:SORTEDCOO2RSB_TIME:A.mtx S N 42 3 3 6 0.016632 -%:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 42 3 3 6 0.000 -%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 42 3 3 6 1.00 -%:SORTEDCOO2RSB_SCALING:A.mtx S N 42 3 3 6 1.00 -%:RSB_SUBDIVISION_SCALING:A.mtx S N 42 3 3 6 1.00 -%:RSB_SHUFFLE_SCALING:A.mtx S N 42 3 3 6 1.00 -%:CONSTRUCTOR_SCALING:A.mtx S N 42 3 3 6 -nan 1.00 1.00 1.00 +%:CONSTRUCTOR_TIMES:A.mtx S N 20 3 3 6 0.000001 0.080425 0.052647 0.133072 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 20 3 3 6 0.133073 +%:RSB_SUBDIVISION_TIME:A.mtx S N 20 3 3 6 0.080425 +%:RSB_SHUFFLE_TIME:A.mtx S N 20 3 3 6 0.052647 +%:ROW_MAJOR_SORT_TIME:A.mtx S N 20 3 3 6 0.000001 +%:ROW_MAJOR_SORT_SCALING:A.mtx S N 20 3 3 6 1.000 +%:SORTEDCOO2RSB_TIME:A.mtx S N 20 3 3 6 0.133072 +%:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 20 3 3 6 0.000 +%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 20 3 3 6 1.00 +%:SORTEDCOO2RSB_SCALING:A.mtx S N 20 3 3 6 1.00 +%:RSB_SUBDIVISION_SCALING:A.mtx S N 20 3 3 6 1.00 +%:RSB_SHUFFLE_SCALING:A.mtx S N 20 3 3 6 1.00 +%:CONSTRUCTOR_SCALING:A.mtx S N 20 3 3 6 1.00 1.00 1.00 1.00 #%:SM_COUNTS: Tot HalfwordCsr FullwordCsr HalfwordCoo FullwordCoo -%:SM_COUNTS:A.mtx S N 42 3 3 6 1 1 0 0 0 -%:SM_IDXOCCUPATIONRSBVSCOOANDCSR:A.mtx S N 42 3 3 6 28 48 36 -%:SM_IDXOCCUPATION:A.mtx S N 42 3 3 6 28 -%:SM_MEMTRAFFIC:A.mtx S N 42 3 3 6 156 -%:SM_MINMAXAVGNNZ:A.mtx S N 42 3 3 6 6 6 6 +%:SM_COUNTS:A.mtx S N 20 3 3 6 1 1 0 0 0 +%:SM_IDXOCCUPATIONRSBVSCOOANDCSR:A.mtx S N 20 3 3 6 28 48 36 +%:SM_IDXOCCUPATION:A.mtx S N 20 3 3 6 28 +%:SM_MEMTRAFFIC:A.mtx S N 20 3 3 6 156 +%:SM_MINMAXAVGNNZ:A.mtx S N 20 3 3 6 6 6 6 # -%operation:matrix CONSTRUCTOR[42] SPMV[42] SPMV[42] -%operation:A.mtx 0.0243959 1e+09 1e+09 -%constructor:matrix SORT[42] SCAN[42] SHUFFLE[42] INSERT[42] -%constructor:A.mtx 0 0.00912714 0 0.00750494 +%operation:matrix CONSTRUCTOR[20] SPMV[20] SPMV[20] +%operation:A.mtx 0.205256 1e+09 1e+09 +%constructor:matrix SORT[20] SCAN[20] SHUFFLE[20] INSERT[20] +%constructor:A.mtx 9.53674e-07 0.080425 0 0.0526469 # symmetric matrix --- skipping transposed benchmarking -# so far, program took 6.722s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.451s/0.000s . +# so far, program took 11.305s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 3.632s/0.000s . getrusage() stats: -ru_maxrss: 26 (maximum resident set size -- MB) -ru_stime : 0.2076s (system CPU time used) -ru_utime : 26.98s (user CPU time used) +ru_maxrss: 7 (maximum resident set size -- MB) +ru_stime : 0.07815s (system CPU time used) +ru_utime : 27.89s (user CPU time used) # multi-type benchmarking (DSCZ) -- now using typecode S (last was D). -# Cache block size total 4194304 bytes, per-thread 99864 bytes -# so far, program took 6.722s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.451s/0.000s . +# Cache block size total 524288 bytes, per-thread 26214 bytes +# so far, program took 11.305s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 3.632s/0.000s . # Reusing type converted (D->S) arrays from last iteration instead of reloading matrix file. # multi-nrhs benchmarking (1,4) -- now using nrhs 1. # Using alpha=1 beta=1 order=rows for rsb_spmv/rsb_spsv/rsb_spmm/rsb_spsm. # multi-transpose benchmarking -- now using transA = N. # will use input matrix flags: RSB_FLAG_USE_HALFWORD_INDICES, RSB_FLAG_SORTED_INPUT, RSB_FLAG_QUAD_PARTITIONING, RSB_FLAG_SYMMETRIC, RSB_FLAG_OWN_PARTITIONING_ARRAYS -# Using 42 threads -# Constructed matrix (took 0.025s): (3 x 3)[0x555d69ddb2a0]{S} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x2442186 (coo:1, csr:0, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'S' +# Using 20 threads +# Constructed matrix (took 0.167s): (3 x 3)[0x562f6a5ee1d0]{S} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x2442186 (coo:1, csr:0, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'S' # matrix consistency check took 0.000s (ok) RSB Sparse Blocks Autotuner invoked requesting max 6 splits and max 6 merges in 1 rounds, threads spec.0 (specify negative values to enable threads tuning). Will autotune matrix: 3 x 3, type S, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:3 -3 iterations (42 th.) took 0.01141s; avg 0.003804s ( +/- 0.93/ 1.33 %); best 0.003769s; worst 0.003855s; std dev. 3.674e-05 (taking best). -Reference operation time is 0.00376892 s (0.006368 Mflops) with 42 threads. -Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=rows) (max 6 steps, inclusive 3 grace steps) on: 3 x 3, type S, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz (tpop: 0.003769 Mflops: 0.006) -Merge (3 -> 1 leaves) took w.c.t. of 1.192e-05s, ~5.007e-06s of computing time (of which 1.192e-06s sorting, 2.146e-06s analysis) -3 iterations (42 th.) took 2.599e-05s; avg 8.663e-06s ( +/- 99.61/188.99 %); best 3.411e-08s; worst 2.503e-05s; std dev. 1.158e-05 (taking best). -Reference operation time is 3.41058e-08 s (703.7 Mflops) with 42 threads. -After merge step 1: tpop: 3.411e-08 s ~Mflops: 703.693 nsubm:1 otn:42 -Applying merge (3 -> 1 leaves, 42 th.) yielded SPEEDUP of 110506.816x: 0.003769s -> 3.411e-08s, so taking this instance. +3 iterations (20 th.) took 0.07609s; avg 0.02536s ( +/- 36.19/ 26.16 %); best 0.01619s; worst 0.032s; std dev. 0.006702 (taking best). +Reference operation time is 0.016185 s (0.001483 Mflops) with 20 threads. +Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=rows) (max 6 steps, inclusive 3 grace steps) on: 3 x 3, type S, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz (tpop: 0.01619 Mflops: 0.001) +Merge (3 -> 1 leaves) took w.c.t. of 3.099e-05s, ~1.192e-05s of computing time (of which 2.146e-06s sorting, 5.96e-06s analysis) +3 iterations (20 th.) took 3.195e-05s; avg 1.065e-05s ( +/- 91.04/170.90 %); best 9.537e-07s; worst 2.885e-05s; std dev. 1.288e-05 (taking best). +Reference operation time is 9.53674e-07 s (25.17 Mflops) with 20 threads. +After merge step 1: tpop: 9.537e-07 s ~Mflops: 25.166 nsubm:1 otn:20 +Applying merge (3 -> 1 leaves, 20 th.) yielded SPEEDUP of 16971.250x: 0.01619s -> 9.537e-07s, so taking this instance. Merged all the matrix leaves: no reason to continue merging. -A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.01149s (of which 1.502e-05s partitioning, 0s I/O); computing times: 5.007e-06s in par. loops, 1.192e-06s sorting, 2.146e-06s analyzing) -Total merge + benchmarking process took 0.01149s, equivalent to 336749.4/3.0 new/old ops (0.02258s for 2 clones -- as 662146.1/6.0 ops, or 331073.1/3.0 ops per clone), SPEEDUP of 110506.816x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 42 th.sp.) yielded SPEEDUP of 110506.816x (0.003769s -> 3.411e-08s), will amortize in 3.0 ops by saving 0.003769s per op. -In 1 tuning rounds (tot. 0.034s, 0.023s for constructor, 2 clones) obtained a SPEEDUP of 11050581.6% (1.105e+05x) (from 0.006368 to 703.7 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.09177s (of which 3.695e-05s partitioning, 0s I/O); computing times: 1.192e-05s in par. loops, 2.146e-06s sorting, 5.96e-06s analyzing) +Total merge + benchmarking process took 0.09177s, equivalent to 96232.2/5.7 new/old ops (0.1637s for 2 clones -- as 171635.2/10.1 ops, or 85817.6/5.1 ops per clone), SPEEDUP of 16971.250x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 20 th.sp.) yielded SPEEDUP of 16971.250x (0.01619s -> 9.537e-07s), will amortize in 5.7 ops by saving 0.01618s per op. +In 1 tuning rounds (tot. 0.24s, 0.16s for constructor, 2 clones) obtained a SPEEDUP of 1697025.0% (1.697e+04x) (from 0.001483 to 25.17 Mflops). #pr: updating sample at index 3 (2^th of 16), 0^th touch for (0,0,0,0,0,1,0). -First run of RSB Autotuner took 0.034153 s (3.769e-03 s -> 3.411e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.240008 s (1.619e-02 s -> 9.537e-07 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). RSB Sparse Blocks Autotuner invoked requesting max 0 splits and max 0 merges in 1 rounds, auto threads spec. -Second run of RSB Autotuner took 0.102811 s and estimated a speedup of 1.000000 x (3.411e-08 s -> 3.411e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 1.19991 s and estimated a speedup of 1.000000 x (9.537e-07 s -> 9.537e-07 s per op) in same matrix (1 -> 1 lsubm) #min:1 #max:1 #sum:3 #norm:1.73205078 #used index storage compared to COO:28 vs 48 bytes (58.33%) ; compared to CSR:28 vs 40 bytes (77.78%) #%:CONSTRUCTOR_*:SORT SCAN INSERT SCAN+INSERT -%:CONSTRUCTOR_TIMES:A.mtx S N 42 3 3 6 0.000000 0.009358 0.007780 0.017138 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 42 3 3 6 0.017138 -%:RSB_SUBDIVISION_TIME:A.mtx S N 42 3 3 6 0.009358 -%:RSB_SHUFFLE_TIME:A.mtx S N 42 3 3 6 0.007780 -%:ROW_MAJOR_SORT_TIME:A.mtx S N 42 3 3 6 0.000000 -%:ROW_MAJOR_SORT_SCALING:A.mtx S N 42 3 3 6 -nan -%:SORTEDCOO2RSB_TIME:A.mtx S N 42 3 3 6 0.017138 -%:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 42 3 3 6 0.000 -%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 42 3 3 6 1.00 -%:SORTEDCOO2RSB_SCALING:A.mtx S N 42 3 3 6 1.00 -%:RSB_SUBDIVISION_SCALING:A.mtx S N 42 3 3 6 1.00 -%:RSB_SHUFFLE_SCALING:A.mtx S N 42 3 3 6 1.00 -%:CONSTRUCTOR_SCALING:A.mtx S N 42 3 3 6 -nan 1.00 1.00 1.00 +%:CONSTRUCTOR_TIMES:A.mtx S N 20 3 3 6 0.000001 0.055321 0.055992 0.111313 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 20 3 3 6 0.111314 +%:RSB_SUBDIVISION_TIME:A.mtx S N 20 3 3 6 0.055321 +%:RSB_SHUFFLE_TIME:A.mtx S N 20 3 3 6 0.055992 +%:ROW_MAJOR_SORT_TIME:A.mtx S N 20 3 3 6 0.000001 +%:ROW_MAJOR_SORT_SCALING:A.mtx S N 20 3 3 6 1.000 +%:SORTEDCOO2RSB_TIME:A.mtx S N 20 3 3 6 0.111313 +%:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 20 3 3 6 0.000 +%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 20 3 3 6 1.00 +%:SORTEDCOO2RSB_SCALING:A.mtx S N 20 3 3 6 1.00 +%:RSB_SUBDIVISION_SCALING:A.mtx S N 20 3 3 6 1.00 +%:RSB_SHUFFLE_SCALING:A.mtx S N 20 3 3 6 1.00 +%:CONSTRUCTOR_SCALING:A.mtx S N 20 3 3 6 1.00 1.00 1.00 1.00 #%:SM_COUNTS: Tot HalfwordCsr FullwordCsr HalfwordCoo FullwordCoo -%:SM_COUNTS:A.mtx S N 42 3 3 6 1 1 0 0 0 -%:SM_IDXOCCUPATIONRSBVSCOOANDCSR:A.mtx S N 42 3 3 6 28 48 36 -%:SM_IDXOCCUPATION:A.mtx S N 42 3 3 6 28 -%:SM_MEMTRAFFIC:A.mtx S N 42 3 3 6 96 -%:SM_MINMAXAVGNNZ:A.mtx S N 42 3 3 6 6 6 6 +%:SM_COUNTS:A.mtx S N 20 3 3 6 1 1 0 0 0 +%:SM_IDXOCCUPATIONRSBVSCOOANDCSR:A.mtx S N 20 3 3 6 28 48 36 +%:SM_IDXOCCUPATION:A.mtx S N 20 3 3 6 28 +%:SM_MEMTRAFFIC:A.mtx S N 20 3 3 6 96 +%:SM_MINMAXAVGNNZ:A.mtx S N 20 3 3 6 6 6 6 # -%operation:matrix CONSTRUCTOR[42] SPMV[42] SPMV[42] -%operation:A.mtx 0.0247149 1e+09 1e+09 -%constructor:matrix SORT[42] SCAN[42] SHUFFLE[42] INSERT[42] -%constructor:A.mtx 0 0.00935817 0 0.00777984 +%operation:matrix CONSTRUCTOR[20] SPMV[20] SPMV[20] +%operation:A.mtx 0.167343 1e+09 1e+09 +%constructor:matrix SORT[20] SCAN[20] SHUFFLE[20] INSERT[20] +%constructor:A.mtx 9.53674e-07 0.055321 0 0.0559921 # symmetric matrix --- skipping transposed benchmarking # multi-nrhs benchmarking (1,4) -- now using nrhs 4. # Using alpha=1 beta=1 order=rows for rsb_spmv/rsb_spsv/rsb_spmm/rsb_spsm. # multi-transpose benchmarking -- now using transA = N. # will use input matrix flags: RSB_FLAG_USE_HALFWORD_INDICES, RSB_FLAG_SORTED_INPUT, RSB_FLAG_QUAD_PARTITIONING, RSB_FLAG_SYMMETRIC, RSB_FLAG_OWN_PARTITIONING_ARRAYS -# Using 42 threads -# Constructed matrix (took 0.000s): (3 x 3)[0x555d69ddb2a0]{S} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x2442186 (coo:1, csr:0, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'S' +# Using 20 threads +# Constructed matrix (took 0.188s): (3 x 3)[0x562f6a5ee1d0]{S} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x2442186 (coo:1, csr:0, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'S' # matrix consistency check took 0.000s (ok) RSB Sparse Blocks Autotuner invoked requesting max 6 splits and max 6 merges in 1 rounds, threads spec.0 (specify negative values to enable threads tuning). Will autotune matrix: 3 x 3, type S, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:3 -3 iterations (42 th.) took 7.296e-05s; avg 2.432e-05s ( +/- 13.73/ 27.45 %); best 2.098e-05s; worst 3.099e-05s; std dev. 4.72e-06 (taking best). -Reference operation time is 2.09808e-05 s (4.576 Mflops) with 42 threads. -Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=4, order=rows) (max 6 steps, inclusive 3 grace steps) on: 3 x 3, type S, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz (tpop: 2.098e-05 Mflops: 4.576) -Merge (3 -> 1 leaves) took w.c.t. of 8.106e-06s, ~4.053e-06s of computing time (of which 9.537e-07s sorting, 2.146e-06s analysis) -3 iterations (42 th.) took 4.053e-06s; avg 1.351e-06s ( +/- 97.48/129.41 %); best 3.411e-08s; worst 3.099e-06s; std dev. 1.296e-06 (taking best). -Reference operation time is 3.41058e-08 s (2815 Mflops) with 42 threads. -After merge step 1: tpop: 3.411e-08 s ~Mflops: 2814.772 nsubm:1 otn:42 -Applying merge (3 -> 1 leaves, 42 th.) yielded SPEEDUP of 615.170x: 2.098e-05s -> 3.411e-08s, so taking this instance. +3 iterations (20 th.) took 0.07998s; avg 0.02666s ( +/- 24.63/ 19.65 %); best 0.02009s; worst 0.0319s; std dev. 0.004909 (taking best). +Reference operation time is 0.0200939 s (0.004778 Mflops) with 20 threads. +Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=4, order=rows) (max 6 steps, inclusive 3 grace steps) on: 3 x 3, type S, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz (tpop: 0.02009 Mflops: 0.005) +Merge (3 -> 1 leaves) took w.c.t. of 3.695e-05s, ~1.311e-05s of computing time (of which 1.907e-06s sorting, 7.153e-06s analysis) +3 iterations (20 th.) took 1.192e-05s; avg 3.974e-06s ( +/- 88.00/152.00 %); best 4.77e-07s; worst 1.001e-05s; std dev. 4.341e-06 (taking best). +Reference operation time is 4.76992e-07 s (201.3 Mflops) with 20 threads. +After merge step 1: tpop: 4.77e-07 s ~Mflops: 201.261 nsubm:1 otn:20 +Applying merge (3 -> 1 leaves, 20 th.) yielded SPEEDUP of 42126.309x: 0.02009s -> 4.77e-07s, so taking this instance. Merged all the matrix leaves: no reason to continue merging. -A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.000139s (of which 1.097e-05s partitioning, 0s I/O); computing times: 4.053e-06s in par. loops, 9.537e-07s sorting, 2.146e-06s analyzing) -Total merge + benchmarking process took 0.000139s, equivalent to 4075.5/6.6 new/old ops (8.488e-05s for 2 clones -- as 2488.6/4.0 ops, or 1244.3/2.0 ops per clone), SPEEDUP of 615.170x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 42 th.sp.) yielded SPEEDUP of 615.170x (2.098e-05s -> 3.411e-08s), will amortize in 6.6 ops by saving 2.095e-05s per op. -In 1 tuning rounds (tot. 0.00028s, 8.5e-05s for constructor, 2 clones) obtained a SPEEDUP of 61417.0% (615.2x) (from 4.576 to 2815 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.08439s (of which 4.196e-05s partitioning, 0s I/O); computing times: 1.311e-05s in par. loops, 1.907e-06s sorting, 7.153e-06s analyzing) +Total merge + benchmarking process took 0.08439s, equivalent to 176927.5/4.2 new/old ops (0.1638s for 2 clones -- as 343480.9/8.2 ops, or 171740.4/4.1 ops per clone), SPEEDUP of 42126.309x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 20 th.sp.) yielded SPEEDUP of 42126.309x (0.02009s -> 4.77e-07s), will amortize in 4.2 ops by saving 0.02009s per op. +In 1 tuning rounds (tot. 0.24s, 0.16s for constructor, 2 clones) obtained a SPEEDUP of 4212530.9% (4.213e+04x) (from 0.004778 to 201.3 Mflops). #pr: updating sample at index 11 (3^th of 16), 0^th touch for (0,0,0,0,1,1,0). -First run of RSB Autotuner took 0.000289917 s (2.098e-05 s -> 3.411e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.24441 s (2.009e-02 s -> 4.770e-07 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). RSB Sparse Blocks Autotuner invoked requesting max 0 splits and max 0 merges in 1 rounds, auto threads spec. -Second run of RSB Autotuner took 0.00267816 s and estimated a speedup of 1.000000 x (3.411e-08 s -> 3.411e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 1.25556 s and estimated a speedup of 1.000000 x (9.537e-07 s -> 9.537e-07 s per op) in same matrix (1 -> 1 lsubm) #min:1 #max:1 #sum:3 #norm:1.73205078 #used index storage compared to COO:28 vs 48 bytes (58.33%) ; compared to CSR:28 vs 40 bytes (77.78%) #%:CONSTRUCTOR_*:SORT SCAN INSERT SCAN+INSERT -%:CONSTRUCTOR_TIMES:A.mtx S N 42 3 3 6 0.000000 0.000070 0.000031 0.000101 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 42 3 3 6 0.000101 -%:RSB_SUBDIVISION_TIME:A.mtx S N 42 3 3 6 0.000070 -%:RSB_SHUFFLE_TIME:A.mtx S N 42 3 3 6 0.000031 -%:ROW_MAJOR_SORT_TIME:A.mtx S N 42 3 3 6 0.000000 -%:ROW_MAJOR_SORT_SCALING:A.mtx S N 42 3 3 6 -nan -%:SORTEDCOO2RSB_TIME:A.mtx S N 42 3 3 6 0.000101 -%:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 42 3 3 6 0.000 -%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 42 3 3 6 1.00 -%:SORTEDCOO2RSB_SCALING:A.mtx S N 42 3 3 6 1.00 -%:RSB_SUBDIVISION_SCALING:A.mtx S N 42 3 3 6 1.00 -%:RSB_SHUFFLE_SCALING:A.mtx S N 42 3 3 6 1.00 -%:CONSTRUCTOR_SCALING:A.mtx S N 42 3 3 6 -nan 1.00 1.00 1.00 +%:CONSTRUCTOR_TIMES:A.mtx S N 20 3 3 6 0.000001 0.075707 0.056012 0.131719 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 20 3 3 6 0.131720 +%:RSB_SUBDIVISION_TIME:A.mtx S N 20 3 3 6 0.075707 +%:RSB_SHUFFLE_TIME:A.mtx S N 20 3 3 6 0.056012 +%:ROW_MAJOR_SORT_TIME:A.mtx S N 20 3 3 6 0.000001 +%:ROW_MAJOR_SORT_SCALING:A.mtx S N 20 3 3 6 1.000 +%:SORTEDCOO2RSB_TIME:A.mtx S N 20 3 3 6 0.131719 +%:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 20 3 3 6 0.000 +%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 20 3 3 6 1.00 +%:SORTEDCOO2RSB_SCALING:A.mtx S N 20 3 3 6 1.00 +%:RSB_SUBDIVISION_SCALING:A.mtx S N 20 3 3 6 1.00 +%:RSB_SHUFFLE_SCALING:A.mtx S N 20 3 3 6 1.00 +%:CONSTRUCTOR_SCALING:A.mtx S N 20 3 3 6 1.00 1.00 1.00 1.00 #%:SM_COUNTS: Tot HalfwordCsr FullwordCsr HalfwordCoo FullwordCoo -%:SM_COUNTS:A.mtx S N 42 3 3 6 1 1 0 0 0 -%:SM_IDXOCCUPATIONRSBVSCOOANDCSR:A.mtx S N 42 3 3 6 28 48 36 -%:SM_IDXOCCUPATION:A.mtx S N 42 3 3 6 28 -%:SM_MEMTRAFFIC:A.mtx S N 42 3 3 6 96 -%:SM_MINMAXAVGNNZ:A.mtx S N 42 3 3 6 6 6 6 +%:SM_COUNTS:A.mtx S N 20 3 3 6 1 1 0 0 0 +%:SM_IDXOCCUPATIONRSBVSCOOANDCSR:A.mtx S N 20 3 3 6 28 48 36 +%:SM_IDXOCCUPATION:A.mtx S N 20 3 3 6 28 +%:SM_MEMTRAFFIC:A.mtx S N 20 3 3 6 96 +%:SM_MINMAXAVGNNZ:A.mtx S N 20 3 3 6 6 6 6 # -%operation:matrix CONSTRUCTOR[42] SPMV[42] SPMV[42] -%operation:A.mtx 0.000133991 1e+09 1e+09 -%constructor:matrix SORT[42] SCAN[42] SHUFFLE[42] INSERT[42] -%constructor:A.mtx 0 6.98566e-05 0 3.09944e-05 +%operation:matrix CONSTRUCTOR[20] SPMV[20] SPMV[20] +%operation:A.mtx 0.187731 1e+09 1e+09 +%constructor:matrix SORT[20] SCAN[20] SHUFFLE[20] INSERT[20] +%constructor:A.mtx 9.53674e-07 0.075707 0 0.0560119 # symmetric matrix --- skipping transposed benchmarking -# so far, program took 6.918s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.591s/0.000s . +# so far, program took 14.876s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 6.572s/0.000s . getrusage() stats: -ru_maxrss: 26 (maximum resident set size -- MB) -ru_stime : 0.2997s (system CPU time used) -ru_utime : 34.55s (user CPU time used) +ru_maxrss: 7 (maximum resident set size -- MB) +ru_stime : 0.08595s (system CPU time used) +ru_utime : 50.9s (user CPU time used) # multi-type benchmarking (DSCZ) -- now using typecode C (last was S). -# Cache block size total 4194304 bytes, per-thread 99864 bytes -# so far, program took 6.918s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.591s/0.000s . +# Cache block size total 524288 bytes, per-thread 26214 bytes +# so far, program took 14.876s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 6.572s/0.000s . # Reusing type converted (S->C) arrays from last iteration instead of reloading matrix file. # multi-nrhs benchmarking (1,4) -- now using nrhs 1. # Using alpha=1 beta=1 order=rows for rsb_spmv/rsb_spsv/rsb_spmm/rsb_spsm. # multi-transpose benchmarking -- now using transA = N. # will use input matrix flags: RSB_FLAG_USE_HALFWORD_INDICES, RSB_FLAG_SORTED_INPUT, RSB_FLAG_QUAD_PARTITIONING, RSB_FLAG_SYMMETRIC, RSB_FLAG_OWN_PARTITIONING_ARRAYS -# Using 42 threads -# Constructed matrix (took 0.007s): (3 x 3)[0x555d69dde5e0]{C} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x2442186 (coo:1, csr:0, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'S' +# Using 20 threads +# Constructed matrix (took 0.168s): (3 x 3)[0x562f6a5f14e0]{C} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x2442186 (coo:1, csr:0, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'S' # matrix consistency check took 0.000s (ok) RSB Sparse Blocks Autotuner invoked requesting max 6 splits and max 6 merges in 1 rounds, threads spec.0 (specify negative values to enable threads tuning). Will autotune matrix: 3 x 3, type C, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:3 -3 iterations (42 th.) took 8.297e-05s; avg 2.766e-05s ( +/- 34.48/ 62.07 %); best 1.812e-05s; worst 4.482e-05s; std dev. 1.216e-05 (taking best). -Reference operation time is 1.81198e-05 s (5.298 Mflops) with 42 threads. -Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=rows) (max 6 steps, inclusive 3 grace steps) on: 3 x 3, type C, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz (tpop: 1.812e-05 Mflops: 5.298) -Merge (3 -> 1 leaves) took w.c.t. of 6.914e-06s, ~2.146e-06s of computing time (of which 1.192e-06s sorting, 9.537e-07s analysis) -3 iterations (42 th.) took 3.386e-05s; avg 1.129e-05s ( +/- 99.70/191.55 %); best 3.411e-08s; worst 3.29e-05s; std dev. 1.529e-05 (taking best). -Reference operation time is 3.41058e-08 s (2815 Mflops) with 42 threads. -After merge step 1: tpop: 3.411e-08 s ~Mflops: 2814.772 nsubm:1 otn:42 -Applying merge (3 -> 1 leaves, 42 th.) yielded SPEEDUP of 531.283x: 1.812e-05s -> 3.411e-08s, so taking this instance. +3 iterations (20 th.) took 0.072s; avg 0.024s ( +/- 33.21/ 16.65 %); best 0.01603s; worst 0.028s; std dev. 0.005637 (taking best). +Reference operation time is 0.0160298 s (0.005989 Mflops) with 20 threads. +Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=rows) (max 6 steps, inclusive 3 grace steps) on: 3 x 3, type C, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz (tpop: 0.01603 Mflops: 0.006) +Merge (3 -> 1 leaves) took w.c.t. of 3.505e-05s, ~1.097e-05s of computing time (of which 2.146e-06s sorting, 8.106e-06s analysis) +3 iterations (20 th.) took 4.697e-05s; avg 1.566e-05s ( +/- 93.91/186.29 %); best 9.537e-07s; worst 4.482e-05s; std dev. 2.062e-05 (taking best). +Reference operation time is 9.53674e-07 s (100.7 Mflops) with 20 threads. +After merge step 1: tpop: 9.537e-07 s ~Mflops: 100.663 nsubm:1 otn:20 +Applying merge (3 -> 1 leaves, 20 th.) yielded SPEEDUP of 16808.500x: 0.01603s -> 9.537e-07s, so taking this instance. Merged all the matrix leaves: no reason to continue merging. -A total of 1 merge steps (of max 6) (3 -> 1 subms) took 9.584e-05s (of which 1.001e-05s partitioning, 0s I/O); computing times: 2.146e-06s in par. loops, 1.192e-06s sorting, 9.537e-07s analyzing) -Total merge + benchmarking process took 9.584e-05s, equivalent to 2810.2/5.3 new/old ops (8.392e-05s for 2 clones -- as 2460.7/4.6 ops, or 1230.3/2.3 ops per clone), SPEEDUP of 531.283x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 42 th.sp.) yielded SPEEDUP of 531.283x (1.812e-05s -> 3.411e-08s), will amortize in 5.3 ops by saving 1.809e-05s per op. -In 1 tuning rounds (tot. 0.00025s, 8.4e-05s for constructor, 2 clones) obtained a SPEEDUP of 53028.3% (531.3x) (from 5.298 to 2815 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.08045s (of which 3.982e-05s partitioning, 0s I/O); computing times: 1.097e-05s in par. loops, 2.146e-06s sorting, 8.106e-06s analyzing) +Total merge + benchmarking process took 0.08045s, equivalent to 84357.0/5.0 new/old ops (0.1479s for 2 clones -- as 155059.2/9.2 ops, or 77529.6/4.6 ops per clone), SPEEDUP of 16808.500x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 20 th.sp.) yielded SPEEDUP of 16808.500x (0.01603s -> 9.537e-07s), will amortize in 5.0 ops by saving 0.01603s per op. +In 1 tuning rounds (tot. 0.22s, 0.15s for constructor, 2 clones) obtained a SPEEDUP of 1680750.0% (1.681e+04x) (from 0.005989 to 100.7 Mflops). #pr: updating sample at index 5 (4^th of 16), 0^th touch for (0,0,0,0,0,2,0). -First run of RSB Autotuner took 0.000259161 s (1.812e-05 s -> 3.411e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.220105 s (1.603e-02 s -> 9.537e-07 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). RSB Sparse Blocks Autotuner invoked requesting max 0 splits and max 0 merges in 1 rounds, auto threads spec. -Second run of RSB Autotuner took 0.000974894 s and estimated a speedup of 1.000000 x (3.411e-08 s -> 3.411e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 1.27947 s and estimated a speedup of 1.000000 x (4.770e-07 s -> 4.770e-07 s per op) in same matrix (1 -> 1 lsubm) #min:1 0 #max:1 0 #sum:3 0 #norm:1.73205078 0 #used index storage compared to COO:28 vs 48 bytes (58.33%) ; compared to CSR:28 vs 40 bytes (77.78%) #%:CONSTRUCTOR_*:SORT SCAN INSERT SCAN+INSERT -%:CONSTRUCTOR_TIMES:A.mtx S N 42 3 3 6 0.000000 0.006602 0.000029 0.006631 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 42 3 3 6 0.006631 -%:RSB_SUBDIVISION_TIME:A.mtx S N 42 3 3 6 0.006602 -%:RSB_SHUFFLE_TIME:A.mtx S N 42 3 3 6 0.000029 -%:ROW_MAJOR_SORT_TIME:A.mtx S N 42 3 3 6 0.000000 -%:ROW_MAJOR_SORT_SCALING:A.mtx S N 42 3 3 6 -nan -%:SORTEDCOO2RSB_TIME:A.mtx S N 42 3 3 6 0.006631 -%:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 42 3 3 6 0.000 -%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 42 3 3 6 1.00 -%:SORTEDCOO2RSB_SCALING:A.mtx S N 42 3 3 6 1.00 -%:RSB_SUBDIVISION_SCALING:A.mtx S N 42 3 3 6 1.00 -%:RSB_SHUFFLE_SCALING:A.mtx S N 42 3 3 6 1.00 -%:CONSTRUCTOR_SCALING:A.mtx S N 42 3 3 6 -nan 1.00 1.00 1.00 +%:CONSTRUCTOR_TIMES:A.mtx S N 20 3 3 6 0.000000 0.067722 0.044011 0.111733 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 20 3 3 6 0.111733 +%:RSB_SUBDIVISION_TIME:A.mtx S N 20 3 3 6 0.067722 +%:RSB_SHUFFLE_TIME:A.mtx S N 20 3 3 6 0.044011 +%:ROW_MAJOR_SORT_TIME:A.mtx S N 20 3 3 6 0.000000 +%:ROW_MAJOR_SORT_SCALING:A.mtx S N 20 3 3 6 -nan +%:SORTEDCOO2RSB_TIME:A.mtx S N 20 3 3 6 0.111733 +%:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 20 3 3 6 0.000 +%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 20 3 3 6 1.00 +%:SORTEDCOO2RSB_SCALING:A.mtx S N 20 3 3 6 1.00 +%:RSB_SUBDIVISION_SCALING:A.mtx S N 20 3 3 6 1.00 +%:RSB_SHUFFLE_SCALING:A.mtx S N 20 3 3 6 1.00 +%:CONSTRUCTOR_SCALING:A.mtx S N 20 3 3 6 -nan 1.00 1.00 1.00 #%:SM_COUNTS: Tot HalfwordCsr FullwordCsr HalfwordCoo FullwordCoo -%:SM_COUNTS:A.mtx S N 42 3 3 6 1 1 0 0 0 -%:SM_IDXOCCUPATIONRSBVSCOOANDCSR:A.mtx S N 42 3 3 6 28 48 36 -%:SM_IDXOCCUPATION:A.mtx S N 42 3 3 6 28 -%:SM_MEMTRAFFIC:A.mtx S N 42 3 3 6 156 -%:SM_MINMAXAVGNNZ:A.mtx S N 42 3 3 6 6 6 6 +%:SM_COUNTS:A.mtx S N 20 3 3 6 1 1 0 0 0 +%:SM_IDXOCCUPATIONRSBVSCOOANDCSR:A.mtx S N 20 3 3 6 28 48 36 +%:SM_IDXOCCUPATION:A.mtx S N 20 3 3 6 28 +%:SM_MEMTRAFFIC:A.mtx S N 20 3 3 6 156 +%:SM_MINMAXAVGNNZ:A.mtx S N 20 3 3 6 6 6 6 # -%operation:matrix CONSTRUCTOR[42] SPMV[42] SPMV[42] -%operation:A.mtx 0.00666499 1e+09 1e+09 -%constructor:matrix SORT[42] SCAN[42] SHUFFLE[42] INSERT[42] -%constructor:A.mtx 0 0.00660205 0 2.90871e-05 +%operation:matrix CONSTRUCTOR[20] SPMV[20] SPMV[20] +%operation:A.mtx 0.167732 1e+09 1e+09 +%constructor:matrix SORT[20] SCAN[20] SHUFFLE[20] INSERT[20] +%constructor:A.mtx 0 0.0677218 0 0.0440111 # symmetric matrix --- skipping transposed benchmarking # multi-nrhs benchmarking (1,4) -- now using nrhs 4. # Using alpha=1 beta=1 order=rows for rsb_spmv/rsb_spsv/rsb_spmm/rsb_spsm. # multi-transpose benchmarking -- now using transA = N. # will use input matrix flags: RSB_FLAG_USE_HALFWORD_INDICES, RSB_FLAG_SORTED_INPUT, RSB_FLAG_QUAD_PARTITIONING, RSB_FLAG_SYMMETRIC, RSB_FLAG_OWN_PARTITIONING_ARRAYS -# Using 42 threads -# Constructed matrix (took 0.000s): (3 x 3)[0x555d69dde5e0]{C} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x2442186 (coo:1, csr:0, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'S' +# Using 20 threads +# Constructed matrix (took 0.199s): (3 x 3)[0x562f6a5f14e0]{C} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x2442186 (coo:1, csr:0, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'S' # matrix consistency check took 0.000s (ok) RSB Sparse Blocks Autotuner invoked requesting max 6 splits and max 6 merges in 1 rounds, threads spec.0 (specify negative values to enable threads tuning). Will autotune matrix: 3 x 3, type C, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:3 -3 iterations (42 th.) took 8.798e-05s; avg 2.933e-05s ( +/- 28.46/ 50.41 %); best 2.098e-05s; worst 4.411e-05s; std dev. 1.048e-05 (taking best). -Reference operation time is 2.09808e-05 s (18.3 Mflops) with 42 threads. -Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=4, order=rows) (max 6 steps, inclusive 3 grace steps) on: 3 x 3, type C, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz (tpop: 2.098e-05 Mflops: 18.302) -Merge (3 -> 1 leaves) took w.c.t. of 5.96e-06s, ~1.907e-06s of computing time (of which 9.537e-07s sorting, 9.537e-07s analysis) -3 iterations (42 th.) took 5.007e-06s; avg 1.669e-06s ( +/- 42.86/ 85.71 %); best 9.537e-07s; worst 3.099e-06s; std dev. 1.012e-06 (taking best). -Reference operation time is 9.53674e-07 s (402.7 Mflops) with 42 threads. -After merge step 1: tpop: 9.537e-07 s ~Mflops: 402.653 nsubm:1 otn:42 -Applying merge (3 -> 1 leaves, 42 th.) yielded SPEEDUP of 22.000x: 2.098e-05s -> 9.537e-07s, so taking this instance. +3 iterations (20 th.) took 0.088s; avg 0.02933s ( +/- 45.49/ 44.79 %); best 0.01599s; worst 0.04247s; std dev. 0.01081 (taking best). +Reference operation time is 0.0159891 s (0.02402 Mflops) with 20 threads. +Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=4, order=rows) (max 6 steps, inclusive 3 grace steps) on: 3 x 3, type C, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz (tpop: 0.01599 Mflops: 0.024) +Merge (3 -> 1 leaves) took w.c.t. of 2.694e-05s, ~7.868e-06s of computing time (of which 2.146e-06s sorting, 5.96e-06s analysis) +3 iterations (20 th.) took 1.001e-05s; avg 3.338e-06s ( +/- 71.43/114.29 %); best 9.537e-07s; worst 7.153e-06s; std dev. 2.725e-06 (taking best). +Reference operation time is 9.53674e-07 s (402.7 Mflops) with 20 threads. +After merge step 1: tpop: 9.537e-07 s ~Mflops: 402.653 nsubm:1 otn:20 +Applying merge (3 -> 1 leaves, 20 th.) yielded SPEEDUP of 16765.750x: 0.01599s -> 9.537e-07s, so taking this instance. Merged all the matrix leaves: no reason to continue merging. -A total of 1 merge steps (of max 6) (3 -> 1 subms) took 6.7e-05s (of which 7.868e-06s partitioning, 0s I/O); computing times: 1.907e-06s in par. loops, 9.537e-07s sorting, 9.537e-07s analyzing) -Total merge + benchmarking process took 6.7e-05s, equivalent to 70.2/3.2 new/old ops (8.202e-05s for 2 clones -- as 86.0/3.9 ops, or 43.0/2.0 ops per clone), SPEEDUP of 22.000x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 42 th.sp.) yielded SPEEDUP of 22.000x (2.098e-05s -> 9.537e-07s), will amortize in 3.3 ops by saving 2.003e-05s per op. -In 1 tuning rounds (tot. 0.00022s, 8.2e-05s for constructor, 2 clones) obtained a SPEEDUP of 2100.0% (22x) (from 18.3 to 402.7 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.09198s (of which 3.29e-05s partitioning, 0s I/O); computing times: 7.868e-06s in par. loops, 2.146e-06s sorting, 5.96e-06s analyzing) +Total merge + benchmarking process took 0.09198s, equivalent to 96446.0/5.8 new/old ops (0.2118s for 2 clones -- as 222110.2/13.2 ops, or 111055.1/6.6 ops per clone), SPEEDUP of 16765.750x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 20 th.sp.) yielded SPEEDUP of 16765.750x (0.01599s -> 9.537e-07s), will amortize in 5.8 ops by saving 0.01599s per op. +In 1 tuning rounds (tot. 0.3s, 0.21s for constructor, 2 clones) obtained a SPEEDUP of 1676475.0% (1.677e+04x) (from 0.02402 to 402.7 Mflops). #pr: updating sample at index 13 (5^th of 16), 0^th touch for (0,0,0,0,1,2,0). -First run of RSB Autotuner took 0.000230074 s (2.098e-05 s -> 9.537e-07 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.299972 s (1.599e-02 s -> 9.537e-07 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). RSB Sparse Blocks Autotuner invoked requesting max 0 splits and max 0 merges in 1 rounds, auto threads spec. -Second run of RSB Autotuner took 0.000926018 s and estimated a speedup of 1.000000 x (3.411e-08 s -> 3.411e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 1.36397 s and estimated a speedup of 1.000000 x (9.537e-07 s -> 9.537e-07 s per op) in same matrix (1 -> 1 lsubm) #min:1 0 #max:1 0 #sum:3 0 #norm:1.73205078 0 #used index storage compared to COO:28 vs 48 bytes (58.33%) ; compared to CSR:28 vs 40 bytes (77.78%) #%:CONSTRUCTOR_*:SORT SCAN INSERT SCAN+INSERT -%:CONSTRUCTOR_TIMES:A.mtx S N 42 3 3 6 0.000000 0.000066 0.000031 0.000097 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 42 3 3 6 0.000097 -%:RSB_SUBDIVISION_TIME:A.mtx S N 42 3 3 6 0.000066 -%:RSB_SHUFFLE_TIME:A.mtx S N 42 3 3 6 0.000031 -%:ROW_MAJOR_SORT_TIME:A.mtx S N 42 3 3 6 0.000000 -%:ROW_MAJOR_SORT_SCALING:A.mtx S N 42 3 3 6 -nan -%:SORTEDCOO2RSB_TIME:A.mtx S N 42 3 3 6 0.000097 -%:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 42 3 3 6 0.000 -%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 42 3 3 6 1.00 -%:SORTEDCOO2RSB_SCALING:A.mtx S N 42 3 3 6 1.00 -%:RSB_SUBDIVISION_SCALING:A.mtx S N 42 3 3 6 1.00 -%:RSB_SHUFFLE_SCALING:A.mtx S N 42 3 3 6 1.00 -%:CONSTRUCTOR_SCALING:A.mtx S N 42 3 3 6 -nan 1.00 1.00 1.00 +%:CONSTRUCTOR_TIMES:A.mtx S N 20 3 3 6 0.000000 0.063377 0.079997 0.143374 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 20 3 3 6 0.143374 +%:RSB_SUBDIVISION_TIME:A.mtx S N 20 3 3 6 0.063377 +%:RSB_SHUFFLE_TIME:A.mtx S N 20 3 3 6 0.079997 +%:ROW_MAJOR_SORT_TIME:A.mtx S N 20 3 3 6 0.000000 +%:ROW_MAJOR_SORT_SCALING:A.mtx S N 20 3 3 6 -nan +%:SORTEDCOO2RSB_TIME:A.mtx S N 20 3 3 6 0.143374 +%:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 20 3 3 6 0.000 +%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 20 3 3 6 1.00 +%:SORTEDCOO2RSB_SCALING:A.mtx S N 20 3 3 6 1.00 +%:RSB_SUBDIVISION_SCALING:A.mtx S N 20 3 3 6 1.00 +%:RSB_SHUFFLE_SCALING:A.mtx S N 20 3 3 6 1.00 +%:CONSTRUCTOR_SCALING:A.mtx S N 20 3 3 6 -nan 1.00 1.00 1.00 #%:SM_COUNTS: Tot HalfwordCsr FullwordCsr HalfwordCoo FullwordCoo -%:SM_COUNTS:A.mtx S N 42 3 3 6 1 1 0 0 0 -%:SM_IDXOCCUPATIONRSBVSCOOANDCSR:A.mtx S N 42 3 3 6 28 48 36 -%:SM_IDXOCCUPATION:A.mtx S N 42 3 3 6 28 -%:SM_MEMTRAFFIC:A.mtx S N 42 3 3 6 156 -%:SM_MINMAXAVGNNZ:A.mtx S N 42 3 3 6 6 6 6 +%:SM_COUNTS:A.mtx S N 20 3 3 6 1 1 0 0 0 +%:SM_IDXOCCUPATIONRSBVSCOOANDCSR:A.mtx S N 20 3 3 6 28 48 36 +%:SM_IDXOCCUPATION:A.mtx S N 20 3 3 6 28 +%:SM_MEMTRAFFIC:A.mtx S N 20 3 3 6 156 +%:SM_MINMAXAVGNNZ:A.mtx S N 20 3 3 6 6 6 6 # -%operation:matrix CONSTRUCTOR[42] SPMV[42] SPMV[42] -%operation:A.mtx 0.000133038 1e+09 1e+09 -%constructor:matrix SORT[42] SCAN[42] SHUFFLE[42] INSERT[42] -%constructor:A.mtx 0 6.60419e-05 0 3.09944e-05 +%operation:matrix CONSTRUCTOR[20] SPMV[20] SPMV[20] +%operation:A.mtx 0.19941 1e+09 1e+09 +%constructor:matrix SORT[20] SCAN[20] SHUFFLE[20] INSERT[20] +%constructor:A.mtx 0 0.0633769 0 0.0799971 # symmetric matrix --- skipping transposed benchmarking -# so far, program took 6.956s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.593s/0.000s . +# so far, program took 18.720s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 9.735s/0.000s . getrusage() stats: -ru_maxrss: 26 (maximum resident set size -- MB) -ru_stime : 0.3034s (system CPU time used) -ru_utime : 36.01s (user CPU time used) +ru_maxrss: 7 (maximum resident set size -- MB) +ru_stime : 0.1017s (system CPU time used) +ru_utime : 78.11s (user CPU time used) # multi-type benchmarking (DSCZ) -- now using typecode Z (last was C). -# Cache block size total 4194304 bytes, per-thread 99864 bytes -# so far, program took 6.956s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.593s/0.000s . +# Cache block size total 524288 bytes, per-thread 26214 bytes +# so far, program took 18.720s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 9.735s/0.000s . # Reusing type converted (C->Z) arrays from last iteration instead of reloading matrix file. # multi-nrhs benchmarking (1,4) -- now using nrhs 1. # Using alpha=1 beta=1 order=rows for rsb_spmv/rsb_spsv/rsb_spmm/rsb_spsm. # multi-transpose benchmarking -- now using transA = N. # will use input matrix flags: RSB_FLAG_USE_HALFWORD_INDICES, RSB_FLAG_SORTED_INPUT, RSB_FLAG_QUAD_PARTITIONING, RSB_FLAG_SYMMETRIC, RSB_FLAG_OWN_PARTITIONING_ARRAYS -# Using 42 threads -# Constructed matrix (took 0.000s): (3 x 3)[0x555d69dde5e0]{Z} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x2442186 (coo:1, csr:0, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'S' +# Using 20 threads +# Constructed matrix (took 0.167s): (3 x 3)[0x562f6a5f14e0]{Z} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x2442186 (coo:1, csr:0, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'S' # matrix consistency check took 0.000s (ok) RSB Sparse Blocks Autotuner invoked requesting max 6 splits and max 6 merges in 1 rounds, threads spec.0 (specify negative values to enable threads tuning). Will autotune matrix: 3 x 3, type Z, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:3 -3 iterations (42 th.) took 7.987e-05s; avg 2.662e-05s ( +/- 24.78/ 45.97 %); best 2.003e-05s; worst 3.886e-05s; std dev. 8.663e-06 (taking best). -Reference operation time is 2.00272e-05 s (4.793 Mflops) with 42 threads. -Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=rows) (max 6 steps, inclusive 3 grace steps) on: 3 x 3, type Z, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz (tpop: 2.003e-05 Mflops: 4.793) -Merge (3 -> 1 leaves) took w.c.t. of 5.96e-06s, ~1.907e-06s of computing time (of which 9.537e-07s sorting, 1.192e-06s analysis) -3 iterations (42 th.) took 1.001e-05s; avg 3.338e-06s ( +/- 98.98/171.43 %); best 3.411e-08s; worst 9.06e-06s; std dev. 4.065e-06 (taking best). -Reference operation time is 3.41058e-08 s (2815 Mflops) with 42 threads. -After merge step 1: tpop: 3.411e-08 s ~Mflops: 2814.772 nsubm:1 otn:42 -Applying merge (3 -> 1 leaves, 42 th.) yielded SPEEDUP of 587.207x: 2.003e-05s -> 3.411e-08s, so taking this instance. +3 iterations (20 th.) took 0.05598s; avg 0.01866s ( +/- 14.37/ 28.55 %); best 0.01598s; worst 0.02399s; std dev. 0.003768 (taking best). +Reference operation time is 0.01598 s (0.006008 Mflops) with 20 threads. +Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=rows) (max 6 steps, inclusive 3 grace steps) on: 3 x 3, type Z, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz (tpop: 0.01598 Mflops: 0.006) +Merge (3 -> 1 leaves) took w.c.t. of 3.195e-05s, ~1.192e-05s of computing time (of which 2.146e-06s sorting, 6.199e-06s analysis) +3 iterations (20 th.) took 3.004e-05s; avg 1.001e-05s ( +/- 90.48/178.57 %); best 9.537e-07s; worst 2.789e-05s; std dev. 1.264e-05 (taking best). +Reference operation time is 9.53674e-07 s (100.7 Mflops) with 20 threads. +After merge step 1: tpop: 9.537e-07 s ~Mflops: 100.663 nsubm:1 otn:20 +Applying merge (3 -> 1 leaves, 20 th.) yielded SPEEDUP of 16756.250x: 0.01598s -> 9.537e-07s, so taking this instance. Merged all the matrix leaves: no reason to continue merging. -A total of 1 merge steps (of max 6) (3 -> 1 subms) took 7.391e-05s (of which 8.106e-06s partitioning, 0s I/O); computing times: 1.907e-06s in par. loops, 9.537e-07s sorting, 1.192e-06s analyzing) -Total merge + benchmarking process took 7.391e-05s, equivalent to 2167.1/3.7 new/old ops (8.297e-05s for 2 clones -- as 2432.7/4.1 ops, or 1216.4/2.1 ops per clone), SPEEDUP of 587.207x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 42 th.sp.) yielded SPEEDUP of 587.207x (2.003e-05s -> 3.411e-08s), will amortize in 3.7 ops by saving 1.999e-05s per op. -In 1 tuning rounds (tot. 0.00022s, 8.3e-05s for constructor, 2 clones) obtained a SPEEDUP of 58620.7% (587.2x) (from 4.793 to 2815 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.07198s (of which 3.695e-05s partitioning, 0s I/O); computing times: 1.192e-05s in par. loops, 2.146e-06s sorting, 6.199e-06s analyzing) +Total merge + benchmarking process took 0.07198s, equivalent to 75475.2/4.5 new/old ops (0.1558s for 2 clones -- as 163378.5/9.8 ops, or 81689.2/4.9 ops per clone), SPEEDUP of 16756.250x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 20 th.sp.) yielded SPEEDUP of 16756.250x (0.01598s -> 9.537e-07s), will amortize in 4.5 ops by saving 0.01598s per op. +In 1 tuning rounds (tot. 0.21s, 0.16s for constructor, 2 clones) obtained a SPEEDUP of 1675525.0% (1.676e+04x) (from 0.006008 to 100.7 Mflops). #pr: updating sample at index 7 (6^th of 16), 0^th touch for (0,0,0,0,0,3,0). -First run of RSB Autotuner took 0.00022912 s (2.003e-05 s -> 3.411e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.212004 s (1.598e-02 s -> 9.537e-07 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). RSB Sparse Blocks Autotuner invoked requesting max 0 splits and max 0 merges in 1 rounds, auto threads spec. -Second run of RSB Autotuner took 0.000936985 s and estimated a speedup of 1.000000 x (3.411e-08 s -> 3.411e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 1.07193 s and estimated a speedup of 1.000000 x (9.537e-07 s -> 9.537e-07 s per op) in same matrix (1 -> 1 lsubm) #min:1 0 #max:1 0 #sum:3 0 #norm:1.7320508075688772 0 #used index storage compared to COO:28 vs 48 bytes (58.33%) ; compared to CSR:28 vs 40 bytes (77.78%) #%:CONSTRUCTOR_*:SORT SCAN INSERT SCAN+INSERT -%:CONSTRUCTOR_TIMES:A.mtx S N 42 3 3 6 0.000000 0.000067 0.000032 0.000099 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 42 3 3 6 0.000099 -%:RSB_SUBDIVISION_TIME:A.mtx S N 42 3 3 6 0.000067 -%:RSB_SHUFFLE_TIME:A.mtx S N 42 3 3 6 0.000032 -%:ROW_MAJOR_SORT_TIME:A.mtx S N 42 3 3 6 0.000000 -%:ROW_MAJOR_SORT_SCALING:A.mtx S N 42 3 3 6 -nan -%:SORTEDCOO2RSB_TIME:A.mtx S N 42 3 3 6 0.000099 -%:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 42 3 3 6 0.000 -%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 42 3 3 6 1.00 -%:SORTEDCOO2RSB_SCALING:A.mtx S N 42 3 3 6 1.00 -%:RSB_SUBDIVISION_SCALING:A.mtx S N 42 3 3 6 1.00 -%:RSB_SHUFFLE_SCALING:A.mtx S N 42 3 3 6 1.00 -%:CONSTRUCTOR_SCALING:A.mtx S N 42 3 3 6 -nan 1.00 1.00 1.00 +%:CONSTRUCTOR_TIMES:A.mtx S N 20 3 3 6 0.000001 0.055451 0.055960 0.111411 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 20 3 3 6 0.111412 +%:RSB_SUBDIVISION_TIME:A.mtx S N 20 3 3 6 0.055451 +%:RSB_SHUFFLE_TIME:A.mtx S N 20 3 3 6 0.055960 +%:ROW_MAJOR_SORT_TIME:A.mtx S N 20 3 3 6 0.000001 +%:ROW_MAJOR_SORT_SCALING:A.mtx S N 20 3 3 6 1.000 +%:SORTEDCOO2RSB_TIME:A.mtx S N 20 3 3 6 0.111411 +%:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 20 3 3 6 0.000 +%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 20 3 3 6 1.00 +%:SORTEDCOO2RSB_SCALING:A.mtx S N 20 3 3 6 1.00 +%:RSB_SUBDIVISION_SCALING:A.mtx S N 20 3 3 6 1.00 +%:RSB_SHUFFLE_SCALING:A.mtx S N 20 3 3 6 1.00 +%:CONSTRUCTOR_SCALING:A.mtx S N 20 3 3 6 1.00 1.00 1.00 1.00 #%:SM_COUNTS: Tot HalfwordCsr FullwordCsr HalfwordCoo FullwordCoo -%:SM_COUNTS:A.mtx S N 42 3 3 6 1 1 0 0 0 -%:SM_IDXOCCUPATIONRSBVSCOOANDCSR:A.mtx S N 42 3 3 6 28 48 36 -%:SM_IDXOCCUPATION:A.mtx S N 42 3 3 6 28 -%:SM_MEMTRAFFIC:A.mtx S N 42 3 3 6 276 -%:SM_MINMAXAVGNNZ:A.mtx S N 42 3 3 6 6 6 6 +%:SM_COUNTS:A.mtx S N 20 3 3 6 1 1 0 0 0 +%:SM_IDXOCCUPATIONRSBVSCOOANDCSR:A.mtx S N 20 3 3 6 28 48 36 +%:SM_IDXOCCUPATION:A.mtx S N 20 3 3 6 28 +%:SM_MEMTRAFFIC:A.mtx S N 20 3 3 6 276 +%:SM_MINMAXAVGNNZ:A.mtx S N 20 3 3 6 6 6 6 # -%operation:matrix CONSTRUCTOR[42] SPMV[42] SPMV[42] -%operation:A.mtx 0.000134945 1e+09 1e+09 -%constructor:matrix SORT[42] SCAN[42] SHUFFLE[42] INSERT[42] -%constructor:A.mtx 0 6.69956e-05 0 3.19481e-05 +%operation:matrix CONSTRUCTOR[20] SPMV[20] SPMV[20] +%operation:A.mtx 0.167447 1e+09 1e+09 +%constructor:matrix SORT[20] SCAN[20] SHUFFLE[20] INSERT[20] +%constructor:A.mtx 9.53674e-07 0.0554509 0 0.0559599 # symmetric matrix --- skipping transposed benchmarking # multi-nrhs benchmarking (1,4) -- now using nrhs 4. # Using alpha=1 beta=1 order=rows for rsb_spmv/rsb_spsv/rsb_spmm/rsb_spsm. # multi-transpose benchmarking -- now using transA = N. # will use input matrix flags: RSB_FLAG_USE_HALFWORD_INDICES, RSB_FLAG_SORTED_INPUT, RSB_FLAG_QUAD_PARTITIONING, RSB_FLAG_SYMMETRIC, RSB_FLAG_OWN_PARTITIONING_ARRAYS -# Using 42 threads -# Constructed matrix (took 0.004s): (3 x 3)[0x555d69dde5e0]{Z} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x2442186 (coo:1, csr:0, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'S' +# Using 20 threads +# Constructed matrix (took 0.168s): (3 x 3)[0x562f6a5f14e0]{Z} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x2442186 (coo:1, csr:0, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'S' # matrix consistency check took 0.000s (ok) RSB Sparse Blocks Autotuner invoked requesting max 6 splits and max 6 merges in 1 rounds, threads spec.0 (specify negative values to enable threads tuning). Will autotune matrix: 3 x 3, type Z, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:3 -3 iterations (42 th.) took 0.000134s; avg 4.466e-05s ( +/- 53.02/ 72.42 %); best 2.098e-05s; worst 7.701e-05s; std dev. 2.368e-05 (taking best). -Reference operation time is 2.09808e-05 s (18.3 Mflops) with 42 threads. -Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=4, order=rows) (max 6 steps, inclusive 3 grace steps) on: 3 x 3, type Z, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz (tpop: 2.098e-05 Mflops: 18.302) -Merge (3 -> 1 leaves) took w.c.t. of 5.96e-06s, ~1.907e-06s of computing time (of which 9.537e-07s sorting, 9.537e-07s analysis) -3 iterations (42 th.) took 1.311e-05s; avg 4.371e-06s ( +/- 99.22/178.18 %); best 3.411e-08s; worst 1.216e-05s; std dev. 5.521e-06 (taking best). -Reference operation time is 3.41058e-08 s (1.126e+04 Mflops) with 42 threads. -After merge step 1: tpop: 3.411e-08 s ~Mflops: 11259.089 nsubm:1 otn:42 -Applying merge (3 -> 1 leaves, 42 th.) yielded SPEEDUP of 615.170x: 2.098e-05s -> 3.411e-08s, so taking this instance. +3 iterations (20 th.) took 0.08s; avg 0.02667s ( +/- 10.07/ 20.06 %); best 0.02398s; worst 0.03202s; std dev. 0.003783 (taking best). +Reference operation time is 0.0239809 s (0.01601 Mflops) with 20 threads. +Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=4, order=rows) (max 6 steps, inclusive 3 grace steps) on: 3 x 3, type Z, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz (tpop: 0.02398 Mflops: 0.016) +Merge (3 -> 1 leaves) took w.c.t. of 3.004e-05s, ~1.216e-05s of computing time (of which 2.861e-06s sorting, 5.007e-06s analysis) +3 iterations (20 th.) took 1.097e-05s; avg 3.656e-06s ( +/- 73.91/115.22 %); best 9.537e-07s; worst 7.868e-06s; std dev. 3.018e-06 (taking best). +Reference operation time is 9.53674e-07 s (402.7 Mflops) with 20 threads. +After merge step 1: tpop: 9.537e-07 s ~Mflops: 402.653 nsubm:1 otn:20 +Applying merge (3 -> 1 leaves, 20 th.) yielded SPEEDUP of 25145.750x: 0.02398s -> 9.537e-07s, so taking this instance. Merged all the matrix leaves: no reason to continue merging. -A total of 1 merge steps (of max 6) (3 -> 1 subms) took 7.391e-05s (of which 7.868e-06s partitioning, 0s I/O); computing times: 1.907e-06s in par. loops, 9.537e-07s sorting, 9.537e-07s analyzing) -Total merge + benchmarking process took 7.391e-05s, equivalent to 2167.1/3.5 new/old ops (7.987e-05s for 2 clones -- as 2341.8/3.8 ops, or 1170.9/1.9 ops per clone), SPEEDUP of 615.170x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 42 th.sp.) yielded SPEEDUP of 615.170x (2.098e-05s -> 3.411e-08s), will amortize in 3.5 ops by saving 2.095e-05s per op. -In 1 tuning rounds (tot. 0.00027s, 8e-05s for constructor, 2 clones) obtained a SPEEDUP of 61417.0% (615.2x) (from 18.3 to 1.126e+04 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.07197s (of which 3.481e-05s partitioning, 0s I/O); computing times: 1.216e-05s in par. loops, 2.861e-06s sorting, 5.007e-06s analyzing) +Total merge + benchmarking process took 0.07197s, equivalent to 75470.2/3.0 new/old ops (0.1478s for 2 clones -- as 154978.8/6.2 ops, or 77489.4/3.1 ops per clone), SPEEDUP of 25145.750x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 20 th.sp.) yielded SPEEDUP of 25145.750x (0.02398s -> 9.537e-07s), will amortize in 3.0 ops by saving 0.02398s per op. +In 1 tuning rounds (tot. 0.23s, 0.15s for constructor, 2 clones) obtained a SPEEDUP of 2514475.0% (2.515e+04x) (from 0.01601 to 402.7 Mflops). #pr: updating sample at index 15 (7^th of 16), 0^th touch for (0,0,0,0,1,3,0). -First run of RSB Autotuner took 0.000418901 s (2.098e-05 s -> 3.411e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.228249 s (2.398e-02 s -> 9.537e-07 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). RSB Sparse Blocks Autotuner invoked requesting max 0 splits and max 0 merges in 1 rounds, auto threads spec. -Second run of RSB Autotuner took 0.000925064 s and estimated a speedup of 1.000000 x (9.537e-07 s -> 9.537e-07 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 1.25967 s and estimated a speedup of 1.000000 x (9.537e-07 s -> 9.537e-07 s per op) in same matrix (1 -> 1 lsubm) #min:1 0 #max:1 0 #sum:3 0 #norm:1.7320508075688772 0 #used index storage compared to COO:28 vs 48 bytes (58.33%) ; compared to CSR:28 vs 40 bytes (77.78%) #%:CONSTRUCTOR_*:SORT SCAN INSERT SCAN+INSERT -%:CONSTRUCTOR_TIMES:A.mtx S N 42 3 3 6 0.000000 0.004384 0.000029 0.004413 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 42 3 3 6 0.004413 -%:RSB_SUBDIVISION_TIME:A.mtx S N 42 3 3 6 0.004384 -%:RSB_SHUFFLE_TIME:A.mtx S N 42 3 3 6 0.000029 -%:ROW_MAJOR_SORT_TIME:A.mtx S N 42 3 3 6 0.000000 -%:ROW_MAJOR_SORT_SCALING:A.mtx S N 42 3 3 6 -nan -%:SORTEDCOO2RSB_TIME:A.mtx S N 42 3 3 6 0.004413 -%:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 42 3 3 6 0.000 -%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 42 3 3 6 1.00 -%:SORTEDCOO2RSB_SCALING:A.mtx S N 42 3 3 6 1.00 -%:RSB_SUBDIVISION_SCALING:A.mtx S N 42 3 3 6 1.00 -%:RSB_SHUFFLE_SCALING:A.mtx S N 42 3 3 6 1.00 -%:CONSTRUCTOR_SCALING:A.mtx S N 42 3 3 6 -nan 1.00 1.00 1.00 +%:CONSTRUCTOR_TIMES:A.mtx S N 20 3 3 6 0.000000 0.071778 0.039996 0.111774 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 20 3 3 6 0.111774 +%:RSB_SUBDIVISION_TIME:A.mtx S N 20 3 3 6 0.071778 +%:RSB_SHUFFLE_TIME:A.mtx S N 20 3 3 6 0.039996 +%:ROW_MAJOR_SORT_TIME:A.mtx S N 20 3 3 6 0.000000 +%:ROW_MAJOR_SORT_SCALING:A.mtx S N 20 3 3 6 -nan +%:SORTEDCOO2RSB_TIME:A.mtx S N 20 3 3 6 0.111774 +%:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 20 3 3 6 0.000 +%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 20 3 3 6 1.00 +%:SORTEDCOO2RSB_SCALING:A.mtx S N 20 3 3 6 1.00 +%:RSB_SUBDIVISION_SCALING:A.mtx S N 20 3 3 6 1.00 +%:RSB_SHUFFLE_SCALING:A.mtx S N 20 3 3 6 1.00 +%:CONSTRUCTOR_SCALING:A.mtx S N 20 3 3 6 -nan 1.00 1.00 1.00 #%:SM_COUNTS: Tot HalfwordCsr FullwordCsr HalfwordCoo FullwordCoo -%:SM_COUNTS:A.mtx S N 42 3 3 6 1 1 0 0 0 -%:SM_IDXOCCUPATIONRSBVSCOOANDCSR:A.mtx S N 42 3 3 6 28 48 36 -%:SM_IDXOCCUPATION:A.mtx S N 42 3 3 6 28 -%:SM_MEMTRAFFIC:A.mtx S N 42 3 3 6 276 -%:SM_MINMAXAVGNNZ:A.mtx S N 42 3 3 6 6 6 6 +%:SM_COUNTS:A.mtx S N 20 3 3 6 1 1 0 0 0 +%:SM_IDXOCCUPATIONRSBVSCOOANDCSR:A.mtx S N 20 3 3 6 28 48 36 +%:SM_IDXOCCUPATION:A.mtx S N 20 3 3 6 28 +%:SM_MEMTRAFFIC:A.mtx S N 20 3 3 6 276 +%:SM_MINMAXAVGNNZ:A.mtx S N 20 3 3 6 6 6 6 # -%operation:matrix CONSTRUCTOR[42] SPMV[42] SPMV[42] -%operation:A.mtx 0.00444818 1e+09 1e+09 -%constructor:matrix SORT[42] SCAN[42] SHUFFLE[42] INSERT[42] -%constructor:A.mtx 0 0.00438404 0 2.90871e-05 +%operation:matrix CONSTRUCTOR[20] SPMV[20] SPMV[20] +%operation:A.mtx 0.167812 1e+09 1e+09 +%constructor:matrix SORT[20] SCAN[20] SHUFFLE[20] INSERT[20] +%constructor:A.mtx 0 0.0717778 0 0.0399961 # symmetric matrix --- skipping transposed benchmarking -# so far, program took 6.993s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.596s/0.000s . +# so far, program took 22.084s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 12.507s/0.000s . getrusage() stats: -ru_maxrss: 26 (maximum resident set size -- MB) -ru_stime : 0.3034s (system CPU time used) -ru_utime : 37.44s (user CPU time used) +ru_maxrss: 7 (maximum resident set size -- MB) +ru_stime : 0.1017s (system CPU time used) +ru_utime : 100.8s (user CPU time used) # benchmarking terminated --- finalizing run. # ====== BEGIN Total summary record. #pr: ======== Limiting to type D: #pr: 2 samples (out of 8) matched the dump limiting criteria. #pr: Dump from a base of 8 samples (of max 16) ordered by (1,1,1,1,2,4,2) = (filename x cores x incX x incY x nrhs x typecode x transA). pr: BESTCODE MTX NR NC NNZ NRHS TYPE SYM TRANS NT AT-NT AT-MKL-NT BPNZ AT-BPNZ NSUBM AT-SUBM RSBBEST-MFLOPS OPTIME MKL-OPTIME AT-OPTIME AT-MKL-OPTIME AT-TIME RWminBW-GBps CB-bpf AT-MS CMFLOPS -pr: 1:R_R A 3 3 6 1 D S N 42 42 0 4.0000 4.6667 3 1 703.69 3.746e-03 0.000e+00 3.411e-08 0.000e+00 3.406e-02 4.34e+00 5.17e+00 1 2.40e-05 -pr: 9:R_R A 3 3 6 4 D S N 42 42 0 4.0000 4.6667 3 1 2814.77 3.731e-03 0.000e+00 3.411e-08 0.000e+00 3.563e-02 1.07e+01 2.79e+00 1 9.60e-05 +pr: 1:R_R A 3 3 6 1 D S N 20 20 0 4.0000 4.6667 3 1 25.17 2.001e-02 0.000e+00 9.537e-07 0.000e+00 3.479e-01 1.55e-01 5.17e+00 1 2.40e-05 +pr: 9:R_R A 3 3 6 4 D S N 20 20 0 4.0000 4.6667 3 1 100.66 2.664e-02 0.000e+00 9.537e-07 0.000e+00 2.678e-01 3.82e-01 2.79e+00 1 9.60e-05 #pr: 2 samples (out of 8) matched the dump limiting criteria. #pr: below, we define 'successful' autotuning when speedup of 1.010000x is exceeded, and 'tuned' results even the ones which are same as untuned #pr: rsb autotuning was successful in 2 cases (100.00 %) and unsuccessful in 0 cases (0.00 %) -#pr: (in succ. cases rsb autotuning gave avg. 10961451.9 % faster, avg. sp. ratio 109615.519x, max sp. ratio 109835.722x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 1021656.8/998594.9/1044718.6/2043313.5 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 9.3/ 9.1/ 9.5/ 18.6 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 9.3, min. 9.1, max. 9.6 ops) +#pr: (in succ. cases rsb autotuning gave avg. 2445450.0 % faster, avg. sp. ratio 24455.500x, max sp. ratio 27931.000x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 322852.5/280855.0/364850.0/645705.0 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 13.7/ 10.1/ 17.4/ 27.4 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 13.7, min. 10.1, max. 17.4 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 16/ 16/ 16) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 48/ 48/ 48) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 5.747/ 3.636/ 7.858,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 15.012/ 4.339/ 10.673,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 0.206/ 0.130/ 0.281,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 0.537/ 0.155/ 0.382,GBps) #pr: (avg/min/max code balance (bytes read at least once per flop) 3.979/ 2.792/ 5.167) #pr: (avg/min/max (avg) bytes per nnz after successful tuning were 4.667/ 4.667/ 4.667) #pr: (matrix has been subdivided more/less/same in resp. 0 / 2 /0 cases) #pr: (matrix has used more/less/same threads in resp. 0 / 0 /2 cases) #pr: no unsuccessful rsb autotuning attempt (according to 1.01x threshold) -#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.03 s, min 0.03 s, max 0.04 s, tot 0.07 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.03 s, min 0.03 s, max 0.04 s, tot 0.07 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 1.759e+03, min 7.037e+02, max 2.815e+03 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 1.607e-02, min 6.407e-03, max 2.573e-02 (2 samples) -#pr: best tun. rsb operation time was: on avg. 3.411e-08s, min 3.411e-08s, max 3.411e-08s, tot 6.821e-08s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 3.739e-03s, min 3.731e-03s, max 3.746e-03s, tot 7.477e-03s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 2.722e+00 5.883e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 4.090e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.31 s, min 0.27 s, max 0.35 s, tot 0.62 s (2 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.31 s, min 0.27 s, max 0.35 s, tot 0.62 s (2 samples) +#pr: best tun. rsb canon. mflops were: on avg. 6.291e+01, min 2.517e+01, max 1.007e+02 (2 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 2.402e-03, min 1.200e-03, max 3.604e-03 (2 samples) +#pr: best tun. rsb operation time was: on avg. 9.537e-07s, min 9.537e-07s, max 9.537e-07s, tot 1.907e-06s (2 samples) +#pr: ref. unt. rsb operation time was: on avg. 2.332e-02s, min 2.001e-02s, max 2.664e-02s, tot 4.665e-02s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.136e+01 2.455e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.220e+00 #pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 4.000e+00 x, min 4.000e+00 x, max 4.000e+00 x (1 samples, the non-min-nrhs ones) #pr: ======== Limiting to type S: #pr: 2 samples (out of 8) matched the dump limiting criteria. #pr: Dump from a base of 8 samples (of max 16) ordered by (1,1,1,1,2,4,2) = (filename x cores x incX x incY x nrhs x typecode x transA). pr: BESTCODE MTX NR NC NNZ NRHS TYPE SYM TRANS NT AT-NT AT-MKL-NT BPNZ AT-BPNZ NSUBM AT-SUBM RSBBEST-MFLOPS OPTIME MKL-OPTIME AT-OPTIME AT-MKL-OPTIME AT-TIME RWminBW-GBps CB-bpf AT-MS CMFLOPS -pr: 3:R_R A 3 3 6 1 S S N 42 42 0 4.0000 4.6667 3 1 703.69 3.769e-03 0.000e+00 3.411e-08 0.000e+00 3.415e-02 2.58e+00 3.17e+00 1 2.40e-05 -pr: 11:R_R A 3 3 6 4 S S N 42 42 0 4.0000 4.6667 3 1 2814.77 2.098e-05 0.000e+00 3.411e-08 0.000e+00 2.899e-04 5.75e+00 1.54e+00 1 9.60e-05 +pr: 3:R_R A 3 3 6 1 S S N 20 20 0 4.0000 4.6667 3 1 25.17 1.619e-02 0.000e+00 9.537e-07 0.000e+00 2.400e-01 9.23e-02 3.17e+00 1 2.40e-05 +pr: 11:R_R A 3 3 6 4 S S N 20 20 0 4.0000 4.6667 3 1 201.26 2.009e-02 0.000e+00 4.770e-07 0.000e+00 2.444e-01 4.11e-01 1.54e+00 1 9.60e-05 #pr: 2 samples (out of 8) matched the dump limiting criteria. #pr: below, we define 'successful' autotuning when speedup of 1.010000x is exceeded, and 'tuned' results even the ones which are same as untuned #pr: rsb autotuning was successful in 2 cases (100.00 %) and unsuccessful in 0 cases (0.00 %) -#pr: (in succ. cases rsb autotuning gave avg. 5555999.3 % faster, avg. sp. ratio 55560.993x, max sp. ratio 110506.816x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 504942.3/8500.5/1001384.1/1009884.7 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 11.4/ 9.1/ 13.8/ 22.9 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 11.5, min. 9.1, max. 13.8 ops) +#pr: (in succ. cases rsb autotuning gave avg. 2954777.9 % faster, avg. sp. ratio 29548.779x, max sp. ratio 42126.309x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 382032.6/251666.8/512398.5/764065.2 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 13.5/ 12.2/ 14.8/ 27.0 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 13.5, min. 12.2, max. 14.8 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 8/ 8/ 8) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 24/ 24/ 24) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 3.284/ 2.228/ 4.339,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 8.327/ 2.580/ 5.747,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 0.195/ 0.080/ 0.310,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 0.503/ 0.092/ 0.411,GBps) #pr: (avg/min/max code balance (bytes read at least once per flop) 2.354/ 1.542/ 3.167) #pr: (avg/min/max (avg) bytes per nnz after successful tuning were 4.667/ 4.667/ 4.667) #pr: (matrix has been subdivided more/less/same in resp. 0 / 2 /0 cases) #pr: (matrix has used more/less/same threads in resp. 0 / 0 /2 cases) #pr: no unsuccessful rsb autotuning attempt (according to 1.01x threshold) -#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.02 s, min 0.00 s, max 0.03 s, tot 0.03 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.02 s, min 0.00 s, max 0.03 s, tot 0.03 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 1.759e+03, min 7.037e+02, max 2.815e+03 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 2.291e+00, min 6.368e-03, max 4.576e+00 (2 samples) -#pr: best tun. rsb operation time was: on avg. 3.411e-08s, min 3.411e-08s, max 3.411e-08s, tot 6.821e-08s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 1.895e-03s, min 2.098e-05s, max 3.769e-03s, tot 3.790e-03s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 4.929e+00 9.599e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 4.090e+00 -#pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 4.000e+00 x, min 4.000e+00 x, max 4.000e+00 x (1 samples, the non-min-nrhs ones) +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.24 s, min 0.24 s, max 0.24 s, tot 0.48 s (2 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.24 s, min 0.24 s, max 0.24 s, tot 0.48 s (2 samples) +#pr: best tun. rsb canon. mflops were: on avg. 1.132e+02, min 2.517e+01, max 2.013e+02 (2 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 3.130e-03, min 1.483e-03, max 4.778e-03 (2 samples) +#pr: best tun. rsb operation time was: on avg. 7.153e-07s, min 4.770e-07s, max 9.537e-07s, tot 1.431e-06s (2 samples) +#pr: ref. unt. rsb operation time was: on avg. 1.814e-02s, min 1.619e-02s, max 2.009e-02s, tot 3.628e-02s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.029e+01 4.006e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.220e+00 +#pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 7.997e+00 x, min 7.997e+00 x, max 7.997e+00 x (1 samples, the non-min-nrhs ones) #pr: ======== Limiting to type C: #pr: 2 samples (out of 8) matched the dump limiting criteria. #pr: Dump from a base of 8 samples (of max 16) ordered by (1,1,1,1,2,4,2) = (filename x cores x incX x incY x nrhs x typecode x transA). pr: BESTCODE MTX NR NC NNZ NRHS TYPE SYM TRANS NT AT-NT AT-MKL-NT BPNZ AT-BPNZ NSUBM AT-SUBM RSBBEST-MFLOPS OPTIME MKL-OPTIME AT-OPTIME AT-MKL-OPTIME AT-TIME RWminBW-GBps CB-bpf AT-MS CMFLOPS -pr: 5:R_R A 3 3 6 1 C S N 42 42 0 4.0000 4.6667 3 1 2814.77 1.812e-05 0.000e+00 3.411e-08 0.000e+00 2.592e-04 4.34e+00 1.29e+00 1 9.60e-05 -pr: 13:R_R A 3 3 6 4 C S N 42 42 0 4.0000 4.6667 3 1 402.65 2.098e-05 0.000e+00 9.537e-07 0.000e+00 2.301e-04 3.82e-01 6.98e-01 1 3.84e-04 +pr: 5:R_R A 3 3 6 1 C S N 20 20 0 4.0000 4.6667 3 1 100.66 1.603e-02 0.000e+00 9.537e-07 0.000e+00 2.201e-01 1.55e-01 1.29e+00 1 9.60e-05 +pr: 13:R_R A 3 3 6 4 C S N 20 20 0 4.0000 4.6667 3 1 402.65 1.599e-02 0.000e+00 9.537e-07 0.000e+00 3.000e-01 3.82e-01 6.98e-01 1 3.84e-04 #pr: 2 samples (out of 8) matched the dump limiting criteria. #pr: below, we define 'successful' autotuning when speedup of 1.010000x is exceeded, and 'tuned' results even the ones which are same as untuned #pr: rsb autotuning was successful in 2 cases (100.00 %) and unsuccessful in 0 cases (0.00 %) -#pr: (in succ. cases rsb autotuning gave avg. 27564.1 % faster, avg. sp. ratio 276.641x, max sp. ratio 531.283x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 3920.0/241.2/7598.7/7840.0 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 12.6/ 11.0/ 14.3/ 25.3 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 12.9, min. 11.5, max. 14.3 ops) +#pr: (in succ. cases rsb autotuning gave avg. 1678612.5 % faster, avg. sp. ratio 16787.125x, max sp. ratio 16808.500x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 272670.1/230796.8/314543.5/545340.2 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 16.2/ 13.7/ 18.8/ 32.5 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 16.2, min. 13.7, max. 18.8 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 16/ 16/ 16) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 48/ 48/ 48) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 1.958/ 0.281/ 3.636,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 4.721/ 0.382/ 4.339,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 0.206/ 0.130/ 0.281,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 0.537/ 0.155/ 0.382,GBps) #pr: (avg/min/max code balance (bytes read at least once per flop) 0.995/ 0.698/ 1.292) #pr: (avg/min/max (avg) bytes per nnz after successful tuning were 4.667/ 4.667/ 4.667) #pr: (matrix has been subdivided more/less/same in resp. 0 / 2 /0 cases) #pr: (matrix has used more/less/same threads in resp. 0 / 0 /2 cases) #pr: no unsuccessful rsb autotuning attempt (according to 1.01x threshold) -#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.00 s, min 0.00 s, max 0.00 s, tot 0.00 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.00 s, min 0.00 s, max 0.00 s, tot 0.00 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 1.609e+03, min 4.027e+02, max 2.815e+03 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 1.180e+01, min 5.298e+00, max 1.830e+01 (2 samples) -#pr: best tun. rsb operation time was: on avg. 4.939e-07s, min 3.411e-08s, max 9.537e-07s, tot 9.878e-07s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 1.955e-05s, min 1.812e-05s, max 2.098e-05s, tot 3.910e-05s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 5.883e+00 7.612e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 4.090e+00 -#pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 1.431e-01 x, min 1.431e-01 x, max 1.431e-01 x (1 samples, the non-min-nrhs ones) +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.26 s, min 0.22 s, max 0.30 s, tot 0.52 s (2 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.26 s, min 0.22 s, max 0.30 s, tot 0.52 s (2 samples) +#pr: best tun. rsb canon. mflops were: on avg. 2.517e+02, min 1.007e+02, max 4.027e+02 (2 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 1.500e-02, min 5.989e-03, max 2.402e-02 (2 samples) +#pr: best tun. rsb operation time was: on avg. 9.537e-07s, min 9.537e-07s, max 9.537e-07s, tot 1.907e-06s (2 samples) +#pr: ref. unt. rsb operation time was: on avg. 1.601e-02s, min 1.599e-02s, max 1.603e-02s, tot 3.202e-02s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.136e+01 2.455e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.220e+00 +#pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 4.000e+00 x, min 4.000e+00 x, max 4.000e+00 x (1 samples, the non-min-nrhs ones) #pr: ======== Limiting to type Z: #pr: 2 samples (out of 8) matched the dump limiting criteria. #pr: Dump from a base of 8 samples (of max 16) ordered by (1,1,1,1,2,4,2) = (filename x cores x incX x incY x nrhs x typecode x transA). pr: BESTCODE MTX NR NC NNZ NRHS TYPE SYM TRANS NT AT-NT AT-MKL-NT BPNZ AT-BPNZ NSUBM AT-SUBM RSBBEST-MFLOPS OPTIME MKL-OPTIME AT-OPTIME AT-MKL-OPTIME AT-TIME RWminBW-GBps CB-bpf AT-MS CMFLOPS -pr: 7:R_R A 3 3 6 1 Z S N 42 42 0 4.0000 4.6667 3 1 2814.77 2.003e-05 0.000e+00 3.411e-08 0.000e+00 2.291e-04 7.86e+00 2.29e+00 1 9.60e-05 -pr: 15:R_R A 3 3 6 4 Z S N 42 42 0 4.0000 4.6667 3 1 11259.09 2.098e-05 0.000e+00 3.411e-08 0.000e+00 4.189e-04 2.05e+01 1.32e+00 1 3.84e-04 +pr: 7:R_R A 3 3 6 1 Z S N 20 20 0 4.0000 4.6667 3 1 100.66 1.598e-02 0.000e+00 9.537e-07 0.000e+00 2.120e-01 2.81e-01 2.29e+00 1 9.60e-05 +pr: 15:R_R A 3 3 6 4 Z S N 20 20 0 4.0000 4.6667 3 1 402.65 2.398e-02 0.000e+00 9.537e-07 0.000e+00 2.282e-01 7.34e-01 1.32e+00 1 3.84e-04 #pr: 2 samples (out of 8) matched the dump limiting criteria. #pr: below, we define 'successful' autotuning when speedup of 1.010000x is exceeded, and 'tuned' results even the ones which are same as untuned #pr: rsb autotuning was successful in 2 cases (100.00 %) and unsuccessful in 0 cases (0.00 %) -#pr: (in succ. cases rsb autotuning gave avg. 60018.8 % faster, avg. sp. ratio 601.188x, max sp. ratio 615.170x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 9500.2/6717.9/12282.4/19000.3 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 15.7/ 11.4/ 20.0/ 31.4 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 15.7, min. 11.5, max. 20.0 ops) +#pr: (in succ. cases rsb autotuning gave avg. 2095000.0 % faster, avg. sp. ratio 20951.000x, max sp. ratio 25145.750x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 230819.4/222302.2/239336.5/461638.8 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 11.4/ 9.5/ 13.3/ 22.8 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 11.4, min. 9.5, max. 13.3 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 32/ 32/ 32) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 96/ 96/ 96) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 10.673/ 6.451/ 14.895,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 28.382/ 7.858/ 20.524,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 0.382/ 0.231/ 0.533,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 1.015/ 0.281/ 0.734,GBps) #pr: (avg/min/max code balance (bytes read at least once per flop) 1.807/ 1.323/ 2.292) #pr: (avg/min/max (avg) bytes per nnz after successful tuning were 4.667/ 4.667/ 4.667) #pr: (matrix has been subdivided more/less/same in resp. 0 / 2 /0 cases) #pr: (matrix has used more/less/same threads in resp. 0 / 0 /2 cases) #pr: no unsuccessful rsb autotuning attempt (according to 1.01x threshold) -#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.00 s, min 0.00 s, max 0.00 s, tot 0.00 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.00 s, min 0.00 s, max 0.00 s, tot 0.00 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 7.037e+03, min 2.815e+03, max 1.126e+04 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 1.155e+01, min 4.793e+00, max 1.830e+01 (2 samples) -#pr: best tun. rsb operation time was: on avg. 3.411e-08s, min 3.411e-08s, max 3.411e-08s, tot 6.821e-08s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 2.050e-05s, min 2.003e-05s, max 2.098e-05s, tot 4.101e-05s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.436e+00 3.316e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 4.090e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.22 s, min 0.21 s, max 0.23 s, tot 0.44 s (2 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.22 s, min 0.21 s, max 0.23 s, tot 0.44 s (2 samples) +#pr: best tun. rsb canon. mflops were: on avg. 2.517e+02, min 1.007e+02, max 4.027e+02 (2 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 1.101e-02, min 6.008e-03, max 1.601e-02 (2 samples) +#pr: best tun. rsb operation time was: on avg. 9.537e-07s, min 9.537e-07s, max 9.537e-07s, tot 1.907e-06s (2 samples) +#pr: ref. unt. rsb operation time was: on avg. 1.998e-02s, min 1.598e-02s, max 2.398e-02s, tot 3.996e-02s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 5.993e+00 1.384e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.220e+00 #pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 4.000e+00 x, min 4.000e+00 x, max 4.000e+00 x (1 samples, the non-min-nrhs ones) #pr: ======== Limiting to nrhs=1: #pr: 4 samples (out of 8) matched the dump limiting criteria. #pr: Dump from a base of 8 samples (of max 16) ordered by (1,1,1,1,2,4,2) = (filename x cores x incX x incY x nrhs x typecode x transA). pr: BESTCODE MTX NR NC NNZ NRHS TYPE SYM TRANS NT AT-NT AT-MKL-NT BPNZ AT-BPNZ NSUBM AT-SUBM RSBBEST-MFLOPS OPTIME MKL-OPTIME AT-OPTIME AT-MKL-OPTIME AT-TIME RWminBW-GBps CB-bpf AT-MS CMFLOPS -pr: 1:R_R A 3 3 6 1 D S N 42 42 0 4.0000 4.6667 3 1 703.69 3.746e-03 0.000e+00 3.411e-08 0.000e+00 3.406e-02 4.34e+00 5.17e+00 1 2.40e-05 -pr: 3:R_R A 3 3 6 1 S S N 42 42 0 4.0000 4.6667 3 1 703.69 3.769e-03 0.000e+00 3.411e-08 0.000e+00 3.415e-02 2.58e+00 3.17e+00 1 2.40e-05 -pr: 5:R_R A 3 3 6 1 C S N 42 42 0 4.0000 4.6667 3 1 2814.77 1.812e-05 0.000e+00 3.411e-08 0.000e+00 2.592e-04 4.34e+00 1.29e+00 1 9.60e-05 -pr: 7:R_R A 3 3 6 1 Z S N 42 42 0 4.0000 4.6667 3 1 2814.77 2.003e-05 0.000e+00 3.411e-08 0.000e+00 2.291e-04 7.86e+00 2.29e+00 1 9.60e-05 +pr: 1:R_R A 3 3 6 1 D S N 20 20 0 4.0000 4.6667 3 1 25.17 2.001e-02 0.000e+00 9.537e-07 0.000e+00 3.479e-01 1.55e-01 5.17e+00 1 2.40e-05 +pr: 3:R_R A 3 3 6 1 S S N 20 20 0 4.0000 4.6667 3 1 25.17 1.619e-02 0.000e+00 9.537e-07 0.000e+00 2.400e-01 9.23e-02 3.17e+00 1 2.40e-05 +pr: 5:R_R A 3 3 6 1 C S N 20 20 0 4.0000 4.6667 3 1 100.66 1.603e-02 0.000e+00 9.537e-07 0.000e+00 2.201e-01 1.55e-01 1.29e+00 1 9.60e-05 +pr: 7:R_R A 3 3 6 1 Z S N 20 20 0 4.0000 4.6667 3 1 100.66 1.598e-02 0.000e+00 9.537e-07 0.000e+00 2.120e-01 2.81e-01 2.29e+00 1 9.60e-05 #pr: 4 samples (out of 8) matched the dump limiting criteria. #pr: below, we define 'successful' autotuning when speedup of 1.010000x is exceeded, and 'tuned' results even the ones which are same as untuned #pr: rsb autotuning was successful in 4 cases (100.00 %) and unsuccessful in 0 cases (0.00 %) -#pr: (in succ. cases rsb autotuning gave avg. 5536425.7 % faster, avg. sp. ratio 55365.257x, max sp. ratio 110506.816x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 503573.9/6717.9/1001384.1/2014295.7 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 11.0/ 9.1/ 14.3/ 43.9 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 11.0, min. 9.1, max. 14.3 ops) +#pr: (in succ. cases rsb autotuning gave avg. 1787800.0 % faster, avg. sp. ratio 17879.000x, max sp. ratio 20980.000x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 267403.9/222302.2/364850.0/1069615.8 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 14.8/ 13.3/ 17.4/ 59.2 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 14.8, min. 13.3, max. 17.4 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 18/ 8/ 32) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 54/ 24/ 96) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 3.988/ 2.228/ 6.451,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 19.117/ 2.580/ 7.858,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 0.143/ 0.080/ 0.231,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 0.684/ 0.092/ 0.281,GBps) #pr: (avg/min/max code balance (bytes read at least once per flop) 2.979/ 1.292/ 5.167) #pr: (avg/min/max (avg) bytes per nnz after successful tuning were 4.667/ 4.667/ 4.667) #pr: (matrix has been subdivided more/less/same in resp. 0 / 4 /0 cases) #pr: (matrix has used more/less/same threads in resp. 0 / 0 /4 cases) #pr: no unsuccessful rsb autotuning attempt (according to 1.01x threshold) -#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.02 s, min 0.00 s, max 0.03 s, tot 0.07 s (4 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.02 s, min 0.00 s, max 0.03 s, tot 0.07 s (4 samples) -#pr: best tun. rsb canon. mflops were: on avg. 1.759e+03, min 7.037e+02, max 2.815e+03 (4 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 2.526e+00, min 6.368e-03, max 5.298e+00 (4 samples) -#pr: best tun. rsb operation time was: on avg. 3.411e-08s, min 3.411e-08s, max 3.411e-08s, tot 1.364e-07s (4 samples) -#pr: ref. unt. rsb operation time was: on avg. 1.888e-03s, min 1.812e-05s, max 3.769e-03s, tot 7.553e-03s (4 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 3.316e+00 9.599e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 4.090e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.26 s, min 0.21 s, max 0.35 s, tot 1.02 s (4 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.26 s, min 0.21 s, max 0.35 s, tot 1.02 s (4 samples) +#pr: best tun. rsb canon. mflops were: on avg. 6.291e+01, min 2.517e+01, max 1.007e+02 (4 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 3.670e-03, min 1.200e-03, max 6.008e-03 (4 samples) +#pr: best tun. rsb operation time was: on avg. 9.537e-07s, min 9.537e-07s, max 9.537e-07s, tot 3.815e-06s (4 samples) +#pr: ref. unt. rsb operation time was: on avg. 1.705e-02s, min 1.598e-02s, max 2.001e-02s, tot 6.820e-02s (4 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.384e+01 4.006e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.220e+00 #pr: ======== Limiting to nrhs=4: #pr: 4 samples (out of 8) matched the dump limiting criteria. #pr: Dump from a base of 8 samples (of max 16) ordered by (1,1,1,1,2,4,2) = (filename x cores x incX x incY x nrhs x typecode x transA). pr: BESTCODE MTX NR NC NNZ NRHS TYPE SYM TRANS NT AT-NT AT-MKL-NT BPNZ AT-BPNZ NSUBM AT-SUBM RSBBEST-MFLOPS OPTIME MKL-OPTIME AT-OPTIME AT-MKL-OPTIME AT-TIME RWminBW-GBps CB-bpf AT-MS CMFLOPS -pr: 9:R_R A 3 3 6 4 D S N 42 42 0 4.0000 4.6667 3 1 2814.77 3.731e-03 0.000e+00 3.411e-08 0.000e+00 3.563e-02 1.07e+01 2.79e+00 1 9.60e-05 -pr: 11:R_R A 3 3 6 4 S S N 42 42 0 4.0000 4.6667 3 1 2814.77 2.098e-05 0.000e+00 3.411e-08 0.000e+00 2.899e-04 5.75e+00 1.54e+00 1 9.60e-05 -pr: 13:R_R A 3 3 6 4 C S N 42 42 0 4.0000 4.6667 3 1 402.65 2.098e-05 0.000e+00 9.537e-07 0.000e+00 2.301e-04 3.82e-01 6.98e-01 1 3.84e-04 -pr: 15:R_R A 3 3 6 4 Z S N 42 42 0 4.0000 4.6667 3 1 11259.09 2.098e-05 0.000e+00 3.411e-08 0.000e+00 4.189e-04 2.05e+01 1.32e+00 1 3.84e-04 +pr: 9:R_R A 3 3 6 4 D S N 20 20 0 4.0000 4.6667 3 1 100.66 2.664e-02 0.000e+00 9.537e-07 0.000e+00 2.678e-01 3.82e-01 2.79e+00 1 9.60e-05 +pr: 11:R_R A 3 3 6 4 S S N 20 20 0 4.0000 4.6667 3 1 201.26 2.009e-02 0.000e+00 4.770e-07 0.000e+00 2.444e-01 4.11e-01 1.54e+00 1 9.60e-05 +pr: 13:R_R A 3 3 6 4 C S N 20 20 0 4.0000 4.6667 3 1 402.65 1.599e-02 0.000e+00 9.537e-07 0.000e+00 3.000e-01 3.82e-01 6.98e-01 1 3.84e-04 +pr: 15:R_R A 3 3 6 4 Z S N 20 20 0 4.0000 4.6667 3 1 402.65 2.398e-02 0.000e+00 9.537e-07 0.000e+00 2.282e-01 7.34e-01 1.32e+00 1 3.84e-04 #pr: 4 samples (out of 8) matched the dump limiting criteria. #pr: below, we define 'successful' autotuning when speedup of 1.010000x is exceeded, and 'tuned' results even the ones which are same as untuned #pr: rsb autotuning was successful in 4 cases (100.00 %) and unsuccessful in 0 cases (0.00 %) -#pr: (in succ. cases rsb autotuning gave avg. 2766091.4 % faster, avg. sp. ratio 27661.914x, max sp. ratio 109395.316x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 266435.7/241.2/1044718.6/1065742.8 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 13.6/ 9.5/ 20.0/ 54.3 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 13.7, min. 9.6, max. 20.0 ops) +#pr: (in succ. cases rsb autotuning gave avg. 2799120.2 % faster, avg. sp. ratio 27992.202x, max sp. ratio 42126.309x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 336783.4/239336.5/512398.5/1347133.5 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 12.6/ 9.5/ 18.8/ 50.5 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 12.6, min. 9.5, max. 18.8 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 18/ 8/ 32) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 54/ 24/ 96) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 6.843/ 0.281/ 14.895,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 37.326/ 0.382/ 20.524,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 0.351/ 0.281/ 0.533,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 1.908/ 0.382/ 0.734,GBps) #pr: (avg/min/max code balance (bytes read at least once per flop) 1.589/ 0.698/ 2.792) #pr: (avg/min/max (avg) bytes per nnz after successful tuning were 4.667/ 4.667/ 4.667) #pr: (matrix has been subdivided more/less/same in resp. 0 / 4 /0 cases) #pr: (matrix has used more/less/same threads in resp. 0 / 0 /4 cases) #pr: no unsuccessful rsb autotuning attempt (according to 1.01x threshold) -#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.01 s, min 0.00 s, max 0.04 s, tot 0.04 s (4 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.01 s, min 0.00 s, max 0.04 s, tot 0.04 s (4 samples) -#pr: best tun. rsb canon. mflops were: on avg. 4.323e+03, min 4.027e+02, max 1.126e+04 (4 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 1.030e+01, min 2.573e-02, max 1.830e+01 (4 samples) -#pr: best tun. rsb operation time was: on avg. 2.640e-07s, min 3.411e-08s, max 9.537e-07s, tot 1.056e-06s (4 samples) -#pr: ref. unt. rsb operation time was: on avg. 9.485e-04s, min 2.098e-05s, max 3.731e-03s, tot 3.794e-03s (4 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.436e+00 7.612e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 4.090e+00 -#pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 3.036e+00 x, min 1.431e-01 x, max 4.000e+00 x (4 samples, the non-min-nrhs ones) +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.26 s, min 0.23 s, max 0.30 s, tot 1.04 s (4 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.26 s, min 0.23 s, max 0.30 s, tot 1.04 s (4 samples) +#pr: best tun. rsb canon. mflops were: on avg. 2.768e+02, min 1.007e+02, max 4.027e+02 (4 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 1.210e-02, min 3.604e-03, max 2.402e-02 (4 samples) +#pr: best tun. rsb operation time was: on avg. 8.345e-07s, min 4.770e-07s, max 9.537e-07s, tot 3.338e-06s (4 samples) +#pr: ref. unt. rsb operation time was: on avg. 2.168e-02s, min 1.599e-02s, max 2.664e-02s, tot 8.670e-02s (4 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 5.993e+00 1.136e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.220e+00 +#pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 4.999e+00 x, min 4.000e+00 x, max 7.997e+00 x (4 samples, the non-min-nrhs ones) #pr: ======== Limiting to transA=N: #pr: Dump from a base of 8 samples (of max 16) ordered by (1,1,1,1,2,4,2) = (filename x cores x incX x incY x nrhs x typecode x transA). pr: BESTCODE MTX NR NC NNZ NRHS TYPE SYM TRANS NT AT-NT AT-MKL-NT BPNZ AT-BPNZ NSUBM AT-SUBM RSBBEST-MFLOPS OPTIME MKL-OPTIME AT-OPTIME AT-MKL-OPTIME AT-TIME RWminBW-GBps CB-bpf AT-MS CMFLOPS -pr: 1:R_R A 3 3 6 1 D S N 42 42 0 4.0000 4.6667 3 1 703.69 3.746e-03 0.000e+00 3.411e-08 0.000e+00 3.406e-02 4.34e+00 5.17e+00 1 2.40e-05 -pr: 3:R_R A 3 3 6 1 S S N 42 42 0 4.0000 4.6667 3 1 703.69 3.769e-03 0.000e+00 3.411e-08 0.000e+00 3.415e-02 2.58e+00 3.17e+00 1 2.40e-05 -pr: 5:R_R A 3 3 6 1 C S N 42 42 0 4.0000 4.6667 3 1 2814.77 1.812e-05 0.000e+00 3.411e-08 0.000e+00 2.592e-04 4.34e+00 1.29e+00 1 9.60e-05 -pr: 7:R_R A 3 3 6 1 Z S N 42 42 0 4.0000 4.6667 3 1 2814.77 2.003e-05 0.000e+00 3.411e-08 0.000e+00 2.291e-04 7.86e+00 2.29e+00 1 9.60e-05 -pr: 9:R_R A 3 3 6 4 D S N 42 42 0 4.0000 4.6667 3 1 2814.77 3.731e-03 0.000e+00 3.411e-08 0.000e+00 3.563e-02 1.07e+01 2.79e+00 1 9.60e-05 -pr: 11:R_R A 3 3 6 4 S S N 42 42 0 4.0000 4.6667 3 1 2814.77 2.098e-05 0.000e+00 3.411e-08 0.000e+00 2.899e-04 5.75e+00 1.54e+00 1 9.60e-05 -pr: 13:R_R A 3 3 6 4 C S N 42 42 0 4.0000 4.6667 3 1 402.65 2.098e-05 0.000e+00 9.537e-07 0.000e+00 2.301e-04 3.82e-01 6.98e-01 1 3.84e-04 -pr: 15:R_R A 3 3 6 4 Z S N 42 42 0 4.0000 4.6667 3 1 11259.09 2.098e-05 0.000e+00 3.411e-08 0.000e+00 4.189e-04 2.05e+01 1.32e+00 1 3.84e-04 +pr: 1:R_R A 3 3 6 1 D S N 20 20 0 4.0000 4.6667 3 1 25.17 2.001e-02 0.000e+00 9.537e-07 0.000e+00 3.479e-01 1.55e-01 5.17e+00 1 2.40e-05 +pr: 3:R_R A 3 3 6 1 S S N 20 20 0 4.0000 4.6667 3 1 25.17 1.619e-02 0.000e+00 9.537e-07 0.000e+00 2.400e-01 9.23e-02 3.17e+00 1 2.40e-05 +pr: 5:R_R A 3 3 6 1 C S N 20 20 0 4.0000 4.6667 3 1 100.66 1.603e-02 0.000e+00 9.537e-07 0.000e+00 2.201e-01 1.55e-01 1.29e+00 1 9.60e-05 +pr: 7:R_R A 3 3 6 1 Z S N 20 20 0 4.0000 4.6667 3 1 100.66 1.598e-02 0.000e+00 9.537e-07 0.000e+00 2.120e-01 2.81e-01 2.29e+00 1 9.60e-05 +pr: 9:R_R A 3 3 6 4 D S N 20 20 0 4.0000 4.6667 3 1 100.66 2.664e-02 0.000e+00 9.537e-07 0.000e+00 2.678e-01 3.82e-01 2.79e+00 1 9.60e-05 +pr: 11:R_R A 3 3 6 4 S S N 20 20 0 4.0000 4.6667 3 1 201.26 2.009e-02 0.000e+00 4.770e-07 0.000e+00 2.444e-01 4.11e-01 1.54e+00 1 9.60e-05 +pr: 13:R_R A 3 3 6 4 C S N 20 20 0 4.0000 4.6667 3 1 402.65 1.599e-02 0.000e+00 9.537e-07 0.000e+00 3.000e-01 3.82e-01 6.98e-01 1 3.84e-04 +pr: 15:R_R A 3 3 6 4 Z S N 20 20 0 4.0000 4.6667 3 1 402.65 2.398e-02 0.000e+00 9.537e-07 0.000e+00 2.282e-01 7.34e-01 1.32e+00 1 3.84e-04 #pr: below, we define 'successful' autotuning when speedup of 1.010000x is exceeded, and 'tuned' results even the ones which are same as untuned #pr: rsb autotuning was successful in 8 cases (100.00 %) and unsuccessful in 0 cases (0.00 %) -#pr: (in succ. cases rsb autotuning gave avg. 4151258.5 % faster, avg. sp. ratio 41513.585x, max sp. ratio 110506.816x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 385004.8/241.2/1044718.6/3080038.5 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 12.3/ 9.1/ 20.0/ 98.2 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 12.4, min. 9.1, max. 20.0 ops) +#pr: (in succ. cases rsb autotuning gave avg. 2293460.1 % faster, avg. sp. ratio 22935.601x, max sp. ratio 42126.309x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 302093.7/222302.2/512398.5/2416749.2 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 13.7/ 9.5/ 18.8/109.7 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 13.7, min. 9.5, max. 18.8 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 18/ 8/ 32) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 54/ 24/ 96) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 5.415/ 0.281/ 14.895,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 56.443/ 0.382/ 20.524,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 0.247/ 0.080/ 0.533,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 2.592/ 0.092/ 0.734,GBps) #pr: (avg/min/max code balance (bytes read at least once per flop) 2.284/ 0.698/ 5.167) #pr: (avg/min/max (avg) bytes per nnz after successful tuning were 4.667/ 4.667/ 4.667) #pr: (matrix has been subdivided more/less/same in resp. 0 / 8 /0 cases) #pr: (matrix has used more/less/same threads in resp. 0 / 0 /8 cases) #pr: no unsuccessful rsb autotuning attempt (according to 1.01x threshold) -#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.01 s, min 0.00 s, max 0.04 s, tot 0.11 s (8 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.01 s, min 0.00 s, max 0.04 s, tot 0.11 s (8 samples) -#pr: best tun. rsb canon. mflops were: on avg. 3.041e+03, min 4.027e+02, max 1.126e+04 (8 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 6.414e+00, min 6.368e-03, max 1.830e+01 (8 samples) -#pr: best tun. rsb operation time was: on avg. 1.491e-07s, min 3.411e-08s, max 9.537e-07s, tot 1.192e-06s (8 samples) -#pr: ref. unt. rsb operation time was: on avg. 1.418e-03s, min 1.812e-05s, max 3.769e-03s, tot 1.135e-02s (8 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.436e+00 7.612e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 4.090e+00 -#pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 3.036e+00 x, min 1.431e-01 x, max 4.000e+00 x (4 samples, the non-min-nrhs ones) +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.26 s, min 0.21 s, max 0.35 s, tot 2.06 s (8 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.26 s, min 0.21 s, max 0.35 s, tot 2.06 s (8 samples) +#pr: best tun. rsb canon. mflops were: on avg. 1.699e+02, min 2.517e+01, max 4.027e+02 (8 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 7.886e-03, min 1.200e-03, max 2.402e-02 (8 samples) +#pr: best tun. rsb operation time was: on avg. 8.941e-07s, min 4.770e-07s, max 9.537e-07s, tot 7.153e-06s (8 samples) +#pr: ref. unt. rsb operation time was: on avg. 1.936e-02s, min 1.598e-02s, max 2.664e-02s, tot 1.549e-01s (8 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 5.993e+00 4.006e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.220e+00 +#pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 4.999e+00 x, min 4.000e+00 x, max 7.997e+00 x (4 samples, the non-min-nrhs ones) #pr: ======== Limiting to both transA=N and nrhs=1: #pr: 4 samples (out of 8) matched the dump limiting criteria. #pr: Dump from a base of 8 samples (of max 16) ordered by (1,1,1,1,2,4,2) = (filename x cores x incX x incY x nrhs x typecode x transA). pr: BESTCODE MTX NR NC NNZ NRHS TYPE SYM TRANS NT AT-NT AT-MKL-NT BPNZ AT-BPNZ NSUBM AT-SUBM RSBBEST-MFLOPS OPTIME MKL-OPTIME AT-OPTIME AT-MKL-OPTIME AT-TIME RWminBW-GBps CB-bpf AT-MS CMFLOPS -pr: 1:R_R A 3 3 6 1 D S N 42 42 0 4.0000 4.6667 3 1 703.69 3.746e-03 0.000e+00 3.411e-08 0.000e+00 3.406e-02 4.34e+00 5.17e+00 1 2.40e-05 -pr: 3:R_R A 3 3 6 1 S S N 42 42 0 4.0000 4.6667 3 1 703.69 3.769e-03 0.000e+00 3.411e-08 0.000e+00 3.415e-02 2.58e+00 3.17e+00 1 2.40e-05 -pr: 5:R_R A 3 3 6 1 C S N 42 42 0 4.0000 4.6667 3 1 2814.77 1.812e-05 0.000e+00 3.411e-08 0.000e+00 2.592e-04 4.34e+00 1.29e+00 1 9.60e-05 -pr: 7:R_R A 3 3 6 1 Z S N 42 42 0 4.0000 4.6667 3 1 2814.77 2.003e-05 0.000e+00 3.411e-08 0.000e+00 2.291e-04 7.86e+00 2.29e+00 1 9.60e-05 +pr: 1:R_R A 3 3 6 1 D S N 20 20 0 4.0000 4.6667 3 1 25.17 2.001e-02 0.000e+00 9.537e-07 0.000e+00 3.479e-01 1.55e-01 5.17e+00 1 2.40e-05 +pr: 3:R_R A 3 3 6 1 S S N 20 20 0 4.0000 4.6667 3 1 25.17 1.619e-02 0.000e+00 9.537e-07 0.000e+00 2.400e-01 9.23e-02 3.17e+00 1 2.40e-05 +pr: 5:R_R A 3 3 6 1 C S N 20 20 0 4.0000 4.6667 3 1 100.66 1.603e-02 0.000e+00 9.537e-07 0.000e+00 2.201e-01 1.55e-01 1.29e+00 1 9.60e-05 +pr: 7:R_R A 3 3 6 1 Z S N 20 20 0 4.0000 4.6667 3 1 100.66 1.598e-02 0.000e+00 9.537e-07 0.000e+00 2.120e-01 2.81e-01 2.29e+00 1 9.60e-05 #pr: 4 samples (out of 8) matched the dump limiting criteria. #pr: below, we define 'successful' autotuning when speedup of 1.010000x is exceeded, and 'tuned' results even the ones which are same as untuned #pr: rsb autotuning was successful in 4 cases (100.00 %) and unsuccessful in 0 cases (0.00 %) -#pr: (in succ. cases rsb autotuning gave avg. 5536425.7 % faster, avg. sp. ratio 55365.257x, max sp. ratio 110506.816x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 503573.9/6717.9/1001384.1/2014295.7 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 11.0/ 9.1/ 14.3/ 43.9 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 11.0, min. 9.1, max. 14.3 ops) +#pr: (in succ. cases rsb autotuning gave avg. 1787800.0 % faster, avg. sp. ratio 17879.000x, max sp. ratio 20980.000x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 267403.9/222302.2/364850.0/1069615.8 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 14.8/ 13.3/ 17.4/ 59.2 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 14.8, min. 13.3, max. 17.4 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 18/ 8/ 32) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 54/ 24/ 96) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 3.988/ 2.228/ 6.451,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 19.117/ 2.580/ 7.858,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 0.143/ 0.080/ 0.231,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 0.684/ 0.092/ 0.281,GBps) #pr: (avg/min/max code balance (bytes read at least once per flop) 2.979/ 1.292/ 5.167) #pr: (avg/min/max (avg) bytes per nnz after successful tuning were 4.667/ 4.667/ 4.667) #pr: (matrix has been subdivided more/less/same in resp. 0 / 4 /0 cases) #pr: (matrix has used more/less/same threads in resp. 0 / 0 /4 cases) #pr: no unsuccessful rsb autotuning attempt (according to 1.01x threshold) -#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.02 s, min 0.00 s, max 0.03 s, tot 0.07 s (4 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.02 s, min 0.00 s, max 0.03 s, tot 0.07 s (4 samples) -#pr: best tun. rsb canon. mflops were: on avg. 1.759e+03, min 7.037e+02, max 2.815e+03 (4 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 2.526e+00, min 6.368e-03, max 5.298e+00 (4 samples) -#pr: best tun. rsb operation time was: on avg. 3.411e-08s, min 3.411e-08s, max 3.411e-08s, tot 1.364e-07s (4 samples) -#pr: ref. unt. rsb operation time was: on avg. 1.888e-03s, min 1.812e-05s, max 3.769e-03s, tot 7.553e-03s (4 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 3.316e+00 9.599e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 4.090e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.26 s, min 0.21 s, max 0.35 s, tot 1.02 s (4 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.26 s, min 0.21 s, max 0.35 s, tot 1.02 s (4 samples) +#pr: best tun. rsb canon. mflops were: on avg. 6.291e+01, min 2.517e+01, max 1.007e+02 (4 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 3.670e-03, min 1.200e-03, max 6.008e-03 (4 samples) +#pr: best tun. rsb operation time was: on avg. 9.537e-07s, min 9.537e-07s, max 9.537e-07s, tot 3.815e-06s (4 samples) +#pr: ref. unt. rsb operation time was: on avg. 1.705e-02s, min 1.598e-02s, max 2.001e-02s, tot 6.820e-02s (4 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.384e+01 4.006e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.220e+00 #pr: ======== Limiting to both transA=N and nrhs=4: #pr: 4 samples (out of 8) matched the dump limiting criteria. #pr: Dump from a base of 8 samples (of max 16) ordered by (1,1,1,1,2,4,2) = (filename x cores x incX x incY x nrhs x typecode x transA). pr: BESTCODE MTX NR NC NNZ NRHS TYPE SYM TRANS NT AT-NT AT-MKL-NT BPNZ AT-BPNZ NSUBM AT-SUBM RSBBEST-MFLOPS OPTIME MKL-OPTIME AT-OPTIME AT-MKL-OPTIME AT-TIME RWminBW-GBps CB-bpf AT-MS CMFLOPS -pr: 9:R_R A 3 3 6 4 D S N 42 42 0 4.0000 4.6667 3 1 2814.77 3.731e-03 0.000e+00 3.411e-08 0.000e+00 3.563e-02 1.07e+01 2.79e+00 1 9.60e-05 -pr: 11:R_R A 3 3 6 4 S S N 42 42 0 4.0000 4.6667 3 1 2814.77 2.098e-05 0.000e+00 3.411e-08 0.000e+00 2.899e-04 5.75e+00 1.54e+00 1 9.60e-05 -pr: 13:R_R A 3 3 6 4 C S N 42 42 0 4.0000 4.6667 3 1 402.65 2.098e-05 0.000e+00 9.537e-07 0.000e+00 2.301e-04 3.82e-01 6.98e-01 1 3.84e-04 -pr: 15:R_R A 3 3 6 4 Z S N 42 42 0 4.0000 4.6667 3 1 11259.09 2.098e-05 0.000e+00 3.411e-08 0.000e+00 4.189e-04 2.05e+01 1.32e+00 1 3.84e-04 +pr: 9:R_R A 3 3 6 4 D S N 20 20 0 4.0000 4.6667 3 1 100.66 2.664e-02 0.000e+00 9.537e-07 0.000e+00 2.678e-01 3.82e-01 2.79e+00 1 9.60e-05 +pr: 11:R_R A 3 3 6 4 S S N 20 20 0 4.0000 4.6667 3 1 201.26 2.009e-02 0.000e+00 4.770e-07 0.000e+00 2.444e-01 4.11e-01 1.54e+00 1 9.60e-05 +pr: 13:R_R A 3 3 6 4 C S N 20 20 0 4.0000 4.6667 3 1 402.65 1.599e-02 0.000e+00 9.537e-07 0.000e+00 3.000e-01 3.82e-01 6.98e-01 1 3.84e-04 +pr: 15:R_R A 3 3 6 4 Z S N 20 20 0 4.0000 4.6667 3 1 402.65 2.398e-02 0.000e+00 9.537e-07 0.000e+00 2.282e-01 7.34e-01 1.32e+00 1 3.84e-04 #pr: 4 samples (out of 8) matched the dump limiting criteria. #pr: below, we define 'successful' autotuning when speedup of 1.010000x is exceeded, and 'tuned' results even the ones which are same as untuned #pr: rsb autotuning was successful in 4 cases (100.00 %) and unsuccessful in 0 cases (0.00 %) -#pr: (in succ. cases rsb autotuning gave avg. 2766091.4 % faster, avg. sp. ratio 27661.914x, max sp. ratio 109395.316x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 266435.7/241.2/1044718.6/1065742.8 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 13.6/ 9.5/ 20.0/ 54.3 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 13.7, min. 9.6, max. 20.0 ops) +#pr: (in succ. cases rsb autotuning gave avg. 2799120.2 % faster, avg. sp. ratio 27992.202x, max sp. ratio 42126.309x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 336783.4/239336.5/512398.5/1347133.5 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 12.6/ 9.5/ 18.8/ 50.5 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 12.6, min. 9.5, max. 18.8 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 18/ 8/ 32) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 54/ 24/ 96) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 6.843/ 0.281/ 14.895,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 37.326/ 0.382/ 20.524,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 0.351/ 0.281/ 0.533,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 1.908/ 0.382/ 0.734,GBps) #pr: (avg/min/max code balance (bytes read at least once per flop) 1.589/ 0.698/ 2.792) #pr: (avg/min/max (avg) bytes per nnz after successful tuning were 4.667/ 4.667/ 4.667) #pr: (matrix has been subdivided more/less/same in resp. 0 / 4 /0 cases) #pr: (matrix has used more/less/same threads in resp. 0 / 0 /4 cases) #pr: no unsuccessful rsb autotuning attempt (according to 1.01x threshold) -#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.01 s, min 0.00 s, max 0.04 s, tot 0.04 s (4 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.01 s, min 0.00 s, max 0.04 s, tot 0.04 s (4 samples) -#pr: best tun. rsb canon. mflops were: on avg. 4.323e+03, min 4.027e+02, max 1.126e+04 (4 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 1.030e+01, min 2.573e-02, max 1.830e+01 (4 samples) -#pr: best tun. rsb operation time was: on avg. 2.640e-07s, min 3.411e-08s, max 9.537e-07s, tot 1.056e-06s (4 samples) -#pr: ref. unt. rsb operation time was: on avg. 9.485e-04s, min 2.098e-05s, max 3.731e-03s, tot 3.794e-03s (4 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.436e+00 7.612e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 4.090e+00 -#pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 3.036e+00 x, min 1.431e-01 x, max 4.000e+00 x (4 samples, the non-min-nrhs ones) +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.26 s, min 0.23 s, max 0.30 s, tot 1.04 s (4 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.26 s, min 0.23 s, max 0.30 s, tot 1.04 s (4 samples) +#pr: best tun. rsb canon. mflops were: on avg. 2.768e+02, min 1.007e+02, max 4.027e+02 (4 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 1.210e-02, min 3.604e-03, max 2.402e-02 (4 samples) +#pr: best tun. rsb operation time was: on avg. 8.345e-07s, min 4.770e-07s, max 9.537e-07s, tot 3.338e-06s (4 samples) +#pr: ref. unt. rsb operation time was: on avg. 2.168e-02s, min 1.599e-02s, max 2.664e-02s, tot 8.670e-02s (4 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 5.993e+00 1.136e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.220e+00 +#pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 4.999e+00 x, min 4.000e+00 x, max 7.997e+00 x (4 samples, the non-min-nrhs ones) #pr: ======== Limiting to transA=T: #pr: No sample (out of 8) matched the dump criteria -- skipping dump round. #pr: ======== Limiting to both transA=T and nrhs=1: @@ -5042,49 +5053,49 @@ #pr: ======== All results (not limiting) #pr: Dump from a base of 8 samples (of max 16) ordered by (1,1,1,1,2,4,2) = (filename x cores x incX x incY x nrhs x typecode x transA). pr: BESTCODE MTX NR NC NNZ NRHS TYPE SYM TRANS NT AT-NT AT-MKL-NT BPNZ AT-BPNZ NSUBM AT-SUBM RSBBEST-MFLOPS OPTIME MKL-OPTIME AT-OPTIME AT-MKL-OPTIME AT-TIME RWminBW-GBps CB-bpf AT-MS CMFLOPS -pr: 1:R_R A 3 3 6 1 D S N 42 42 0 4.0000 4.6667 3 1 703.69 3.746e-03 0.000e+00 3.411e-08 0.000e+00 3.406e-02 4.34e+00 5.17e+00 1 2.40e-05 -pr: 3:R_R A 3 3 6 1 S S N 42 42 0 4.0000 4.6667 3 1 703.69 3.769e-03 0.000e+00 3.411e-08 0.000e+00 3.415e-02 2.58e+00 3.17e+00 1 2.40e-05 -pr: 5:R_R A 3 3 6 1 C S N 42 42 0 4.0000 4.6667 3 1 2814.77 1.812e-05 0.000e+00 3.411e-08 0.000e+00 2.592e-04 4.34e+00 1.29e+00 1 9.60e-05 -pr: 7:R_R A 3 3 6 1 Z S N 42 42 0 4.0000 4.6667 3 1 2814.77 2.003e-05 0.000e+00 3.411e-08 0.000e+00 2.291e-04 7.86e+00 2.29e+00 1 9.60e-05 -pr: 9:R_R A 3 3 6 4 D S N 42 42 0 4.0000 4.6667 3 1 2814.77 3.731e-03 0.000e+00 3.411e-08 0.000e+00 3.563e-02 1.07e+01 2.79e+00 1 9.60e-05 -pr: 11:R_R A 3 3 6 4 S S N 42 42 0 4.0000 4.6667 3 1 2814.77 2.098e-05 0.000e+00 3.411e-08 0.000e+00 2.899e-04 5.75e+00 1.54e+00 1 9.60e-05 -pr: 13:R_R A 3 3 6 4 C S N 42 42 0 4.0000 4.6667 3 1 402.65 2.098e-05 0.000e+00 9.537e-07 0.000e+00 2.301e-04 3.82e-01 6.98e-01 1 3.84e-04 -pr: 15:R_R A 3 3 6 4 Z S N 42 42 0 4.0000 4.6667 3 1 11259.09 2.098e-05 0.000e+00 3.411e-08 0.000e+00 4.189e-04 2.05e+01 1.32e+00 1 3.84e-04 +pr: 1:R_R A 3 3 6 1 D S N 20 20 0 4.0000 4.6667 3 1 25.17 2.001e-02 0.000e+00 9.537e-07 0.000e+00 3.479e-01 1.55e-01 5.17e+00 1 2.40e-05 +pr: 3:R_R A 3 3 6 1 S S N 20 20 0 4.0000 4.6667 3 1 25.17 1.619e-02 0.000e+00 9.537e-07 0.000e+00 2.400e-01 9.23e-02 3.17e+00 1 2.40e-05 +pr: 5:R_R A 3 3 6 1 C S N 20 20 0 4.0000 4.6667 3 1 100.66 1.603e-02 0.000e+00 9.537e-07 0.000e+00 2.201e-01 1.55e-01 1.29e+00 1 9.60e-05 +pr: 7:R_R A 3 3 6 1 Z S N 20 20 0 4.0000 4.6667 3 1 100.66 1.598e-02 0.000e+00 9.537e-07 0.000e+00 2.120e-01 2.81e-01 2.29e+00 1 9.60e-05 +pr: 9:R_R A 3 3 6 4 D S N 20 20 0 4.0000 4.6667 3 1 100.66 2.664e-02 0.000e+00 9.537e-07 0.000e+00 2.678e-01 3.82e-01 2.79e+00 1 9.60e-05 +pr: 11:R_R A 3 3 6 4 S S N 20 20 0 4.0000 4.6667 3 1 201.26 2.009e-02 0.000e+00 4.770e-07 0.000e+00 2.444e-01 4.11e-01 1.54e+00 1 9.60e-05 +pr: 13:R_R A 3 3 6 4 C S N 20 20 0 4.0000 4.6667 3 1 402.65 1.599e-02 0.000e+00 9.537e-07 0.000e+00 3.000e-01 3.82e-01 6.98e-01 1 3.84e-04 +pr: 15:R_R A 3 3 6 4 Z S N 20 20 0 4.0000 4.6667 3 1 402.65 2.398e-02 0.000e+00 9.537e-07 0.000e+00 2.282e-01 7.34e-01 1.32e+00 1 3.84e-04 #pr: below, we define 'successful' autotuning when speedup of 1.010000x is exceeded, and 'tuned' results even the ones which are same as untuned #pr: rsb autotuning was successful in 8 cases (100.00 %) and unsuccessful in 0 cases (0.00 %) -#pr: (in succ. cases rsb autotuning gave avg. 4151258.5 % faster, avg. sp. ratio 41513.585x, max sp. ratio 110506.816x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 385004.8/241.2/1044718.6/3080038.5 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 12.3/ 9.1/ 20.0/ 98.2 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 12.4, min. 9.1, max. 20.0 ops) +#pr: (in succ. cases rsb autotuning gave avg. 2293460.1 % faster, avg. sp. ratio 22935.601x, max sp. ratio 42126.309x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 302093.7/222302.2/512398.5/2416749.2 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 13.7/ 9.5/ 18.8/109.7 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 13.7, min. 9.5, max. 18.8 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 18/ 8/ 32) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 54/ 24/ 96) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 5.415/ 0.281/ 14.895,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 56.443/ 0.382/ 20.524,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 0.247/ 0.080/ 0.533,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 2.592/ 0.092/ 0.734,GBps) #pr: (avg/min/max code balance (bytes read at least once per flop) 2.284/ 0.698/ 5.167) #pr: (avg/min/max (avg) bytes per nnz after successful tuning were 4.667/ 4.667/ 4.667) #pr: (matrix has been subdivided more/less/same in resp. 0 / 8 /0 cases) #pr: (matrix has used more/less/same threads in resp. 0 / 0 /8 cases) #pr: no unsuccessful rsb autotuning attempt (according to 1.01x threshold) -#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.01 s, min 0.00 s, max 0.04 s, tot 0.11 s (8 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.01 s, min 0.00 s, max 0.04 s, tot 0.11 s (8 samples) -#pr: best tun. rsb canon. mflops were: on avg. 3.041e+03, min 4.027e+02, max 1.126e+04 (8 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 6.414e+00, min 6.368e-03, max 1.830e+01 (8 samples) -#pr: best tun. rsb operation time was: on avg. 1.491e-07s, min 3.411e-08s, max 9.537e-07s, tot 1.192e-06s (8 samples) -#pr: ref. unt. rsb operation time was: on avg. 1.418e-03s, min 1.812e-05s, max 3.769e-03s, tot 1.135e-02s (8 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.436e+00 7.612e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 4.090e+00 -#pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 3.036e+00 x, min 1.431e-01 x, max 4.000e+00 x (4 samples, the non-min-nrhs ones) -#pr: Record collection took 0.81 s. +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.26 s, min 0.21 s, max 0.35 s, tot 2.06 s (8 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.26 s, min 0.21 s, max 0.35 s, tot 2.06 s (8 samples) +#pr: best tun. rsb canon. mflops were: on avg. 1.699e+02, min 2.517e+01, max 4.027e+02 (8 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 7.886e-03, min 1.200e-03, max 2.402e-02 (8 samples) +#pr: best tun. rsb operation time was: on avg. 8.941e-07s, min 4.770e-07s, max 9.537e-07s, tot 7.153e-06s (8 samples) +#pr: ref. unt. rsb operation time was: on avg. 1.936e-02s, min 1.598e-02s, max 2.664e-02s, tot 1.549e-01s (8 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 5.993e+00 4.006e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.220e+00 +#pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 4.999e+00 x, min 4.000e+00 x, max 7.997e+00 x (4 samples, the non-min-nrhs ones) +#pr: Record collection took 13.83 s. #pr: Record comprises 40 memory benchmark samples (prepend RSB_PR_MBW=1 to dump this). -#pr: Record comprises 100 environment variables in 4266 bytes (prepend RSB_PR_ENV=1 to dump this). +#pr: Record comprises 100 environment variables in 4321 bytes (prepend RSB_PR_ENV=1 to dump this). # ====== END Total summary record. -#pr: ======== Saved a performance record of 16 samples to rsbench_pr__1749955887_gcc-13.2.rpr -# Removing the temporary record file rsbench_pr__1749955887_gcc-13.2.rpr.tmp. -# terminating run at 1749955894 (after 7.0s of w.c.t.) -srcdir="/build/reproducible-path/librsb-1.3.0.2+dfsg" /bin/bash ./scripts/doc-tests.sh +#pr: ======== Saved a performance record of 16 samples to rsbench_pr__1715548787_gcc-13.2.rpr +# Removing the temporary record file rsbench_pr__1715548787_gcc-13.2.rpr.tmp. +# terminating run at 1715548809 (after 22.1s of w.c.t.) +srcdir="/build/reproducible-path/librsb-1.3.0.2+dfsg" /bin/sh ./scripts/doc-tests.sh + set -o pipefail + test x/build/reproducible-path/librsb-1.3.0.2+dfsg = x + cat /build/reproducible-path/librsb-1.3.0.2+dfsg/examples/autotune.c /build/reproducible-path/librsb-1.3.0.2+dfsg/examples/backsolve.c /build/reproducible-path/librsb-1.3.0.2+dfsg/examples/hello-spblas.c /build/reproducible-path/librsb-1.3.0.2+dfsg/examples/hello.c /build/reproducible-path/librsb-1.3.0.2+dfsg/examples/io-spblas.c /build/reproducible-path/librsb-1.3.0.2+dfsg/examples/power.c /build/reproducible-path/librsb-1.3.0.2+dfsg/examples/snippets.c /build/reproducible-path/librsb-1.3.0.2+dfsg/examples/transpose.c @@ -5096,11 +5107,11 @@ ++ /build/reproducible-path/librsb-1.3.0.2+dfsg/rsbench -h ++ wc -l + test 63 -ge 61 -++ /build/reproducible-path/librsb-1.3.0.2+dfsg/rsbench -h ++ wc -c +++ /build/reproducible-path/librsb-1.3.0.2+dfsg/rsbench -h + test 2014 -ge 1966 -++ /build/reproducible-path/librsb-1.3.0.2+dfsg/rsbench -oa -Ob -h ++ wc -l +++ /build/reproducible-path/librsb-1.3.0.2+dfsg/rsbench -oa -Ob -h + test 182 -ge 157 ++ /build/reproducible-path/librsb-1.3.0.2+dfsg/rsbench -oa -Ob -h ++ wc -c @@ -5138,7 +5149,7 @@ type char codes:D S C Z gmake[4]: Entering directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/examples' if test /build/reproducible-path/librsb-1.3.0.2+dfsg != /build/reproducible-path/librsb-1.3.0.2+dfsg ; then cp /build/reproducible-path/librsb-1.3.0.2+dfsg/pd.mtx /build/reproducible-path/librsb-1.3.0.2+dfsg/vf.mtx /build/reproducible-path/librsb-1.3.0.2+dfsg/examples ; fi -( PATH="/build/reproducible-path/librsb-1.3.0.2+dfsg:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games" /bin/bash /build/reproducible-path/librsb-1.3.0.2+dfsg/examples/bench.sh; ) +( PATH="/build/reproducible-path/librsb-1.3.0.2+dfsg:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/i/capture/the/path" /bin/sh /build/reproducible-path/librsb-1.3.0.2+dfsg/examples/bench.sh; ) + which rsbench /build/reproducible-path/librsb-1.3.0.2+dfsg/rsbench + BRF=test.rpr @@ -5148,15 +5159,15 @@ Will invoke autotuning for ~10.000000 s x 1 rounds, specifying verbosity=0 and threads=0. (>0 means no structure tuning; 0 means only structure tuning, <0 means tuning of both with (negated) thread count suggestion). # Requested no transposition. # performance record file set to: test.rpr -# beginning run at 1749955894 +# beginning run at 1715548810 # /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/rsbench -oa -Ob --bench --lower 100 --as-symmetric --types : -n 1 --notranspose --compare-competitors --verbose --verbose --write-performance-record=test.rpr # compiled with: CC=gcc CFLAGS=-g -O2 -Werror=implicit-function-declaration -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -fcf-protection -O3 -std=c99 -# average timer granularity: 3.44e-08 s +# average timer granularity: 1.02e-06 s # Will write a final performance record to file test.rpr and periodic checkpoints to test.rpr.tmp # will NOT perform ancillary tests. # will flush cache memory: between each operation measurement series, and NOT between each operation. # will keep any zero encountered in the matrix. -# env: export PATH=/build/reproducible-path/librsb-1.3.0.2+dfsg:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games +# env: export PATH=/build/reproducible-path/librsb-1.3.0.2+dfsg:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/i/capture/the/path # env: export LD_LIBRARY_PATH=/build/reproducible-path/librsb-1.3.0.2+dfsg/.libs # env: HOSTNAME is not set # env: KMP_AFFINITY is not set @@ -5195,15 +5206,15 @@ # env: SLURM_NTASKS is not set # env: SLURM_STEP_TASKS_PER_NODE is not set # env: SLURM_TASKS_PER_NODE is not set -# detected hostname: ionos5-amd64 +# detected hostname: i-capture-the-hostname # user specified a verbosity level of 2 (each --verbose occurrence counts +1) # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 99864 bytes +# Cache block size total 524288 bytes, per-thread 26214 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 -# RSB_IO_WANT_EXECUTING_THREADS: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 +# RSB_IO_WANT_EXECUTING_THREADS: 20 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout # RSB_IO_WANT_VERBOSE_ERRORS: stderr @@ -5215,40 +5226,40 @@ # This test will measure times in scanning arrays sized and aligned to fit in caches. # 2 cache levels detected Will fill struct with 40 samples... -# Memory benchmark took 5.807s +# Memory benchmark took 6.506s # auto-tuning oriented output implies times==0 iterations and sort-after-load. #pr: allocated a performance record for 4 samples (1120 bytes). # multi-type benchmarking (DSCZ) -- now using typecode D (last was D). -# Cache block size total 4194304 bytes, per-thread 99864 bytes -# so far, program took 5.809s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.000s/0.000s . +# Cache block size total 524288 bytes, per-thread 26214 bytes +# so far, program took 6.548s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.000s/0.000s . # Using 1 threads # Using alpha=1 beta=1 order=cols for rsb_spmv/rsb_spsv/rsb_spmm/rsb_spsm. # will use input matrix flags: RSB_FLAG_USE_HALFWORD_INDICES, RSB_FLAG_SORTED_INPUT, RSB_FLAG_LOWER, RSB_FLAG_QUAD_PARTITIONING, RSB_FLAG_SYMMETRIC, RSB_FLAG_OWN_PARTITIONING_ARRAYS # Using 1 threads Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 1.030e-02 s (100.00 %) - analyzed arrays in 6.287e-03 s (61.03 %) - cleaned-up arrays in 8.821e-06 s (0.09 %) - deduplicated arrays in 1.216e-05 s (0.12 %) - sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 3.931e-03 s (38.16 %) - memory allocations took 2.408e-05 s (0.23 %) - leafs setup took 4.053e-06 s (0.04 %) - halfword conversion took 3.195e-05 s (0.31 %) -Built (100 x 100)[0x56006924f4e0]{D} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x2446196 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LS' -# Constructed matrix (took 0.010s): (100 x 100)[0x56006924f4e0]{D} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x2446196 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LS' + converted COO to RSB in 2.118e-01 s (100.00 %) + analyzed arrays in 5.525e-02 s (26.09 %) + cleaned-up arrays in 1.693e-05 s (0.01 %) + deduplicated arrays in 1.502e-05 s (0.01 %) + sorted arrays in 9.537e-07 s (0.00 %) + shuffled partitions in 1.126e-01 s (53.17 %) + memory allocations took 1.907e-05 s (0.01 %) + leafs setup took 1.597e-05 s (0.01 %) + halfword conversion took 4.385e-02 s (20.70 %) +Built (100 x 100)[0x55cecb5f0510]{D} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x2446196 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LS' +# Constructed matrix (took 0.212s): (100 x 100)[0x55cecb5f0510]{D} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x2446196 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LS' # matrix consistency check took 0.000s (ok) RSB Sparse Blocks Autotuner invoked requesting max 6 splits and max 6 merges in 1 rounds, threads spec.0 (specify negative values to enable threads tuning). Will autotune matrix: 100 x 100, type D, 5050 nnz, 50 nnz/r, 4 subms, 3 lsubms, 2.1212 bpnz. Parameters: verbosity:2 mintimes:3 maxtimes:10 mindt:0 maxdt:3 Saved plot to test-tuning-lower-100x100-5050nz--D-N-1--base.eps # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5259,11 +5270,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5274,11 +5285,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5288,16 +5299,16 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 0.000129s; avg 4.299e-05s ( +/- 35.12/ 67.47 %); best 2.789e-05s; worst 7.2e-05s; std dev. 2.052e-05 (taking best). -Reference operation time is 2.7895e-05 s (724.1 Mflops) with 1 threads. -Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=cols) (max 6 steps, inclusive 3 grace steps) on: 100 x 100, type D, 5050 nnz, 50 nnz/r, 4 subms, 3 lsubms, 2.1212 bpnz (tpop: 2.789e-05 Mflops: 724.145) -Merge (3 -> 1 leaves) took w.c.t. of 8.011e-05s, ~7.105e-05s of computing time (of which 1.907e-05s sorting, 3.099e-06s analysis) +3 iterations (1 th.) took 0.07994s; avg 0.02665s ( +/- 10.04/ 5.07 %); best 0.02397s; worst 0.028s; std dev. 0.001892 (taking best). +Reference operation time is 0.023972 s (0.8426 Mflops) with 1 threads. +Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=cols) (max 6 steps, inclusive 3 grace steps) on: 100 x 100, type D, 5050 nnz, 50 nnz/r, 4 subms, 3 lsubms, 2.1212 bpnz (tpop: 0.02397 Mflops: 0.843) +Merge (3 -> 1 leaves) took w.c.t. of 0.0001249s, ~8.702e-05s of computing time (of which 3.886e-05s sorting, 1.097e-05s analysis) # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5308,11 +5319,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5322,14 +5333,14 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 3.815e-05s; avg 1.272e-05s ( +/- 6.25/ 10.62 %); best 1.192e-05s; worst 1.407e-05s; std dev. 9.603e-07 (taking best). -Reference operation time is 1.19209e-05 s (1694 Mflops) with 1 threads. +3 iterations (1 th.) took 5.293e-05s; avg 1.764e-05s ( +/- 21.62/ 36.49 %); best 1.383e-05s; worst 2.408e-05s; std dev. 4.578e-06 (taking best). +Reference operation time is 1.38283e-05 s (1461 Mflops) with 1 threads. # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5339,25 +5350,25 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success -After merge step 1: tpop: 1.192e-05 s ~Mflops: 1694.499 nsubm:1 otn:1 -Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 2.340x: 2.789e-05s -> 1.192e-05s, so taking this instance. +After merge step 1: tpop: 1.383e-05 s ~Mflops: 1460.775 nsubm:1 otn:1 +Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 1733.552x: 0.02397s -> 1.383e-05s, so taking this instance. Saved plot to test-tuning-lower-100x100-5050nz--D-N-1--mv-tuned_merge1_1x1th.eps Merged all the matrix leaves: no reason to continue merging. -A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.004157s (of which 8.416e-05s partitioning, 0.003908s I/O); computing times: 7.105e-05s in par. loops, 1.907e-05s sorting, 3.099e-06s analyzing) -Total merge + benchmarking process took 0.004157s, equivalent to 348.7/149.0 new/old ops (8.512e-05s for 2 clones -- as 7.1/3.1 ops, or 3.6/1.5 ops per clone), SPEEDUP of 2.340x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 2.340x (2.789e-05s -> 1.192e-05s), will amortize in 260.2 ops by saving 1.597e-05s per op. -In 1 tuning rounds (tot. 0.0044s, 8.5e-05s for constructor, 2 clones) obtained a SPEEDUP of 134.0% (2.34x) (from 724.1 to 1694 Mflops). Employed 0.0041s for I/O of matrix plots. +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.2561s (of which 0.000138s partitioning, 0.1601s I/O); computing times: 8.702e-05s in par. loops, 3.886e-05s sorting, 1.097e-05s analyzing) +Total merge + benchmarking process took 0.2561s, equivalent to 18518.0/10.7 new/old ops (0.1871s for 2 clones -- as 13528.8/7.8 ops, or 6764.4/3.9 ops per clone), SPEEDUP of 1733.552x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 1733.552x (0.02397s -> 1.383e-05s), will amortize in 10.7 ops by saving 0.02396s per op. +In 1 tuning rounds (tot. 0.43s, 0.19s for constructor, 2 clones) obtained a SPEEDUP of 173255.2% (1734x) (from 0.8426 to 1461 Mflops). Employed 0.2s for I/O of matrix plots. #pr: updating sample at index 1 (0^th of 4), 0^th touch for (0,0,0,0,0,0,0). -First run of RSB Autotuner took 0.00850582 s (2.789e-05 s -> 1.192e-05 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.623561 s (2.397e-02 s -> 1.383e-05 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). RSB Sparse Blocks Autotuner invoked requesting max 0 splits and max 0 merges in 1 rounds, auto threads spec. Will autotune matrix: 100 x 100, type D, 5050 nnz, 50 nnz/r, 1 subms, 1 lsubms, 2.0800 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:10 # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5368,11 +5379,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5383,13 +5394,13 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success Started tuning inner round: will search for an optimal matrix instance. -Starting with requested 0 threads ; current default 1 ; at most 42. +Starting with requested 0 threads ; current default 1 ; at most 20. # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5400,11 +5411,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5414,27 +5425,27 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 4.697e-05s; avg 1.566e-05s ( +/- 4.06/ 8.12 %); best 1.502e-05s; worst 1.693e-05s; std dev. 8.991e-07 (taking best). -Reference operation time is 1.50204e-05 s (1345 Mflops) with 1 threads. +3 iterations (1 th.) took 6.485e-05s; avg 2.162e-05s ( +/- 36.03/ 70.96 %); best 1.383e-05s; worst 3.695e-05s; std dev. 1.085e-05 (taking best). +Reference operation time is 1.38283e-05 s (1461 Mflops) with 1 threads. Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 8.011e-05 s (100.00 %) - analyzed arrays in 2.003e-05 s (25.00 %) - cleaned-up arrays in 1.097e-05 s (13.69 %) - deduplicated arrays in 1.502e-05 s (18.75 %) + converted COO to RSB in 9.929e-02 s (100.00 %) + analyzed arrays in 4.724e-02 s (47.58 %) + cleaned-up arrays in 1.502e-05 s (0.02 %) + deduplicated arrays in 1.383e-05 s (0.01 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 2.408e-05 s (30.06 %) - memory allocations took 3.099e-06 s (3.87 %) - leafs setup took 9.537e-07 s (1.19 %) - halfword conversion took 4.053e-06 s (5.06 %) -Built (100 x 100)[0x56006925e230]{D} @ (0(0..100),0(0..100)) (5050 nnz, 50 nnz/r) flags 0x42644094 (coo:0, csr:1, hw:0, ic:1, fi:0), storage: 1, subm: 1, symflags:'LS' -Starting autotuning stage, with subdivision of 1 (current threads=1, requested threads=0, max threads = 42). -# librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes -# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 + shuffled partitions in 5.199e-02 s (52.36 %) + memory allocations took 7.153e-06 s (0.01 %) + leafs setup took 5.007e-06 s (0.01 %) + halfword conversion took 1.407e-05 s (0.01 %) +Built (100 x 100)[0x55cecb5fbf60]{D} @ (0(0..100),0(0..100)) (5050 nnz, 50 nnz/r) flags 0x42644094 (coo:0, csr:1, hw:0, ic:1, fi:0), storage: 1, subm: 1, symflags:'LS' +Starting autotuning stage, with subdivision of 1 (current threads=1, requested threads=0, max threads = 20). +# librsb version 1.3.0.2 - 202212201855: Initializing +# Cache block size total 524288 bytes, per-thread 524288 bytes +# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5445,12 +5456,12 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 0.25 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 99864 bytes +# Cache block size total 524288 bytes, per-thread 26214 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 -# RSB_IO_WANT_EXECUTING_THREADS: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 +# RSB_IO_WANT_EXECUTING_THREADS: 20 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout # RSB_IO_WANT_VERBOSE_ERRORS: stderr @@ -5461,22 +5472,22 @@ # librsb version 1.3.0.2 - 202212201855: Initialization success Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 1.268e-04 s (100.00 %) - analyzed arrays in 3.004e-05 s (23.68 %) - cleaned-up arrays in 1.097e-05 s (8.65 %) - deduplicated arrays in 1.407e-05 s (11.09 %) + converted COO to RSB in 1.319e-01 s (100.00 %) + analyzed arrays in 3.186e-02 s (24.16 %) + cleaned-up arrays in 1.502e-05 s (0.01 %) + deduplicated arrays in 1.383e-05 s (0.01 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 4.101e-05 s (32.33 %) - memory allocations took 3.815e-06 s (3.01 %) - leafs setup took 9.537e-07 s (0.75 %) - halfword conversion took 2.599e-05 s (20.49 %) -Built (100 x 100)[0x56006924f810]{D} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 3, symflags:'LS' -# librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes -# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 + shuffled partitions in 5.198e-02 s (39.42 %) + memory allocations took 8.345e-06 s (0.01 %) + leafs setup took 5.960e-06 s (0.00 %) + halfword conversion took 4.798e-02 s (36.38 %) +Built (100 x 100)[0x55cecb5f0860]{D} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 3, symflags:'LS' +# librsb version 1.3.0.2 - 202212201855: Initializing +# Cache block size total 524288 bytes, per-thread 524288 bytes +# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5487,11 +5498,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 0.25 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5502,11 +5513,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 0.25 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5516,16 +5527,16 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 0.25 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 9.108e-05s; avg 3.036e-05s ( +/- 7.33/ 5.24 %); best 2.813e-05s; worst 3.195e-05s; std dev. 1.621e-06 (taking best). -Reference operation time is 2.81334e-05 s (718 Mflops) with 1 threads. -Challenging best inner round reference (1.50204e-05 s/1 threads) with: subdivision 0.25, 3 leaves, 2.121 bytes/nz, 2.81334e-05 s/0 threads (speedup 0.533898 x), same?n. +3 iterations (1 th.) took 0.06356s; avg 0.02119s ( +/- 24.32/ 13.10 %); best 0.01604s; worst 0.02396s; std dev. 0.003647 (taking best). +Reference operation time is 0.0160351 s (1.26 Mflops) with 1 threads. +Challenging best inner round reference (1.38283e-05 s/1 threads) with: subdivision 0.25, 3 leaves, 2.121 bytes/nz, 0.0160351 s/0 threads (speedup 0.000862377 x), same?n. New candidate clone performs slowly; discarding it: 100 x 100, type D, 5050 nnz, 50 nnz/r, 4 subms, 3 lsubms, 2.1212 bpnz # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5536,12 +5547,12 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 0.5 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 99864 bytes +# Cache block size total 524288 bytes, per-thread 26214 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 -# RSB_IO_WANT_EXECUTING_THREADS: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 +# RSB_IO_WANT_EXECUTING_THREADS: 20 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout # RSB_IO_WANT_VERBOSE_ERRORS: stderr @@ -5552,22 +5563,22 @@ # librsb version 1.3.0.2 - 202212201855: Initialization success Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 5.510e-04 s (100.00 %) - analyzed arrays in 5.603e-05 s (10.17 %) - cleaned-up arrays in 1.097e-05 s (1.99 %) - deduplicated arrays in 1.502e-05 s (2.73 %) - sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 6.008e-05 s (10.90 %) - memory allocations took 1.907e-06 s (0.35 %) - leafs setup took 9.537e-07 s (0.17 %) - halfword conversion took 4.060e-04 s (73.69 %) -Built (100 x 100)[0x560069250200]{D} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 10, symflags:'LS' -# librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes -# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 + converted COO to RSB in 1.879e-01 s (100.00 %) + analyzed arrays in 6.783e-02 s (36.10 %) + cleaned-up arrays in 1.311e-05 s (0.01 %) + deduplicated arrays in 1.407e-05 s (0.01 %) + sorted arrays in 9.537e-07 s (0.00 %) + shuffled partitions in 5.202e-02 s (27.69 %) + memory allocations took 1.502e-05 s (0.01 %) + leafs setup took 1.001e-05 s (0.01 %) + halfword conversion took 6.797e-02 s (36.18 %) +Built (100 x 100)[0x55cecb5f1370]{D} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 12, symflags:'LS' +# librsb version 1.3.0.2 - 202212201855: Initializing +# Cache block size total 524288 bytes, per-thread 524288 bytes +# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5578,11 +5589,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 0.5 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5593,11 +5604,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 0.5 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5607,16 +5618,16 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 0.5 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 9.704e-05s; avg 3.235e-05s ( +/- 10.81/ 8.35 %); best 2.885e-05s; worst 3.505e-05s; std dev. 2.592e-06 (taking best). -Reference operation time is 2.88486e-05 s (700.2 Mflops) with 1 threads. -Challenging best inner round reference (1.50204e-05 s/1 threads) with: subdivision 0.5, 10 leaves, 2.206 bytes/nz, 2.88486e-05 s/0 threads (speedup 0.520661 x), same?n. -New candidate clone performs slowly; discarding it: 100 x 100, type D, 5050 nnz, 50 nnz/r, 14 subms, 10 lsubms, 2.2059 bpnz +3 iterations (1 th.) took 0.0756s; avg 0.0252s ( +/- 6.39/ 11.10 %); best 0.02359s; worst 0.028s; std dev. 0.001985 (taking best). +Reference operation time is 0.0235898 s (0.8563 Mflops) with 1 threads. +Challenging best inner round reference (1.38283e-05 s/1 threads) with: subdivision 0.5, 12 leaves, 2.217 bytes/nz, 0.0235898 s/0 threads (speedup 0.000586196 x), same?n. +New candidate clone performs slowly; discarding it: 100 x 100, type D, 5050 nnz, 50 nnz/r, 17 subms, 12 lsubms, 2.2170 bpnz # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5627,12 +5638,12 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 99864 bytes +# Cache block size total 524288 bytes, per-thread 26214 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 -# RSB_IO_WANT_EXECUTING_THREADS: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 +# RSB_IO_WANT_EXECUTING_THREADS: 20 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout # RSB_IO_WANT_VERBOSE_ERRORS: stderr @@ -5643,22 +5654,22 @@ # librsb version 1.3.0.2 - 202212201855: Initialization success Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 2.029e-04 s (100.00 %) - analyzed arrays in 7.796e-05 s (38.43 %) - cleaned-up arrays in 8.106e-06 s (4.00 %) - deduplicated arrays in 1.192e-05 s (5.88 %) - sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 7.010e-05 s (34.55 %) - memory allocations took 2.861e-06 s (1.41 %) - leafs setup took 2.861e-06 s (1.41 %) - halfword conversion took 2.909e-05 s (14.34 %) -Built (100 x 100)[0x56006925e350]{D} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 22, symflags:'LS' + converted COO to RSB in 1.719e-01 s (100.00 %) + analyzed arrays in 6.783e-02 s (39.46 %) + cleaned-up arrays in 1.407e-05 s (0.01 %) + deduplicated arrays in 1.287e-05 s (0.01 %) + sorted arrays in 9.537e-07 s (0.00 %) + shuffled partitions in 5.203e-02 s (30.27 %) + memory allocations took 1.431e-05 s (0.01 %) + leafs setup took 8.821e-06 s (0.01 %) + halfword conversion took 5.197e-02 s (30.23 %) +Built (100 x 100)[0x55cecb5fc080]{D} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 28, symflags:'LS' # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5669,11 +5680,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5684,11 +5695,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5698,16 +5709,16 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 0.0001059s; avg 3.529e-05s ( +/- 3.38/ 4.73 %); best 3.409e-05s; worst 3.695e-05s; std dev. 1.216e-06 (taking best). -Reference operation time is 3.40939e-05 s (592.5 Mflops) with 1 threads. -Challenging best inner round reference (1.50204e-05 s/1 threads) with: subdivision 1, 22 leaves, 2.295 bytes/nz, 3.40939e-05 s/0 threads (speedup 0.440559 x), same?n. -New candidate clone performs slowly; discarding it: 100 x 100, type D, 5050 nnz, 50 nnz/r, 30 subms, 22 lsubms, 2.2947 bpnz +3 iterations (1 th.) took 0.08757s; avg 0.02919s ( +/- 45.07/ 23.18 %); best 0.01604s; worst 0.03596s; std dev. 0.009304 (taking best). +Reference operation time is 0.0160358 s (1.26 Mflops) with 1 threads. +Challenging best inner round reference (1.38283e-05 s/1 threads) with: subdivision 1, 28 leaves, 2.339 bytes/nz, 0.0160358 s/0 threads (speedup 0.000862338 x), same?n. +New candidate clone performs slowly; discarding it: 100 x 100, type D, 5050 nnz, 50 nnz/r, 38 subms, 28 lsubms, 2.3390 bpnz # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5718,12 +5729,12 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 2 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 99864 bytes +# Cache block size total 524288 bytes, per-thread 26214 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 -# RSB_IO_WANT_EXECUTING_THREADS: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 +# RSB_IO_WANT_EXECUTING_THREADS: 20 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout # RSB_IO_WANT_VERBOSE_ERRORS: stderr @@ -5734,22 +5745,22 @@ # librsb version 1.3.0.2 - 202212201855: Initialization success Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 3.281e-04 s (100.00 %) - analyzed arrays in 1.609e-04 s (49.06 %) - cleaned-up arrays in 6.914e-06 s (2.11 %) - deduplicated arrays in 1.192e-05 s (3.63 %) - sorted arrays in 9.537e-07 s (0.29 %) - shuffled partitions in 1.111e-04 s (33.87 %) - memory allocations took 5.245e-06 s (1.60 %) - leafs setup took 3.815e-06 s (1.16 %) - halfword conversion took 2.718e-05 s (8.28 %) -Built (100 x 100)[0x560069284fc0]{D} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 49, symflags:'LS' -# librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes -# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 + converted COO to RSB in 2.159e-01 s (100.00 %) + analyzed arrays in 1.038e-01 s (48.09 %) + cleaned-up arrays in 1.407e-05 s (0.01 %) + deduplicated arrays in 1.407e-05 s (0.01 %) + sorted arrays in 9.537e-07 s (0.00 %) + shuffled partitions in 6.002e-02 s (27.80 %) + memory allocations took 2.193e-05 s (0.01 %) + leafs setup took 1.502e-05 s (0.01 %) + halfword conversion took 5.197e-02 s (24.08 %) +Built (100 x 100)[0x55cecb622d20]{D} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 57, symflags:'LS' +# librsb version 1.3.0.2 - 202212201855: Initializing +# Cache block size total 524288 bytes, per-thread 524288 bytes +# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5760,11 +5771,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 2 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5775,11 +5786,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 2 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5789,16 +5800,16 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 2 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 0.000123s; avg 4.101e-05s ( +/- 4.65/ 6.98 %); best 3.91e-05s; worst 4.387e-05s; std dev. 2.06e-06 (taking best). -Reference operation time is 3.91006e-05 s (516.6 Mflops) with 1 threads. -Challenging best inner round reference (1.50204e-05 s/1 threads) with: subdivision 2, 49 leaves, 2.435 bytes/nz, 3.91006e-05 s/0 threads (speedup 0.384146 x), same?n. -New candidate clone performs slowly; discarding it: 100 x 100, type D, 5050 nnz, 50 nnz/r, 67 subms, 49 lsubms, 2.4349 bpnz -# librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes -# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +3 iterations (1 th.) took 0.1316s; avg 0.04387s ( +/- 54.37/ 63.19 %); best 0.02001s; worst 0.07159s; std dev. 0.02123 (taking best). +Reference operation time is 0.020014 s (1.009 Mflops) with 1 threads. +Challenging best inner round reference (1.38283e-05 s/1 threads) with: subdivision 2, 57 leaves, 2.47 bytes/nz, 0.020014 s/0 threads (speedup 0.000690929 x), same?n. +New candidate clone performs slowly; discarding it: 100 x 100, type D, 5050 nnz, 50 nnz/r, 78 subms, 57 lsubms, 2.4705 bpnz +# librsb version 1.3.0.2 - 202212201855: Initializing +# Cache block size total 524288 bytes, per-thread 524288 bytes +# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5809,12 +5820,12 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 4 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 99864 bytes +# Cache block size total 524288 bytes, per-thread 26214 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 -# RSB_IO_WANT_EXECUTING_THREADS: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 +# RSB_IO_WANT_EXECUTING_THREADS: 20 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout # RSB_IO_WANT_VERBOSE_ERRORS: stderr @@ -5825,22 +5836,22 @@ # librsb version 1.3.0.2 - 202212201855: Initialization success Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 4.671e-04 s (100.00 %) - analyzed arrays in 2.110e-04 s (45.18 %) - cleaned-up arrays in 7.868e-06 s (1.68 %) - deduplicated arrays in 1.311e-05 s (2.81 %) - sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.931e-04 s (41.35 %) - memory allocations took 6.914e-06 s (1.48 %) - leafs setup took 5.960e-06 s (1.28 %) - halfword conversion took 2.813e-05 s (6.02 %) -Built (100 x 100)[0x560069284fc0]{D} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 102, symflags:'LS' -# librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes -# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 + converted COO to RSB in 1.838e-01 s (100.00 %) + analyzed arrays in 5.578e-02 s (30.34 %) + cleaned-up arrays in 1.478e-05 s (0.01 %) + deduplicated arrays in 1.287e-05 s (0.01 %) + sorted arrays in 1.192e-06 s (0.00 %) + shuffled partitions in 6.003e-02 s (32.65 %) + memory allocations took 2.718e-05 s (0.01 %) + leafs setup took 2.098e-05 s (0.01 %) + halfword conversion took 6.796e-02 s (36.97 %) +Built (100 x 100)[0x55cecb622d20]{D} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 120, symflags:'LS' +# librsb version 1.3.0.2 - 202212201855: Initializing +# Cache block size total 524288 bytes, per-thread 524288 bytes +# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5851,11 +5862,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 4 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5866,11 +5877,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 4 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5880,17 +5891,17 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 4 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 0.0001631s; avg 5.436e-05s ( +/- 4.39/ 6.58 %); best 5.198e-05s; worst 5.794e-05s; std dev. 2.575e-06 (taking best). -Reference operation time is 5.19753e-05 s (388.6 Mflops) with 1 threads. -Challenging best inner round reference (1.50204e-05 s/1 threads) with: subdivision 4, 102 leaves, 2.646 bytes/nz, 5.19753e-05 s/0 threads (speedup 0.288991 x), same?n. -New candidate clone performs slowly; discarding it: 100 x 100, type D, 5050 nnz, 50 nnz/r, 139 subms, 102 lsubms, 2.6455 bpnz -Best sparse multiply performance with subdivision multiplier of 1: 1344.84 Mflops. +3 iterations (1 th.) took 0.0879s; avg 0.0293s ( +/- 18.49/ 22.88 %); best 0.02388s; worst 0.036s; std dev. 0.005031 (taking best). +Reference operation time is 0.0238841 s (0.8458 Mflops) with 1 threads. +Challenging best inner round reference (1.38283e-05 s/1 threads) with: subdivision 4, 120 leaves, 2.726 bytes/nz, 0.0238841 s/0 threads (speedup 0.000578975 x), same?n. +New candidate clone performs slowly; discarding it: 100 x 100, type D, 5050 nnz, 50 nnz/r, 162 subms, 120 lsubms, 2.7255 bpnz +Best sparse multiply performance with subdivision multiplier of 1: 1460.77 Mflops. # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5900,29 +5911,29 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success -Last tuner inner round (1 of 1) took 0.003016 s (eq. to 2e+02/ 2e+02 old/new op.times), gained local/global speedup 1 x (1.50204e-05 : 1.50204e-05) / 1 x (1.50204e-05 : 1.50204e-05). This is not amortizable ! +Last tuner inner round (1 of 1) took 1.43986 s (eq. to 1e+05/ 1e+05 old/new op.times), gained local/global speedup 1 x (1.38283e-05 : 1.38283e-05) / 1 x (1.38283e-05 : 1.38283e-05). This is not amortizable ! Auto tuning inner round 1 did not find a configuration better than the original. -In 1 tuning rounds (tot. 0.003s, 0.0021s for constructor, 0 clones) obtained NO speedup (best stays 1345 Mflops). -Second run of RSB Autotuner took 0.00304699 s and estimated a speedup of 1.000000 x (1.502e-05 s -> 1.502e-05 s per op) in same matrix (1 -> 1 lsubm) +In 1 tuning rounds (tot. 1.4s, 0.99s for constructor, 0 clones) obtained NO speedup (best stays 1461 Mflops). +Second run of RSB Autotuner took 1.43997 s and estimated a speedup of 1.000000 x (1.383e-05 s -> 1.383e-05 s per op) in same matrix (1 -> 1 lsubm) #min:1 #max:1 #sum:100 #norm:10 #used index storage compared to COO:10504 vs 40400 bytes (26.00%) ; compared to CSR:10504 vs 20604 bytes (50.99%) #%:CONSTRUCTOR_*:SORT SCAN INSERT SCAN+INSERT -%:CONSTRUCTOR_TIMES:lower-100x100-5050nz S N 1 100 100 5050 0.000000 0.006287 0.003931 0.010218 -%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.010218 -%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.006287 -%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.003931 -%:ROW_MAJOR_SORT_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.000000 -%:ROW_MAJOR_SORT_SCALING:lower-100x100-5050nz S N 1 100 100 5050 -nan -%:SORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.010218 +%:CONSTRUCTOR_TIMES:lower-100x100-5050nz S N 1 100 100 5050 0.000001 0.055254 0.112598 0.167852 +%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.167853 +%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.055254 +%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.112598 +%:ROW_MAJOR_SORT_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.000001 +%:ROW_MAJOR_SORT_SCALING:lower-100x100-5050nz S N 1 100 100 5050 1.000 +%:SORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.167852 %:ROW_MAJOR_SORT_TO_MOP:lower-100x100-5050nz S N 1 100 100 5050 0.000 %:UNSORTEDCOO2RSB_SCALING:lower-100x100-5050nz S N 1 100 100 5050 1.00 %:SORTEDCOO2RSB_SCALING:lower-100x100-5050nz S N 1 100 100 5050 1.00 %:RSB_SUBDIVISION_SCALING:lower-100x100-5050nz S N 1 100 100 5050 1.00 %:RSB_SHUFFLE_SCALING:lower-100x100-5050nz S N 1 100 100 5050 1.00 -%:CONSTRUCTOR_SCALING:lower-100x100-5050nz S N 1 100 100 5050 -nan 1.00 1.00 1.00 +%:CONSTRUCTOR_SCALING:lower-100x100-5050nz S N 1 100 100 5050 1.00 1.00 1.00 1.00 #%:SM_COUNTS: Tot HalfwordCsr FullwordCsr HalfwordCoo FullwordCoo %:SM_COUNTS:lower-100x100-5050nz S N 1 100 100 5050 1 1 0 0 0 %:SM_IDXOCCUPATIONRSBVSCOOANDCSR:lower-100x100-5050nz S N 1 100 100 5050 10504 40400 20600 @@ -5931,45 +5942,45 @@ %:SM_MINMAXAVGNNZ:lower-100x100-5050nz S N 1 100 100 5050 5050 5050 5050 # %operation:matrix CONSTRUCTOR[1] SPMV[1] SPMV[1] -%operation:lower-100x100-5050nz 0.0103021 1e+09 1e+09 +%operation:lower-100x100-5050nz 0.211772 1e+09 1e+09 %constructor:matrix SORT[1] SCAN[1] SHUFFLE[1] INSERT[1] -%constructor:lower-100x100-5050nz 0 0.0062871 0 0.00393105 -# so far, program took 5.849s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.012s/0.000s . +%constructor:lower-100x100-5050nz 9.53674e-07 0.055254 0 0.112598 +# so far, program took 8.968s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 2.064s/0.000s . getrusage() stats: -ru_maxrss: 26 (maximum resident set size -- MB) -ru_stime : 0.1451s (system CPU time used) -ru_utime : 7.103s (user CPU time used) +ru_maxrss: 7 (maximum resident set size -- MB) +ru_stime : 0.05174s (system CPU time used) +ru_utime : 19.9s (user CPU time used) # multi-type benchmarking (DSCZ) -- now using typecode S (last was D). -# Cache block size total 4194304 bytes, per-thread 4194304 bytes -# so far, program took 5.849s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.012s/0.000s . +# Cache block size total 524288 bytes, per-thread 524288 bytes +# so far, program took 8.968s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 2.064s/0.000s . # Using 1 threads # Using alpha=1 beta=1 order=cols for rsb_spmv/rsb_spsv/rsb_spmm/rsb_spsm. # will use input matrix flags: RSB_FLAG_USE_HALFWORD_INDICES, RSB_FLAG_SORTED_INPUT, RSB_FLAG_LOWER, RSB_FLAG_QUAD_PARTITIONING, RSB_FLAG_SYMMETRIC, RSB_FLAG_OWN_PARTITIONING_ARRAYS # Using 1 threads Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 2.815e-02 s (100.00 %) - analyzed arrays in 5.365e-03 s (19.06 %) - cleaned-up arrays in 7.868e-06 s (0.03 %) - deduplicated arrays in 1.216e-05 s (0.04 %) - sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.519e-02 s (53.96 %) - memory allocations took 5.007e-06 s (0.02 %) - leafs setup took 1.192e-06 s (0.00 %) - halfword conversion took 7.570e-03 s (26.89 %) -Built (100 x 100)[0x56006925e350]{S} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x2446196 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LS' -# Constructed matrix (took 0.028s): (100 x 100)[0x56006925e350]{S} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x2446196 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LS' + converted COO to RSB in 1.993e-01 s (100.00 %) + analyzed arrays in 3.532e-02 s (17.72 %) + cleaned-up arrays in 1.407e-05 s (0.01 %) + deduplicated arrays in 1.407e-05 s (0.01 %) + sorted arrays in 9.537e-07 s (0.00 %) + shuffled partitions in 1.080e-01 s (54.16 %) + memory allocations took 1.287e-05 s (0.01 %) + leafs setup took 7.153e-06 s (0.00 %) + halfword conversion took 5.601e-02 s (28.10 %) +Built (100 x 100)[0x55cecb5fc080]{S} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x2446196 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LS' +# Constructed matrix (took 0.199s): (100 x 100)[0x55cecb5fc080]{S} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x2446196 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LS' # matrix consistency check took 0.000s (ok) RSB Sparse Blocks Autotuner invoked requesting max 6 splits and max 6 merges in 1 rounds, threads spec.0 (specify negative values to enable threads tuning). Will autotune matrix: 100 x 100, type S, 5050 nnz, 50 nnz/r, 4 subms, 3 lsubms, 2.1212 bpnz. Parameters: verbosity:2 mintimes:3 maxtimes:10 mindt:0 maxdt:3 Saved plot to test-tuning-lower-100x100-5050nz--S-N-1--base.eps # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5980,11 +5991,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -5995,11 +6006,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6009,16 +6020,16 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 0.004146s; avg 0.001382s ( +/- 97.83/154.99 %); best 3.004e-05s; worst 0.003524s; std dev. 0.001532 (taking best). -Reference operation time is 3.00407e-05 s (672.4 Mflops) with 1 threads. -Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=cols) (max 6 steps, inclusive 3 grace steps) on: 100 x 100, type S, 5050 nnz, 50 nnz/r, 4 subms, 3 lsubms, 2.1212 bpnz (tpop: 3.004e-05 Mflops: 672.420) -Merge (3 -> 1 leaves) took w.c.t. of 4.292e-05s, ~3.695e-05s of computing time (of which 1.502e-05s sorting, 2.146e-06s analysis) +3 iterations (1 th.) took 0.09595s; avg 0.03198s ( +/- 24.95/ 24.90 %); best 0.024s; worst 0.03995s; std dev. 0.006509 (taking best). +Reference operation time is 0.024004 s (0.8415 Mflops) with 1 threads. +Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=cols) (max 6 steps, inclusive 3 grace steps) on: 100 x 100, type S, 5050 nnz, 50 nnz/r, 4 subms, 3 lsubms, 2.1212 bpnz (tpop: 0.024 Mflops: 0.842) +Merge (3 -> 1 leaves) took w.c.t. of 9.012e-05s, ~6.89e-05s of computing time (of which 2.909e-05s sorting, 6.199e-06s analysis) # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6029,11 +6040,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6043,14 +6054,14 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 3.695e-05s; avg 1.232e-05s ( +/- 3.23/ 4.52 %); best 1.192e-05s; worst 1.287e-05s; std dev. 4.052e-07 (taking best). -Reference operation time is 1.19209e-05 s (1694 Mflops) with 1 threads. +3 iterations (1 th.) took 4.387e-05s; avg 1.462e-05s ( +/- 5.43/ 9.24 %); best 1.383e-05s; worst 1.597e-05s; std dev. 9.603e-07 (taking best). +Reference operation time is 1.38283e-05 s (1461 Mflops) with 1 threads. # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6060,25 +6071,25 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success -After merge step 1: tpop: 1.192e-05 s ~Mflops: 1694.499 nsubm:1 otn:1 -Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 2.520x: 3.004e-05s -> 1.192e-05s, so taking this instance. +After merge step 1: tpop: 1.383e-05 s ~Mflops: 1460.775 nsubm:1 otn:1 +Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 1735.862x: 0.024s -> 1.383e-05s, so taking this instance. Saved plot to test-tuning-lower-100x100-5050nz--S-N-1--mv-tuned_merge1_1x1th.eps Merged all the matrix leaves: no reason to continue merging. -A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.003975s (of which 4.697e-05s partitioning, 0.003668s I/O); computing times: 3.695e-05s in par. loops, 1.502e-05s sorting, 2.146e-06s analyzing) -Total merge + benchmarking process took 0.003975s, equivalent to 333.4/132.3 new/old ops (0.01196s for 2 clones -- as 1003.0/398.0 ops, or 501.5/199.0 ops per clone), SPEEDUP of 2.520x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 2.520x (3.004e-05s -> 1.192e-05s), will amortize in 219.4 ops by saving 1.812e-05s per op. -In 1 tuning rounds (tot. 0.02s, 0.012s for constructor, 2 clones) obtained a SPEEDUP of 152.0% (2.52x) (from 672.4 to 1694 Mflops). Employed 0.024s for I/O of matrix plots. +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.4563s (of which 9.489e-05s partitioning, 0.368s I/O); computing times: 6.89e-05s in par. loops, 2.909e-05s sorting, 6.199e-06s analyzing) +Total merge + benchmarking process took 0.4563s, equivalent to 32997.5/19.0 new/old ops (0.1442s for 2 clones -- as 10429.1/6.0 ops, or 5214.6/3.0 ops per clone), SPEEDUP of 1735.862x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 1735.862x (0.024s -> 1.383e-05s), will amortize in 19.0 ops by saving 0.02399s per op. +In 1 tuning rounds (tot. 0.61s, 0.14s for constructor, 2 clones) obtained a SPEEDUP of 173486.2% (1736x) (from 0.8415 to 1461 Mflops). Employed 0.25s for I/O of matrix plots. #pr: updating sample at index 2 (1^th of 4), 0^th touch for (0,0,0,0,0,1,0). -First run of RSB Autotuner took 0.0445051 s (3.004e-05 s -> 1.192e-05 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.860304 s (2.400e-02 s -> 1.383e-05 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). RSB Sparse Blocks Autotuner invoked requesting max 0 splits and max 0 merges in 1 rounds, auto threads spec. Will autotune matrix: 100 x 100, type S, 5050 nnz, 50 nnz/r, 1 subms, 1 lsubms, 2.0800 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:10 # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6089,11 +6100,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6104,13 +6115,13 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success Started tuning inner round: will search for an optimal matrix instance. -Starting with requested 0 threads ; current default 1 ; at most 42. +Starting with requested 0 threads ; current default 1 ; at most 20. # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6121,11 +6132,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6135,27 +6146,27 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 4.697e-05s; avg 1.566e-05s ( +/- 4.06/ 8.12 %); best 1.502e-05s; worst 1.693e-05s; std dev. 8.991e-07 (taking best). -Reference operation time is 1.50204e-05 s (1345 Mflops) with 1 threads. +3 iterations (1 th.) took 5.603e-05s; avg 1.868e-05s ( +/- 25.96/ 50.64 %); best 1.383e-05s; worst 2.813e-05s; std dev. 6.688e-06 (taking best). +Reference operation time is 1.38283e-05 s (1461 Mflops) with 1 threads. Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 7.892e-05 s (100.00 %) - analyzed arrays in 2.098e-05 s (26.59 %) - cleaned-up arrays in 1.097e-05 s (13.90 %) - deduplicated arrays in 1.502e-05 s (19.03 %) + converted COO to RSB in 7.936e-02 s (100.00 %) + analyzed arrays in 3.533e-02 s (44.51 %) + cleaned-up arrays in 1.597e-05 s (0.02 %) + deduplicated arrays in 1.407e-05 s (0.02 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 2.503e-05 s (31.72 %) - memory allocations took 2.861e-06 s (3.63 %) - leafs setup took 0.000e+00 s (0.00 %) - halfword conversion took 4.053e-06 s (5.14 %) -Built (100 x 100)[0x56006925e230]{S} @ (0(0..100),0(0..100)) (5050 nnz, 50 nnz/r) flags 0x42644094 (coo:0, csr:1, hw:0, ic:1, fi:0), storage: 1, subm: 1, symflags:'LS' -Starting autotuning stage, with subdivision of 1 (current threads=1, requested threads=0, max threads = 42). -# librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes -# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 + shuffled partitions in 4.399e-02 s (55.42 %) + memory allocations took 7.868e-06 s (0.01 %) + leafs setup took 3.099e-06 s (0.00 %) + halfword conversion took 6.914e-06 s (0.01 %) +Built (100 x 100)[0x55cecb5fbf60]{S} @ (0(0..100),0(0..100)) (5050 nnz, 50 nnz/r) flags 0x42644094 (coo:0, csr:1, hw:0, ic:1, fi:0), storage: 1, subm: 1, symflags:'LS' +Starting autotuning stage, with subdivision of 1 (current threads=1, requested threads=0, max threads = 20). +# librsb version 1.3.0.2 - 202212201855: Initializing +# Cache block size total 524288 bytes, per-thread 524288 bytes +# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6166,12 +6177,12 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 0.25 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 99864 bytes +# Cache block size total 524288 bytes, per-thread 26214 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 -# RSB_IO_WANT_EXECUTING_THREADS: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 +# RSB_IO_WANT_EXECUTING_THREADS: 20 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout # RSB_IO_WANT_VERBOSE_ERRORS: stderr @@ -6182,22 +6193,22 @@ # librsb version 1.3.0.2 - 202212201855: Initialization success Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 6.509e-05 s (100.00 %) - analyzed arrays in 1.788e-05 s (27.47 %) - cleaned-up arrays in 1.097e-05 s (16.85 %) - deduplicated arrays in 1.502e-05 s (23.08 %) - sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.502e-05 s (23.08 %) - memory allocations took 2.146e-06 s (3.30 %) - leafs setup took 0.000e+00 s (0.00 %) - halfword conversion took 4.053e-06 s (6.23 %) -Built (100 x 100)[0x560069250200]{S} @ (0(0..100),0(0..100)) (5050 nnz, 50 nnz/r) flags 0x42644096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 1, symflags:'LS' -# librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes -# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 + converted COO to RSB in 1.559e-01 s (100.00 %) + analyzed arrays in 3.988e-02 s (25.58 %) + cleaned-up arrays in 1.407e-05 s (0.01 %) + deduplicated arrays in 1.407e-05 s (0.01 %) + sorted arrays in 9.537e-07 s (0.00 %) + shuffled partitions in 6.001e-02 s (38.49 %) + memory allocations took 5.960e-06 s (0.00 %) + leafs setup took 4.053e-06 s (0.00 %) + halfword conversion took 5.597e-02 s (35.90 %) +Built (100 x 100)[0x55cecb5f16b0]{S} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 3, symflags:'LS' +# librsb version 1.3.0.2 - 202212201855: Initializing +# Cache block size total 524288 bytes, per-thread 524288 bytes +# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6208,11 +6219,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 0.25 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6223,11 +6234,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 0.25 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6237,16 +6248,16 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 0.25 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 4.792e-05s; avg 1.597e-05s ( +/- 5.97/ 11.94 %); best 1.502e-05s; worst 1.788e-05s; std dev. 1.349e-06 (taking best). -Reference operation time is 1.50204e-05 s (1345 Mflops) with 1 threads. -Challenging best inner round reference (1.50204e-05 s/1 threads) with: subdivision 0.25, 1 leaves, 2.08 bytes/nz, 1.50204e-05 s/0 threads (speedup 1 x), same?n. -New candidate clone performs slowly; discarding it: 100 x 100, type S, 5050 nnz, 50 nnz/r, 1 subms, 1 lsubms, 2.0800 bpnz -# librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes -# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +3 iterations (1 th.) took 0.06762s; avg 0.02254s ( +/- 48.21/ 24.20 %); best 0.01167s; worst 0.028s; std dev. 0.007684 (taking best). +Reference operation time is 0.0116739 s (1.73 Mflops) with 1 threads. +Challenging best inner round reference (1.38283e-05 s/1 threads) with: subdivision 0.25, 3 leaves, 2.121 bytes/nz, 0.0116739 s/0 threads (speedup 0.00118454 x), same?n. +New candidate clone performs slowly; discarding it: 100 x 100, type S, 5050 nnz, 50 nnz/r, 4 subms, 3 lsubms, 2.1212 bpnz +# librsb version 1.3.0.2 - 202212201855: Initializing +# Cache block size total 524288 bytes, per-thread 524288 bytes +# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6257,12 +6268,12 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 0.5 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 99864 bytes +# Cache block size total 524288 bytes, per-thread 26214 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 -# RSB_IO_WANT_EXECUTING_THREADS: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 +# RSB_IO_WANT_EXECUTING_THREADS: 20 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout # RSB_IO_WANT_VERBOSE_ERRORS: stderr @@ -6273,22 +6284,22 @@ # librsb version 1.3.0.2 - 202212201855: Initialization success Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 1.481e-04 s (100.00 %) - analyzed arrays in 4.888e-05 s (33.01 %) - cleaned-up arrays in 1.121e-05 s (7.57 %) - deduplicated arrays in 1.478e-05 s (9.98 %) + converted COO to RSB in 1.279e-01 s (100.00 %) + analyzed arrays in 4.393e-02 s (34.35 %) + cleaned-up arrays in 1.502e-05 s (0.01 %) + deduplicated arrays in 1.383e-05 s (0.01 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 4.315e-05 s (29.15 %) - memory allocations took 2.146e-06 s (1.45 %) - leafs setup took 9.537e-07 s (0.64 %) - halfword conversion took 2.694e-05 s (18.20 %) -Built (100 x 100)[0x560069250200]{S} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 6, symflags:'LS' -# librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes -# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 + shuffled partitions in 3.994e-02 s (31.23 %) + memory allocations took 9.298e-06 s (0.01 %) + leafs setup took 9.060e-06 s (0.01 %) + halfword conversion took 4.397e-02 s (34.38 %) +Built (100 x 100)[0x55cecb5f16b0]{S} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 8, symflags:'LS' +# librsb version 1.3.0.2 - 202212201855: Initializing +# Cache block size total 524288 bytes, per-thread 524288 bytes +# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6299,11 +6310,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 0.5 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6314,11 +6325,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 0.5 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6328,16 +6339,16 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 0.5 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 9.799e-05s; avg 3.266e-05s ( +/- 10.95/ 16.06 %); best 2.909e-05s; worst 3.791e-05s; std dev. 3.79e-06 (taking best). -Reference operation time is 2.90871e-05 s (694.5 Mflops) with 1 threads. -Challenging best inner round reference (1.50204e-05 s/1 threads) with: subdivision 0.5, 6 leaves, 2.163 bytes/nz, 2.90871e-05 s/0 threads (speedup 0.516393 x), same?n. -New candidate clone performs slowly; discarding it: 100 x 100, type S, 5050 nnz, 50 nnz/r, 8 subms, 6 lsubms, 2.1632 bpnz +3 iterations (1 th.) took 0.06766s; avg 0.02255s ( +/- 48.32/ 41.75 %); best 0.01166s; worst 0.03197s; std dev. 0.00836 (taking best). +Reference operation time is 0.011656 s (1.733 Mflops) with 1 threads. +Challenging best inner round reference (1.38283e-05 s/1 threads) with: subdivision 0.5, 8 leaves, 2.185 bytes/nz, 0.011656 s/0 threads (speedup 0.00118636 x), same?n. +New candidate clone performs slowly; discarding it: 100 x 100, type S, 5050 nnz, 50 nnz/r, 11 subms, 8 lsubms, 2.1846 bpnz # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6348,12 +6359,12 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 99864 bytes +# Cache block size total 524288 bytes, per-thread 26214 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 -# RSB_IO_WANT_EXECUTING_THREADS: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 +# RSB_IO_WANT_EXECUTING_THREADS: 20 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout # RSB_IO_WANT_VERBOSE_ERRORS: stderr @@ -6364,22 +6375,22 @@ # librsb version 1.3.0.2 - 202212201855: Initialization success Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 1.781e-04 s (100.00 %) - analyzed arrays in 6.890e-05 s (38.69 %) - cleaned-up arrays in 1.097e-05 s (6.16 %) - deduplicated arrays in 1.502e-05 s (8.43 %) + converted COO to RSB in 1.719e-01 s (100.00 %) + analyzed arrays in 5.984e-02 s (34.82 %) + cleaned-up arrays in 1.478e-05 s (0.01 %) + deduplicated arrays in 1.407e-05 s (0.01 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 5.102e-05 s (28.65 %) - memory allocations took 3.099e-06 s (1.74 %) - leafs setup took 2.146e-06 s (1.20 %) - halfword conversion took 2.694e-05 s (15.13 %) -Built (100 x 100)[0x56006925e350]{S} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 16, symflags:'LS' + shuffled partitions in 5.602e-02 s (32.59 %) + memory allocations took 1.645e-05 s (0.01 %) + leafs setup took 1.097e-05 s (0.01 %) + halfword conversion took 5.595e-02 s (32.56 %) +Built (100 x 100)[0x55cecb5fc080]{S} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 19, symflags:'LS' # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6390,11 +6401,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6405,11 +6416,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6419,16 +6430,16 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 0.000103s; avg 3.433e-05s ( +/- 9.72/ 18.75 %); best 3.099e-05s; worst 4.077e-05s; std dev. 4.553e-06 (taking best). -Reference operation time is 3.09944e-05 s (651.7 Mflops) with 1 threads. -Challenging best inner round reference (1.50204e-05 s/1 threads) with: subdivision 1, 16 leaves, 2.25 bytes/nz, 3.09944e-05 s/0 threads (speedup 0.484615 x), same?n. -New candidate clone performs slowly; discarding it: 100 x 100, type S, 5050 nnz, 50 nnz/r, 22 subms, 16 lsubms, 2.2503 bpnz +3 iterations (1 th.) took 0.09554s; avg 0.03185s ( +/- 13.51/ 13.03 %); best 0.02754s; worst 0.03599s; std dev. 0.003452 (taking best). +Reference operation time is 0.0275421 s (0.7334 Mflops) with 1 threads. +Challenging best inner round reference (1.38283e-05 s/1 threads) with: subdivision 1, 19 leaves, 2.272 bytes/nz, 0.0275421 s/0 threads (speedup 0.000502078 x), same?n. +New candidate clone performs slowly; discarding it: 100 x 100, type S, 5050 nnz, 50 nnz/r, 26 subms, 19 lsubms, 2.2725 bpnz # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6439,12 +6450,12 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 2 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 99864 bytes +# Cache block size total 524288 bytes, per-thread 26214 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 -# RSB_IO_WANT_EXECUTING_THREADS: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 +# RSB_IO_WANT_EXECUTING_THREADS: 20 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout # RSB_IO_WANT_VERBOSE_ERRORS: stderr @@ -6455,22 +6466,22 @@ # librsb version 1.3.0.2 - 202212201855: Initialization success Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 2.849e-04 s (100.00 %) - analyzed arrays in 1.380e-04 s (48.45 %) - cleaned-up arrays in 1.097e-05 s (3.85 %) - deduplicated arrays in 1.502e-05 s (5.27 %) - sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 8.392e-05 s (29.46 %) - memory allocations took 5.007e-06 s (1.76 %) - leafs setup took 4.053e-06 s (1.42 %) - halfword conversion took 2.694e-05 s (9.46 %) -Built (100 x 100)[0x56006925e350]{S} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 37, symflags:'LS' -# librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes -# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 + converted COO to RSB in 1.719e-01 s (100.00 %) + analyzed arrays in 7.589e-02 s (44.15 %) + cleaned-up arrays in 1.407e-05 s (0.01 %) + deduplicated arrays in 1.407e-05 s (0.01 %) + sorted arrays in 9.537e-07 s (0.00 %) + shuffled partitions in 3.599e-02 s (20.94 %) + memory allocations took 1.597e-05 s (0.01 %) + leafs setup took 9.060e-06 s (0.01 %) + halfword conversion took 5.996e-02 s (34.88 %) +Built (100 x 100)[0x55cecb60f160]{S} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 42, symflags:'LS' +# librsb version 1.3.0.2 - 202212201855: Initializing +# Cache block size total 524288 bytes, per-thread 524288 bytes +# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6481,11 +6492,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 2 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6496,11 +6507,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 2 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6510,16 +6521,16 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 2 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 0.000133s; avg 4.435e-05s ( +/- 11.83/ 5.91 %); best 3.91e-05s; worst 4.697e-05s; std dev. 3.709e-06 (taking best). -Reference operation time is 3.91006e-05 s (516.6 Mflops) with 1 threads. -Challenging best inner round reference (1.50204e-05 s/1 threads) with: subdivision 2, 37 leaves, 2.385 bytes/nz, 3.91006e-05 s/0 threads (speedup 0.384146 x), same?n. -New candidate clone performs slowly; discarding it: 100 x 100, type S, 5050 nnz, 50 nnz/r, 51 subms, 37 lsubms, 2.3850 bpnz -# librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes -# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +3 iterations (1 th.) took 0.08392s; avg 0.02797s ( +/- 14.23/ 14.40 %); best 0.02399s; worst 0.032s; std dev. 0.003269 (taking best). +Reference operation time is 0.023994 s (0.8419 Mflops) with 1 threads. +Challenging best inner round reference (1.38283e-05 s/1 threads) with: subdivision 2, 42 leaves, 2.409 bytes/nz, 0.023994 s/0 threads (speedup 0.000576323 x), same?n. +New candidate clone performs slowly; discarding it: 100 x 100, type S, 5050 nnz, 50 nnz/r, 58 subms, 42 lsubms, 2.4087 bpnz +# librsb version 1.3.0.2 - 202212201855: Initializing +# Cache block size total 524288 bytes, per-thread 524288 bytes +# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6530,12 +6541,12 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 4 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 99864 bytes +# Cache block size total 524288 bytes, per-thread 26214 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 -# RSB_IO_WANT_EXECUTING_THREADS: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 +# RSB_IO_WANT_EXECUTING_THREADS: 20 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout # RSB_IO_WANT_VERBOSE_ERRORS: stderr @@ -6546,22 +6557,22 @@ # librsb version 1.3.0.2 - 202212201855: Initialization success Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 4.039e-04 s (100.00 %) - analyzed arrays in 1.950e-04 s (48.29 %) - cleaned-up arrays in 8.106e-06 s (2.01 %) - deduplicated arrays in 1.287e-05 s (3.19 %) + converted COO to RSB in 1.795e-01 s (100.00 %) + analyzed arrays in 6.748e-02 s (37.59 %) + cleaned-up arrays in 1.502e-05 s (0.01 %) + deduplicated arrays in 1.407e-05 s (0.01 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.500e-04 s (37.13 %) - memory allocations took 2.861e-06 s (0.71 %) - leafs setup took 5.960e-06 s (1.48 %) - halfword conversion took 2.694e-05 s (6.67 %) -Built (100 x 100)[0x560069271400]{S} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 78, symflags:'LS' -# librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes -# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 + shuffled partitions in 5.601e-02 s (31.20 %) + memory allocations took 2.265e-05 s (0.01 %) + leafs setup took 1.907e-05 s (0.01 %) + halfword conversion took 5.596e-02 s (31.17 %) +Built (100 x 100)[0x55cecb60f160]{S} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 90, symflags:'LS' +# librsb version 1.3.0.2 - 202212201855: Initializing +# Cache block size total 524288 bytes, per-thread 524288 bytes +# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6572,11 +6583,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 4 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6587,11 +6598,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 4 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6601,17 +6612,17 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 4 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 0.001593s; avg 0.000531s ( +/- 91.15/129.77 %); best 4.697e-05s; worst 0.00122s; std dev. 0.0005003 (taking best). -Reference operation time is 4.69685e-05 s (430.1 Mflops) with 1 threads. -Challenging best inner round reference (1.50204e-05 s/1 threads) with: subdivision 4, 78 leaves, 2.549 bytes/nz, 4.69685e-05 s/0 threads (speedup 0.319797 x), same?n. -New candidate clone performs slowly; discarding it: 100 x 100, type S, 5050 nnz, 50 nnz/r, 107 subms, 78 lsubms, 2.5489 bpnz -Best sparse multiply performance with subdivision multiplier of 1: 1344.84 Mflops. +3 iterations (1 th.) took 0.09992s; avg 0.03331s ( +/- 15.99/ 20.13 %); best 0.02798s; worst 0.04001s; std dev. 0.005008 (taking best). +Reference operation time is 0.027983 s (0.7219 Mflops) with 1 threads. +Challenging best inner round reference (1.38283e-05 s/1 threads) with: subdivision 4, 90 leaves, 2.605 bytes/nz, 0.027983 s/0 threads (speedup 0.000494168 x), same?n. +New candidate clone performs slowly; discarding it: 100 x 100, type S, 5050 nnz, 50 nnz/r, 122 subms, 90 lsubms, 2.6051 bpnz +Best sparse multiply performance with subdivision multiplier of 1: 1460.77 Mflops. # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6621,29 +6632,29 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success -Last tuner inner round (1 of 1) took 0.00435996 s (eq. to 3e+02/ 3e+02 old/new op.times), gained local/global speedup 1 x (1.50204e-05 : 1.50204e-05) / 1 x (1.50204e-05 : 1.50204e-05). This is not amortizable ! +Last tuner inner round (1 of 1) took 1.30395 s (eq. to 9e+04/ 9e+04 old/new op.times), gained local/global speedup 1 x (1.38283e-05 : 1.38283e-05) / 1 x (1.38283e-05 : 1.38283e-05). This is not amortizable ! Auto tuning inner round 1 did not find a configuration better than the original. -In 1 tuning rounds (tot. 0.0044s, 0.0014s for constructor, 0 clones) obtained NO speedup (best stays 1345 Mflops). -Second run of RSB Autotuner took 0.00439095 s and estimated a speedup of 1.000000 x (1.502e-05 s -> 1.502e-05 s per op) in same matrix (1 -> 1 lsubm) +In 1 tuning rounds (tot. 1.3s, 0.89s for constructor, 0 clones) obtained NO speedup (best stays 1461 Mflops). +Second run of RSB Autotuner took 1.30405 s and estimated a speedup of 1.000000 x (1.383e-05 s -> 1.383e-05 s per op) in same matrix (1 -> 1 lsubm) #min:1 #max:1 #sum:100 #norm:10 #used index storage compared to COO:10504 vs 40400 bytes (26.00%) ; compared to CSR:10504 vs 20604 bytes (50.99%) #%:CONSTRUCTOR_*:SORT SCAN INSERT SCAN+INSERT -%:CONSTRUCTOR_TIMES:lower-100x100-5050nz S N 1 100 100 5050 0.000000 0.005365 0.015191 0.020556 -%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.020556 -%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.005365 -%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.015191 -%:ROW_MAJOR_SORT_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.000000 -%:ROW_MAJOR_SORT_SCALING:lower-100x100-5050nz S N 1 100 100 5050 -nan -%:SORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.020556 +%:CONSTRUCTOR_TIMES:lower-100x100-5050nz S N 1 100 100 5050 0.000001 0.035320 0.107965 0.143285 +%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.143286 +%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.035320 +%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.107965 +%:ROW_MAJOR_SORT_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.000001 +%:ROW_MAJOR_SORT_SCALING:lower-100x100-5050nz S N 1 100 100 5050 1.000 +%:SORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.143285 %:ROW_MAJOR_SORT_TO_MOP:lower-100x100-5050nz S N 1 100 100 5050 0.000 %:UNSORTEDCOO2RSB_SCALING:lower-100x100-5050nz S N 1 100 100 5050 1.00 %:SORTEDCOO2RSB_SCALING:lower-100x100-5050nz S N 1 100 100 5050 1.00 %:RSB_SUBDIVISION_SCALING:lower-100x100-5050nz S N 1 100 100 5050 1.00 %:RSB_SHUFFLE_SCALING:lower-100x100-5050nz S N 1 100 100 5050 1.00 -%:CONSTRUCTOR_SCALING:lower-100x100-5050nz S N 1 100 100 5050 -nan 1.00 1.00 1.00 +%:CONSTRUCTOR_SCALING:lower-100x100-5050nz S N 1 100 100 5050 1.00 1.00 1.00 1.00 #%:SM_COUNTS: Tot HalfwordCsr FullwordCsr HalfwordCoo FullwordCoo %:SM_COUNTS:lower-100x100-5050nz S N 1 100 100 5050 1 1 0 0 0 %:SM_IDXOCCUPATIONRSBVSCOOANDCSR:lower-100x100-5050nz S N 1 100 100 5050 10504 40400 20600 @@ -6652,45 +6663,45 @@ %:SM_MINMAXAVGNNZ:lower-100x100-5050nz S N 1 100 100 5050 5050 5050 5050 # %operation:matrix CONSTRUCTOR[1] SPMV[1] SPMV[1] -%operation:lower-100x100-5050nz 0.0281522 1e+09 1e+09 +%operation:lower-100x100-5050nz 0.199342 1e+09 1e+09 %constructor:matrix SORT[1] SCAN[1] SHUFFLE[1] INSERT[1] -%constructor:lower-100x100-5050nz 0 0.00536513 0 0.0151908 -# so far, program took 5.939s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.060s/0.000s . +%constructor:lower-100x100-5050nz 9.53674e-07 0.0353198 0 0.107965 +# so far, program took 11.476s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 4.228s/0.000s . getrusage() stats: -ru_maxrss: 26 (maximum resident set size -- MB) -ru_stime : 0.1455s (system CPU time used) -ru_utime : 10.5s (user CPU time used) +ru_maxrss: 7 (maximum resident set size -- MB) +ru_stime : 0.05417s (system CPU time used) +ru_utime : 35.57s (user CPU time used) # multi-type benchmarking (DSCZ) -- now using typecode C (last was D). -# Cache block size total 4194304 bytes, per-thread 4194304 bytes -# so far, program took 5.939s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.060s/0.000s . +# Cache block size total 524288 bytes, per-thread 524288 bytes +# so far, program took 11.476s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 4.228s/0.000s . # Using 1 threads # Using alpha=1 beta=1 order=cols for rsb_spmv/rsb_spsv/rsb_spmm/rsb_spsm. # will use input matrix flags: RSB_FLAG_USE_HALFWORD_INDICES, RSB_FLAG_SORTED_INPUT, RSB_FLAG_LOWER, RSB_FLAG_QUAD_PARTITIONING, RSB_FLAG_SYMMETRIC, RSB_FLAG_OWN_PARTITIONING_ARRAYS # Using 1 threads Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 1.521e-04 s (100.00 %) - analyzed arrays in 2.789e-05 s (18.34 %) - cleaned-up arrays in 8.106e-06 s (5.33 %) - deduplicated arrays in 1.192e-05 s (7.84 %) - sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 7.510e-05 s (49.37 %) - memory allocations took 3.099e-06 s (2.04 %) - leafs setup took 9.537e-07 s (0.63 %) - halfword conversion took 2.408e-05 s (15.83 %) -Built (100 x 100)[0x56006925e350]{C} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x2446196 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LS' -# Constructed matrix (took 0.000s): (100 x 100)[0x56006925e350]{C} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x2446196 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LS' + converted COO to RSB in 2.231e-01 s (100.00 %) + analyzed arrays in 5.511e-02 s (24.70 %) + cleaned-up arrays in 1.407e-05 s (0.01 %) + deduplicated arrays in 1.287e-05 s (0.01 %) + sorted arrays in 9.537e-07 s (0.00 %) + shuffled partitions in 1.120e-01 s (50.18 %) + memory allocations took 1.407e-05 s (0.01 %) + leafs setup took 1.001e-05 s (0.00 %) + halfword conversion took 5.599e-02 s (25.10 %) +Built (100 x 100)[0x55cecb5fc080]{C} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x2446196 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LS' +# Constructed matrix (took 0.223s): (100 x 100)[0x55cecb5fc080]{C} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x2446196 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LS' # matrix consistency check took 0.000s (ok) RSB Sparse Blocks Autotuner invoked requesting max 6 splits and max 6 merges in 1 rounds, threads spec.0 (specify negative values to enable threads tuning). Will autotune matrix: 100 x 100, type C, 5050 nnz, 50 nnz/r, 4 subms, 3 lsubms, 2.1212 bpnz. Parameters: verbosity:2 mintimes:3 maxtimes:10 mindt:0 maxdt:3 Saved plot to test-tuning-lower-100x100-5050nz--C-N-1--base.eps # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6701,11 +6712,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6716,11 +6727,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6730,16 +6741,16 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 0.0002151s; avg 7.168e-05s ( +/- 12.20/ 21.40 %); best 6.294e-05s; worst 8.702e-05s; std dev. 1.088e-05 (taking best). -Reference operation time is 6.29425e-05 s (1284 Mflops) with 1 threads. -Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=cols) (max 6 steps, inclusive 3 grace steps) on: 100 x 100, type C, 5050 nnz, 50 nnz/r, 4 subms, 3 lsubms, 2.1212 bpnz (tpop: 6.294e-05 Mflops: 1283.711) -Merge (3 -> 1 leaves) took w.c.t. of 4.315e-05s, ~3.791e-05s of computing time (of which 1.693e-05s sorting, 1.192e-06s analysis) +3 iterations (1 th.) took 0.07597s; avg 0.02532s ( +/- 20.65/ 26.28 %); best 0.02009s; worst 0.03198s; std dev. 0.004955 (taking best). +Reference operation time is 0.0200942 s (4.021 Mflops) with 1 threads. +Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=cols) (max 6 steps, inclusive 3 grace steps) on: 100 x 100, type C, 5050 nnz, 50 nnz/r, 4 subms, 3 lsubms, 2.1212 bpnz (tpop: 0.02009 Mflops: 4.021) +Merge (3 -> 1 leaves) took w.c.t. of 0.000114s, ~8.702e-05s of computing time (of which 4.101e-05s sorting, 6.914e-06s analysis) # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6750,11 +6761,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6764,14 +6775,14 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 0.0001321s; avg 4.403e-05s ( +/- 1.99/ 2.35 %); best 4.315e-05s; worst 4.506e-05s; std dev. 7.867e-07 (taking best). -Reference operation time is 4.31538e-05 s (1872 Mflops) with 1 threads. +3 iterations (1 th.) took 0.000119s; avg 3.966e-05s ( +/- 9.22/ 18.44 %); best 3.6e-05s; worst 4.697e-05s; std dev. 5.17e-06 (taking best). +Reference operation time is 3.60012e-05 s (2244 Mflops) with 1 threads. # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6781,25 +6792,25 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success -After merge step 1: tpop: 4.315e-05 s ~Mflops: 1872.374 nsubm:1 otn:1 -Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 1.459x: 6.294e-05s -> 4.315e-05s, so taking this instance. +After merge step 1: tpop: 3.6e-05 s ~Mflops: 2244.369 nsubm:1 otn:1 +Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 558.152x: 0.02009s -> 3.6e-05s, so taking this instance. Saved plot to test-tuning-lower-100x100-5050nz--C-N-1--mv-tuned_merge1_1x1th.eps Merged all the matrix leaves: no reason to continue merging. -A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.004237s (of which 0.0001791s partitioning, 0.003858s I/O); computing times: 3.791e-05s in par. loops, 1.693e-05s sorting, 1.192e-06s analyzing) -Total merge + benchmarking process took 0.004237s, equivalent to 98.2/67.3 new/old ops (0.0005798s for 2 clones -- as 13.4/9.2 ops, or 6.7/4.6 ops per clone), SPEEDUP of 1.459x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 1.459x (6.294e-05s -> 4.315e-05s), will amortize in 214.1 ops by saving 1.979e-05s per op. -In 1 tuning rounds (tot. 0.005s, 0.00058s for constructor, 2 clones) obtained a SPEEDUP of 45.9% (1.459x) (from 1284 to 1872 Mflops). Employed 0.0048s for I/O of matrix plots. +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.232s (of which 0.0001202s partitioning, 0.152s I/O); computing times: 8.702e-05s in par. loops, 4.101e-05s sorting, 6.914e-06s analyzing) +Total merge + benchmarking process took 0.232s, equivalent to 6443.9/11.5 new/old ops (0.159s for 2 clones -- as 4416.2/7.9 ops, or 2208.1/4.0 ops per clone), SPEEDUP of 558.152x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 558.152x (0.02009s -> 3.6e-05s), will amortize in 11.6 ops by saving 0.02006s per op. +In 1 tuning rounds (tot. 0.39s, 0.16s for constructor, 2 clones) obtained a SPEEDUP of 55715.2% (558.2x) (from 4.021 to 2244 Mflops). Employed 0.16s for I/O of matrix plots. #pr: updating sample at index 3 (2^th of 4), 0^th touch for (0,0,0,0,0,2,0). -First run of RSB Autotuner took 0.00979686 s (6.294e-05 s -> 4.315e-05 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.543984 s (2.009e-02 s -> 3.600e-05 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). RSB Sparse Blocks Autotuner invoked requesting max 0 splits and max 0 merges in 1 rounds, auto threads spec. Will autotune matrix: 100 x 100, type C, 5050 nnz, 50 nnz/r, 1 subms, 1 lsubms, 2.0800 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:10 # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6810,11 +6821,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6825,13 +6836,13 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success Started tuning inner round: will search for an optimal matrix instance. -Starting with requested 0 threads ; current default 1 ; at most 42. +Starting with requested 0 threads ; current default 1 ; at most 20. # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6842,11 +6853,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6856,27 +6867,27 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 0.0001321s; avg 4.403e-05s ( +/- 1.99/ 2.35 %); best 4.315e-05s; worst 4.506e-05s; std dev. 7.867e-07 (taking best). -Reference operation time is 4.31538e-05 s (1872 Mflops) with 1 threads. +3 iterations (1 th.) took 0.0001428s; avg 4.76e-05s ( +/- 22.37/ 17.70 %); best 3.695e-05s; worst 5.603e-05s; std dev. 7.944e-06 (taking best). +Reference operation time is 3.69549e-05 s (2186 Mflops) with 1 threads. Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 7.796e-05 s (100.00 %) - analyzed arrays in 2.003e-05 s (25.69 %) - cleaned-up arrays in 1.097e-05 s (14.07 %) - deduplicated arrays in 1.502e-05 s (19.27 %) + converted COO to RSB in 9.146e-02 s (100.00 %) + analyzed arrays in 3.548e-02 s (38.80 %) + cleaned-up arrays in 1.311e-05 s (0.01 %) + deduplicated arrays in 1.097e-05 s (0.01 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 2.503e-05 s (32.11 %) - memory allocations took 1.907e-06 s (2.45 %) - leafs setup took 9.537e-07 s (1.22 %) - halfword conversion took 4.053e-06 s (5.20 %) -Built (100 x 100)[0x56006925e230]{C} @ (0(0..100),0(0..100)) (5050 nnz, 50 nnz/r) flags 0x42644094 (coo:0, csr:1, hw:0, ic:1, fi:0), storage: 1, subm: 1, symflags:'LS' -Starting autotuning stage, with subdivision of 1 (current threads=1, requested threads=0, max threads = 42). -# librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes -# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 + shuffled partitions in 5.594e-02 s (61.16 %) + memory allocations took 9.537e-07 s (0.00 %) + leafs setup took 2.146e-06 s (0.00 %) + halfword conversion took 6.914e-06 s (0.01 %) +Built (100 x 100)[0x55cecb5fbf60]{C} @ (0(0..100),0(0..100)) (5050 nnz, 50 nnz/r) flags 0x42644094 (coo:0, csr:1, hw:0, ic:1, fi:0), storage: 1, subm: 1, symflags:'LS' +Starting autotuning stage, with subdivision of 1 (current threads=1, requested threads=0, max threads = 20). +# librsb version 1.3.0.2 - 202212201855: Initializing +# Cache block size total 524288 bytes, per-thread 524288 bytes +# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6887,12 +6898,12 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 0.25 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 99864 bytes +# Cache block size total 524288 bytes, per-thread 26214 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 -# RSB_IO_WANT_EXECUTING_THREADS: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 +# RSB_IO_WANT_EXECUTING_THREADS: 20 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout # RSB_IO_WANT_VERBOSE_ERRORS: stderr @@ -6903,22 +6914,22 @@ # librsb version 1.3.0.2 - 202212201855: Initialization success Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 1.400e-04 s (100.00 %) - analyzed arrays in 3.695e-05 s (26.41 %) - cleaned-up arrays in 1.121e-05 s (8.01 %) - deduplicated arrays in 1.478e-05 s (10.56 %) + converted COO to RSB in 1.639e-01 s (100.00 %) + analyzed arrays in 3.590e-02 s (21.90 %) + cleaned-up arrays in 2.289e-05 s (0.01 %) + deduplicated arrays in 9.060e-06 s (0.01 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 4.792e-05 s (34.24 %) - memory allocations took 3.099e-06 s (2.21 %) - leafs setup took 9.537e-07 s (0.68 %) - halfword conversion took 2.503e-05 s (17.89 %) -Built (100 x 100)[0x560069250200]{C} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 3, symflags:'LS' -# librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes -# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 + shuffled partitions in 5.597e-02 s (34.15 %) + memory allocations took 8.821e-06 s (0.01 %) + leafs setup took 3.099e-06 s (0.00 %) + halfword conversion took 7.199e-02 s (43.92 %) +Built (100 x 100)[0x55cecb5fc080]{C} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 3, symflags:'LS' +# librsb version 1.3.0.2 - 202212201855: Initializing +# Cache block size total 524288 bytes, per-thread 524288 bytes +# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6929,11 +6940,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 0.25 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6944,11 +6955,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 0.25 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6958,16 +6969,16 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 0.25 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 0.0001931s; avg 6.437e-05s ( +/- 2.22/ 2.59 %); best 6.294e-05s; worst 6.604e-05s; std dev. 1.277e-06 (taking best). -Reference operation time is 6.29425e-05 s (1284 Mflops) with 1 threads. -Challenging best inner round reference (4.31538e-05 s/1 threads) with: subdivision 0.25, 3 leaves, 2.121 bytes/nz, 6.29425e-05 s/0 threads (speedup 0.685606 x), same?n. +3 iterations (1 th.) took 0.07196s; avg 0.02399s ( +/- 33.32/ 49.59 %); best 0.01599s; worst 0.03588s; std dev. 0.008575 (taking best). +Reference operation time is 0.0159941 s (5.052 Mflops) with 1 threads. +Challenging best inner round reference (3.69549e-05 s/1 threads) with: subdivision 0.25, 3 leaves, 2.121 bytes/nz, 0.0159941 s/0 threads (speedup 0.00231054 x), same?n. New candidate clone performs slowly; discarding it: 100 x 100, type C, 5050 nnz, 50 nnz/r, 4 subms, 3 lsubms, 2.1212 bpnz # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -6978,12 +6989,12 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 0.5 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 99864 bytes +# Cache block size total 524288 bytes, per-thread 26214 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 -# RSB_IO_WANT_EXECUTING_THREADS: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 +# RSB_IO_WANT_EXECUTING_THREADS: 20 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout # RSB_IO_WANT_VERBOSE_ERRORS: stderr @@ -6994,22 +7005,22 @@ # librsb version 1.3.0.2 - 202212201855: Initialization success Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 1.650e-04 s (100.00 %) - analyzed arrays in 6.008e-05 s (36.42 %) - cleaned-up arrays in 1.097e-05 s (6.65 %) - deduplicated arrays in 1.502e-05 s (9.10 %) + converted COO to RSB in 1.798e-01 s (100.00 %) + analyzed arrays in 7.178e-02 s (39.92 %) + cleaned-up arrays in 1.597e-05 s (0.01 %) + deduplicated arrays in 1.407e-05 s (0.01 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 4.792e-05 s (29.05 %) - memory allocations took 1.907e-06 s (1.16 %) - leafs setup took 9.537e-07 s (0.58 %) - halfword conversion took 2.599e-05 s (15.75 %) -Built (100 x 100)[0x560069250200]{C} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 10, symflags:'LS' -# librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes -# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 + shuffled partitions in 5.599e-02 s (31.14 %) + memory allocations took 9.060e-06 s (0.01 %) + leafs setup took 7.868e-06 s (0.00 %) + halfword conversion took 5.199e-02 s (28.91 %) +Built (100 x 100)[0x55cecb5fc080]{C} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 12, symflags:'LS' +# librsb version 1.3.0.2 - 202212201855: Initializing +# Cache block size total 524288 bytes, per-thread 524288 bytes +# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7020,11 +7031,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 0.5 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7035,11 +7046,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 0.5 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7049,16 +7060,16 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 0.5 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 0.000205s; avg 6.835e-05s ( +/- 1.98/ 3.95 %); best 6.7e-05s; worst 7.105e-05s; std dev. 1.911e-06 (taking best). -Reference operation time is 6.69956e-05 s (1206 Mflops) with 1 threads. -Challenging best inner round reference (4.31538e-05 s/1 threads) with: subdivision 0.5, 10 leaves, 2.206 bytes/nz, 6.69956e-05 s/0 threads (speedup 0.644128 x), same?n. -New candidate clone performs slowly; discarding it: 100 x 100, type C, 5050 nnz, 50 nnz/r, 14 subms, 10 lsubms, 2.2059 bpnz +3 iterations (1 th.) took 0.09176s; avg 0.03059s ( +/- 34.43/ 17.45 %); best 0.02006s; worst 0.03592s; std dev. 0.007447 (taking best). +Reference operation time is 0.020057 s (4.029 Mflops) with 1 threads. +Challenging best inner round reference (3.69549e-05 s/1 threads) with: subdivision 0.5, 12 leaves, 2.217 bytes/nz, 0.020057 s/0 threads (speedup 0.0018425 x), same?n. +New candidate clone performs slowly; discarding it: 100 x 100, type C, 5050 nnz, 50 nnz/r, 17 subms, 12 lsubms, 2.2170 bpnz # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7069,12 +7080,12 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 99864 bytes +# Cache block size total 524288 bytes, per-thread 26214 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 -# RSB_IO_WANT_EXECUTING_THREADS: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 +# RSB_IO_WANT_EXECUTING_THREADS: 20 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout # RSB_IO_WANT_VERBOSE_ERRORS: stderr @@ -7085,22 +7096,22 @@ # librsb version 1.3.0.2 - 202212201855: Initialization success Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 2.000e-04 s (100.00 %) - analyzed arrays in 8.392e-05 s (41.95 %) - cleaned-up arrays in 8.106e-06 s (4.05 %) - deduplicated arrays in 1.192e-05 s (5.96 %) - sorted arrays in 9.537e-07 s (0.48 %) - shuffled partitions in 6.294e-05 s (31.47 %) - memory allocations took 3.099e-06 s (1.55 %) - leafs setup took 2.146e-06 s (1.07 %) - halfword conversion took 2.694e-05 s (13.47 %) -Built (100 x 100)[0x56006925e350]{C} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 22, symflags:'LS' + converted COO to RSB in 1.799e-01 s (100.00 %) + analyzed arrays in 5.184e-02 s (28.82 %) + cleaned-up arrays in 1.693e-05 s (0.01 %) + deduplicated arrays in 1.621e-05 s (0.01 %) + sorted arrays in 9.537e-07 s (0.00 %) + shuffled partitions in 5.601e-02 s (31.14 %) + memory allocations took 1.383e-05 s (0.01 %) + leafs setup took 1.287e-05 s (0.01 %) + halfword conversion took 7.194e-02 s (40.00 %) +Built (100 x 100)[0x55cecb5fc080]{C} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 28, symflags:'LS' # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7111,11 +7122,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7126,11 +7137,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7140,16 +7151,16 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 0.0002139s; avg 7.129e-05s ( +/- 3.34/ 3.68 %); best 6.89e-05s; worst 7.391e-05s; std dev. 2.051e-06 (taking best). -Reference operation time is 6.8903e-05 s (1173 Mflops) with 1 threads. -Challenging best inner round reference (4.31538e-05 s/1 threads) with: subdivision 1, 22 leaves, 2.295 bytes/nz, 6.8903e-05 s/0 threads (speedup 0.626298 x), same?n. -New candidate clone performs slowly; discarding it: 100 x 100, type C, 5050 nnz, 50 nnz/r, 30 subms, 22 lsubms, 2.2947 bpnz +3 iterations (1 th.) took 0.07159s; avg 0.02386s ( +/- 51.37/ 34.04 %); best 0.01161s; worst 0.03199s; std dev. 0.00882 (taking best). +Reference operation time is 0.011605 s (6.963 Mflops) with 1 threads. +Challenging best inner round reference (3.69549e-05 s/1 threads) with: subdivision 1, 28 leaves, 2.339 bytes/nz, 0.011605 s/0 threads (speedup 0.00318439 x), same?n. +New candidate clone performs slowly; discarding it: 100 x 100, type C, 5050 nnz, 50 nnz/r, 38 subms, 28 lsubms, 2.3390 bpnz # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7160,12 +7171,12 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 2 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 99864 bytes +# Cache block size total 524288 bytes, per-thread 26214 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 -# RSB_IO_WANT_EXECUTING_THREADS: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 +# RSB_IO_WANT_EXECUTING_THREADS: 20 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout # RSB_IO_WANT_VERBOSE_ERRORS: stderr @@ -7176,22 +7187,22 @@ # librsb version 1.3.0.2 - 202212201855: Initialization success Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 3.221e-04 s (100.00 %) - analyzed arrays in 1.659e-04 s (51.52 %) - cleaned-up arrays in 7.868e-06 s (2.44 %) - deduplicated arrays in 1.311e-05 s (4.07 %) + converted COO to RSB in 1.559e-01 s (100.00 %) + analyzed arrays in 5.582e-02 s (35.81 %) + cleaned-up arrays in 1.597e-05 s (0.01 %) + deduplicated arrays in 1.407e-05 s (0.01 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.001e-04 s (31.09 %) - memory allocations took 3.099e-06 s (0.96 %) - leafs setup took 2.861e-06 s (0.89 %) - halfword conversion took 2.813e-05 s (8.73 %) -Built (100 x 100)[0x560069284fc0]{C} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 49, symflags:'LS' -# librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes -# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 + shuffled partitions in 4.404e-02 s (28.25 %) + memory allocations took 1.597e-05 s (0.01 %) + leafs setup took 1.287e-05 s (0.01 %) + halfword conversion took 5.595e-02 s (35.89 %) +Built (100 x 100)[0x55cecb622d20]{C} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 57, symflags:'LS' +# librsb version 1.3.0.2 - 202212201855: Initializing +# Cache block size total 524288 bytes, per-thread 524288 bytes +# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7202,11 +7213,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 2 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7217,11 +7228,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 2 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7231,16 +7242,16 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 2 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 0.0002379s; avg 7.931e-05s ( +/- 5.61/ 5.81 %); best 7.486e-05s; worst 8.392e-05s; std dev. 3.7e-06 (taking best). -Reference operation time is 7.48634e-05 s (1079 Mflops) with 1 threads. -Challenging best inner round reference (4.31538e-05 s/1 threads) with: subdivision 2, 49 leaves, 2.433 bytes/nz, 7.48634e-05 s/0 threads (speedup 0.576433 x), same?n. -New candidate clone performs slowly; discarding it: 100 x 100, type C, 5050 nnz, 50 nnz/r, 67 subms, 49 lsubms, 2.4333 bpnz -# librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes -# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +3 iterations (1 th.) took 0.06763s; avg 0.02254s ( +/- 32.41/ 40.30 %); best 0.01524s; worst 0.03163s; std dev. 0.006809 (taking best). +Reference operation time is 0.0152369 s (5.303 Mflops) with 1 threads. +Challenging best inner round reference (3.69549e-05 s/1 threads) with: subdivision 2, 57 leaves, 2.471 bytes/nz, 0.0152369 s/0 threads (speedup 0.00242536 x), same?n. +New candidate clone performs slowly; discarding it: 100 x 100, type C, 5050 nnz, 50 nnz/r, 78 subms, 57 lsubms, 2.4713 bpnz +# librsb version 1.3.0.2 - 202212201855: Initializing +# Cache block size total 524288 bytes, per-thread 524288 bytes +# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7251,12 +7262,12 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 4 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 99864 bytes +# Cache block size total 524288 bytes, per-thread 26214 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 -# RSB_IO_WANT_EXECUTING_THREADS: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 +# RSB_IO_WANT_EXECUTING_THREADS: 20 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout # RSB_IO_WANT_VERBOSE_ERRORS: stderr @@ -7267,22 +7278,22 @@ # librsb version 1.3.0.2 - 202212201855: Initialization success Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 1.666e-03 s (100.00 %) - analyzed arrays in 5.169e-04 s (31.02 %) - cleaned-up arrays in 7.868e-06 s (0.47 %) - deduplicated arrays in 1.311e-05 s (0.79 %) - sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.919e-04 s (11.52 %) - memory allocations took 9.003e-04 s (54.04 %) - leafs setup took 8.106e-06 s (0.49 %) - halfword conversion took 2.789e-05 s (1.67 %) -Built (100 x 100)[0x560069284fc0]{C} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 102, symflags:'LS' -# librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes -# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 + converted COO to RSB in 1.438e-01 s (100.00 %) + analyzed arrays in 5.578e-02 s (38.78 %) + cleaned-up arrays in 1.717e-05 s (0.01 %) + deduplicated arrays in 1.502e-05 s (0.01 %) + sorted arrays in 9.537e-07 s (0.00 %) + shuffled partitions in 4.404e-02 s (30.62 %) + memory allocations took 2.193e-05 s (0.02 %) + leafs setup took 2.146e-06 s (0.00 %) + halfword conversion took 4.396e-02 s (30.56 %) +Built (100 x 100)[0x55cecb622d20]{C} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 120, symflags:'LS' +# librsb version 1.3.0.2 - 202212201855: Initializing +# Cache block size total 524288 bytes, per-thread 524288 bytes +# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7293,11 +7304,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 4 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7308,11 +7319,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 4 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7322,17 +7333,17 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 4 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 0.000293s; avg 9.767e-05s ( +/- 7.00/ 6.67 %); best 9.084e-05s; worst 0.0001042s; std dev. 5.455e-06 (taking best). -Reference operation time is 9.08375e-05 s (889.5 Mflops) with 1 threads. -Challenging best inner round reference (4.31538e-05 s/1 threads) with: subdivision 4, 102 leaves, 2.642 bytes/nz, 9.08375e-05 s/0 threads (speedup 0.475066 x), same?n. -New candidate clone performs slowly; discarding it: 100 x 100, type C, 5050 nnz, 50 nnz/r, 140 subms, 102 lsubms, 2.6424 bpnz -Best sparse multiply performance with subdivision multiplier of 1: 1872.37 Mflops. +3 iterations (1 th.) took 0.06773s; avg 0.02258s ( +/- 29.12/ 22.53 %); best 0.016s; worst 0.02767s; std dev. 0.004876 (taking best). +Reference operation time is 0.0160038 s (5.049 Mflops) with 1 threads. +Challenging best inner round reference (3.69549e-05 s/1 threads) with: subdivision 4, 120 leaves, 2.726 bytes/nz, 0.0160038 s/0 threads (speedup 0.00230912 x), same?n. +New candidate clone performs slowly; discarding it: 100 x 100, type C, 5050 nnz, 50 nnz/r, 162 subms, 120 lsubms, 2.7255 bpnz +Best sparse multiply performance with subdivision multiplier of 1: 2186.45 Mflops. # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7342,29 +7353,29 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success -Last tuner inner round (1 of 1) took 0.00480914 s (eq. to 1e+02/ 1e+02 old/new op.times), gained local/global speedup 1 x (4.31538e-05 : 4.31538e-05) / 1 x (4.31538e-05 : 4.31538e-05). This is not amortizable ! +Last tuner inner round (1 of 1) took 1.2879 s (eq. to 3e+04/ 3e+04 old/new op.times), gained local/global speedup 1 x (3.69549e-05 : 3.69549e-05) / 1 x (3.69549e-05 : 3.69549e-05). This is not amortizable ! Auto tuning inner round 1 did not find a configuration better than the original. -In 1 tuning rounds (tot. 0.0048s, 0.0029s for constructor, 0 clones) obtained NO speedup (best stays 1872 Mflops). -Second run of RSB Autotuner took 0.00496006 s and estimated a speedup of 1.000000 x (4.315e-05 s -> 4.315e-05 s per op) in same matrix (1 -> 1 lsubm) +In 1 tuning rounds (tot. 1.3s, 0.92s for constructor, 0 clones) obtained NO speedup (best stays 2186 Mflops). +Second run of RSB Autotuner took 1.28802 s and estimated a speedup of 1.000000 x (3.695e-05 s -> 3.695e-05 s per op) in same matrix (1 -> 1 lsubm) #min:1 0 #max:1 0 #sum:100 0 #norm:10 0 #used index storage compared to COO:10504 vs 40400 bytes (26.00%) ; compared to CSR:10504 vs 20604 bytes (50.99%) #%:CONSTRUCTOR_*:SORT SCAN INSERT SCAN+INSERT -%:CONSTRUCTOR_TIMES:lower-100x100-5050nz S N 1 100 100 5050 0.000000 0.000028 0.000075 0.000103 -%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.000103 -%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.000028 -%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.000075 -%:ROW_MAJOR_SORT_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.000000 -%:ROW_MAJOR_SORT_SCALING:lower-100x100-5050nz S N 1 100 100 5050 -nan -%:SORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.000103 +%:CONSTRUCTOR_TIMES:lower-100x100-5050nz S N 1 100 100 5050 0.000001 0.055113 0.111959 0.167072 +%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.167073 +%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.055113 +%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.111959 +%:ROW_MAJOR_SORT_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.000001 +%:ROW_MAJOR_SORT_SCALING:lower-100x100-5050nz S N 1 100 100 5050 1.000 +%:SORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.167072 %:ROW_MAJOR_SORT_TO_MOP:lower-100x100-5050nz S N 1 100 100 5050 0.000 %:UNSORTEDCOO2RSB_SCALING:lower-100x100-5050nz S N 1 100 100 5050 1.00 %:SORTEDCOO2RSB_SCALING:lower-100x100-5050nz S N 1 100 100 5050 1.00 %:RSB_SUBDIVISION_SCALING:lower-100x100-5050nz S N 1 100 100 5050 1.00 %:RSB_SHUFFLE_SCALING:lower-100x100-5050nz S N 1 100 100 5050 1.00 -%:CONSTRUCTOR_SCALING:lower-100x100-5050nz S N 1 100 100 5050 -nan 1.00 1.00 1.00 +%:CONSTRUCTOR_SCALING:lower-100x100-5050nz S N 1 100 100 5050 1.00 1.00 1.00 1.00 #%:SM_COUNTS: Tot HalfwordCsr FullwordCsr HalfwordCoo FullwordCoo %:SM_COUNTS:lower-100x100-5050nz S N 1 100 100 5050 1 1 0 0 0 %:SM_IDXOCCUPATIONRSBVSCOOANDCSR:lower-100x100-5050nz S N 1 100 100 5050 10504 40400 20600 @@ -7373,45 +7384,45 @@ %:SM_MINMAXAVGNNZ:lower-100x100-5050nz S N 1 100 100 5050 5050 5050 5050 # %operation:matrix CONSTRUCTOR[1] SPMV[1] SPMV[1] -%operation:lower-100x100-5050nz 0.000152111 1e+09 1e+09 +%operation:lower-100x100-5050nz 0.223123 1e+09 1e+09 %constructor:matrix SORT[1] SCAN[1] SHUFFLE[1] INSERT[1] -%constructor:lower-100x100-5050nz 0 2.7895e-05 0 7.51019e-05 -# so far, program took 5.969s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.075s/0.000s . +%constructor:lower-100x100-5050nz 9.53674e-07 0.0551131 0 0.111959 +# so far, program took 13.644s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 6.060s/0.000s . getrusage() stats: -ru_maxrss: 26 (maximum resident set size -- MB) -ru_stime : 0.1486s (system CPU time used) -ru_utime : 11.74s (user CPU time used) +ru_maxrss: 7 (maximum resident set size -- MB) +ru_stime : 0.0609s (system CPU time used) +ru_utime : 50.8s (user CPU time used) # multi-type benchmarking (DSCZ) -- now using typecode Z (last was D). -# Cache block size total 4194304 bytes, per-thread 4194304 bytes -# so far, program took 5.969s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.075s/0.000s . +# Cache block size total 524288 bytes, per-thread 524288 bytes +# so far, program took 13.644s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 6.060s/0.000s . # Using 1 threads # Using alpha=1 beta=1 order=cols for rsb_spmv/rsb_spsv/rsb_spmm/rsb_spsm. # will use input matrix flags: RSB_FLAG_USE_HALFWORD_INDICES, RSB_FLAG_SORTED_INPUT, RSB_FLAG_LOWER, RSB_FLAG_QUAD_PARTITIONING, RSB_FLAG_SYMMETRIC, RSB_FLAG_OWN_PARTITIONING_ARRAYS # Using 1 threads Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 2.641e-02 s (100.00 %) - analyzed arrays in 3.826e-03 s (14.49 %) - cleaned-up arrays in 8.106e-06 s (0.03 %) - deduplicated arrays in 1.287e-05 s (0.05 %) - sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.514e-02 s (57.32 %) - memory allocations took 2.861e-06 s (0.01 %) - leafs setup took 9.537e-07 s (0.00 %) - halfword conversion took 7.417e-03 s (28.09 %) -Built (100 x 100)[0x56006925e350]{Z} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x2446196 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LS' -# Constructed matrix (took 0.026s): (100 x 100)[0x56006925e350]{Z} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x2446196 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LS' + converted COO to RSB in 1.714e-01 s (100.00 %) + analyzed arrays in 1.942e-02 s (11.33 %) + cleaned-up arrays in 1.478e-05 s (0.01 %) + deduplicated arrays in 1.287e-05 s (0.01 %) + sorted arrays in 1.192e-06 s (0.00 %) + shuffled partitions in 1.119e-01 s (65.31 %) + memory allocations took 1.526e-05 s (0.01 %) + leafs setup took 5.007e-06 s (0.00 %) + halfword conversion took 3.999e-02 s (23.33 %) +Built (100 x 100)[0x55cecb5fc080]{Z} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x2446196 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LS' +# Constructed matrix (took 0.171s): (100 x 100)[0x55cecb5fc080]{Z} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x2446196 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LS' # matrix consistency check took 0.000s (ok) RSB Sparse Blocks Autotuner invoked requesting max 6 splits and max 6 merges in 1 rounds, threads spec.0 (specify negative values to enable threads tuning). Will autotune matrix: 100 x 100, type Z, 5050 nnz, 50 nnz/r, 4 subms, 3 lsubms, 2.1212 bpnz. Parameters: verbosity:2 mintimes:3 maxtimes:10 mindt:0 maxdt:3 Saved plot to test-tuning-lower-100x100-5050nz--Z-N-1--base.eps # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7422,11 +7433,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7437,11 +7448,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7451,16 +7462,16 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 0.0002179s; avg 7.264e-05s ( +/- 11.71/ 18.16 %); best 6.413e-05s; worst 8.583e-05s; std dev. 9.458e-06 (taking best). -Reference operation time is 6.41346e-05 s (1260 Mflops) with 1 threads. -Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=cols) (max 6 steps, inclusive 3 grace steps) on: 100 x 100, type Z, 5050 nnz, 50 nnz/r, 4 subms, 3 lsubms, 2.1212 bpnz (tpop: 6.413e-05 Mflops: 1259.850) -Merge (3 -> 1 leaves) took w.c.t. of 5.007e-05s, ~4.411e-05s of computing time (of which 2.289e-05s sorting, 9.537e-07s analysis) +3 iterations (1 th.) took 0.07997s; avg 0.02666s ( +/- 55.12/ 65.20 %); best 0.01196s; worst 0.04404s; std dev. 0.01323 (taking best). +Reference operation time is 0.0119641 s (6.754 Mflops) with 1 threads. +Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=cols) (max 6 steps, inclusive 3 grace steps) on: 100 x 100, type Z, 5050 nnz, 50 nnz/r, 4 subms, 3 lsubms, 2.1212 bpnz (tpop: 0.01196 Mflops: 6.754) +Merge (3 -> 1 leaves) took w.c.t. of 0.000134s, ~0.0001099s of computing time (of which 5.913e-05s sorting, 7.868e-06s analysis) # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7471,11 +7482,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7485,14 +7496,14 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 0.0001311s; avg 4.371e-05s ( +/- 1.27/ 0.91 %); best 4.315e-05s; worst 4.411e-05s; std dev. 4.052e-07 (taking best). -Reference operation time is 4.31538e-05 s (1872 Mflops) with 1 threads. +3 iterations (1 th.) took 0.00014s; avg 4.665e-05s ( +/- 8.01/ 16.01 %); best 4.292e-05s; worst 5.412e-05s; std dev. 5.282e-06 (taking best). +Reference operation time is 4.29153e-05 s (1883 Mflops) with 1 threads. # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7502,25 +7513,25 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success -After merge step 1: tpop: 4.315e-05 s ~Mflops: 1872.374 nsubm:1 otn:1 -Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 1.486x: 6.413e-05s -> 4.315e-05s, so taking this instance. +After merge step 1: tpop: 4.292e-05 s ~Mflops: 1882.776 nsubm:1 otn:1 +Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 278.783x: 0.01196s -> 4.292e-05s, so taking this instance. Saved plot to test-tuning-lower-100x100-5050nz--Z-N-1--mv-tuned_merge1_1x1th.eps Merged all the matrix leaves: no reason to continue merging. -A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.003919s (of which 5.198e-05s partitioning, 0.003546s I/O); computing times: 4.411e-05s in par. loops, 2.289e-05s sorting, 9.537e-07s analyzing) -Total merge + benchmarking process took 0.003919s, equivalent to 90.8/61.1 new/old ops (9.108e-05s for 2 clones -- as 2.1/1.4 ops, or 1.1/0.7 ops per clone), SPEEDUP of 1.486x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 1.486x (6.413e-05s -> 4.315e-05s), will amortize in 186.8 ops by saving 2.098e-05s per op. -In 1 tuning rounds (tot. 0.0042s, 9.1e-05s for constructor, 2 clones) obtained a SPEEDUP of 48.6% (1.486x) (from 1260 to 1872 Mflops). Employed 0.0094s for I/O of matrix plots. +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.2324s (of which 0.0001402s partitioning, 0.1515s I/O); computing times: 0.0001099s in par. loops, 5.913e-05s sorting, 7.868e-06s analyzing) +Total merge + benchmarking process took 0.2324s, equivalent to 5415.6/19.4 new/old ops (0.1557s for 2 clones -- as 3629.2/13.0 ops, or 1814.6/6.5 ops per clone), SPEEDUP of 278.783x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 278.783x (0.01196s -> 4.292e-05s), will amortize in 19.5 ops by saving 0.01192s per op. +In 1 tuning rounds (tot. 0.39s, 0.16s for constructor, 2 clones) obtained a SPEEDUP of 27778.3% (278.8x) (from 6.754 to 1883 Mflops). Employed 0.15s for I/O of matrix plots. #pr: updating sample at index 4 (3^th of 4), 0^th touch for (0,0,0,0,0,3,0). -First run of RSB Autotuner took 0.0137711 s (6.413e-05 s -> 4.315e-05 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.54043 s (1.196e-02 s -> 4.292e-05 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). RSB Sparse Blocks Autotuner invoked requesting max 0 splits and max 0 merges in 1 rounds, auto threads spec. Will autotune matrix: 100 x 100, type Z, 5050 nnz, 50 nnz/r, 1 subms, 1 lsubms, 2.0800 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:10 # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7531,11 +7542,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7546,13 +7557,13 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success Started tuning inner round: will search for an optimal matrix instance. -Starting with requested 0 threads ; current default 1 ; at most 42. +Starting with requested 0 threads ; current default 1 ; at most 20. # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7563,11 +7574,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7577,27 +7588,27 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 0.0001328s; avg 4.427e-05s ( +/- 3.05/ 3.95 %); best 4.292e-05s; worst 4.601e-05s; std dev. 1.296e-06 (taking best). -Reference operation time is 4.29153e-05 s (1883 Mflops) with 1 threads. +3 iterations (1 th.) took 0.000155s; avg 5.166e-05s ( +/- 15.08/ 22.31 %); best 4.387e-05s; worst 6.318e-05s; std dev. 8.315e-06 (taking best). +Reference operation time is 4.3869e-05 s (1842 Mflops) with 1 threads. Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 7.200e-05 s (100.00 %) - analyzed arrays in 2.193e-05 s (30.46 %) - cleaned-up arrays in 8.106e-06 s (11.26 %) - deduplicated arrays in 1.311e-05 s (18.21 %) - sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 2.408e-05 s (33.44 %) - memory allocations took 1.907e-06 s (2.65 %) - leafs setup took 0.000e+00 s (0.00 %) - halfword conversion took 2.861e-06 s (3.97 %) -Built (100 x 100)[0x56006925e230]{Z} @ (0(0..100),0(0..100)) (5050 nnz, 50 nnz/r) flags 0x42644094 (coo:0, csr:1, hw:0, ic:1, fi:0), storage: 1, subm: 1, symflags:'LS' -Starting autotuning stage, with subdivision of 1 (current threads=1, requested threads=0, max threads = 42). -# librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes -# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 + converted COO to RSB in 1.030e-01 s (100.00 %) + analyzed arrays in 3.499e-02 s (33.96 %) + cleaned-up arrays in 1.502e-05 s (0.01 %) + deduplicated arrays in 1.287e-05 s (0.01 %) + sorted arrays in 9.537e-07 s (0.00 %) + shuffled partitions in 6.798e-02 s (65.98 %) + memory allocations took 8.345e-06 s (0.01 %) + leafs setup took 6.914e-06 s (0.01 %) + halfword conversion took 1.597e-05 s (0.02 %) +Built (100 x 100)[0x55cecb5fbf60]{Z} @ (0(0..100),0(0..100)) (5050 nnz, 50 nnz/r) flags 0x42644094 (coo:0, csr:1, hw:0, ic:1, fi:0), storage: 1, subm: 1, symflags:'LS' +Starting autotuning stage, with subdivision of 1 (current threads=1, requested threads=0, max threads = 20). +# librsb version 1.3.0.2 - 202212201855: Initializing +# Cache block size total 524288 bytes, per-thread 524288 bytes +# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7608,12 +7619,12 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 0.25 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 99864 bytes +# Cache block size total 524288 bytes, per-thread 26214 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 -# RSB_IO_WANT_EXECUTING_THREADS: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 +# RSB_IO_WANT_EXECUTING_THREADS: 20 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout # RSB_IO_WANT_VERBOSE_ERRORS: stderr @@ -7624,22 +7635,22 @@ # librsb version 1.3.0.2 - 202212201855: Initialization success Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 1.409e-04 s (100.00 %) - analyzed arrays in 4.101e-05 s (29.10 %) - cleaned-up arrays in 7.868e-06 s (5.58 %) - deduplicated arrays in 1.216e-05 s (8.63 %) - sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 5.102e-05 s (36.21 %) - memory allocations took 1.907e-06 s (1.35 %) - leafs setup took 0.000e+00 s (0.00 %) - halfword conversion took 2.599e-05 s (18.44 %) -Built (100 x 100)[0x56006925e350]{Z} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 6, symflags:'LS' -# librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes -# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 + converted COO to RSB in 1.434e-01 s (100.00 %) + analyzed arrays in 3.544e-02 s (24.71 %) + cleaned-up arrays in 1.407e-05 s (0.01 %) + deduplicated arrays in 1.407e-05 s (0.01 %) + sorted arrays in 9.537e-07 s (0.00 %) + shuffled partitions in 5.646e-02 s (39.37 %) + memory allocations took 1.097e-05 s (0.01 %) + leafs setup took 6.914e-06 s (0.00 %) + halfword conversion took 5.146e-02 s (35.88 %) +Built (100 x 100)[0x55cecb5fc080]{Z} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 8, symflags:'LS' +# librsb version 1.3.0.2 - 202212201855: Initializing +# Cache block size total 524288 bytes, per-thread 524288 bytes +# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7650,11 +7661,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 0.25 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7665,11 +7676,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 0.25 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7679,16 +7690,16 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 0.25 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 0.0002069s; avg 6.898e-05s ( +/- 5.65/ 10.25 %); best 6.509e-05s; worst 7.606e-05s; std dev. 5.01e-06 (taking best). -Reference operation time is 6.50883e-05 s (1241 Mflops) with 1 threads. -Challenging best inner round reference (4.29153e-05 s/1 threads) with: subdivision 0.25, 6 leaves, 2.163 bytes/nz, 6.50883e-05 s/0 threads (speedup 0.659341 x), same?n. -New candidate clone performs slowly; discarding it: 100 x 100, type Z, 5050 nnz, 50 nnz/r, 8 subms, 6 lsubms, 2.1632 bpnz -# librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes -# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +3 iterations (1 th.) took 0.07175s; avg 0.02392s ( +/- 15.68/ 15.28 %); best 0.02017s; worst 0.02757s; std dev. 0.003024 (taking best). +Reference operation time is 0.0201671 s (4.007 Mflops) with 1 threads. +Challenging best inner round reference (4.3869e-05 s/1 threads) with: subdivision 0.25, 8 leaves, 2.185 bytes/nz, 0.0201671 s/0 threads (speedup 0.00217528 x), same?n. +New candidate clone performs slowly; discarding it: 100 x 100, type Z, 5050 nnz, 50 nnz/r, 11 subms, 8 lsubms, 2.1846 bpnz +# librsb version 1.3.0.2 - 202212201855: Initializing +# Cache block size total 524288 bytes, per-thread 524288 bytes +# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7699,12 +7710,12 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 0.5 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 99864 bytes +# Cache block size total 524288 bytes, per-thread 26214 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 -# RSB_IO_WANT_EXECUTING_THREADS: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 +# RSB_IO_WANT_EXECUTING_THREADS: 20 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout # RSB_IO_WANT_VERBOSE_ERRORS: stderr @@ -7715,22 +7726,22 @@ # librsb version 1.3.0.2 - 202212201855: Initialization success Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 1.860e-04 s (100.00 %) - analyzed arrays in 6.604e-05 s (35.51 %) - cleaned-up arrays in 8.106e-06 s (4.36 %) - deduplicated arrays in 1.287e-05 s (6.92 %) + converted COO to RSB in 1.836e-01 s (100.00 %) + analyzed arrays in 6.758e-02 s (36.80 %) + cleaned-up arrays in 1.597e-05 s (0.01 %) + deduplicated arrays in 1.502e-05 s (0.01 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 6.700e-05 s (36.03 %) - memory allocations took 3.815e-06 s (2.05 %) - leafs setup took 2.146e-06 s (1.15 %) - halfword conversion took 2.599e-05 s (13.97 %) -Built (100 x 100)[0x56006925e350]{Z} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 16, symflags:'LS' -# librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes -# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 + shuffled partitions in 4.407e-02 s (24.00 %) + memory allocations took 1.407e-05 s (0.01 %) + leafs setup took 9.060e-06 s (0.00 %) + halfword conversion took 7.191e-02 s (39.16 %) +Built (100 x 100)[0x55cecb5fc080]{Z} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 19, symflags:'LS' +# librsb version 1.3.0.2 - 202212201855: Initializing +# Cache block size total 524288 bytes, per-thread 524288 bytes +# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7741,11 +7752,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 0.5 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7756,11 +7767,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 0.5 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7770,16 +7781,16 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 0.5 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 0.0002289s; avg 7.629e-05s ( +/- 4.38/ 7.50 %); best 7.296e-05s; worst 8.202e-05s; std dev. 4.065e-06 (taking best). -Reference operation time is 7.29561e-05 s (1108 Mflops) with 1 threads. -Challenging best inner round reference (4.29153e-05 s/1 threads) with: subdivision 0.5, 16 leaves, 2.25 bytes/nz, 7.29561e-05 s/0 threads (speedup 0.588235 x), same?n. -New candidate clone performs slowly; discarding it: 100 x 100, type Z, 5050 nnz, 50 nnz/r, 22 subms, 16 lsubms, 2.2503 bpnz +3 iterations (1 th.) took 0.07202s; avg 0.02401s ( +/- 18.02/ 18.93 %); best 0.01968s; worst 0.02855s; std dev. 0.003625 (taking best). +Reference operation time is 0.01968 s (4.106 Mflops) with 1 threads. +Challenging best inner round reference (4.3869e-05 s/1 threads) with: subdivision 0.5, 19 leaves, 2.272 bytes/nz, 0.01968 s/0 threads (speedup 0.00222911 x), same?n. +New candidate clone performs slowly; discarding it: 100 x 100, type Z, 5050 nnz, 50 nnz/r, 26 subms, 19 lsubms, 2.2725 bpnz # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7790,12 +7801,12 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 99864 bytes +# Cache block size total 524288 bytes, per-thread 26214 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 -# RSB_IO_WANT_EXECUTING_THREADS: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 +# RSB_IO_WANT_EXECUTING_THREADS: 20 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout # RSB_IO_WANT_VERBOSE_ERRORS: stderr @@ -7806,22 +7817,22 @@ # librsb version 1.3.0.2 - 202212201855: Initialization success Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 2.851e-04 s (100.00 %) - analyzed arrays in 1.330e-04 s (46.66 %) - cleaned-up arrays in 8.106e-06 s (2.84 %) - deduplicated arrays in 1.192e-05 s (4.18 %) - sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 9.704e-05 s (34.03 %) - memory allocations took 4.053e-06 s (1.42 %) - leafs setup took 2.861e-06 s (1.00 %) - halfword conversion took 2.813e-05 s (9.87 %) -Built (100 x 100)[0x56006925e350]{Z} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 36, symflags:'LS' + converted COO to RSB in 1.614e-01 s (100.00 %) + analyzed arrays in 6.407e-02 s (39.70 %) + cleaned-up arrays in 1.502e-05 s (0.01 %) + deduplicated arrays in 1.311e-05 s (0.01 %) + sorted arrays in 9.537e-07 s (0.00 %) + shuffled partitions in 4.963e-02 s (30.75 %) + memory allocations took 4.482e-05 s (0.03 %) + leafs setup took 1.311e-05 s (0.01 %) + halfword conversion took 4.761e-02 s (29.50 %) +Built (100 x 100)[0x55cecb64a470]{Z} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 39, symflags:'LS' # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7832,11 +7843,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7847,11 +7858,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7861,16 +7872,16 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 0.0002511s; avg 8.368e-05s ( +/- 4.56/ 7.69 %); best 7.987e-05s; worst 9.012e-05s; std dev. 4.578e-06 (taking best). -Reference operation time is 7.98702e-05 s (1012 Mflops) with 1 threads. -Challenging best inner round reference (4.29153e-05 s/1 threads) with: subdivision 1, 36 leaves, 2.383 bytes/nz, 7.98702e-05 s/0 threads (speedup 0.537313 x), same?n. -New candidate clone performs slowly; discarding it: 100 x 100, type Z, 5050 nnz, 50 nnz/r, 50 subms, 36 lsubms, 2.3834 bpnz +3 iterations (1 th.) took 0.06212s; avg 0.02071s ( +/- 8.21/ 15.89 %); best 0.01901s; worst 0.024s; std dev. 0.002328 (taking best). +Reference operation time is 0.0190079 s (4.251 Mflops) with 1 threads. +Challenging best inner round reference (4.3869e-05 s/1 threads) with: subdivision 1, 39 leaves, 2.387 bytes/nz, 0.0190079 s/0 threads (speedup 0.00230793 x), same?n. +New candidate clone performs slowly; discarding it: 100 x 100, type Z, 5050 nnz, 50 nnz/r, 54 subms, 39 lsubms, 2.3865 bpnz # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7881,12 +7892,12 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 2 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 99864 bytes +# Cache block size total 524288 bytes, per-thread 26214 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 -# RSB_IO_WANT_EXECUTING_THREADS: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 +# RSB_IO_WANT_EXECUTING_THREADS: 20 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout # RSB_IO_WANT_VERBOSE_ERRORS: stderr @@ -7897,22 +7908,22 @@ # librsb version 1.3.0.2 - 202212201855: Initialization success Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 4.199e-04 s (100.00 %) - analyzed arrays in 1.919e-04 s (45.71 %) - cleaned-up arrays in 8.106e-06 s (1.93 %) - deduplicated arrays in 1.311e-05 s (3.12 %) + converted COO to RSB in 1.841e-01 s (100.00 %) + analyzed arrays in 7.164e-02 s (38.90 %) + cleaned-up arrays in 1.717e-05 s (0.01 %) + deduplicated arrays in 1.597e-05 s (0.01 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.709e-04 s (40.72 %) - memory allocations took 3.815e-06 s (0.91 %) - leafs setup took 5.007e-06 s (1.19 %) - halfword conversion took 2.599e-05 s (6.19 %) -Built (100 x 100)[0x5600692ac710]{Z} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 74, symflags:'LS' -# librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes -# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 + shuffled partitions in 6.339e-02 s (34.42 %) + memory allocations took 2.980e-05 s (0.02 %) + leafs setup took 2.003e-05 s (0.01 %) + halfword conversion took 4.904e-02 s (26.63 %) +Built (100 x 100)[0x55cecb64a470]{Z} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 84, symflags:'LS' +# librsb version 1.3.0.2 - 202212201855: Initializing +# Cache block size total 524288 bytes, per-thread 524288 bytes +# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7923,11 +7934,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 2 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7938,11 +7949,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 2 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7952,16 +7963,16 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 2 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 0.000282s; avg 9.402e-05s ( +/- 4.40/ 7.52 %); best 8.988e-05s; worst 0.0001011s; std dev. 5.025e-06 (taking best). -Reference operation time is 8.98838e-05 s (898.9 Mflops) with 1 threads. -Challenging best inner round reference (4.29153e-05 s/1 threads) with: subdivision 2, 74 leaves, 2.531 bytes/nz, 8.98838e-05 s/0 threads (speedup 0.477454 x), same?n. -New candidate clone performs slowly; discarding it: 100 x 100, type Z, 5050 nnz, 50 nnz/r, 102 subms, 74 lsubms, 2.5307 bpnz -# librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes -# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +3 iterations (1 th.) took 0.07944s; avg 0.02648s ( +/- 12.42/ 6.30 %); best 0.02319s; worst 0.02815s; std dev. 0.002326 (taking best). +Reference operation time is 0.0231919 s (3.484 Mflops) with 1 threads. +Challenging best inner round reference (4.3869e-05 s/1 threads) with: subdivision 2, 84 leaves, 2.581 bytes/nz, 0.0231919 s/0 threads (speedup 0.00189156 x), same?n. +New candidate clone performs slowly; discarding it: 100 x 100, type Z, 5050 nnz, 50 nnz/r, 114 subms, 84 lsubms, 2.5806 bpnz +# librsb version 1.3.0.2 - 202212201855: Initializing +# Cache block size total 524288 bytes, per-thread 524288 bytes +# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -7972,12 +7983,12 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 4 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 99864 bytes +# Cache block size total 524288 bytes, per-thread 26214 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 -# RSB_IO_WANT_EXECUTING_THREADS: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 +# RSB_IO_WANT_EXECUTING_THREADS: 20 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout # RSB_IO_WANT_VERBOSE_ERRORS: stderr @@ -7988,22 +7999,22 @@ # librsb version 1.3.0.2 - 202212201855: Initialization success Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 1.158e-03 s (100.00 %) - analyzed arrays in 2.420e-04 s (20.90 %) - cleaned-up arrays in 8.106e-06 s (0.70 %) - deduplicated arrays in 1.287e-05 s (1.11 %) + converted COO to RSB in 1.714e-01 s (100.00 %) + analyzed arrays in 6.733e-02 s (39.28 %) + cleaned-up arrays in 1.597e-05 s (0.01 %) + deduplicated arrays in 1.407e-05 s (0.01 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 8.531e-04 s (73.67 %) - memory allocations took 7.153e-06 s (0.62 %) - leafs setup took 6.914e-06 s (0.60 %) - halfword conversion took 2.694e-05 s (2.33 %) -Built (100 x 100)[0x5600692ac710]{Z} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 136, symflags:'LS' -# librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes -# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 + shuffled partitions in 5.201e-02 s (30.35 %) + memory allocations took 3.099e-05 s (0.02 %) + leafs setup took 2.408e-05 s (0.01 %) + halfword conversion took 5.197e-02 s (30.32 %) +Built (100 x 100)[0x55cecb64a470]{Z} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 120, symflags:'LS' +# librsb version 1.3.0.2 - 202212201855: Initializing +# Cache block size total 524288 bytes, per-thread 524288 bytes +# RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -8014,11 +8025,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 4 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -8029,11 +8040,11 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 4 # librsb version 1.3.0.2 - 202212201855: Initialization success # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -8043,17 +8054,17 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 4 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 0.0003319s; avg 0.0001106s ( +/- 2.37/ 3.88 %); best 0.000108s; worst 0.0001149s; std dev. 3.059e-06 (taking best). -Reference operation time is 0.000108004 s (748.1 Mflops) with 1 threads. -Challenging best inner round reference (4.29153e-05 s/1 threads) with: subdivision 4, 136 leaves, 2.776 bytes/nz, 0.000108004 s/0 threads (speedup 0.397351 x), same?n. -New candidate clone performs slowly; discarding it: 100 x 100, type Z, 5050 nnz, 50 nnz/r, 186 subms, 136 lsubms, 2.7762 bpnz -Best sparse multiply performance with subdivision multiplier of 1: 1882.78 Mflops. +3 iterations (1 th.) took 0.06392s; avg 0.02131s ( +/- 42.97/ 30.94 %); best 0.01215s; worst 0.0279s; std dev. 0.006679 (taking best). +Reference operation time is 0.0121522 s (6.649 Mflops) with 1 threads. +Challenging best inner round reference (4.3869e-05 s/1 threads) with: subdivision 4, 120 leaves, 2.726 bytes/nz, 0.0121522 s/0 threads (speedup 0.00360997 x), same?n. +New candidate clone performs slowly; discarding it: 100 x 100, type Z, 5050 nnz, 50 nnz/r, 162 subms, 120 lsubms, 2.7255 bpnz +Best sparse multiply performance with subdivision multiplier of 1: 1841.85 Mflops. # librsb version 1.3.0.2 - 202212201855: Initializing -# Cache block size total 4194304 bytes, per-thread 4194304 bytes +# Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset -# min_leaf_matrix_bytes : 32768 -# avg_leaf_matrix_bytes : 8388608 -# rsb_g_threads: 42 +# min_leaf_matrix_bytes : 65536 +# avg_leaf_matrix_bytes : 1048576 +# rsb_g_threads: 20 # RSB_IO_WANT_EXECUTING_THREADS: 1 # RSB_WANT_RSBPP: 1 # RSB_IO_WANT_OUTPUT_STREAM: stdout @@ -8063,29 +8074,29 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success -Last tuner inner round (1 of 1) took 0.0050571 s (eq. to 1e+02/ 1e+02 old/new op.times), gained local/global speedup 1 x (4.29153e-05 : 4.29153e-05) / 1 x (4.29153e-05 : 4.29153e-05). This is not amortizable ! +Last tuner inner round (1 of 1) took 1.29973 s (eq. to 3e+04/ 3e+04 old/new op.times), gained local/global speedup 1 x (4.3869e-05 : 4.3869e-05) / 1 x (4.3869e-05 : 4.3869e-05). This is not amortizable ! Auto tuning inner round 1 did not find a configuration better than the original. -In 1 tuning rounds (tot. 0.0051s, 0.0027s for constructor, 0 clones) obtained NO speedup (best stays 1883 Mflops). -Second run of RSB Autotuner took 0.00508499 s and estimated a speedup of 1.000000 x (4.292e-05 s -> 4.292e-05 s per op) in same matrix (1 -> 1 lsubm) +In 1 tuning rounds (tot. 1.3s, 0.95s for constructor, 0 clones) obtained NO speedup (best stays 1842 Mflops). +Second run of RSB Autotuner took 1.29987 s and estimated a speedup of 1.000000 x (4.387e-05 s -> 4.387e-05 s per op) in same matrix (1 -> 1 lsubm) #min:1 0 #max:1 0 #sum:100 0 #norm:10 0 #used index storage compared to COO:10504 vs 40400 bytes (26.00%) ; compared to CSR:10504 vs 20604 bytes (50.99%) #%:CONSTRUCTOR_*:SORT SCAN INSERT SCAN+INSERT -%:CONSTRUCTOR_TIMES:lower-100x100-5050nz S N 1 100 100 5050 0.000000 0.003826 0.015136 0.018962 -%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.018962 -%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.003826 -%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.015136 -%:ROW_MAJOR_SORT_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.000000 -%:ROW_MAJOR_SORT_SCALING:lower-100x100-5050nz S N 1 100 100 5050 -nan -%:SORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.018962 +%:CONSTRUCTOR_TIMES:lower-100x100-5050nz S N 1 100 100 5050 0.000001 0.019418 0.111929 0.131347 +%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.131348 +%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.019418 +%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.111929 +%:ROW_MAJOR_SORT_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.000001 +%:ROW_MAJOR_SORT_SCALING:lower-100x100-5050nz S N 1 100 100 5050 1.000 +%:SORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.131347 %:ROW_MAJOR_SORT_TO_MOP:lower-100x100-5050nz S N 1 100 100 5050 0.000 %:UNSORTEDCOO2RSB_SCALING:lower-100x100-5050nz S N 1 100 100 5050 1.00 %:SORTEDCOO2RSB_SCALING:lower-100x100-5050nz S N 1 100 100 5050 1.00 %:RSB_SUBDIVISION_SCALING:lower-100x100-5050nz S N 1 100 100 5050 1.00 %:RSB_SHUFFLE_SCALING:lower-100x100-5050nz S N 1 100 100 5050 1.00 -%:CONSTRUCTOR_SCALING:lower-100x100-5050nz S N 1 100 100 5050 -nan 1.00 1.00 1.00 +%:CONSTRUCTOR_SCALING:lower-100x100-5050nz S N 1 100 100 5050 1.00 1.00 1.00 1.00 #%:SM_COUNTS: Tot HalfwordCsr FullwordCsr HalfwordCoo FullwordCoo %:SM_COUNTS:lower-100x100-5050nz S N 1 100 100 5050 1 1 0 0 0 %:SM_IDXOCCUPATIONRSBVSCOOANDCSR:lower-100x100-5050nz S N 1 100 100 5050 10504 40400 20600 @@ -8094,68 +8105,68 @@ %:SM_MINMAXAVGNNZ:lower-100x100-5050nz S N 1 100 100 5050 5050 5050 5050 # %operation:matrix CONSTRUCTOR[1] SPMV[1] SPMV[1] -%operation:lower-100x100-5050nz 0.026406 1e+09 1e+09 +%operation:lower-100x100-5050nz 0.171392 1e+09 1e+09 %constructor:matrix SORT[1] SCAN[1] SHUFFLE[1] INSERT[1] -%constructor:lower-100x100-5050nz 0 0.0038259 0 0.015136 -# so far, program took 6.029s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.094s/0.000s . +%constructor:lower-100x100-5050nz 1.19209e-06 0.019418 0 0.111929 +# so far, program took 15.784s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 7.900s/0.000s . getrusage() stats: -ru_maxrss: 26 (maximum resident set size -- MB) -ru_stime : 0.1486s (system CPU time used) -ru_utime : 14.11s (user CPU time used) +ru_maxrss: 7 (maximum resident set size -- MB) +ru_stime : 0.06826s (system CPU time used) +ru_utime : 66.73s (user CPU time used) # benchmarking terminated --- finalizing run. # ====== BEGIN Total summary record. #pr: ======== All results (not limiting) #pr: Dump from a base of 4 samples (of max 4) ordered by (1,1,1,1,1,4,1) = (filename x cores x incX x incY x nrhs x typecode x transA). pr: BESTCODE MTX NR NC NNZ NRHS TYPE SYM TRANS NT AT-NT AT-MKL-NT BPNZ AT-BPNZ NSUBM AT-SUBM RSBBEST-MFLOPS OPTIME MKL-OPTIME AT-OPTIME AT-MKL-OPTIME AT-TIME RWminBW-GBps CB-bpf AT-MS CMFLOPS -pr: 1:R_R lower-100x100-5050nz 100 100 5050 1 D S N 1 1 0 2.1212 2.0800 3 1 1694.50 2.789e-05 0.000e+00 1.192e-05 0.000e+00 8.506e-03 4.47e+00 2.60e+00 1 2.02e-02 -pr: 2:R_R lower-100x100-5050nz 100 100 5050 1 S S N 1 1 0 2.1212 2.0800 3 1 1694.50 3.004e-05 0.000e+00 1.192e-05 0.000e+00 4.451e-02 2.68e+00 1.56e+00 1 2.02e-02 -pr: 3:R_R lower-100x100-5050nz 100 100 5050 1 C S N 1 1 0 2.1212 2.0800 3 1 1872.37 6.294e-05 0.000e+00 4.315e-05 0.000e+00 9.797e-03 1.24e+00 6.50e-01 1 8.08e-02 -pr: 4:R_R lower-100x100-5050nz 100 100 5050 1 Z S N 1 1 0 2.1212 2.0800 3 1 1872.37 6.413e-05 0.000e+00 4.315e-05 0.000e+00 1.377e-02 2.23e+00 1.17e+00 1 8.08e-02 +pr: 1:R_R lower-100x100-5050nz 100 100 5050 1 D S N 1 1 0 2.1212 2.0800 3 1 1460.77 2.397e-02 0.000e+00 1.383e-05 0.000e+00 6.236e-01 3.85e+00 2.60e+00 1 2.02e-02 +pr: 2:R_R lower-100x100-5050nz 100 100 5050 1 S S N 1 1 0 2.1212 2.0800 3 1 1460.77 2.400e-02 0.000e+00 1.383e-05 0.000e+00 8.603e-01 2.31e+00 1.56e+00 1 2.02e-02 +pr: 3:R_R lower-100x100-5050nz 100 100 5050 1 C S N 1 1 0 2.1212 2.0800 3 1 2244.37 2.009e-02 0.000e+00 3.600e-05 0.000e+00 5.440e-01 1.48e+00 6.50e-01 1 8.08e-02 +pr: 4:R_R lower-100x100-5050nz 100 100 5050 1 Z S N 1 1 0 2.1212 2.0800 3 1 1882.78 1.196e-02 0.000e+00 4.292e-05 0.000e+00 5.404e-01 2.24e+00 1.17e+00 1 8.08e-02 #pr: below, we define 'successful' autotuning when speedup of 1.010000x is exceeded, and 'tuned' results even the ones which are same as untuned #pr: rsb autotuning was successful in 4 cases (100.00 %) and unsuccessful in 0 cases (0.00 %) -#pr: (in succ. cases rsb autotuning gave avg. 95.1 % faster, avg. sp. ratio 1.951x, max sp. ratio 2.520x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 1248.3/227.0/3733.4/4993.0 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 539.2/155.6/1481.5/2156.8 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 1035.0, min. 495.1, max. 2456.2 ops) +#pr: (in succ. cases rsb autotuning gave avg. 107558.7 % faster, avg. sp. ratio 1076.587x, max sp. ratio 1735.862x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 33752.4/12592.9/62213.4/135009.7 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 33.5/ 26.0/ 45.2/134.1 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 33.6, min. 26.0, max. 45.3 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 1683/ 1683/ 1683) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 5050/ 5050/ 5050) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 15150/ 6733/ 26933) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 45450/ 20200/ 80800) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 2.121/ 2.121/ 2.121) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 2.613/ 1.217/ 4.404,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 10.610/ 1.235/ 4.471,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 2.434/ 1.458/ 3.797,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 9.882/ 1.481/ 3.855,GBps) #pr: (avg/min/max code balance (bytes read at least once per flop) 1.495/ 0.650/ 2.599) #pr: (avg/min/max (avg) bytes per nnz after successful tuning were 2.080/ 2.080/ 2.080) #pr: (matrix has been subdivided more/less/same in resp. 0 / 4 /0 cases) #pr: (matrix has used more/less/same threads in resp. 0 / 0 /4 cases) #pr: no unsuccessful rsb autotuning attempt (according to 1.01x threshold) -#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.02 s, min 0.01 s, max 0.04 s, tot 0.08 s (4 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.02 s, min 0.01 s, max 0.04 s, tot 0.08 s (4 samples) -#pr: best tun. rsb canon. mflops were: on avg. 1.783e+03, min 1.694e+03, max 1.872e+03 (4 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 9.850e+02, min 6.724e+02, max 1.284e+03 (4 samples) -#pr: best tun. rsb operation time was: on avg. 2.754e-05s, min 1.192e-05s, max 4.315e-05s, tot 1.101e-04s (4 samples) -#pr: ref. unt. rsb operation time was: on avg. 4.625e-05s, min 2.789e-05s, max 6.413e-05s, tot 1.850e-04s (4 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 4.703e+00 1.702e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 4.213e+00 -#pr: Record collection took 0.20 s. +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.64 s, min 0.54 s, max 0.86 s, tot 2.57 s (4 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.64 s, min 0.54 s, max 0.86 s, tot 2.57 s (4 samples) +#pr: best tun. rsb canon. mflops were: on avg. 1.762e+03, min 1.461e+03, max 2.244e+03 (4 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 3.115e+00, min 8.415e-01, max 6.754e+00 (4 samples) +#pr: best tun. rsb operation time was: on avg. 2.664e-05s, min 1.383e-05s, max 4.292e-05s, tot 1.066e-04s (4 samples) +#pr: ref. unt. rsb operation time was: on avg. 2.001e-02s, min 1.196e-02s, max 2.400e-02s, tot 8.003e-02s (4 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.315e+00 3.424e+00 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.373e+00 +#pr: Record collection took 7.81 s. #pr: Record comprises 40 memory benchmark samples (prepend RSB_PR_MBW=1 to dump this). -#pr: Record comprises 99 environment variables in 4312 bytes (prepend RSB_PR_ENV=1 to dump this). +#pr: Record comprises 99 environment variables in 4367 bytes (prepend RSB_PR_ENV=1 to dump this). # ====== END Total summary record. #pr: ======== Saved a performance record of 4 samples to test.rpr # Removing the temporary record file test.rpr.tmp. -# terminating run at 1749955900 (after 6.0s of w.c.t.) +# terminating run at 1715548826 (after 15.7s of w.c.t.) + ls -ltr test-tuning-lower-100x100-5050nz--C-N-1--base.eps test-tuning-lower-100x100-5050nz--C-N-1--mv-tuned_merge1_1x1th.eps test-tuning-lower-100x100-5050nz--D-N-1--base.eps test-tuning-lower-100x100-5050nz--D-N-1--mv-tuned_merge1_1x1th.eps test-tuning-lower-100x100-5050nz--S-N-1--base.eps test-tuning-lower-100x100-5050nz--S-N-1--mv-tuned_merge1_1x1th.eps test-tuning-lower-100x100-5050nz--Z-N-1--base.eps test-tuning-lower-100x100-5050nz--Z-N-1--mv-tuned_merge1_1x1th.eps --rw-r--r-- 1 pbuilder1 pbuilder1 85634 Jun 14 14:51 test-tuning-lower-100x100-5050nz--D-N-1--base.eps --rw-r--r-- 1 pbuilder1 pbuilder1 84556 Jun 14 14:51 test-tuning-lower-100x100-5050nz--D-N-1--mv-tuned_merge1_1x1th.eps --rw-r--r-- 1 pbuilder1 pbuilder1 85632 Jun 14 14:51 test-tuning-lower-100x100-5050nz--S-N-1--base.eps --rw-r--r-- 1 pbuilder1 pbuilder1 84556 Jun 14 14:51 test-tuning-lower-100x100-5050nz--S-N-1--mv-tuned_merge1_1x1th.eps --rw-r--r-- 1 pbuilder1 pbuilder1 85634 Jun 14 14:51 test-tuning-lower-100x100-5050nz--C-N-1--base.eps --rw-r--r-- 1 pbuilder1 pbuilder1 84556 Jun 14 14:51 test-tuning-lower-100x100-5050nz--C-N-1--mv-tuned_merge1_1x1th.eps --rw-r--r-- 1 pbuilder1 pbuilder1 85634 Jun 14 14:51 test-tuning-lower-100x100-5050nz--Z-N-1--base.eps --rw-r--r-- 1 pbuilder1 pbuilder1 84556 Jun 14 14:51 test-tuning-lower-100x100-5050nz--Z-N-1--mv-tuned_merge1_1x1th.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 85642 May 13 11:20 test-tuning-lower-100x100-5050nz--D-N-1--base.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 84563 May 13 11:20 test-tuning-lower-100x100-5050nz--D-N-1--mv-tuned_merge1_1x1th.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 85641 May 13 11:20 test-tuning-lower-100x100-5050nz--S-N-1--base.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 84564 May 13 11:20 test-tuning-lower-100x100-5050nz--S-N-1--mv-tuned_merge1_1x1th.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 85642 May 13 11:20 test-tuning-lower-100x100-5050nz--C-N-1--base.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 84564 May 13 11:20 test-tuning-lower-100x100-5050nz--C-N-1--mv-tuned_merge1_1x1th.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 85642 May 13 11:20 test-tuning-lower-100x100-5050nz--Z-N-1--base.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 84564 May 13 11:20 test-tuning-lower-100x100-5050nz--Z-N-1--mv-tuned_merge1_1x1th.eps + rsbench --read-performance-record test.rpr + ls -ltr test.txt --rw-r--r-- 1 pbuilder1 pbuilder1 4092 Jun 14 14:51 test.txt +-rw-r--r-- 1 pbuilder2 pbuilder2 4103 May 13 11:20 test.txt + RSB_PR_WLTC=2 + RSB_PR_SR=0 + rsbench --read-performance-record test.rpr @@ -8165,29 +8176,29 @@ /usr/bin/kpsepath ++ kpsepath tex ++ sed 's/!!//g;s/:/\n/g;' -+ find . /nonexistent/first-build/.texlive2023/texmf-config/tex/kpsewhich// /nonexistent/first-build/.texlive2023/texmf-var/tex/kpsewhich// /nonexistent/first-build/texmf/tex/kpsewhich// /usr/local/share/texmf/tex/kpsewhich// /etc/texmf/tex/kpsewhich// /var/lib/texmf/tex/kpsewhich// /usr/share/texmf/tex/kpsewhich// /usr/share/texlive/texmf-dist/tex/kpsewhich// /nonexistent/first-build/.texlive2023/texmf-config/tex/generic// /nonexistent/first-build/.texlive2023/texmf-var/tex/generic// /nonexistent/first-build/texmf/tex/generic// /usr/local/share/texmf/tex/generic// /etc/texmf/tex/generic// /var/lib/texmf/tex/generic// /usr/share/texmf/tex/generic// /usr/share/texlive/texmf-dist/tex/generic// /nonexistent/first-build/.texlive2023/texmf-config/tex/latex// /nonexistent/first-build/.texlive2023/texmf-var/tex/latex// /nonexistent/first-build/texmf/tex/latex// /usr/local/share/texmf/tex/latex// /etc/texmf/tex/latex// /var/lib/texmf/tex/latex// /usr/share/texmf/tex/latex// /usr/share/texlive/texmf-dist/tex/latex// /nonexistent/first-build/.texlive2023/texmf-config/tex/// /nonexistent/first-build/.texlive2023/texmf-var/tex/// /nonexistent/first-build/texmf/tex/// /usr/local/share/texmf/tex/// /etc/texmf/tex/// /var/lib/texmf/tex/// /usr/share/texmf/tex/// /usr/share/texlive/texmf-dist/tex/// -name sciposter.cls -find: '/nonexistent/first-build/.texlive2023/texmf-config/tex/kpsewhich//': No such file or directory -find: '/nonexistent/first-build/.texlive2023/texmf-var/tex/kpsewhich//': No such file or directory -find: '/nonexistent/first-build/texmf/tex/kpsewhich//': No such file or directory ++ find . /nonexistent/second-build/.texlive2023/texmf-config/tex/kpsewhich// /nonexistent/second-build/.texlive2023/texmf-var/tex/kpsewhich// /nonexistent/second-build/texmf/tex/kpsewhich// /usr/local/share/texmf/tex/kpsewhich// /etc/texmf/tex/kpsewhich// /var/lib/texmf/tex/kpsewhich// /usr/share/texmf/tex/kpsewhich// /usr/share/texlive/texmf-dist/tex/kpsewhich// /nonexistent/second-build/.texlive2023/texmf-config/tex/generic// /nonexistent/second-build/.texlive2023/texmf-var/tex/generic// /nonexistent/second-build/texmf/tex/generic// /usr/local/share/texmf/tex/generic// /etc/texmf/tex/generic// /var/lib/texmf/tex/generic// /usr/share/texmf/tex/generic// /usr/share/texlive/texmf-dist/tex/generic// /nonexistent/second-build/.texlive2023/texmf-config/tex/latex// /nonexistent/second-build/.texlive2023/texmf-var/tex/latex// /nonexistent/second-build/texmf/tex/latex// /usr/local/share/texmf/tex/latex// /etc/texmf/tex/latex// /var/lib/texmf/tex/latex// /usr/share/texmf/tex/latex// /usr/share/texlive/texmf-dist/tex/latex// /nonexistent/second-build/.texlive2023/texmf-config/tex/// /nonexistent/second-build/.texlive2023/texmf-var/tex/// /nonexistent/second-build/texmf/tex/// /usr/local/share/texmf/tex/// /etc/texmf/tex/// /var/lib/texmf/tex/// /usr/share/texmf/tex/// /usr/share/texlive/texmf-dist/tex/// -name sciposter.cls +find: '/nonexistent/second-build/.texlive2023/texmf-config/tex/kpsewhich//': No such file or directory +find: '/nonexistent/second-build/.texlive2023/texmf-var/tex/kpsewhich//': No such file or directory +find: '/nonexistent/second-build/texmf/tex/kpsewhich//': No such file or directory find: '/usr/local/share/texmf/tex/kpsewhich//': No such file or directory find: '/etc/texmf/tex/kpsewhich//': No such file or directory find: '/var/lib/texmf/tex/kpsewhich//': No such file or directory find: '/usr/share/texmf/tex/kpsewhich//': No such file or directory find: '/usr/share/texlive/texmf-dist/tex/kpsewhich//': No such file or directory -find: '/nonexistent/first-build/.texlive2023/texmf-config/tex/generic//': No such file or directory -find: '/nonexistent/first-build/.texlive2023/texmf-var/tex/generic//': No such file or directory -find: '/nonexistent/first-build/texmf/tex/generic//': No such file or directory +find: '/nonexistent/second-build/.texlive2023/texmf-config/tex/generic//': No such file or directory +find: '/nonexistent/second-build/.texlive2023/texmf-var/tex/generic//': No such file or directory +find: '/nonexistent/second-build/texmf/tex/generic//': No such file or directory find: '/usr/local/share/texmf/tex/generic//': No such file or directory find: '/usr/share/texmf/tex/generic//': No such file or directory -find: '/nonexistent/first-build/.texlive2023/texmf-config/tex/latex//': No such file or directory -find: '/nonexistent/first-build/.texlive2023/texmf-var/tex/latex//': No such file or directory -find: '/nonexistent/first-build/texmf/tex/latex//': No such file or directory +find: '/nonexistent/second-build/.texlive2023/texmf-config/tex/latex//': No such file or directory +find: '/nonexistent/second-build/.texlive2023/texmf-var/tex/latex//': No such file or directory +find: '/nonexistent/second-build/texmf/tex/latex//': No such file or directory find: '/usr/local/share/texmf/tex/latex//': No such file or directory find: '/etc/texmf/tex/latex//': No such file or directory find: '/var/lib/texmf/tex/latex//': No such file or directory -find: '/nonexistent/first-build/.texlive2023/texmf-config/tex///': No such file or directory -find: '/nonexistent/first-build/.texlive2023/texmf-var/tex///': No such file or directory -find: '/nonexistent/first-build/texmf/tex///': No such file or directory +find: '/nonexistent/second-build/.texlive2023/texmf-config/tex///': No such file or directory +find: '/nonexistent/second-build/.texlive2023/texmf-var/tex///': No such file or directory +find: '/nonexistent/second-build/texmf/tex///': No such file or directory find: '/usr/local/share/texmf/tex///': No such file or directory + exit 0 for mf in pd.mtx vf.mtx ; do if test -f /build/reproducible-path/librsb-1.3.0.2+dfsg/examples/$mf ; then true; else cp -p /build/reproducible-path/librsb-1.3.0.2+dfsg/$mf /build/reproducible-path/librsb-1.3.0.2+dfsg/examples/$mf ; fi; done @@ -8202,7 +8213,7 @@ This error may be safely ignored. Correctly allocated a matrix. Summary information of the matrix: -(3 x 3)[0x55d04439a4a0]{D} @ (0(0..3),0(0..3)) (3 nnz, 1 nnz/r) flags 0x2040384 (coo:1, csr:0, hw:0, ic:1, fi:0), storage: 40, subm: 1, symflags:'' +(3 x 3)[0x563d122ef4a0]{D} @ (0(0..3),0(0..3)) (3 nnz, 1 nnz/r) flags 0x2040384 (coo:1, csr:0, hw:0, ic:1, fi:0), storage: 40, subm: 1, symflags:'' Correctly performed a SPMV. Correctly freed the matrix. Correctly finalized the library. @@ -8217,7 +8228,7 @@ This error may be safely ignored. Correctly allocated a matrix. Summary information of the matrix: -(3 x 3)[0x558b6c8b94a0]{D} @ (0(0..3),0(0..3)) (3 nnz, 1 nnz/r) flags 0x2040384 (coo:1, csr:0, hw:0, ic:1, fi:0), storage: 40, subm: 1, symflags:'' +(3 x 3)[0x55c99d1a34a0]{D} @ (0(0..3),0(0..3)) (3 nnz, 1 nnz/r) flags 0x2040384 (coo:1, csr:0, hw:0, ic:1, fi:0), storage: 40, subm: 1, symflags:'' Correctly performed a SPMV. Correctly freed the matrix. Correctly finalized the library. @@ -8281,51 +8292,51 @@ Done. Building a matrix with 5 nnz, 5 x 5 Duplicates check: 5 - 0 = 5 - converted COO to RSB in 1.521e-04 s (100.00 %) - analyzed arrays in 5.794e-05 s (38.09 %) - cleaned-up arrays in 0.000e+00 s (0.00 %) - deduplicated arrays in 9.537e-07 s (0.63 %) - sorted arrays in 1.287e-05 s (8.46 %) - shuffled partitions in 3.815e-05 s (25.08 %) - memory allocations took 4.053e-06 s (2.66 %) - leafs setup took 0.000e+00 s (0.00 %) - halfword conversion took 3.695e-05 s (24.29 %) -Built (5 x 5)[0x558b6c8bff60]{D} @ (0(0..0),0(0..0)) (5 nnz, 1 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 2, symflags:'' + converted COO to RSB in 1.713e-01 s (100.00 %) + analyzed arrays in 6.211e-02 s (36.25 %) + cleaned-up arrays in 9.537e-07 s (0.00 %) + deduplicated arrays in 6.914e-06 s (0.00 %) + sorted arrays in 1.221e-02 s (7.12 %) + shuffled partitions in 4.797e-02 s (28.00 %) + memory allocations took 1.431e-05 s (0.01 %) + leafs setup took 5.960e-06 s (0.00 %) + halfword conversion took 4.902e-02 s (28.61 %) +Built (5 x 5)[0x55c99d1a6b20]{D} @ (0(0..0),0(0..0)) (5 nnz, 1 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 2, symflags:'' Allocated matrix of 5 nonzeroes: -(5 x 5)[0x558b6c8bff60]{D} @ (0(0..0),0(0..0)) (5 nnz, 1 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 2, symflags:'' +(5 x 5)[0x55c99d1a6b20]{D} @ (0(0..0),0(0..0)) (5 nnz, 1 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 2, symflags:'' -Before auto-tuning, 100 multiplications took 0.001795s. +Before auto-tuning, 100 multiplications took 2.606883s. Threads autotuning (may take more than 1.500000s)... Will use autotuning routine to sample matrix: 5 x 5, type D, 5 nnz, 1 nnz/r, 3 subms, 2 lsubms, 4.0000 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:0.1 -Sampling (15 x 0.1 s stages, transA=N, nrhs=2, timer gran.=3.67522e-08), 42 suggested as starting thread count(default). -3 iterations (42 th.) took 5.007e-05s; avg 1.669e-05s ( +/- 4.29/ 2.86 %); best 1.597e-05s; worst 1.717e-05s; std dev. 5.15e-07 (taking best). -Reference operation time is 1.5974e-05 s (1.252 Mflops) with 42 threads. -3 iterations (42 th.) took 5.102e-05s; avg 1.701e-05s ( +/- 6.07/ 12.15 %); best 1.597e-05s; worst 1.907e-05s; std dev. 1.461e-06 (taking best). -Reference operation time is 1.5974e-05 s (1.252 Mflops) with 42 threads. -After 0.000142s, autotuning routine did not find a better threads count configuration. -(5 x 5)[0x558b6c8bff60]{D} @ (0(0..0),0(0..0)) (5 nnz, 1 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 2, symflags:'' -After threads auto-tuning, 100 multiplications took 0.002351s -- effective speedup of 0.76359 x -Matrix autotuning (may take more than 1.500000s; using 42 threads )... +Sampling (15 x 0.1 s stages, transA=N, nrhs=2, timer gran.=4.39107e-07), 20 suggested as starting thread count(default). +3 iterations (20 th.) took 0.05998s; avg 0.01999s ( +/- 39.84/ 20.09 %); best 0.01203s; worst 0.02401s; std dev. 0.005633 (taking best). +Reference operation time is 0.012027 s (0.001663 Mflops) with 20 threads. +3 iterations (20 th.) took 0.05995s; avg 0.01998s ( +/- 39.67/ 19.86 %); best 0.01206s; worst 0.02395s; std dev. 0.005606 (taking best). +Reference operation time is 0.0120561 s (0.001659 Mflops) with 20 threads. +After 0.120016s, autotuning routine did not find a better threads count configuration. +(5 x 5)[0x55c99d1a6b20]{D} @ (0(0..0),0(0..0)) (5 nnz, 1 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 2, symflags:'' +After threads auto-tuning, 100 multiplications took 2.407970s -- effective speedup of 1.08261 x +Matrix autotuning (may take more than 1.500000s; using 20 threads )... Will autotune matrix: 5 x 5, type D, 5 nnz, 1 nnz/r, 3 subms, 2 lsubms, 4.0000 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:0.1 -Starting autotuning (15 x 0.1 s stages, transA=N, nrhs=2, timer gran.=3.67522e-08), 42 suggested as starting thread count. -3 iterations (42 th.) took 5.603e-05s; avg 1.868e-05s ( +/- 4.26/ 7.23 %); best 1.788e-05s; worst 2.003e-05s; std dev. 9.603e-07 (taking best). -Reference operation time is 1.78814e-05 s (1.118 Mflops) with 42 threads. -Starting merge (user-supplied threads) based auto-tuning procedure (transA=N, nrhs=2, order=cols) (max 6 steps, inclusive 3 grace steps) on: 5 x 5, type D, 5 nnz, 1 nnz/r, 3 subms, 2 lsubms, 4.0000 bpnz (tpop: 1.788e-05 Mflops: 1.118) -Merge (2 -> 1 leaves) took w.c.t. of 1.097e-05s, ~3.099e-06s of computing time (of which 0s sorting, 2.146e-06s analysis) -3 iterations (42 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 88.44/200.00 %); best 3.675e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). -Reference operation time is 3.67522e-08 s (544.2 Mflops) with 42 threads. -After merge step 1: tpop: 3.675e-08 s ~Mflops: 544.185 nsubm:1 otn:42 -Applying merge (2 -> 1 leaves, 42 th.) yielded SPEEDUP of 486.539x: 1.788e-05s -> 3.675e-08s, so taking this instance. +Starting autotuning (15 x 0.1 s stages, transA=N, nrhs=2, timer gran.=4.39107e-07), 20 suggested as starting thread count. +3 iterations (20 th.) took 0.07946s; avg 0.02649s ( +/- 39.52/ 20.80 %); best 0.01602s; worst 0.032s; std dev. 0.007405 (taking best). +Reference operation time is 0.0160208 s (0.001248 Mflops) with 20 threads. +Starting merge (user-supplied threads) based auto-tuning procedure (transA=N, nrhs=2, order=cols) (max 6 steps, inclusive 3 grace steps) on: 5 x 5, type D, 5 nnz, 1 nnz/r, 3 subms, 2 lsubms, 4.0000 bpnz (tpop: 0.01602 Mflops: 0.001) +Merge (2 -> 1 leaves) took w.c.t. of 2.694e-05s, ~0s of computing time (of which 0s sorting, 1.097e-05s analysis) +3 iterations (20 th.) took 4.053e-06s; avg 1.351e-06s ( +/- 67.50/129.41 %); best 4.391e-07s; worst 3.099e-06s; std dev. 1.296e-06 (taking best). +Reference operation time is 4.39107e-07 s (45.55 Mflops) with 20 threads. +After merge step 1: tpop: 4.391e-07 s ~Mflops: 45.547 nsubm:1 otn:20 +Applying merge (2 -> 1 leaves, 20 th.) yielded SPEEDUP of 36484.865x: 0.01602s -> 4.391e-07s, so taking this instance. Merged all the matrix leaves: no reason to continue merging. -A total of 1 merge steps (of max 6) (2 -> 1 subms) took 0.0001159s (of which 2.599e-05s partitioning, 0s I/O); computing times: 3.099e-06s in par. loops, 0s sorting, 2.146e-06s analyzing) -Total merge + benchmarking process took 0.0001159s, equivalent to 3152.8/6.5 new/old ops (0.0001271s for 2 clones -- as 3457.7/7.1 ops, or 1728.8/3.6 ops per clone), SPEEDUP of 486.539x -Applying multi-merge (2 -> 1 leaves, 1 steps, 42 -> 42 th.sp.) yielded SPEEDUP of 486.539x (1.788e-05s -> 3.675e-08s), will amortize in 6.5 ops by saving 1.784e-05s per op. -In 1 tuning rounds (tot. 0.00025s, 0.00013s for constructor, 2 clones) obtained a SPEEDUP of 48553.9% (486.5x) (from 1.118 to 544.2 Mflops). -After 0.000256s, autotuning routine declared speedup of 486.539 x, when using threads count of 42. -(5 x 5)[0x558b6c8c3590]{D} @ (0(0..5),0(0..5)) (5 nnz, 1 nnz/r) flags 0x2040186 (coo:1, csr:0, hw:1, ic:1, fi:0), storage: 40, subm: 1, symflags:'' -After threads auto-tuning, 100 multiplications took 0.000025s -- further speedup of 94.8077 x +A total of 1 merge steps (of max 6) (2 -> 1 subms) took 0.07998s (of which 0.000298s partitioning, 0s I/O); computing times: 0s in par. loops, 0s sorting, 1.097e-05s analyzing) +Total merge + benchmarking process took 0.07998s, equivalent to 182137.6/5.0 new/old ops (0.1561s for 2 clones -- as 355607.4/9.7 ops, or 177803.7/4.9 ops per clone), SPEEDUP of 36484.865x +Applying multi-merge (2 -> 1 leaves, 1 steps, 20 -> 20 th.sp.) yielded SPEEDUP of 36484.865x (0.01602s -> 4.391e-07s), will amortize in 5.0 ops by saving 0.01602s per op. +In 1 tuning rounds (tot. 0.24s, 0.16s for constructor, 2 clones) obtained a SPEEDUP of 3648386.5% (3.648e+04x) (from 0.001248 to 45.55 Mflops). +After 0.236004s, autotuning routine declared speedup of 36484.9 x, when using threads count of 20. +(5 x 5)[0x55c99d1aa1e0]{D} @ (0(0..5),0(0..5)) (5 nnz, 1 nnz/r) flags 0x2040186 (coo:1, csr:0, hw:1, ic:1, fi:0), storage: 40, subm: 1, symflags:'' +After threads auto-tuning, 100 multiplications took 0.000014s -- further speedup of 171182 x 0/2 0 0 -> 0 1/2 1 0 -> 5 0/2 0 3 -> 0 @@ -8336,7 +8347,7 @@ Correctly initialized the library. Correctly allocated a matrix with 7 nonzeroes. Summary information of the matrix: -(6 x 6)[0x558b6c8bff60]{D} @ (0(1..2),0(5..6)) (1 nnz, 0.17 nnz/r) flags 0x20443ee (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 1, symflags:'UT' +(6 x 6)[0x55c99d1a6b20]{D} @ (0(1..2),0(5..6)) (1 nnz, 0.17 nnz/r) flags 0x20443ee (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 1, symflags:'UT' Matrix printout: %%MatrixMarket matrix coordinate real general 6 6 1 @@ -8487,62 +8498,68 @@ Creating 500 x 500 matrix with 62500 nonzeroes. Building a matrix with 62500 nnz, 500 x 500 Duplicates check: 62500 - 0 = 62500 - converted COO to RSB in 5.438e-02 s (100.00 %) - analyzed arrays in 9.135e-03 s (16.80 %) - cleaned-up arrays in 6.604e-05 s (0.12 %) - deduplicated arrays in 1.359e-04 s (0.25 %) - sorted arrays in 2.238e-02 s (41.15 %) - shuffled partitions in 1.511e-02 s (27.78 %) - memory allocations took 3.600e-05 s (0.07 %) - leafs setup took 5.007e-06 s (0.01 %) - halfword conversion took 7.517e-03 s (13.82 %) -Built (500 x 500)[0x55bbebf3f2d0]{D} @ (0(0..0),0(0..0)) (62500 nnz, 1.2e+02 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 37, symflags:'' + converted COO to RSB in 3.715e-01 s (100.00 %) + analyzed arrays in 6.747e-02 s (18.16 %) + cleaned-up arrays in 1.981e-04 s (0.05 %) + deduplicated arrays in 2.251e-04 s (0.06 %) + sorted arrays in 1.475e-01 s (39.71 %) + shuffled partitions in 1.040e-01 s (27.99 %) + memory allocations took 8.917e-05 s (0.02 %) + leafs setup took 2.885e-05 s (0.01 %) + halfword conversion took 5.197e-02 s (13.99 %) +Built (500 x 500)[0x5604b54c52d0]{D} @ (0(0..0),0(0..0)) (62500 nnz, 1.2e+02 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 64, symflags:'' Allocated matrix of 62500 nonzeroes: -(500 x 500)[0x55bbebf3f2d0]{D} @ (0(0..0),0(0..0)) (62500 nnz, 1.2e+02 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 37, symflags:'' +(500 x 500)[0x5604b54c52d0]{D} @ (0(0..0),0(0..0)) (62500 nnz, 1.2e+02 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 64, symflags:'' -Before auto-tuning, 100 multiplications took 0.290371s. +Before auto-tuning, 100 multiplications took 2.363620s. Threads autotuning (may take more than 1.500000s)... -Will use autotuning routine to sample matrix: 500 x 500, type D, 62500 nnz, 1.2e+02 nnz/r, 51 subms, 37 lsubms, 2.0945 bpnz. +Will use autotuning routine to sample matrix: 500 x 500, type D, 62500 nnz, 1.2e+02 nnz/r, 87 subms, 64 lsubms, 2.1321 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:0.1 -Sampling (15 x 0.1 s stages, transA=N, nrhs=2, timer gran.=3.31998e-08), 42 suggested as starting thread count(default). -3 iterations (42 th.) took 0.00294s; avg 0.0009801s ( +/- 22.96/ 16.43 %); best 0.0007551s; worst 0.001141s; std dev. 0.0001639 (taking best). -Reference operation time is 0.000755072 s (331.1 Mflops) with 42 threads. -3 iterations (42 th.) took 0.001769s; avg 0.0005897s ( +/- 8.95/ 12.28 %); best 0.0005369s; worst 0.0006621s; std dev. 5.295e-05 (taking best). -Reference operation time is 0.000536919 s (465.6 Mflops) with 42 threads. -After 0.004781s, autotuning routine did not find a better threads count configuration. -(500 x 500)[0x55bbebf3f2d0]{D} @ (0(0..0),0(0..0)) (62500 nnz, 1.2e+02 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 37, symflags:'' -After threads auto-tuning, 100 multiplications took 0.078888s -- effective speedup of 3.6808 x -Matrix autotuning (may take more than 1.500000s; using 42 threads )... -Will autotune matrix: 500 x 500, type D, 62500 nnz, 1.2e+02 nnz/r, 51 subms, 37 lsubms, 2.0945 bpnz. +Sampling (15 x 0.1 s stages, transA=N, nrhs=2, timer gran.=1.21169e-06), 20 suggested as starting thread count(default). +3 iterations (20 th.) took 0.07984s; avg 0.02661s ( +/- 9.82/ 5.20 %); best 0.024s; worst 0.028s; std dev. 0.00185 (taking best). +Reference operation time is 0.023998 s (10.42 Mflops) with 20 threads. +3 iterations (20 th.) took 0.08402s; avg 0.02801s ( +/- 28.47/ 28.48 %); best 0.02003s; worst 0.03598s; std dev. 0.006512 (taking best). +Reference operation time is 0.0200319 s (12.48 Mflops) with 20 threads. +After 0.163982s, autotuning routine did not find a better threads count configuration. +(500 x 500)[0x5604b54c52d0]{D} @ (0(0..0),0(0..0)) (62500 nnz, 1.2e+02 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 64, symflags:'' +After threads auto-tuning, 100 multiplications took 2.380053s -- effective speedup of 0.993095 x +Matrix autotuning (may take more than 1.500000s; using 20 threads )... +Will autotune matrix: 500 x 500, type D, 62500 nnz, 1.2e+02 nnz/r, 87 subms, 64 lsubms, 2.1321 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:0.1 -Starting autotuning (15 x 0.1 s stages, transA=N, nrhs=2, timer gran.=3.31998e-08), 42 suggested as starting thread count. -3 iterations (42 th.) took 0.003224s; avg 0.001075s ( +/- 47.42/ 61.44 %); best 0.0005651s; worst 0.001735s; std dev. 0.0004893 (taking best). -Reference operation time is 0.000565052 s (442.4 Mflops) with 42 threads. -Starting merge (user-supplied threads) based auto-tuning procedure (transA=N, nrhs=2, order=cols) (max 6 steps, inclusive 3 grace steps) on: 500 x 500, type D, 62500 nnz, 1.2e+02 nnz/r, 51 subms, 37 lsubms, 2.0945 bpnz (tpop: 0.0005651 Mflops: 442.437) -Merge (37 -> 28 leaves) took w.c.t. of 0.0007539s, ~0.001443s of computing time (of which 8.225e-05s sorting, 8.106e-06s analysis) -3 iterations (42 th.) took 0.01235s; avg 0.004117s ( +/- 10.60/ 20.20 %); best 0.003681s; worst 0.004949s; std dev. 0.0005884 (taking best). -Reference operation time is 0.00368094 s (67.92 Mflops) with 42 threads. -After merge step 1: tpop: 0.003681 s ~Mflops: 67.917 nsubm:28 otn:42 -Applying merge (37 -> 28 leaves, 42 th.) yielded SLOWDOWN (1th of 3 tolerable) of 6.514x: 0.0005651s -> 0.003681s. +Starting autotuning (15 x 0.1 s stages, transA=N, nrhs=2, timer gran.=1.21169e-06), 20 suggested as starting thread count. +3 iterations (20 th.) took 0.06399s; avg 0.02133s ( +/- 42.48/ 30.06 %); best 0.01227s; worst 0.02774s; std dev. 0.006589 (taking best). +Reference operation time is 0.0122681 s (20.38 Mflops) with 20 threads. +Starting merge (user-supplied threads) based auto-tuning procedure (transA=N, nrhs=2, order=cols) (max 6 steps, inclusive 3 grace steps) on: 500 x 500, type D, 62500 nnz, 1.2e+02 nnz/r, 87 subms, 64 lsubms, 2.1321 bpnz (tpop: 0.01227 Mflops: 20.378) +Merge (64 -> 40 leaves) took w.c.t. of 0.08012s, ~0.4661s of computing time (of which 0.02407s sorting, 2.003e-05s analysis) +3 iterations (20 th.) took 0.08778s; avg 0.02926s ( +/- 18.03/ 22.31 %); best 0.02399s; worst 0.03579s; std dev. 0.004899 (taking best). +Reference operation time is 0.0239861 s (10.42 Mflops) with 20 threads. +After merge step 1: tpop: 0.02399 s ~Mflops: 10.423 nsubm:40 otn:20 +Applying merge (64 -> 40 leaves, 20 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.955x: 0.01227s -> 0.02399s. Skipping further merge based tests after 1 definite performance degradations in a row (and last exceeding limit). -A total of 1 merge steps (of max 6) (37 -> 28 subms) took 0.01313s (of which 0.0007601s partitioning, 0s I/O); computing times: 0.001443s in par. loops, 8.225e-05s sorting, 8.106e-06s analyzing) -Total merge + benchmarking process took 0.01313s, equivalent to 23.2/23.2 new/old ops (0.0001729s for 1 clones -- as 0.3/0.3 ops, or 0.3/0.3 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) +A total of 1 merge steps (of max 6) (64 -> 40 subms) took 0.168s (of which 0.08015s partitioning, 0s I/O); computing times: 0.4661s in par. loops, 0.02407s sorting, 2.003e-05s analyzing) +Total merge + benchmarking process took 0.168s, equivalent to 13.7/13.7 new/old ops (0.06383s for 1 clones -- as 5.2/5.2 ops, or 5.2/5.2 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) Merging based autotuning FAILED (=NO SPEEDUP); let's try splitting then... -3 iterations (42 th.) took 0.003108s; avg 0.001036s ( +/- 54.34/104.74 %); best 0.000473s; worst 0.002121s; std dev. 0.0007674 (taking best). -Reference operation time is 0.000473022 s (528.5 Mflops) with 42 threads. -Starting split (user-supplied threads) based auto-tuning procedure (transA=N, nrhs=2, order=cols) (max 6 steps, inclusive 3 grace steps) on: 500 x 500, type D, 62500 nnz, 1.2e+02 nnz/r, 51 subms, 37 lsubms, 2.0945 bpnz (tpop: 0.000473 Mflops: 528.516) -Split (37 -> 91 leaves, 51 -> 123 subms) took 0.001581s (of which: 6.199e-06s analysis, -3.15e+10s mem.mgmt); compute time: 0.02214s overall, 0.0003357s searches, 0.02181s shuffle, 0.01233s switch, 0.001623s quadrants. -3 iterations (42 th.) took 0.01251s; avg 0.004169s ( +/- 13.07/ 11.35 %); best 0.003624s; worst 0.004642s; std dev. 0.0004187 (taking best). -Reference operation time is 0.00362396 s (68.99 Mflops) with 42 threads. -After split step 1: tpop: 0.003624 s ~Mflops: 68.985 nsubm:91 otn:42 -Applying split (37 -> 91 leaves, 42 th.) yielded SLOWDOWN (1th of 3 tolerable) of 7.661x: 0.000473s -> 0.003624s. +3 iterations (20 th.) took 0.08401s; avg 0.028s ( +/- 14.18/ 14.29 %); best 0.02403s; worst 0.03201s; std dev. 0.003254 (taking best). +Reference operation time is 0.024035 s (10.4 Mflops) with 20 threads. +Starting split (user-supplied threads) based auto-tuning procedure (transA=N, nrhs=2, order=cols) (max 6 steps, inclusive 3 grace steps) on: 500 x 500, type D, 62500 nnz, 1.2e+02 nnz/r, 87 subms, 64 lsubms, 2.1321 bpnz (tpop: 0.02403 Mflops: 10.402) +Split (64 -> 160 leaves, 87 -> 215 subms) took 0.03979s (of which: 1.788e-05s analysis, -5.49e+10s mem.mgmt); compute time: 0.004906s overall, 0.0003061s searches, 0.0046s shuffle, 0.002395s switch, 0.0003357s quadrants. +3 iterations (20 th.) took 0.06368s; avg 0.02123s ( +/- 24.60/ 30.45 %); best 0.01601s; worst 0.02769s; std dev. 0.004851 (taking best). +Reference operation time is 0.016005 s (15.62 Mflops) with 20 threads. +After split step 1: tpop: 0.01601 s ~Mflops: 15.620 nsubm:160 otn:20 +Applying split (64 -> 160 leaves, 20 th.) yielded SPEEDUP of 1.502x: 0.02403s -> 0.01601s, so taking this instance. +Split (160 -> 400 leaves, 215 -> 535 subms) took 0.03171s (of which: 3.982e-05s analysis, -1.372e+11s mem.mgmt); compute time: 0.004416s overall, 0.0005655s searches, 0.003851s shuffle, 0.00119s switch, 0.0004995s quadrants. +3 iterations (20 th.) took 0.08766s; avg 0.02922s ( +/- 29.63/ 23.22 %); best 0.02056s; worst 0.03601s; std dev. 0.006442 (taking best). +Reference operation time is 0.0205631 s (12.16 Mflops) with 20 threads. +After split step 2: tpop: 0.02056 s ~Mflops: 12.158 nsubm:400 otn:20 +Applying split (160 -> 400 leaves, 20 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.285x: 0.01601s -> 0.02056s. Skipping further split based tests after 1 definite performance degradations in a row (and last exceeding limit). -A total of 1 split steps (of max 6) (37 -> 91 subms) took 0.01423s (of which 0.001707s partitioning, 0s I/O); computing times: 0.02214s in par. loops, 0.0003357s sorting, 6.199e-06s analyzing) -Total split + benchmarking process took 0.01423s, equivalent to 30.1/30.1 new/old ops (0.01128s for 1 clones -- as 23.9/23.9 ops, or 23.9/23.9 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) -In 1 tuning rounds (tot. 0.045s, 0.011s for constructor, 2 clones) obtained NO speedup (best stays 528.5 Mflops). -After 0.045236s, autotuning routine declared speedup of 1 x, when using threads count of 42. -(500 x 500)[0x55bbebf3f2d0]{D} @ (0(0..0),0(0..0)) (62500 nnz, 1.2e+02 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 37, symflags:'' -After threads auto-tuning, 100 multiplications took 0.225608s -- further speedup of 0.349668 x +A total of 2 split steps (of max 6) (64 -> 400 subms) took 0.3s (of which 0.07251s partitioning, 0s I/O); computing times: 0.009322s in par. loops, 0.0008717s sorting, 5.77e-05s analyzing) +Total split + benchmarking process took 0.3s, equivalent to 18.7/12.5 new/old ops (0.1359s for 2 clones -- as 8.5/5.7 ops, or 4.2/2.8 ops per clone), SPEEDUP of 1.502x +Applying multi-split (64 -> 160 leaves, 1 steps, 20 -> 20 th.sp.) yielded SPEEDUP of 1.502x (0.02403s -> 0.01601s), will amortize in 37.4 ops by saving 0.00803s per op. +In 1 tuning rounds (tot. 0.74s, 0.2s for constructor, 3 clones) obtained a SPEEDUP of 50.2% (1.502x) (from 10.4 to 15.62 Mflops). +After 0.740322s, autotuning routine declared speedup of 1.50171 x, when using threads count of 20. +(500 x 500)[0x5604b55cdbf0]{D} @ (0(0..0),0(0..0)) (62500 nnz, 1.2e+02 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 160, symflags:'' +After threads auto-tuning, 100 multiplications took 2.531525s -- further speedup of 0.940166 x librsb timer-based profiling is not supported in this build. If you wish to have it, re-configure librsb with its support. So you can safely ignore the error you might just have seen printed out on screen. /build/reproducible-path/librsb-1.3.0.2+dfsg/examples/backsolve Hello, RSB! @@ -8550,19 +8567,19 @@ Correctly initialized the library. Building a matrix with 7 nnz, 6 x 6 Duplicates check: 1 - 0 = 1 - converted COO to RSB in 1.652e-02 s (100.00 %) - analyzed arrays in 1.084e-02 s (65.60 %) - cleaned-up arrays in 4.053e-06 s (0.02 %) - deduplicated arrays in 9.537e-07 s (0.01 %) - sorted arrays in 9.537e-07 s (0.01 %) - shuffled partitions in 5.653e-03 s (34.22 %) - memory allocations took 1.311e-05 s (0.08 %) - leafs setup took 3.099e-06 s (0.02 %) - halfword conversion took 5.007e-06 s (0.03 %) -Built (6 x 6)[0x55d84fae64d0]{D} @ (0(0..1),0(5..6)) (1 nnz, 0.17 nnz/r) flags 0x20443ee (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 1, symflags:'UT' + converted COO to RSB in 9.145e-02 s (100.00 %) + analyzed arrays in 6.790e-02 s (74.25 %) + cleaned-up arrays in 7.868e-06 s (0.01 %) + deduplicated arrays in 1.907e-06 s (0.00 %) + sorted arrays in 3.099e-06 s (0.00 %) + shuffled partitions in 2.345e-02 s (25.65 %) + memory allocations took 4.721e-05 s (0.05 %) + leafs setup took 1.216e-05 s (0.01 %) + halfword conversion took 1.383e-05 s (0.02 %) +Built (6 x 6)[0x5641913ff4d0]{D} @ (0(0..1),0(5..6)) (1 nnz, 0.17 nnz/r) flags 0x20443ee (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 1, symflags:'UT' Correctly allocated a matrix with 7 nonzeroes. Summary information of the matrix: -(6 x 6)[0x55d84fae64d0]{D} @ (0(0..1),0(5..6)) (1 nnz, 0.17 nnz/r) flags 0x20443ee (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 1, symflags:'UT' +(6 x 6)[0x5641913ff4d0]{D} @ (0(0..1),0(5..6)) (1 nnz, 0.17 nnz/r) flags 0x20443ee (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 1, symflags:'UT' Matrix printout: %%MatrixMarket matrix coordinate real general 6 6 1 @@ -8588,55 +8605,52 @@ 1 1 Will autotune matrix: 6 x 6, type D, 1 nnz, 0.17 nnz/r, 1 subms, 1 lsubms, 4.0000 bpnz. -Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:3.32e-08 -3 iterations (42 th.) took 3.791e-05s; avg 1.264e-05s ( +/- 99.74/192.45 %); best 3.32e-08s; worst 3.695e-05s; std dev. 1.72e-05 (taking best). -Reference operation time is 3.31998e-08 s (60.24 Mflops) with 42 threads. -Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=cols) (max 6 steps, inclusive 3 grace steps) on: 6 x 6, type D, 1 nnz, 0.17 nnz/r, 1 subms, 1 lsubms, 4.0000 bpnz (tpop: 3.32e-08 Mflops: 60.241) -Merge (1 -> 1 leaves) took w.c.t. of 0s, ~0s of computing time (of which 0s sorting, 0s analysis) -3 iterations (42 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 89.56/200.00 %); best 3.32e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). -Reference operation time is 3.31998e-08 s (60.24 Mflops) with 42 threads. -After merge step 1: tpop: 3.32e-08 s ~Mflops: 60.241 nsubm:1 otn:42 -Applying merge (1 -> 1 leaves, 42 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=1.00000x): 3.32e-08s -> 3.32e-08s, so IGNORING this instance. +Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:4.341e-07 +3 iterations (20 th.) took 5.794e-05s; avg 1.931e-05s ( +/- 95.06/185.19 %); best 9.537e-07s; worst 5.507e-05s; std dev. 2.529e-05 (taking best). +Reference operation time is 9.53674e-07 s (2.097 Mflops) with 20 threads. +Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=cols) (max 6 steps, inclusive 3 grace steps) on: 6 x 6, type D, 1 nnz, 0.17 nnz/r, 1 subms, 1 lsubms, 4.0000 bpnz (tpop: 9.537e-07 Mflops: 2.097) +Merge (1 -> 1 leaves) took w.c.t. of 1.192e-06s, ~0s of computing time (of which 0s sorting, 0s analysis) +3 iterations (20 th.) took 4.053e-06s; avg 1.351e-06s ( +/- 29.41/ 58.82 %); best 9.537e-07s; worst 2.146e-06s; std dev. 5.62e-07 (taking best). +Reference operation time is 9.53674e-07 s (2.097 Mflops) with 20 threads. +After merge step 1: tpop: 9.537e-07 s ~Mflops: 2.097 nsubm:1 otn:20 +Applying merge (1 -> 1 leaves, 20 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=1.00000x): 9.537e-07s -> 9.537e-07s, so IGNORING this instance. Merged all the matrix leaves: no reason to continue merging. -A total of 1 merge steps (of max 6) (1 -> 1 subms) took 1.502e-05s (of which 3.099e-06s partitioning, 0s I/O); computing times: 0s in par. loops, 0s sorting, 0s analyzing) -Total merge + benchmarking process took 1.502e-05s, equivalent to 452.4/452.4 new/old ops (0.009469s for 1 clones -- as 285213.6/285213.6 ops, or 285213.6/285213.6 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) +A total of 1 merge steps (of max 6) (1 -> 1 subms) took 2.694e-05s (of which 5.96e-06s partitioning, 0s I/O); computing times: 0s in par. loops, 0s sorting, 0s analyzing) +Total merge + benchmarking process took 2.694e-05s, equivalent to 28.2/28.2 new/old ops (0.05983s for 1 clones -- as 62736.2/62736.2 ops, or 62736.2/62736.2 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) Merging based autotuning FAILED (=NO SPEEDUP); let's try splitting then... -3 iterations (42 th.) took 3.099e-06s; avg 1.033e-06s ( +/- 96.79/200.00 %); best 3.32e-08s; worst 3.099e-06s; std dev. 1.461e-06 (taking best). -Reference operation time is 3.31998e-08 s (60.24 Mflops) with 42 threads. -Starting split (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=cols) (max 6 steps, inclusive 3 grace steps) on: 6 x 6, type D, 1 nnz, 0.17 nnz/r, 1 subms, 1 lsubms, 4.0000 bpnz (tpop: 3.32e-08 Mflops: 60.241) -Split (1 -> 1 leaves, 1 -> 1 subms) took 1.502e-05s (of which: 1.907e-06s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. -3 iterations (42 th.) took 1.192e-06s; avg 3.974e-07s ( +/- 91.64/200.00 %); best 3.32e-08s; worst 1.192e-06s; std dev. 5.62e-07 (taking best). -Reference operation time is 3.31998e-08 s (60.24 Mflops) with 42 threads. -After split step 1: tpop: 3.32e-08 s ~Mflops: 60.241 nsubm:1 otn:42 -Applying split (1 -> 1 leaves, 42 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=1.00000x): 3.32e-08s -> 3.32e-08s, so IGNORING this instance. -Split (1 -> 1 leaves, 1 -> 1 subms) took 1.907e-06s (of which: 0s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. -3 iterations (42 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 89.56/200.00 %); best 3.32e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). -Reference operation time is 3.31998e-08 s (60.24 Mflops) with 42 threads. -After split step 2: tpop: 3.32e-08 s ~Mflops: 60.241 nsubm:1 otn:42 -Applying split (1 -> 1 leaves, 42 th.) yielded NEGLIGIBLE change (2th in a row) (old/new=1.00000x): 3.32e-08s -> 3.32e-08s, so IGNORING this instance. -Split (1 -> 1 leaves, 1 -> 1 subms) took 4.053e-06s (of which: 9.537e-07s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. -3 iterations (42 th.) took 2.146e-06s; avg 7.153e-07s ( +/- 95.36/ 66.67 %); best 3.32e-08s; worst 1.192e-06s; std dev. 5.15e-07 (taking best). -Reference operation time is 3.31998e-08 s (60.24 Mflops) with 42 threads. -After split step 3: tpop: 3.32e-08 s ~Mflops: 60.241 nsubm:1 otn:42 -Applying split (1 -> 1 leaves, 42 th.) yielded NEGLIGIBLE change (3th in a row) (old/new=1.00000x): 3.32e-08s -> 3.32e-08s, so IGNORING this instance. -Split (1 -> 1 leaves, 1 -> 1 subms) took 3.099e-06s (of which: 0s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. -3 iterations (42 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 89.56/200.00 %); best 3.32e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). -Reference operation time is 3.31998e-08 s (60.24 Mflops) with 42 threads. -After split step 4: tpop: 3.32e-08 s ~Mflops: 60.241 nsubm:1 otn:42 -Applying split (1 -> 1 leaves, 42 th.) yielded NEGLIGIBLE change (4th in a row) (old/new=1.00000x): 3.32e-08s -> 3.32e-08s, so IGNORING this instance. -Split (1 -> 1 leaves, 1 -> 1 subms) took 1.907e-06s (of which: 9.537e-07s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. -3 iterations (42 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 89.56/200.00 %); best 3.32e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). -Reference operation time is 3.31998e-08 s (60.24 Mflops) with 42 threads. -After split step 5: tpop: 3.32e-08 s ~Mflops: 60.241 nsubm:1 otn:42 -Applying split (1 -> 1 leaves, 42 th.) yielded NEGLIGIBLE change (5th in a row) (old/new=1.00000x): 3.32e-08s -> 3.32e-08s, so IGNORING this instance. -Split (1 -> 1 leaves, 1 -> 1 subms) took 2.146e-06s (of which: 0s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. -3 iterations (42 th.) took 1.192e-06s; avg 3.974e-07s ( +/- 91.64/200.00 %); best 3.32e-08s; worst 1.192e-06s; std dev. 5.62e-07 (taking best). -Reference operation time is 3.31998e-08 s (60.24 Mflops) with 42 threads. -After split step 6: tpop: 3.32e-08 s ~Mflops: 60.241 nsubm:1 otn:42 -Applying split (1 -> 1 leaves, 42 th.) yielded NEGLIGIBLE change (6th in a row) (old/new=1.00000x): 3.32e-08s -> 3.32e-08s, so IGNORING this instance. -A total of 6 split steps (of max 6) (1 -> 1 subms) took 0.0001769s (of which 5.388e-05s partitioning, 0s I/O); computing times: 0s in par. loops, 0s sorting, 3.815e-06s analyzing) -Total split + benchmarking process took 0.0001769s, equivalent to 5328.5/5328.5 new/old ops (0.01098s for 1 clones -- as 330721.7/330721.7 ops, or 330721.7/330721.7 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) -In 1 tuning rounds (tot. 0.021s, 0.02s for constructor, 2 clones) obtained NO speedup (best stays 60.24 Mflops). +3 iterations (20 th.) took 1.597e-05s; avg 5.325e-06s ( +/- 82.09/159.70 %); best 9.537e-07s; worst 1.383e-05s; std dev. 6.014e-06 (taking best). +Reference operation time is 9.53674e-07 s (2.097 Mflops) with 20 threads. +Starting split (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=cols) (max 6 steps, inclusive 3 grace steps) on: 6 x 6, type D, 1 nnz, 0.17 nnz/r, 1 subms, 1 lsubms, 4.0000 bpnz (tpop: 9.537e-07 Mflops: 2.097) +Split (1 -> 1 leaves, 1 -> 1 subms) took 3.982e-05s (of which: 6.914e-06s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. +3 iterations (20 th.) took 2.861e-06s; avg 9.537e-07s ( +/- 0.00/ 0.00 %); best 9.537e-07s; worst 9.537e-07s; std dev. 0 (taking best). +Reference operation time is 9.53674e-07 s (2.097 Mflops) with 20 threads. +After split step 1: tpop: 9.537e-07 s ~Mflops: 2.097 nsubm:1 otn:20 +Applying split (1 -> 1 leaves, 20 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=1.00000x): 9.537e-07s -> 9.537e-07s, so IGNORING this instance. +Split (1 -> 1 leaves, 1 -> 1 subms) took 5.007e-06s (of which: 9.537e-07s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. +3 iterations (20 th.) took 4.053e-06s; avg 1.351e-06s ( +/- 29.41/ 58.82 %); best 9.537e-07s; worst 2.146e-06s; std dev. 5.62e-07 (taking best). +Reference operation time is 9.53674e-07 s (2.097 Mflops) with 20 threads. +After split step 2: tpop: 9.537e-07 s ~Mflops: 2.097 nsubm:1 otn:20 +Applying split (1 -> 1 leaves, 20 th.) yielded NEGLIGIBLE change (2th in a row) (old/new=1.00000x): 9.537e-07s -> 9.537e-07s, so IGNORING this instance. +Split (1 -> 1 leaves, 1 -> 1 subms) took 7.153e-06s (of which: 1.192e-06s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. +3 iterations (20 th.) took 2.861e-06s; avg 9.537e-07s ( +/- 0.00/ 0.00 %); best 9.537e-07s; worst 9.537e-07s; std dev. 0 (taking best). +Reference operation time is 9.53674e-07 s (2.097 Mflops) with 20 threads. +After split step 3: tpop: 9.537e-07 s ~Mflops: 2.097 nsubm:1 otn:20 +Applying split (1 -> 1 leaves, 20 th.) yielded NEGLIGIBLE change (3th in a row) (old/new=1.00000x): 9.537e-07s -> 9.537e-07s, so IGNORING this instance. +Split (1 -> 1 leaves, 1 -> 1 subms) took 5.007e-06s (of which: 0s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. +3 iterations (20 th.) took 2.146e-06s; avg 7.153e-07s ( +/- 39.30/ 66.67 %); best 4.341e-07s; worst 1.192e-06s; std dev. 5.15e-07 (taking best). +Reference operation time is 4.34148e-07 s (4.607 Mflops) with 20 threads. +After split step 4: tpop: 4.341e-07 s ~Mflops: 4.607 nsubm:1 otn:20 +Applying split (1 -> 1 leaves, 20 th.) yielded SPEEDUP of 2.197x: 9.537e-07s -> 4.341e-07s, so taking this instance. +Split (1 -> 1 leaves, 1 -> 1 subms) took 4.292e-05s (of which: 5.007e-06s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. +3 iterations (20 th.) took 1.502e-05s; avg 5.007e-06s ( +/- 80.95/157.14 %); best 9.537e-07s; worst 1.287e-05s; std dev. 5.564e-06 (taking best). +Reference operation time is 9.53674e-07 s (2.097 Mflops) with 20 threads. +After split step 5: tpop: 9.537e-07 s ~Mflops: 2.097 nsubm:1 otn:20 +Applying split (1 -> 1 leaves, 20 th.) yielded SLOWDOWN (1th of 3 tolerable) of 2.197x: 4.341e-07s -> 9.537e-07s. +Skipping further split based tests after 1 definite performance degradations in a row (and last exceeding limit). +A total of 5 split steps (of max 6) (1 -> 1 subms) took 0.06005s (of which 0.00051s partitioning, 0s I/O); computing times: 0s in par. loops, 0s sorting, 1.407e-05s analyzing) +Total split + benchmarking process took 0.06005s, equivalent to 138324.0/62970.2 new/old ops (0.1192s for 2 clones -- as 274502.9/124964.0 ops, or 137251.4/62482.0 ops per clone), SPEEDUP of 2.197x +Applying multi-split (1 -> 1 leaves, 4 steps, 0 -> 20 th.sp.) yielded SPEEDUP of 2.197x (9.537e-07s -> 4.341e-07s), will amortize in 115592.1 ops by saving 5.195e-07s per op. +In 1 tuning rounds (tot. 0.18s, 0.18s for constructor, 3 clones) obtained a SPEEDUP of 119.7% (2.197x) (from 2.097 to 4.607 Mflops). Backsolving we should get a unitary vector: %%MatrixMarket matrix array real general @@ -8671,185 +8685,159 @@ /build/reproducible-path/librsb-1.3.0.2+dfsg/examples/fortran Building a matrix with 210 nnz, 20 x 20 Duplicates check: 210 - 0 = 210 - converted COO to RSB in 2.582e-02 s (100.00 %) - analyzed arrays in 3.883e-03 s (15.04 %) - cleaned-up arrays in 9.537e-07 s (0.00 %) - deduplicated arrays in 1.907e-06 s (0.01 %) - sorted arrays in 6.942e-03 s (26.88 %) - shuffled partitions in 7.444e-03 s (28.83 %) - memory allocations took 2.909e-05 s (0.11 %) - leafs setup took 3.815e-06 s (0.01 %) - halfword conversion took 7.509e-03 s (29.08 %) -Built (20 x 20)[0x562957e8d9f0]{D} @ (0(0..0),0(0..0)) (210 nnz, 10 nnz/r) flags 0x2446396 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 22, symflags:'LS' -Will autotune matrix: 20 x 20, type D, 210 nnz, 10 nnz/r, 30 subms, 22 lsubms, 3.7524 bpnz. -Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:3.32e-08 -Starting autotuning (16 x 3.31998e-08 s stages, transA=N, nrhs=1, timer gran.=3.31998e-08), 42 suggested as starting thread count(default). -3 iterations (42 th.) took 0.002113s; avg 0.0007043s ( +/- 63.81/111.54 %); best 0.0002549s; worst 0.00149s; std dev. 0.0005574 (taking best). -Reference operation time is 0.000254869 s (3.296 Mflops) with 42 threads. -Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=cols) (max 6 steps, inclusive 3 grace steps) on: 20 x 20, type D, 210 nnz, 10 nnz/r, 30 subms, 22 lsubms, 3.7524 bpnz (tpop: 0.0002549 Mflops: 3.296) -Merge (22 -> 16 leaves) took w.c.t. of 0.000288s, ~0.0002792s of computing time (of which 2.384e-06s sorting, 5.96e-06s analysis) -3 iterations (42 th.) took 0.0123s; avg 0.0041s ( +/- 7.11/ 14.13 %); best 0.003808s; worst 0.004679s; std dev. 0.0004096 (taking best). -Reference operation time is 0.00380802 s (0.2206 Mflops) with 42 threads. -After merge step 1: tpop: 0.003808 s ~Mflops: 0.221 nsubm:16 otn:42 -Applying merge (22 -> 16 leaves, 42 th.) yielded SLOWDOWN (1th of 3 tolerable) of 14.941x: 0.0002549s -> 0.003808s. + converted COO to RSB in 2.724e-01 s (100.00 %) + analyzed arrays in 8.391e-02 s (30.81 %) + cleaned-up arrays in 3.815e-06 s (0.00 %) + deduplicated arrays in 5.007e-06 s (0.00 %) + sorted arrays in 4.834e-02 s (17.75 %) + shuffled partitions in 7.200e-02 s (26.44 %) + memory allocations took 9.394e-05 s (0.03 %) + leafs setup took 1.693e-05 s (0.01 %) + halfword conversion took 6.797e-02 s (24.96 %) +Built (20 x 20)[0x56308928f9f0]{D} @ (0(0..0),0(0..0)) (210 nnz, 10 nnz/r) flags 0x2446396 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 23, symflags:'LS' +Will autotune matrix: 20 x 20, type D, 210 nnz, 10 nnz/r, 32 subms, 23 lsubms, 3.7524 bpnz. +Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:1.068e-06 +Starting autotuning (16 x 1.06801e-06 s stages, transA=N, nrhs=1, timer gran.=1.06801e-06), 20 suggested as starting thread count(default). +3 iterations (20 th.) took 0.08492s; avg 0.02831s ( +/- 31.69/ 32.90 %); best 0.01934s; worst 0.03762s; std dev. 0.007468 (taking best). +Reference operation time is 0.0193379 s (0.04344 Mflops) with 20 threads. +Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=cols) (max 6 steps, inclusive 3 grace steps) on: 20 x 20, type D, 210 nnz, 10 nnz/r, 32 subms, 23 lsubms, 3.7524 bpnz (tpop: 0.01934 Mflops: 0.043) +Merge (23 -> 19 leaves) took w.c.t. of 0.04701s, ~0.05201s of computing time (of which 5.96e-06s sorting, 1.717e-05s analysis) +3 iterations (20 th.) took 0.09324s; avg 0.03108s ( +/- 10.01/ 15.68 %); best 0.02797s; worst 0.03595s; std dev. 0.00349 (taking best). +Reference operation time is 0.027967 s (0.03004 Mflops) with 20 threads. +After merge step 1: tpop: 0.02797 s ~Mflops: 0.030 nsubm:19 otn:20 +Applying merge (23 -> 19 leaves, 20 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.446x: 0.01934s -> 0.02797s. Skipping further merge based tests after 1 definite performance degradations in a row (and last exceeding limit). -A total of 1 merge steps (of max 6) (22 -> 16 subms) took 0.01261s (of which 0.000293s partitioning, 0s I/O); computing times: 0.0002792s in par. loops, 2.384e-06s sorting, 5.96e-06s analyzing) -Total merge + benchmarking process took 0.01261s, equivalent to 49.5/49.5 new/old ops (0.01302s for 1 clones -- as 51.1/51.1 ops, or 51.1/51.1 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) +A total of 1 merge steps (of max 6) (23 -> 19 subms) took 0.1403s (of which 0.04703s partitioning, 0s I/O); computing times: 0.05201s in par. loops, 5.96e-06s sorting, 1.717e-05s analyzing) +Total merge + benchmarking process took 0.1403s, equivalent to 7.3/7.3 new/old ops (0.07591s for 1 clones -- as 3.9/3.9 ops, or 3.9/3.9 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) Merging based autotuning FAILED (=NO SPEEDUP); let's try splitting then... -3 iterations (42 th.) took 0.009579s; avg 0.003193s ( +/- 27.18/ 13.84 %); best 0.002325s; worst 0.003635s; std dev. 0.0006137 (taking best). -Reference operation time is 0.00232506 s (0.3613 Mflops) with 42 threads. -Starting split (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=cols) (max 6 steps, inclusive 3 grace steps) on: 20 x 20, type D, 210 nnz, 10 nnz/r, 30 subms, 22 lsubms, 3.7524 bpnz (tpop: 0.002325 Mflops: 0.361) -Split (22 -> 51 leaves, 30 -> 70 subms) took 0.002639s (of which: 4.053e-06s analysis, -1.925e+10s mem.mgmt); compute time: 0.007694s overall, 8.583e-06s searches, 0.007685s shuffle, 0.00618s switch, 0.0002708s quadrants. -3 iterations (42 th.) took 0.01401s; avg 0.004669s ( +/- 7.70/ 12.80 %); best 0.00431s; worst 0.005267s; std dev. 0.0004256 (taking best). -Reference operation time is 0.00430989 s (0.1949 Mflops) with 42 threads. -After split step 1: tpop: 0.00431 s ~Mflops: 0.195 nsubm:51 otn:42 -Applying split (22 -> 51 leaves, 42 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.854x: 0.002325s -> 0.00431s. +3 iterations (20 th.) took 0.08s; avg 0.02667s ( +/- 25.06/ 20.00 %); best 0.01998s; worst 0.032s; std dev. 0.004998 (taking best). +Reference operation time is 0.0199821 s (0.04204 Mflops) with 20 threads. +Starting split (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=cols) (max 6 steps, inclusive 3 grace steps) on: 20 x 20, type D, 210 nnz, 10 nnz/r, 32 subms, 23 lsubms, 3.7524 bpnz (tpop: 0.01998 Mflops: 0.042) +Split (23 -> 53 leaves, 32 -> 73 subms) took 0.05988s (of which: 9.06e-06s analysis, -1.887e+10s mem.mgmt); compute time: 0.3847s overall, 3.171e-05s searches, 0.3846s shuffle, 0.3677s switch, 3.958e-05s quadrants. +3 iterations (20 th.) took 0.07978s; avg 0.02659s ( +/- 40.34/ 35.15 %); best 0.01587s; worst 0.03594s; std dev. 0.008253 (taking best). +Reference operation time is 0.015867 s (0.05294 Mflops) with 20 threads. +After split step 1: tpop: 0.01587 s ~Mflops: 0.053 nsubm:53 otn:20 +Applying split (23 -> 53 leaves, 20 th.) yielded SPEEDUP of 1.259x: 0.01998s -> 0.01587s, so taking this instance. +Split (53 -> 128 leaves, 73 -> 174 subms) took 0.0239s (of which: 1.502e-05s analysis, -4.46e+10s mem.mgmt); compute time: 0.002888s overall, 5.126e-05s searches, 0.002837s shuffle, 0.001222s switch, 0.0002906s quadrants. +3 iterations (20 th.) took 0.06391s; avg 0.0213s ( +/- 43.21/ 30.43 %); best 0.0121s; worst 0.02779s; std dev. 0.006688 (taking best). +Reference operation time is 0.012099 s (0.06943 Mflops) with 20 threads. +After split step 2: tpop: 0.0121 s ~Mflops: 0.069 nsubm:128 otn:20 +Applying split (53 -> 128 leaves, 20 th.) yielded SPEEDUP of 1.311x: 0.01587s -> 0.0121s, so taking this instance. +Split (128 -> 146 leaves, 174 -> 198 subms) took 0.03951s (of which: 7.486e-05s analysis, -1.029e+10s mem.mgmt); compute time: 0.0008197s overall, 1.597e-05s searches, 0.0008037s shuffle, 0.000504s switch, 6.413e-05s quadrants. +3 iterations (20 th.) took 0.05997s; avg 0.01999s ( +/- 40.27/ 66.93 %); best 0.01194s; worst 0.03337s; std dev. 0.009525 (taking best). +Reference operation time is 0.01194 s (0.07035 Mflops) with 20 threads. +After split step 3: tpop: 0.01194 s ~Mflops: 0.070 nsubm:146 otn:20 +Applying split (128 -> 146 leaves, 20 th.) yielded SPEEDUP of 1.013x: 0.0121s -> 0.01194s, so taking this instance. +Split (146 -> 146 leaves, 198 -> 198 subms) took 0.0303s (of which: 3.004e-05s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. +3 iterations (20 th.) took 0.07194s; avg 0.02398s ( +/- 33.29/ 49.81 %); best 0.016s; worst 0.03592s; std dev. 0.008603 (taking best). +Reference operation time is 0.015996 s (0.05251 Mflops) with 20 threads. +After split step 4: tpop: 0.016 s ~Mflops: 0.053 nsubm:146 otn:20 +Applying split (146 -> 146 leaves, 20 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.340x: 0.01194s -> 0.016s. Skipping further split based tests after 1 definite performance degradations in a row (and last exceeding limit). -A total of 1 split steps (of max 6) (22 -> 51 subms) took 0.01673s (of which 0.002706s partitioning, 0s I/O); computing times: 0.007694s in par. loops, 8.583e-06s sorting, 4.053e-06s analyzing) -Total split + benchmarking process took 0.01673s, equivalent to 7.2/7.2 new/old ops (0.01147s for 1 clones -- as 4.9/4.9 ops, or 4.9/4.9 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) -In 1 tuning rounds (tot. 0.066s, 0.024s for constructor, 2 clones) obtained NO speedup (best stays 0.3613 Mflops). - autotuner chose 42 threads -Will autotune matrix: 20 x 20, type D, 210 nnz, 10 nnz/r, 30 subms, 22 lsubms, 3.7524 bpnz. -Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:3.32e-08 -Starting autotuning (16 x 3.31998e-08 s stages, transA=N, nrhs=1, timer gran.=3.31998e-08), 42 suggested as starting thread count(default). -3 iterations (42 th.) took 0.01119s; avg 0.003729s ( +/- 1.72/ 1.25 %); best 0.003665s; worst 0.003776s; std dev. 4.696e-05 (taking best). -~ 42 threads: 0.003665s (0.23 Mflops) (0/2 degradations so far) - -3 iterations (41 th.) took 0.0112s; avg 0.003733s ( +/- 0.44/ 0.56 %); best 0.003717s; worst 0.003754s; std dev. 1.548e-05 (taking best). - 41 threads: 0.003717s (0.23 Mflops) (1/2 degradations so far) - -3 iterations (40 th.) took 0.0112s; avg 0.003732s ( +/- 0.44/ 0.26 %); best 0.003716s; worst 0.003742s; std dev. 1.164e-05 (taking best). - 40 threads: 0.003716s (0.23 Mflops) (2/2 degradations so far) - -Best threads choice is 42; starting threads were 42; max speed gap is 1x; search took 0.034s. -Starting merge (and threads) based auto-tuning procedure (transA=N, nrhs=1, order=cols) (max 6 steps, inclusive 3 grace steps) on: 20 x 20, type D, 210 nnz, 10 nnz/r, 30 subms, 22 lsubms, 3.7524 bpnz (tpop: 0.003665 Mflops: 0.229) -Merge (22 -> 16 leaves) took w.c.t. of 0.00192s, ~1.097e-05s of computing time (of which 1.907e-06s sorting, 2.861e-06s analysis) -3 iterations (42 th.) took 0.01264s; avg 0.004212s ( +/- 10.91/ 21.38 %); best 0.003753s; worst 0.005113s; std dev. 0.0006369 (taking best). -~ 42 threads: 0.003753s (0.22 Mflops) (0/2 degradations so far) - -3 iterations (41 th.) took 0.01128s; avg 0.003761s ( +/- 3.16/ 4.17 %); best 0.003642s; worst 0.003918s; std dev. 0.0001158 (taking best). - 41 threads: 0.003642s (0.23 Mflops) (0/2 degradations so far) - -3 iterations (40 th.) took 0.01121s; avg 0.003738s ( +/- 0.54/ 0.48 %); best 0.003718s; worst 0.003756s; std dev. 1.555e-05 (taking best). - 40 threads: 0.003718s (0.23 Mflops) (1/2 degradations so far) - -3 iterations (39 th.) took 0.009576s; avg 0.003192s ( +/- 34.77/ 17.89 %); best 0.002082s; worst 0.003763s; std dev. 0.0007849 (taking best). - 39 threads: 0.002082s (0.4 Mflops) (0/2 degradations so far) - -3 iterations (38 th.) took 0.01116s; avg 0.003721s ( +/- 0.28/ 0.34 %); best 0.003711s; worst 0.003734s; std dev. 9.581e-06 (taking best). - 38 threads: 0.003711s (0.23 Mflops) (1/2 degradations so far) - -3 iterations (37 th.) took 0.01123s; avg 0.003744s ( +/- 2.37/ 2.71 %); best 0.003655s; worst 0.003845s; std dev. 7.809e-05 (taking best). - 37 threads: 0.003655s (0.23 Mflops) (2/2 degradations so far) - -Best threads choice is 39; starting threads were 42; max speed gap is 1.8x; search took 0.067s. -After merge step 1: tpop: 0.002082 s ~Mflops: 0.403 nsubm:16 otn:39 -Applying merge (22 -> 16 leaves, 39 th.) yielded SPEEDUP of 1.760x: 0.003665s -> 0.002082s, so taking this instance. -Merge (16 -> 10 leaves) took w.c.t. of 0.001861s, ~1.001e-05s of computing time (of which 1.907e-06s sorting, 3.099e-06s analysis) -3 iterations (42 th.) took 0.0149s; avg 0.004966s ( +/- 22.29/ 15.53 %); best 0.003859s; worst 0.005737s; std dev. 0.0008025 (taking best). -~ 42 threads: 0.003859s (0.22 Mflops) (0/2 degradations so far) - -3 iterations (41 th.) took 0.009396s; avg 0.003132s ( +/- 38.29/ 20.15 %); best 0.001933s; worst 0.003763s; std dev. 0.0008483 (taking best). - 41 threads: 0.001933s (0.43 Mflops) (0/2 degradations so far) - -3 iterations (40 th.) took 0.01122s; avg 0.003741s ( +/- 1.30/ 1.19 %); best 0.003692s; worst 0.003785s; std dev. 3.818e-05 (taking best). - 40 threads: 0.003692s (0.23 Mflops) (1/2 degradations so far) - -3 iterations (39 th.) took 0.01119s; avg 0.003731s ( +/- 0.32/ 0.21 %); best 0.003719s; worst 0.003739s; std dev. 8.572e-06 (taking best). - 39 threads: 0.003719s (0.23 Mflops) (2/2 degradations so far) - -Best threads choice is 41; starting threads were 42; max speed gap is 2x; search took 0.047s. -After merge step 2: tpop: 0.001933 s ~Mflops: 0.435 nsubm:10 otn:41 -Applying merge (16 -> 10 leaves, 41 th.) yielded SPEEDUP of 1.077x: 0.002082s -> 0.001933s, so taking this instance. -Merge (10 -> 8 leaves) took w.c.t. of 2.289e-05s, ~8.821e-06s of computing time (of which 9.537e-07s sorting, 5.96e-06s analysis) -3 iterations (42 th.) took 0.01108s; avg 0.003693s ( +/- 4.25/ 4.52 %); best 0.003536s; worst 0.00386s; std dev. 0.0001325 (taking best). -~ 42 threads: 0.003536s (0.24 Mflops) (0/2 degradations so far) - -3 iterations (41 th.) took 0.01143s; avg 0.00381s ( +/- 1.47/ 1.19 %); best 0.003754s; worst 0.003855s; std dev. 4.208e-05 (taking best). - 41 threads: 0.003754s (0.22 Mflops) (1/2 degradations so far) - -3 iterations (40 th.) took 0.005778s; avg 0.001926s ( +/- 97.61/ 94.81 %); best 4.601e-05s; worst 0.003752s; std dev. 0.001513 (taking best). - 40 threads: 4.601e-05s (18 Mflops) (0/2 degradations so far) - -3 iterations (39 th.) took 0.0001681s; avg 5.603e-05s ( +/- 17.87/ 23.40 %); best 4.601e-05s; worst 6.914e-05s; std dev. 9.692e-06 (taking best). - 39 threads: 4.601e-05s (18 Mflops) (0/2 degradations so far) - -3 iterations (38 th.) took 0.0001991s; avg 6.636e-05s ( +/- 27.78/ 26.83 %); best 4.792e-05s; worst 8.416e-05s; std dev. 1.48e-05 (taking best). - 38 threads: 4.792e-05s (18 Mflops) (1/2 degradations so far) - -3 iterations (37 th.) took 0.0001621s; avg 5.404e-05s ( +/- 3.82/ 3.68 %); best 5.198e-05s; worst 5.603e-05s; std dev. 1.656e-06 (taking best). - 37 threads: 5.198e-05s (16 Mflops) (2/2 degradations so far) - -Best threads choice is 40; starting threads were 42; max speed gap is 82x; search took 0.029s. -After merge step 3: tpop: 4.601e-05 s ~Mflops: 18.255 nsubm:8 otn:40 -Applying merge (10 -> 8 leaves, 40 th.) yielded SPEEDUP of 42.005x: 0.001933s -> 4.601e-05s, so taking this instance. -Merge (8 -> 6 leaves) took w.c.t. of 1.097e-05s, ~4.053e-06s of computing time (of which 2.146e-06s sorting, 2.146e-06s analysis) -3 iterations (42 th.) took 0.000138s; avg 4.601e-05s ( +/- 8.81/ 15.54 %); best 4.196e-05s; worst 5.317e-05s; std dev. 5.073e-06 (taking best). -~ 42 threads: 4.196e-05s (20 Mflops) (0/2 degradations so far) - -3 iterations (41 th.) took 0.0001421s; avg 4.737e-05s ( +/- 19.97/ 30.87 %); best 3.791e-05s; worst 6.199e-05s; std dev. 1.049e-05 (taking best). - 41 threads: 3.791e-05s (22 Mflops) (0/2 degradations so far) - -3 iterations (40 th.) took 0.0001409s; avg 4.697e-05s ( +/- 10.66/ 12.69 %); best 4.196e-05s; worst 5.293e-05s; std dev. 4.528e-06 (taking best). - 40 threads: 4.196e-05s (20 Mflops) (1/2 degradations so far) - -3 iterations (39 th.) took 0.0001261s; avg 4.204e-05s ( +/- 4.73/ 4.91 %); best 4.005e-05s; worst 4.411e-05s; std dev. 1.656e-06 (taking best). - 39 threads: 4.005e-05s (21 Mflops) (2/2 degradations so far) - -Best threads choice is 41; starting threads were 42; max speed gap is 1.1x; search took 0.00057s. -After merge step 4: tpop: 3.791e-05 s ~Mflops: 22.159 nsubm:6 otn:41 -Applying merge (8 -> 6 leaves, 41 th.) yielded SPEEDUP of 1.214x: 4.601e-05s -> 3.791e-05s, so taking this instance. -Merge (6 -> 3 leaves) took w.c.t. of 6.914e-06s, ~3.099e-06s of computing time (of which 1.192e-06s sorting, 9.537e-07s analysis) -3 iterations (42 th.) took 8.178e-05s; avg 2.726e-05s ( +/- 19.53/ 32.07 %); best 2.193e-05s; worst 3.6e-05s; std dev. 6.23e-06 (taking best). -~ 42 threads: 2.193e-05s (38 Mflops) (0/2 degradations so far) - -3 iterations (41 th.) took 6.89e-05s; avg 2.297e-05s ( +/- 4.50/ 9.00 %); best 2.193e-05s; worst 2.503e-05s; std dev. 1.461e-06 (taking best). - 41 threads: 2.193e-05s (38 Mflops) (0/2 degradations so far) - -3 iterations (40 th.) took 7.2e-05s; avg 2.4e-05s ( +/- 20.53/ 16.23 %); best 1.907e-05s; worst 2.789e-05s; std dev. 3.675e-06 (taking best). - 40 threads: 1.907e-05s (44 Mflops) (0/2 degradations so far) - -3 iterations (39 th.) took 6.819e-05s; avg 2.273e-05s ( +/- 6.64/ 5.94 %); best 2.122e-05s; worst 2.408e-05s; std dev. 1.173e-06 (taking best). - 39 threads: 2.122e-05s (40 Mflops) (1/2 degradations so far) - -3 iterations (38 th.) took 6.294e-05s; avg 2.098e-05s ( +/- 10.23/ 10.23 %); best 1.884e-05s; worst 2.313e-05s; std dev. 1.752e-06 (taking best). - 38 threads: 1.884e-05s (45 Mflops) (0/2 degradations so far) - -3 iterations (37 th.) took 7.105e-05s; avg 2.368e-05s ( +/- 19.46/ 22.82 %); best 1.907e-05s; worst 2.909e-05s; std dev. 4.126e-06 (taking best). - 37 threads: 1.907e-05s (44 Mflops) (1/2 degradations so far) - -3 iterations (36 th.) took 0.0003791s; avg 0.0001264s ( +/- 82.45/157.92 %); best 2.217e-05s; worst 0.0003259s; std dev. 0.0001412 (taking best). - 36 threads: 2.217e-05s (38 Mflops) (2/2 degradations so far) - -Best threads choice is 38; starting threads were 42; max speed gap is 1.2x; search took 0.00098s. -After merge step 5: tpop: 1.884e-05 s ~Mflops: 44.598 nsubm:3 otn:38 -Applying merge (6 -> 3 leaves, 38 th.) yielded SPEEDUP of 2.013x: 3.791e-05s -> 1.884e-05s, so taking this instance. -Merge (3 -> 1 leaves) took w.c.t. of 1.287e-05s, ~6.199e-06s of computing time (of which 9.537e-07s sorting, 1.907e-06s analysis) -3 iterations (42 th.) took 2.861e-06s; avg 9.537e-07s ( +/- 0.00/ 0.00 %); best 9.537e-07s; worst 9.537e-07s; std dev. 0 (taking best). -~ 42 threads: 9.537e-07s (8.8e+02 Mflops) (0/2 degradations so far) - -3 iterations (41 th.) took 3.099e-06s; avg 1.033e-06s ( +/- 7.69/ 15.38 %); best 9.537e-07s; worst 1.192e-06s; std dev. 1.124e-07 (taking best). - 41 threads: 9.537e-07s (8.8e+02 Mflops) (0/2 degradations so far) - -3 iterations (40 th.) took 2.861e-06s; avg 9.537e-07s ( +/- 0.00/ 0.00 %); best 9.537e-07s; worst 9.537e-07s; std dev. 0 (taking best). - 40 threads: 9.537e-07s (8.8e+02 Mflops) (0/2 degradations so far) - -3 iterations (39 th.) took 3.099e-06s; avg 1.033e-06s ( +/- 7.69/ 15.38 %); best 9.537e-07s; worst 1.192e-06s; std dev. 1.124e-07 (taking best). - 39 threads: 9.537e-07s (8.8e+02 Mflops) (0/2 degradations so far) - -3 iterations (38 th.) took 2.861e-06s; avg 9.537e-07s ( +/- 0.00/ 0.00 %); best 9.537e-07s; worst 9.537e-07s; std dev. 0 (taking best). - 38 threads: 9.537e-07s (8.8e+02 Mflops) (0/2 degradations so far) - -3 iterations (37 th.) took 3.099e-06s; avg 1.033e-06s ( +/- 7.69/ 15.38 %); best 9.537e-07s; worst 1.192e-06s; std dev. 1.124e-07 (taking best). - 37 threads: 9.537e-07s (8.8e+02 Mflops) (0/2 degradations so far) - -3 iterations (36 th.) took 3.099e-06s; avg 1.033e-06s ( +/- 7.69/ 15.38 %); best 9.537e-07s; worst 1.192e-06s; std dev. 1.124e-07 (taking best). - 36 threads: 9.537e-07s (8.8e+02 Mflops) (0/2 degradations so far) - -3 iterations (35 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 94.78/ 50.00 %); best 3.32e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). - 35 threads: 3.32e-08s (2.5e+04 Mflops) (0/2 degradations so far) - -3 iterations (34 th.) took 2.146e-06s; avg 7.153e-07s ( +/- 95.36/ 66.67 %); best 3.32e-08s; worst 1.192e-06s; std dev. 5.15e-07 (taking best). - 34 threads: 3.32e-08s (2.5e+04 Mflops) (0/2 degradations so far) - -3 iterations (33 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 94.78/ 50.00 %); best 3.32e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). - 33 threads: 3.32e-08s (2.5e+04 Mflops) (0/2 degradations so far) - -3 iterations (32 th.) took 3.099e-06s; avg 1.033e-06s ( +/- 7.69/ 15.38 %); best 9.537e-07s; worst 1.192e-06s; std dev. 1.124e-07 (taking best). - 32 threads: 9.537e-07s (8.8e+02 Mflops) (1/2 degradations so far) - -3 iterations (31 th.) took 2.861e-06s; avg 9.537e-07s ( +/- 0.00/ 0.00 %); best 9.537e-07s; worst 9.537e-07s; std dev. 0 (taking best). - 31 threads: 9.537e-07s (8.8e+02 Mflops) (2/2 degradations so far) - -Best threads choice is 35; starting threads were 42; max speed gap is 29x; search took 9e-05s. -After merge step 6: tpop: 3.32e-08 s ~Mflops: 25301.367 nsubm:1 otn:35 -Applying merge (3 -> 1 leaves, 35 th.) yielded SPEEDUP of 567.325x: 1.884e-05s -> 3.32e-08s, so taking this instance. -Merged all the matrix leaves: no reason to continue merging. -A total of 6 merge steps (of max 6) (22 -> 1 subms) took 0.1713s (of which 0.00386s partitioning, 0s I/O); computing times: 4.315e-05s in par. loops, 9.06e-06s sorting, 1.693e-05s analyzing) -Total merge + benchmarking process took 0.1713s, equivalent to 5159396.8/46.7 new/old ops (0.03399s for 7 clones -- as 1023770.2/9.3 ops, or 146252.9/1.3 ops per clone), SPEEDUP of 110391.382x -Applying multi-merge (22 -> 1 leaves, 6 steps, 42 -> 35 th.sp.) yielded SPEEDUP of 110391.382x (0.003665s -> 3.32e-08s), will amortize in 46.7 ops by saving 0.003665s per op. -In 1 tuning rounds (tot. 0.22s, 0.034s for constructor, 7 clones) obtained a SPEEDUP of 11039038.2% (1.104e+05x) (from 0.2292 to 2.53e+04 Mflops). +A total of 4 split steps (of max 6) (23 -> 146 subms) took 0.636s (of which 0.1548s partitioning, 0s I/O); computing times: 0.3884s in par. loops, 9.894e-05s sorting, 0.000129s analyzing) +Total split + benchmarking process took 0.636s, equivalent to 53.3/31.8 new/old ops (0.292s for 4 clones -- as 24.5/14.6 ops, or 6.1/3.7 ops per clone), SPEEDUP of 1.674x +Applying multi-split (23 -> 146 leaves, 3 steps, 0 -> 20 th.sp.) yielded SPEEDUP of 1.674x (0.01998s -> 0.01194s), will amortize in 79.1 ops by saving 0.008042s per op. +In 1 tuning rounds (tot. 1.1s, 0.37s for constructor, 5 clones) obtained a SPEEDUP of 67.4% (1.674x) (from 0.04204 to 0.07035 Mflops). + autotuner chose 20 threads +Will autotune matrix: 20 x 20, type D, 210 nnz, 10 nnz/r, 198 subms, 146 lsubms, 4.2286 bpnz. +Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:1.068e-06 +Starting autotuning (16 x 1.06801e-06 s stages, transA=N, nrhs=1, timer gran.=1.06801e-06), 20 suggested as starting thread count(default). +3 iterations (20 th.) took 0.06761s; avg 0.02254s ( +/- 11.30/ 22.49 %); best 0.01999s; worst 0.0276s; std dev. 0.003584 (taking best). +~ 20 threads: 0.01999s (0.042 Mflops) (0/2 degradations so far) - +3 iterations (19 th.) took 0.07311s; avg 0.02437s ( +/- 0.67/ 0.49 %); best 0.02421s; worst 0.02449s; std dev. 0.0001192 (taking best). + 19 threads: 0.02421s (0.035 Mflops) (1/2 degradations so far) - +3 iterations (18 th.) took 0.07483s; avg 0.02494s ( +/- 24.49/ 15.10 %); best 0.01884s; worst 0.02871s; std dev. 0.004358 (taking best). + 18 threads: 0.01884s (0.045 Mflops) (0/2 degradations so far) - +3 iterations (17 th.) took 0.09996s; avg 0.03332s ( +/- 16.03/ 17.25 %); best 0.02798s; worst 0.03907s; std dev. 0.004536 (taking best). + 17 threads: 0.02798s (0.03 Mflops) (1/2 degradations so far) - +3 iterations (16 th.) took 0.09195s; avg 0.03065s ( +/- 8.93/ 17.37 %); best 0.02791s; worst 0.03597s; std dev. 0.003766 (taking best). + 16 threads: 0.02791s (0.03 Mflops) (2/2 degradations so far) - +Best threads choice is 18; starting threads were 20; max speed gap is 1.5x; search took 0.41s. +Starting merge (and threads) based auto-tuning procedure (transA=N, nrhs=1, order=cols) (max 6 steps, inclusive 3 grace steps) on: 20 x 20, type D, 210 nnz, 10 nnz/r, 198 subms, 146 lsubms, 4.2286 bpnz (tpop: 0.01884 Mflops: 0.045) +Merge (146 -> 99 leaves) took w.c.t. of 0.01995s, ~0.0007892s of computing time (of which 4.172e-05s sorting, 2.384e-05s analysis) +3 iterations (20 th.) took 0.08397s; avg 0.02799s ( +/- 28.45/ 28.49 %); best 0.02003s; worst 0.03596s; std dev. 0.006507 (taking best). +~ 20 threads: 0.02003s (0.042 Mflops) (0/2 degradations so far) - +3 iterations (19 th.) took 0.06798s; avg 0.02266s ( +/- 11.94/ 6.01 %); best 0.01996s; worst 0.02402s; std dev. 0.001913 (taking best). + 19 threads: 0.01996s (0.042 Mflops) (0/2 degradations so far) - +3 iterations (18 th.) took 0.07193s; avg 0.02398s ( +/- 16.54/ 16.52 %); best 0.02001s; worst 0.02794s; std dev. 0.003236 (taking best). + 18 threads: 0.02001s (0.042 Mflops) (1/2 degradations so far) - +3 iterations (17 th.) took 0.07197s; avg 0.02399s ( +/- 33.16/ 16.61 %); best 0.01604s; worst 0.02798s; std dev. 0.005625 (taking best). + 17 threads: 0.01604s (0.052 Mflops) (0/2 degradations so far) - +3 iterations (16 th.) took 0.07605s; avg 0.02535s ( +/- 5.38/ 10.29 %); best 0.02399s; worst 0.02796s; std dev. 0.001846 (taking best). + 16 threads: 0.02399s (0.035 Mflops) (1/2 degradations so far) - +3 iterations (15 th.) took 0.07188s; avg 0.02396s ( +/- 33.05/ 16.68 %); best 0.01604s; worst 0.02796s; std dev. 0.005599 (taking best). + 15 threads: 0.01604s (0.052 Mflops) (2/2 degradations so far) - +Best threads choice is 17; starting threads were 20; max speed gap is 1.5x; search took 0.44s. +After merge step 1: tpop: 0.01604 s ~Mflops: 0.052 nsubm:99 otn:17 +Applying merge (146 -> 99 leaves, 17 th.) yielded SPEEDUP of 1.175x: 0.01884s -> 0.01604s, so taking this instance. +Merge (99 -> 68 leaves) took w.c.t. of 0.02798s, ~0.0002s of computing time (of which 3.338e-05s sorting, 2.098e-05s analysis) +3 iterations (20 th.) took 0.07194s; avg 0.02398s ( +/- 14.66/ 16.79 %); best 0.02046s; worst 0.02801s; std dev. 0.0031 (taking best). +~ 20 threads: 0.02046s (0.041 Mflops) (0/2 degradations so far) - +3 iterations (19 th.) took 0.06398s; avg 0.02133s ( +/- 6.24/ 12.34 %); best 0.02s; worst 0.02396s; std dev. 0.001861 (taking best). + 19 threads: 0.02s (0.042 Mflops) (0/2 degradations so far) - +3 iterations (18 th.) took 0.07194s; avg 0.02398s ( +/- 33.71/ 35.35 %); best 0.0159s; worst 0.03246s; std dev. 0.006768 (taking best). + 18 threads: 0.0159s (0.053 Mflops) (0/2 degradations so far) - +3 iterations (17 th.) took 0.07197s; avg 0.02399s ( +/- 16.79/ 21.56 %); best 0.01996s; worst 0.02916s; std dev. 0.003842 (taking best). + 17 threads: 0.01996s (0.042 Mflops) (1/2 degradations so far) - +3 iterations (16 th.) took 0.06394s; avg 0.02131s ( +/- 23.21/ 29.52 %); best 0.01637s; worst 0.02761s; std dev. 0.004686 (taking best). + 16 threads: 0.01637s (0.051 Mflops) (2/2 degradations so far) - +Best threads choice is 18; starting threads were 20; max speed gap is 1.3x; search took 0.34s. +After merge step 2: tpop: 0.0159 s ~Mflops: 0.053 nsubm:68 otn:18 +Applying merge (99 -> 68 leaves, 18 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=1.00880x): 0.01604s -> 0.0159s, so IGNORING this instance. +Merge (68 -> 51 leaves) took w.c.t. of 0.02001s, ~0.0001242s of computing time (of which 1.884e-05s sorting, 1.907e-05s analysis) +3 iterations (20 th.) took 0.1079s; avg 0.03597s ( +/- 33.33/ 55.44 %); best 0.02398s; worst 0.05591s; std dev. 0.0142 (taking best). +~ 20 threads: 0.02398s (0.035 Mflops) (0/2 degradations so far) - +3 iterations (19 th.) took 0.05993s; avg 0.01998s ( +/- 40.21/ 20.17 %); best 0.01194s; worst 0.02401s; std dev. 0.00568 (taking best). + 19 threads: 0.01194s (0.07 Mflops) (0/2 degradations so far) - +3 iterations (18 th.) took 0.07199s; avg 0.024s ( +/- 0.31/ 0.40 %); best 0.02392s; worst 0.02409s; std dev. 7.125e-05 (taking best). + 18 threads: 0.02392s (0.035 Mflops) (1/2 degradations so far) - +3 iterations (17 th.) took 0.07195s; avg 0.02398s ( +/- 0.13/ 0.07 %); best 0.02395s; worst 0.024s; std dev. 2.282e-05 (taking best). + 17 threads: 0.02395s (0.035 Mflops) (2/2 degradations so far) - +Best threads choice is 19; starting threads were 20; max speed gap is 2x; search took 0.31s. +After merge step 3: tpop: 0.01194 s ~Mflops: 0.070 nsubm:51 otn:19 +Applying merge (68 -> 51 leaves, 19 th.) yielded SPEEDUP of 1.343x: 0.01604s -> 0.01194s, so taking this instance. +Merge (51 -> 36 leaves) took w.c.t. of 0.007991s, ~0.0001087s of computing time (of which 2.193e-05s sorting, 1.693e-05s analysis) +3 iterations (20 th.) took 0.1193s; avg 0.03976s ( +/- 33.73/ 44.83 %); best 0.02635s; worst 0.05759s; std dev. 0.01313 (taking best). +~ 20 threads: 0.02635s (0.032 Mflops) (0/2 degradations so far) - +3 iterations (19 th.) took 0.1046s; avg 0.03488s ( +/- 52.27/ 49.06 %); best 0.01665s; worst 0.052s; std dev. 0.01445 (taking best). + 19 threads: 0.01665s (0.05 Mflops) (0/2 degradations so far) - +3 iterations (18 th.) took 0.1559s; avg 0.05197s ( +/- 69.30/ 84.67 %); best 0.01595s; worst 0.09598s; std dev. 0.03316 (taking best). + 18 threads: 0.01595s (0.053 Mflops) (0/2 degradations so far) - +3 iterations (17 th.) took 0.09598s; avg 0.03199s ( +/- 49.97/ 87.50 %); best 0.01601s; worst 0.05998s; std dev. 0.01986 (taking best). + 17 threads: 0.01601s (0.052 Mflops) (1/2 degradations so far) - +3 iterations (16 th.) took 0.07687s; avg 0.02562s ( +/- 34.05/ 55.97 %); best 0.0169s; worst 0.03996s; std dev. 0.01022 (taking best). + 16 threads: 0.0169s (0.05 Mflops) (2/2 degradations so far) - +Best threads choice is 18; starting threads were 20; max speed gap is 1.7x; search took 0.55s. +After merge step 4: tpop: 0.01595 s ~Mflops: 0.053 nsubm:36 otn:18 +Applying merge (51 -> 36 leaves, 18 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.336x: 0.01194s -> 0.01595s. +Skipping further merge based tests after 1 definite performance degradations in a row (and last exceeding limit). +A total of 4 merge steps (of max 6) (146 -> 36 subms) took 1.861s (of which 0.076s partitioning, 0s I/O); computing times: 0.001222s in par. loops, 0.0001159s sorting, 8.082e-05s analyzing) +Total merge + benchmarking process took 1.861s, equivalent to 155.8/98.8 new/old ops (0.2083s for 3 clones -- as 17.4/11.1 ops, or 5.8/3.7 ops per clone), SPEEDUP of 1.577x +Applying multi-merge (146 -> 51 leaves, 3 steps, 18 -> 19 th.sp.) yielded SPEEDUP of 1.577x (0.01884s -> 0.01194s), will amortize in 270.0 ops by saving 0.006892s per op. +In 1 tuning rounds (tot. 2.3s, 0.21s for constructor, 3 clones) obtained a SPEEDUP of 57.7% (1.577x) (from 0.0446 to 0.07033 Mflops). check results are ok Building a matrix with 36 nnz, 6 x 6 Duplicates check: 36 - 0 = 36 - converted COO to RSB in 5.889e-05 s (100.00 %) - analyzed arrays in 1.597e-05 s (27.13 %) - cleaned-up arrays in 9.537e-07 s (1.62 %) - deduplicated arrays in 0.000e+00 s (0.00 %) - sorted arrays in 2.003e-05 s (34.01 %) - shuffled partitions in 1.407e-05 s (23.89 %) - memory allocations took 4.768e-06 s (8.10 %) - leafs setup took 0.000e+00 s (0.00 %) - halfword conversion took 1.907e-06 s (3.24 %) -Built (6 x 6)[0x562957e92d70]{Z} @ (0(0..6),0(0..6)) (36 nnz, 6 nnz/r) flags 0x20440b4 (coo:0, csr:1, hw:0, ic:1, fi:0), storage: 1, subm: 1, symflags:'UL' + converted COO to RSB in 9.534e-02 s (100.00 %) + analyzed arrays in 3.658e-02 s (38.36 %) + cleaned-up arrays in 3.099e-06 s (0.00 %) + deduplicated arrays in 9.537e-07 s (0.00 %) + sorted arrays in 1.932e-02 s (20.26 %) + shuffled partitions in 3.943e-02 s (41.35 %) + memory allocations took 6.914e-06 s (0.01 %) + leafs setup took 4.053e-06 s (0.00 %) + halfword conversion took 0.000e+00 s (0.00 %) +Built (6 x 6)[0x56308928ff60]{Z} @ (0(0..6),0(0..6)) (36 nnz, 6 nnz/r) flags 0x20440b4 (coo:0, csr:1, hw:0, ic:1, fi:0), storage: 1, subm: 1, symflags:'UL' Read matrix pd.mtx 6 x 6 : 36 Matrix has no symmetry Using NRHS=4 -Repeated USMV took 0.6795E-04 s -A single USMM took 0.3004E-04 s -USMM-to-USMV speed ratio is is 2.262 x +Repeated USMV took 0.5293E-04 s +A single USMM took 0.3409E-04 s +USMM-to-USMV speed ratio is is 1.552 x Call auto-tuning routine.. Repeat measurement. -Tuned USMM took 0.4053E-05 s -Tuned-to-untuned speed ratio is is 7.412 x +Tuned USMM took 0.7868E-05 s +Tuned-to-untuned speed ratio is is 4.333 x FAILED: 0 PASSED: 2 /build/reproducible-path/librsb-1.3.0.2+dfsg/examples/fortran_rsb_fi @@ -8898,240 +8886,254 @@ Loading matrix from file "/build/reproducible-path/librsb-1.3.0.2+dfsg/pd.mtx". Building a matrix with 36 nnz, 6 x 6 Duplicates check: 36 - 0 = 36 - converted COO to RSB in 2.070e-02 s (100.00 %) - analyzed arrays in 5.632e-03 s (27.21 %) - cleaned-up arrays in 5.960e-06 s (0.03 %) - deduplicated arrays in 9.537e-07 s (0.00 %) - sorted arrays in 4.239e-03 s (20.48 %) - shuffled partitions in 7.472e-03 s (36.10 %) - memory allocations took 1.192e-05 s (0.06 %) - leafs setup took 5.007e-06 s (0.02 %) - halfword conversion took 3.319e-03 s (16.04 %) -Built (6 x 6)[0x562201486a20]{D} @ (0(0..0),0(0..0)) (36 nnz, 6 nnz/r) flags 0x42046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 22, symflags:'' + converted COO to RSB in 2.672e-01 s (100.00 %) + analyzed arrays in 7.989e-02 s (29.90 %) + cleaned-up arrays in 1.192e-05 s (0.00 %) + deduplicated arrays in 2.861e-06 s (0.00 %) + sorted arrays in 4.319e-02 s (16.17 %) + shuffled partitions in 6.402e-02 s (23.96 %) + memory allocations took 3.576e-05 s (0.01 %) + leafs setup took 9.060e-06 s (0.00 %) + halfword conversion took 7.997e-02 s (29.93 %) +Built (6 x 6)[0x557aea7b7a20]{D} @ (0(0..0),0(0..0)) (36 nnz, 6 nnz/r) flags 0x42046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 22, symflags:'' Considering D clone. Base matrix: -(6 x 6)[0x56220148f060]{D} @ (0(0..0),0(0..0)) (36 nnz, 6 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 22, symflags:'' +(6 x 6)[0x557aea7bce10]{D} @ (0(0..0),0(0..0)) (36 nnz, 6 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 22, symflags:'' Will use autotuning routine to sample matrix: 6 x 6, type D, 36 nnz, 6 nnz/r, 29 subms, 22 lsubms, 4.6667 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:0.1 -3 iterations (42 th.) took 0.0007401s; avg 0.0002467s ( +/- 7.12/ 11.92 %); best 0.0002291s; worst 0.0002761s; std dev. 2.092e-05 (taking best). -Reference operation time is 0.00022912 s (0.6285 Mflops) with 42 threads. -After 0.000777s, autotuning routine did not find a better threads count configuration. +3 iterations (20 th.) took 0.1199s; avg 0.03997s ( +/- 0.15/ 0.08 %); best 0.03991s; worst 0.04s; std dev. 4.215e-05 (taking best). +Reference operation time is 0.0399101 s (0.003608 Mflops) with 20 threads. +After 0.119996s, autotuning routine did not find a better threads count configuration. Will autotune matrix: 6 x 6, type D, 36 nnz, 6 nnz/r, 29 subms, 22 lsubms, 4.6667 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:0.1 -3 iterations (42 th.) took 0.001009s; avg 0.0003363s ( +/- 13.16/ 7.04 %); best 0.0002921s; worst 0.00036s; std dev. 3.133e-05 (taking best). -Reference operation time is 0.000292063 s (0.493 Mflops) with 42 threads. -Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=2, order=cols) (max 6 steps, inclusive 3 grace steps) on: 6 x 6, type D, 36 nnz, 6 nnz/r, 29 subms, 22 lsubms, 4.6667 bpnz (tpop: 0.0002921 Mflops: 0.493) -Merge (22 -> 16 leaves) took w.c.t. of 0.0004799s, ~0.0004718s of computing time (of which 2.861e-06s sorting, 3.099e-06s analysis) -3 iterations (42 th.) took 0.01255s; avg 0.004182s ( +/- 10.61/ 16.41 %); best 0.003738s; worst 0.004868s; std dev. 0.0004922 (taking best). -Reference operation time is 0.00373793 s (0.03852 Mflops) with 42 threads. -After merge step 1: tpop: 0.003738 s ~Mflops: 0.039 nsubm:16 otn:42 -Applying merge (22 -> 16 leaves, 42 th.) yielded SLOWDOWN (1th of 3 tolerable) of 12.798x: 0.0002921s -> 0.003738s. +3 iterations (20 th.) took 0.1s; avg 0.03333s ( +/- 40.02/ 20.01 %); best 0.01999s; worst 0.04001s; std dev. 0.009433 (taking best). +Reference operation time is 0.019995 s (0.007202 Mflops) with 20 threads. +Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=2, order=cols) (max 6 steps, inclusive 3 grace steps) on: 6 x 6, type D, 36 nnz, 6 nnz/r, 29 subms, 22 lsubms, 4.6667 bpnz (tpop: 0.01999 Mflops: 0.007) +Merge (22 -> 16 leaves) took w.c.t. of 0.004911s, ~0.0001042s of computing time (of which 4.053e-06s sorting, 1.001e-05s analysis) +3 iterations (20 th.) took 0.1151s; avg 0.03836s ( +/- 58.25/ 74.79 %); best 0.01602s; worst 0.06705s; std dev. 0.02131 (taking best). +Reference operation time is 0.016016 s (0.008991 Mflops) with 20 threads. +After merge step 1: tpop: 0.01602 s ~Mflops: 0.009 nsubm:16 otn:20 +Applying merge (22 -> 16 leaves, 20 th.) yielded SPEEDUP of 1.248x: 0.01999s -> 0.01602s, so taking this instance. +Merge (16 -> 10 leaves) took w.c.t. of 0.01215s, ~4.196e-05s of computing time (of which 5.245e-06s sorting, 1.407e-05s analysis) +3 iterations (20 th.) took 0.1198s; avg 0.03994s ( +/- 49.96/ 49.83 %); best 0.01999s; worst 0.05984s; std dev. 0.01627 (taking best). +Reference operation time is 0.0199862 s (0.007205 Mflops) with 20 threads. +After merge step 2: tpop: 0.01999 s ~Mflops: 0.007 nsubm:10 otn:20 +Applying merge (16 -> 10 leaves, 20 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.248x: 0.01602s -> 0.01999s. Skipping further merge based tests after 1 definite performance degradations in a row (and last exceeding limit). -A total of 1 merge steps (of max 6) (22 -> 16 subms) took 0.01305s (of which 0.000484s partitioning, 0s I/O); computing times: 0.0004718s in par. loops, 2.861e-06s sorting, 3.099e-06s analyzing) -Total merge + benchmarking process took 0.01305s, equivalent to 44.7/44.7 new/old ops (5.913e-05s for 1 clones -- as 0.2/0.2 ops, or 0.2/0.2 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) -Merging based autotuning FAILED (=NO SPEEDUP); let's try splitting then... -3 iterations (42 th.) took 0.01096s; avg 0.003652s ( +/- 2.80/ 2.33 %); best 0.00355s; worst 0.003737s; std dev. 7.736e-05 (taking best). -Reference operation time is 0.00354981 s (0.04057 Mflops) with 42 threads. -Starting split (same threads) based auto-tuning procedure (transA=N, nrhs=2, order=cols) (max 6 steps, inclusive 3 grace steps) on: 6 x 6, type D, 36 nnz, 6 nnz/r, 29 subms, 22 lsubms, 4.6667 bpnz (tpop: 0.00355 Mflops: 0.041) -Split (22 -> 28 leaves, 29 -> 37 subms) took 0.001853s (of which: 4.053e-06s analysis, -3.5e+09s mem.mgmt); compute time: 2.098e-05s overall, 1.907e-06s searches, 1.907e-05s shuffle, 5.96e-06s switch, 3.099e-06s quadrants. -3 iterations (42 th.) took 0.01257s; avg 0.00419s ( +/- 10.37/ 19.80 %); best 0.003756s; worst 0.00502s; std dev. 0.000587 (taking best). -Reference operation time is 0.00375581 s (0.03834 Mflops) with 42 threads. -After split step 1: tpop: 0.003756 s ~Mflops: 0.038 nsubm:28 otn:42 -Applying split (22 -> 28 leaves, 42 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.058x: 0.00355s -> 0.003756s. -Split (28 -> 28 leaves, 37 -> 37 subms) took 0.001985s (of which: 4.768e-06s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. -3 iterations (42 th.) took 0.0116s; avg 0.003868s ( +/- 5.22/ 9.36 %); best 0.003666s; worst 0.00423s; std dev. 0.0002566 (taking best). -Reference operation time is 0.00366592 s (0.03928 Mflops) with 42 threads. -After split step 2: tpop: 0.003666 s ~Mflops: 0.039 nsubm:28 otn:42 -Applying split (28 -> 28 leaves, 42 th.) yielded SLOWDOWN (2th of 3 tolerable) of 1.033x: 0.00355s -> 0.003666s. -Split (28 -> 28 leaves, 37 -> 37 subms) took 0.001915s (of which: 5.007e-06s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. -3 iterations (42 th.) took 0.007675s; avg 0.002558s ( +/- 86.48/ 59.56 %); best 0.0003459s; worst 0.004082s; std dev. 0.001601 (taking best). -Reference operation time is 0.000345945 s (0.4163 Mflops) with 42 threads. -After split step 3: tpop: 0.0003459 s ~Mflops: 0.416 nsubm:28 otn:42 -Applying split (28 -> 28 leaves, 42 th.) yielded SPEEDUP of 10.261x: 0.00355s -> 0.0003459s, so taking this instance. -Split (28 -> 28 leaves, 37 -> 37 subms) took 4.005e-05s (of which: 4.053e-06s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. -3 iterations (42 th.) took 0.0119s; avg 0.003966s ( +/- 6.22/ 12.32 %); best 0.00372s; worst 0.004455s; std dev. 0.0003456 (taking best). -Reference operation time is 0.00371981 s (0.03871 Mflops) with 42 threads. -After split step 4: tpop: 0.00372 s ~Mflops: 0.039 nsubm:28 otn:42 -Applying split (28 -> 28 leaves, 42 th.) yielded SLOWDOWN (1th of 3 tolerable) of 10.753x: 0.0003459s -> 0.00372s. -Skipping further split based tests after 1 definite performance degradations in a row (and last exceeding limit). -A total of 4 split steps (of max 6) (22 -> 28 subms) took 0.04987s (of which 0.005924s partitioning, 0s I/O); computing times: 2.098e-05s in par. loops, 1.907e-06s sorting, 1.788e-05s analyzing) -Total split + benchmarking process took 0.04987s, equivalent to 144.1/14.0 new/old ops (0.01098s for 2 clones -- as 31.8/3.1 ops, or 15.9/1.5 ops per clone), SPEEDUP of 10.261x -Applying multi-split (22 -> 28 leaves, 3 steps, 0 -> 42 th.sp.) yielded SPEEDUP of 10.261x (0.00355s -> 0.0003459s), will amortize in 15.6 ops by saving 0.003204s per op. -In 1 tuning rounds (tot. 0.086s, 0.011s for constructor, 3 clones) obtained a SPEEDUP of 926.1% (10.26x) (from 0.04057 to 0.4163 Mflops). -After 0.085944s, global autotuning declared speedup of 10.2612 x, when using threads count of 42 and a new matrix: -(6 x 6)[0x562201496a20]{D} @ (0(0..0),0(0..0)) (36 nnz, 6 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 28, symflags:'' +A total of 2 merge steps (of max 6) (22 -> 10 subms) took 0.3481s (of which 0.01709s partitioning, 0s I/O); computing times: 0.0001462s in par. loops, 9.298e-06s sorting, 2.408e-05s analyzing) +Total merge + benchmarking process took 0.3481s, equivalent to 21.7/17.4 new/old ops (0.1959s for 2 clones -- as 12.2/9.8 ops, or 6.1/4.9 ops per clone), SPEEDUP of 1.248x +Applying multi-merge (22 -> 16 leaves, 1 steps, 0 -> 20 th.sp.) yielded SPEEDUP of 1.248x (0.01999s -> 0.01602s), will amortize in 87.5 ops by saving 0.003979s per op. +In 1 tuning rounds (tot. 0.55s, 0.2s for constructor, 2 clones) obtained a SPEEDUP of 24.8% (1.248x) (from 0.007202 to 0.008991 Mflops). +After 0.548119s, global autotuning declared speedup of 1.24844 x, when using threads count of 20 and a new matrix: +(6 x 6)[0x557aea7bf1e0]{D} @ (0(0..0),0(0..0)) (36 nnz, 6 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 16, symflags:'' Considering S clone. Building a matrix with 36 nnz, 6 x 6 Duplicates check: 36 - 0 = 36 - converted COO to RSB in 2.054e-02 s (100.00 %) - analyzed arrays in 5.539e-03 s (26.97 %) - cleaned-up arrays in 1.192e-06 s (0.01 %) - deduplicated arrays in 0.000e+00 s (0.00 %) - sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 7.469e-03 s (36.36 %) - memory allocations took 5.007e-06 s (0.02 %) - leafs setup took 2.861e-06 s (0.01 %) - halfword conversion took 7.521e-03 s (36.62 %) -Built (6 x 6)[0x56220148da80]{S} @ (0(0..0),0(0..0)) (36 nnz, 6 nnz/r) flags 0x42046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 16, symflags:'' + converted COO to RSB in 2.198e-01 s (100.00 %) + analyzed arrays in 9.976e-02 s (45.38 %) + cleaned-up arrays in 2.146e-06 s (0.00 %) + deduplicated arrays in 9.537e-07 s (0.00 %) + sorted arrays in 9.537e-07 s (0.00 %) + shuffled partitions in 6.002e-02 s (27.30 %) + memory allocations took 5.007e-05 s (0.02 %) + leafs setup took 8.106e-06 s (0.00 %) + halfword conversion took 5.997e-02 s (27.28 %) +Built (6 x 6)[0x557aea7bf1e0]{S} @ (0(0..0),0(0..0)) (36 nnz, 6 nnz/r) flags 0x42046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 16, symflags:'' Base matrix: -(6 x 6)[0x56220148da80]{S} @ (0(0..0),0(0..0)) (36 nnz, 6 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 16, symflags:'' +(6 x 6)[0x557aea7bf1e0]{S} @ (0(0..0),0(0..0)) (36 nnz, 6 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 16, symflags:'' Will use autotuning routine to sample matrix: 6 x 6, type S, 36 nnz, 6 nnz/r, 21 subms, 16 lsubms, 4.8889 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:0.1 -3 iterations (42 th.) took 0.01132s; avg 0.003772s ( +/- 1.14/ 0.85 %); best 0.003729s; worst 0.003804s; std dev. 3.164e-05 (taking best). -Reference operation time is 0.00372887 s (0.03862 Mflops) with 42 threads. -After 0.011335s, autotuning routine did not find a better threads count configuration. +3 iterations (20 th.) took 0.08992s; avg 0.02997s ( +/- 46.81/ 26.74 %); best 0.01594s; worst 0.03799s; std dev. 0.009954 (taking best). +Reference operation time is 0.0159428 s (0.009032 Mflops) with 20 threads. +After 0.089999s, autotuning routine did not find a better threads count configuration. Will autotune matrix: 6 x 6, type S, 36 nnz, 6 nnz/r, 21 subms, 16 lsubms, 4.8889 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:0.1 -3 iterations (42 th.) took 0.01116s; avg 0.003719s ( +/- 0.71/ 0.64 %); best 0.003693s; worst 0.003743s; std dev. 2.062e-05 (taking best). -Reference operation time is 0.00369287 s (0.03899 Mflops) with 42 threads. -Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=2, order=cols) (max 6 steps, inclusive 3 grace steps) on: 6 x 6, type S, 36 nnz, 6 nnz/r, 21 subms, 16 lsubms, 4.8889 bpnz (tpop: 0.003693 Mflops: 0.039) -Merge (16 -> 10 leaves) took w.c.t. of 0.001988s, ~1.693e-05s of computing time (of which 1.907e-06s sorting, 2.861e-06s analysis) -3 iterations (42 th.) took 0.01298s; avg 0.004328s ( +/- 15.22/ 25.93 %); best 0.003669s; worst 0.00545s; std dev. 0.0007976 (taking best). -Reference operation time is 0.00366902 s (0.03925 Mflops) with 42 threads. -After merge step 1: tpop: 0.003669 s ~Mflops: 0.039 nsubm:10 otn:42 -Applying merge (16 -> 10 leaves, 42 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=1.00650x): 0.003693s -> 0.003669s, so IGNORING this instance. -Merge (10 -> 7 leaves) took w.c.t. of 1.311e-05s, ~5.007e-06s of computing time (of which 9.537e-07s sorting, 2.861e-06s analysis) -3 iterations (42 th.) took 0.01134s; avg 0.003779s ( +/- 0.86/ 1.48 %); best 0.003747s; worst 0.003835s; std dev. 3.967e-05 (taking best). -Reference operation time is 0.00374699 s (0.03843 Mflops) with 42 threads. -After merge step 2: tpop: 0.003747 s ~Mflops: 0.038 nsubm:7 otn:42 -Applying merge (10 -> 7 leaves, 42 th.) yielded NEGLIGIBLE change (2th in a row) (old/new=0.98556x): 0.003693s -> 0.003747s, so IGNORING this instance. -Merge (7 -> 4 leaves) took w.c.t. of 1.192e-05s, ~4.053e-06s of computing time (of which 0s sorting, 2.146e-06s analysis) -3 iterations (42 th.) took 0.01118s; avg 0.003727s ( +/- 0.18/ 0.25 %); best 0.00372s; worst 0.003736s; std dev. 6.812e-06 (taking best). -Reference operation time is 0.00372005 s (0.03871 Mflops) with 42 threads. -After merge step 3: tpop: 0.00372 s ~Mflops: 0.039 nsubm:4 otn:42 -Applying merge (7 -> 4 leaves, 42 th.) yielded NEGLIGIBLE change (3th in a row) (old/new=0.99269x): 0.003693s -> 0.00372s, so IGNORING this instance. -Merge (4 -> 1 leaves) took w.c.t. of 1.097e-05s, ~5.007e-06s of computing time (of which 9.537e-07s sorting, 9.537e-07s analysis) -3 iterations (42 th.) took 3.099e-06s; avg 1.033e-06s ( +/- 96.69/ 84.62 %); best 3.425e-08s; worst 1.907e-06s; std dev. 7.867e-07 (taking best). -Reference operation time is 3.42488e-08 s (4205 Mflops) with 42 threads. -After merge step 4: tpop: 3.425e-08 s ~Mflops: 4204.523 nsubm:1 otn:42 -Applying merge (4 -> 1 leaves, 42 th.) yielded SPEEDUP of 107824.574x: 0.003693s -> 3.425e-08s, so taking this instance. -Merged all the matrix leaves: no reason to continue merging. -A total of 4 merge steps (of max 6) (16 -> 1 subms) took 0.0488s (of which 0.002038s partitioning, 0s I/O); computing times: 3.099e-05s in par. loops, 3.815e-06s sorting, 8.821e-06s analyzing) -Total merge + benchmarking process took 0.0488s, equivalent to 1424893.8/13.2 new/old ops (0.02274s for 2 clones -- as 663940.1/6.2 ops, or 331970.1/3.1 ops per clone), SPEEDUP of 107824.574x -Applying multi-merge (16 -> 1 leaves, 4 steps, 0 -> 42 th.sp.) yielded SPEEDUP of 107824.574x (0.003693s -> 3.425e-08s), will amortize in 13.2 ops by saving 0.003693s per op. -In 1 tuning rounds (tot. 0.072s, 0.023s for constructor, 2 clones) obtained a SPEEDUP of 10782357.4% (1.078e+05x) (from 0.03899 to 4205 Mflops). -After 0.071535s, global autotuning declared speedup of 107825 x, when using threads count of 42 and a new matrix: -(6 x 6)[0x56220148f850]{S} @ (0(0..6),0(0..6)) (36 nnz, 6 nnz/r) flags 0x2244086 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 1, symflags:'' +3 iterations (20 th.) took 0.07512s; avg 0.02504s ( +/- 36.08/ 27.83 %); best 0.01601s; worst 0.03201s; std dev. 0.006695 (taking best). +Reference operation time is 0.0160072 s (0.008996 Mflops) with 20 threads. +Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=2, order=cols) (max 6 steps, inclusive 3 grace steps) on: 6 x 6, type S, 36 nnz, 6 nnz/r, 21 subms, 16 lsubms, 4.8889 bpnz (tpop: 0.01601 Mflops: 0.009) +Merge (16 -> 10 leaves) took w.c.t. of 0.02402s, ~4.888e-05s of computing time (of which 3.815e-06s sorting, 8.821e-06s analysis) +3 iterations (20 th.) took 0.1239s; avg 0.0413s ( +/- 32.21/ 64.42 %); best 0.028s; worst 0.06791s; std dev. 0.01882 (taking best). +Reference operation time is 0.0279989 s (0.005143 Mflops) with 20 threads. +After merge step 1: tpop: 0.028 s ~Mflops: 0.005 nsubm:10 otn:20 +Applying merge (16 -> 10 leaves, 20 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.749x: 0.01601s -> 0.028s. +Skipping further merge based tests after 1 definite performance degradations in a row (and last exceeding limit). +A total of 1 merge steps (of max 6) (16 -> 10 subms) took 0.148s (of which 0.02402s partitioning, 0s I/O); computing times: 4.888e-05s in par. loops, 3.815e-06s sorting, 8.821e-06s analyzing) +Total merge + benchmarking process took 0.148s, equivalent to 9.2/9.2 new/old ops (0.1068s for 1 clones -- as 6.7/6.7 ops, or 6.7/6.7 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) +Merging based autotuning FAILED (=NO SPEEDUP); let's try splitting then... +3 iterations (20 th.) took 0.07599s; avg 0.02533s ( +/- 5.24/ 10.46 %); best 0.024s; worst 0.02798s; std dev. 0.001873 (taking best). +Reference operation time is 0.0240021 s (0.005999 Mflops) with 20 threads. +Starting split (same threads) based auto-tuning procedure (transA=N, nrhs=2, order=cols) (max 6 steps, inclusive 3 grace steps) on: 6 x 6, type S, 36 nnz, 6 nnz/r, 21 subms, 16 lsubms, 4.8889 bpnz (tpop: 0.024 Mflops: 0.006) +Split (16 -> 28 leaves, 21 -> 37 subms) took 0.06797s (of which: 9.06e-06s analysis, -6.862e+09s mem.mgmt); compute time: 0.06655s overall, 1.192e-05s searches, 0.06654s shuffle, 0.06637s switch, 8.106e-06s quadrants. +3 iterations (20 th.) took 0.09993s; avg 0.03331s ( +/- 25.78/ 29.76 %); best 0.02472s; worst 0.04322s; std dev. 0.007612 (taking best). +Reference operation time is 0.0247209 s (0.005825 Mflops) with 20 threads. +After split step 1: tpop: 0.02472 s ~Mflops: 0.006 nsubm:28 otn:20 +Applying split (16 -> 28 leaves, 20 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.030x: 0.024s -> 0.02472s. +Split (28 -> 28 leaves, 37 -> 37 subms) took 0.03187s (of which: 1.097e-05s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. +3 iterations (20 th.) took 0.1038s; avg 0.03459s ( +/- 18.97/ 15.56 %); best 0.02803s; worst 0.03997s; std dev. 0.004947 (taking best). +Reference operation time is 0.0280259 s (0.005138 Mflops) with 20 threads. +After split step 2: tpop: 0.02803 s ~Mflops: 0.005 nsubm:28 otn:20 +Applying split (28 -> 28 leaves, 20 th.) yielded SLOWDOWN (2th of 3 tolerable) of 1.168x: 0.024s -> 0.02803s. +Split (28 -> 28 leaves, 37 -> 37 subms) took 0.03596s (of which: 6.199e-06s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. +3 iterations (20 th.) took 0.07997s; avg 0.02666s ( +/- 13.81/ 23.72 %); best 0.02297s; worst 0.03298s; std dev. 0.004491 (taking best). +Reference operation time is 0.0229731 s (0.006268 Mflops) with 20 threads. +After split step 3: tpop: 0.02297 s ~Mflops: 0.006 nsubm:28 otn:20 +Applying split (28 -> 28 leaves, 20 th.) yielded SPEEDUP of 1.045x: 0.024s -> 0.02297s, so taking this instance. +Split (28 -> 28 leaves, 37 -> 37 subms) took 0.03191s (of which: 0s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. +3 iterations (20 th.) took 0.09993s; avg 0.03331s ( +/- 16.02/ 8.10 %); best 0.02798s; worst 0.03601s; std dev. 0.003773 (taking best). +Reference operation time is 0.0279751 s (0.005147 Mflops) with 20 threads. +After split step 4: tpop: 0.02798 s ~Mflops: 0.005 nsubm:28 otn:20 +Applying split (28 -> 28 leaves, 20 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.218x: 0.02297s -> 0.02798s. +Skipping further split based tests after 1 definite performance degradations in a row (and last exceeding limit). +A total of 4 split steps (of max 6) (16 -> 28 subms) took 0.652s (of which 0.1683s partitioning, 0s I/O); computing times: 0.06655s in par. loops, 1.192e-05s sorting, 2.623e-05s analyzing) +Total split + benchmarking process took 0.652s, equivalent to 28.4/27.2 new/old ops (0.1959s for 2 clones -- as 8.5/8.2 ops, or 4.3/4.1 ops per clone), SPEEDUP of 1.045x +Applying multi-split (16 -> 28 leaves, 3 steps, 0 -> 20 th.sp.) yielded SPEEDUP of 1.045x (0.024s -> 0.02297s), will amortize in 633.6 ops by saving 0.001029s per op. +In 1 tuning rounds (tot. 1.2s, 0.3s for constructor, 3 clones) obtained a SPEEDUP of 4.5% (1.045x) (from 0.005999 to 0.006268 Mflops). +After 1.154074s, global autotuning declared speedup of 1.04479 x, when using threads count of 20 and a new matrix: +(6 x 6)[0x557aea7cbe70]{S} @ (0(0..0),0(0..0)) (36 nnz, 6 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 28, symflags:'' Considering C clone. Building a matrix with 36 nnz, 6 x 6 Duplicates check: 36 - 0 = 36 - converted COO to RSB in 2.082e-02 s (100.00 %) - analyzed arrays in 6.003e-03 s (28.83 %) - cleaned-up arrays in 0.000e+00 s (0.00 %) - deduplicated arrays in 0.000e+00 s (0.00 %) + converted COO to RSB in 1.718e-01 s (100.00 %) + analyzed arrays in 5.174e-02 s (30.12 %) + cleaned-up arrays in 1.907e-06 s (0.00 %) + deduplicated arrays in 9.537e-07 s (0.00 %) sorted arrays in 9.537e-07 s (0.00 %) - shuffled partitions in 7.181e-03 s (34.48 %) - memory allocations took 4.053e-06 s (0.02 %) - leafs setup took 3.099e-06 s (0.01 %) - halfword conversion took 7.631e-03 s (36.65 %) -Built (6 x 6)[0x56220148da80]{C} @ (0(0..0),0(0..0)) (36 nnz, 6 nnz/r) flags 0x42046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 22, symflags:'' + shuffled partitions in 5.600e-02 s (32.60 %) + memory allocations took 2.241e-05 s (0.01 %) + leafs setup took 1.097e-05 s (0.01 %) + halfword conversion took 6.400e-02 s (37.25 %) +Built (6 x 6)[0x557aea7c3730]{C} @ (0(0..0),0(0..0)) (36 nnz, 6 nnz/r) flags 0x42046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 22, symflags:'' Base matrix: -(6 x 6)[0x56220148da80]{C} @ (0(0..0),0(0..0)) (36 nnz, 6 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 22, symflags:'' +(6 x 6)[0x557aea7c3730]{C} @ (0(0..0),0(0..0)) (36 nnz, 6 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 22, symflags:'' Will use autotuning routine to sample matrix: 6 x 6, type C, 36 nnz, 6 nnz/r, 29 subms, 22 lsubms, 4.6667 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:0.1 -3 iterations (42 th.) took 0.01247s; avg 0.004156s ( +/- 10.16/ 20.23 %); best 0.003734s; worst 0.004997s; std dev. 0.0005944 (taking best). -Reference operation time is 0.00373411 s (0.1543 Mflops) with 42 threads. -After 0.012489s, autotuning routine did not find a better threads count configuration. +3 iterations (20 th.) took 0.08391s; avg 0.02797s ( +/- 42.73/ 28.62 %); best 0.01602s; worst 0.03597s; std dev. 0.008612 (taking best). +Reference operation time is 0.0160191 s (0.03596 Mflops) with 20 threads. +After 0.083984s, autotuning routine did not find a better threads count configuration. Will autotune matrix: 6 x 6, type C, 36 nnz, 6 nnz/r, 29 subms, 22 lsubms, 4.6667 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:0.1 -3 iterations (42 th.) took 0.01163s; avg 0.003877s ( +/- 4.90/ 5.14 %); best 0.003687s; worst 0.004076s; std dev. 0.000159 (taking best). -Reference operation time is 0.0036869 s (0.1562 Mflops) with 42 threads. -Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=2, order=cols) (max 6 steps, inclusive 3 grace steps) on: 6 x 6, type C, 36 nnz, 6 nnz/r, 29 subms, 22 lsubms, 4.6667 bpnz (tpop: 0.003687 Mflops: 0.156) -Merge (22 -> 16 leaves) took w.c.t. of 0.001875s, ~1.001e-05s of computing time (of which 0s sorting, 3.099e-06s analysis) -3 iterations (42 th.) took 0.01446s; avg 0.00482s ( +/- 25.47/ 42.27 %); best 0.003592s; worst 0.006857s; std dev. 0.001451 (taking best). -Reference operation time is 0.00359201 s (0.1604 Mflops) with 42 threads. -After merge step 1: tpop: 0.003592 s ~Mflops: 0.160 nsubm:16 otn:42 -Applying merge (22 -> 16 leaves, 42 th.) yielded SPEEDUP of 1.026x: 0.003687s -> 0.003592s, so taking this instance. -Merge (16 -> 10 leaves) took w.c.t. of 0.002056s, ~1.216e-05s of computing time (of which 1.907e-06s sorting, 2.861e-06s analysis) -3 iterations (42 th.) took 0.01458s; avg 0.004858s ( +/- 35.99/ 42.70 %); best 0.00311s; worst 0.006933s; std dev. 0.001578 (taking best). -Reference operation time is 0.00310993 s (0.1852 Mflops) with 42 threads. -After merge step 2: tpop: 0.00311 s ~Mflops: 0.185 nsubm:10 otn:42 -Applying merge (16 -> 10 leaves, 42 th.) yielded SPEEDUP of 1.155x: 0.003592s -> 0.00311s, so taking this instance. -Merge (10 -> 7 leaves) took w.c.t. of 1.717e-05s, ~4.053e-06s of computing time (of which 9.537e-07s sorting, 3.815e-06s analysis) -3 iterations (42 th.) took 0.01156s; avg 0.003854s ( +/- 49.59/ 52.06 %); best 0.001943s; worst 0.005861s; std dev. 0.001601 (taking best). -Reference operation time is 0.00194311 s (0.2964 Mflops) with 42 threads. -After merge step 3: tpop: 0.001943 s ~Mflops: 0.296 nsubm:7 otn:42 -Applying merge (10 -> 7 leaves, 42 th.) yielded SPEEDUP of 1.600x: 0.00311s -> 0.001943s, so taking this instance. -Merge (7 -> 4 leaves) took w.c.t. of 2.098e-05s, ~5.96e-06s of computing time (of which 9.537e-07s sorting, 5.007e-06s analysis) -3 iterations (42 th.) took 0.01124s; avg 0.003747s ( +/- 0.83/ 0.69 %); best 0.003716s; worst 0.003773s; std dev. 2.353e-05 (taking best). -Reference operation time is 0.00371599 s (0.155 Mflops) with 42 threads. -After merge step 4: tpop: 0.003716 s ~Mflops: 0.155 nsubm:4 otn:42 -Applying merge (7 -> 4 leaves, 42 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.912x: 0.001943s -> 0.003716s. +3 iterations (20 th.) took 0.08793s; avg 0.02931s ( +/- 31.95/ 22.73 %); best 0.01995s; worst 0.03597s; std dev. 0.006816 (taking best). +Reference operation time is 0.0199459 s (0.02888 Mflops) with 20 threads. +Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=2, order=cols) (max 6 steps, inclusive 3 grace steps) on: 6 x 6, type C, 36 nnz, 6 nnz/r, 29 subms, 22 lsubms, 4.6667 bpnz (tpop: 0.01995 Mflops: 0.029) +Merge (22 -> 16 leaves) took w.c.t. of 0.01184s, ~1.597e-05s of computing time (of which 4.053e-06s sorting, 1.001e-05s analysis) +3 iterations (20 th.) took 0.1559s; avg 0.05197s ( +/- 31.60/ 47.07 %); best 0.03555s; worst 0.07643s; std dev. 0.01763 (taking best). +Reference operation time is 0.035547 s (0.0162 Mflops) with 20 threads. +After merge step 1: tpop: 0.03555 s ~Mflops: 0.016 nsubm:16 otn:20 +Applying merge (22 -> 16 leaves, 20 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.782x: 0.01995s -> 0.03555s. Skipping further merge based tests after 1 definite performance degradations in a row (and last exceeding limit). -A total of 4 merge steps (of max 6) (22 -> 4 subms) took 0.08923s (of which 0.003987s partitioning, 0s I/O); computing times: 3.219e-05s in par. loops, 3.815e-06s sorting, 1.478e-05s analyzing) -Total merge + benchmarking process took 0.08923s, equivalent to 45.9/24.2 new/old ops (0.04473s for 4 clones -- as 23.0/12.1 ops, or 5.8/3.0 ops per clone), SPEEDUP of 1.897x -Applying multi-merge (22 -> 7 leaves, 3 steps, 0 -> 42 th.sp.) yielded SPEEDUP of 1.897x (0.003687s -> 0.001943s), will amortize in 51.2 ops by saving 0.001744s per op. -In 1 tuning rounds (tot. 0.11s, 0.045s for constructor, 4 clones) obtained a SPEEDUP of 89.7% (1.897x) (from 0.1562 to 0.2964 Mflops). -After 0.112427s, global autotuning declared speedup of 1.89742 x, when using threads count of 42 and a new matrix: -(6 x 6)[0x562201494de0]{C} @ (0(0..0),0(0..0)) (36 nnz, 6 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 7, symflags:'' +A total of 1 merge steps (of max 6) (22 -> 16 subms) took 0.1679s (of which 0.0119s partitioning, 0s I/O); computing times: 1.597e-05s in par. loops, 4.053e-06s sorting, 1.001e-05s analyzing) +Total merge + benchmarking process took 0.1679s, equivalent to 8.4/8.4 new/old ops (0.08797s for 1 clones -- as 4.4/4.4 ops, or 4.4/4.4 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) +Merging based autotuning FAILED (=NO SPEEDUP); let's try splitting then... +3 iterations (20 th.) took 0.1063s; avg 0.03543s ( +/- 3.49/ 1.81 %); best 0.0342s; worst 0.03608s; std dev. 0.0008757 (taking best). +Reference operation time is 0.0341959 s (0.01684 Mflops) with 20 threads. +Starting split (same threads) based auto-tuning procedure (transA=N, nrhs=2, order=cols) (max 6 steps, inclusive 3 grace steps) on: 6 x 6, type C, 36 nnz, 6 nnz/r, 29 subms, 22 lsubms, 4.6667 bpnz (tpop: 0.0342 Mflops: 0.017) +Split (22 -> 28 leaves, 29 -> 37 subms) took 0.05579s (of which: 1.192e-05s analysis, -3.431e+09s mem.mgmt); compute time: 8.774e-05s overall, 5.007e-06s searches, 8.273e-05s shuffle, 2.98e-05s switch, 8.106e-06s quadrants. +3 iterations (20 th.) took 0.09995s; avg 0.03332s ( +/- 4.04/ 8.07 %); best 0.03197s; worst 0.036s; std dev. 0.001901 (taking best). +Reference operation time is 0.03197 s (0.01802 Mflops) with 20 threads. +After split step 1: tpop: 0.03197 s ~Mflops: 0.018 nsubm:28 otn:20 +Applying split (22 -> 28 leaves, 20 th.) yielded SPEEDUP of 1.070x: 0.0342s -> 0.03197s, so taking this instance. +Split (28 -> 28 leaves, 37 -> 37 subms) took 0.03595s (of which: 1.502e-05s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. +3 iterations (20 th.) took 0.08798s; avg 0.02933s ( +/- 31.76/ 22.70 %); best 0.02001s; worst 0.03598s; std dev. 0.006785 (taking best). +Reference operation time is 0.0200121 s (0.02878 Mflops) with 20 threads. +After split step 2: tpop: 0.02001 s ~Mflops: 0.029 nsubm:28 otn:20 +Applying split (28 -> 28 leaves, 20 th.) yielded SPEEDUP of 1.598x: 0.03197s -> 0.02001s, so taking this instance. +Split (28 -> 28 leaves, 37 -> 37 subms) took 0.04391s (of which: 1.192e-05s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. +3 iterations (20 th.) took 0.09196s; avg 0.03065s ( +/- 21.69/ 30.39 %); best 0.02401s; worst 0.03997s; std dev. 0.006786 (taking best). +Reference operation time is 0.0240071 s (0.02399 Mflops) with 20 threads. +After split step 3: tpop: 0.02401 s ~Mflops: 0.024 nsubm:28 otn:20 +Applying split (28 -> 28 leaves, 20 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.200x: 0.02001s -> 0.02401s. +Split (28 -> 28 leaves, 37 -> 37 subms) took 0.03994s (of which: 1.311e-05s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. +3 iterations (20 th.) took 0.08003s; avg 0.02668s ( +/- 54.47/ 49.87 %); best 0.01215s; worst 0.03998s; std dev. 0.0114 (taking best). +Reference operation time is 0.012145 s (0.04743 Mflops) with 20 threads. +After split step 4: tpop: 0.01215 s ~Mflops: 0.047 nsubm:28 otn:20 +Applying split (28 -> 28 leaves, 20 th.) yielded SPEEDUP of 1.648x: 0.02001s -> 0.01215s, so taking this instance. +Split (28 -> 28 leaves, 37 -> 37 subms) took 0.03601s (of which: 1.001e-05s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. +3 iterations (20 th.) took 0.0845s; avg 0.02817s ( +/- 43.23/ 70.30 %); best 0.01599s; worst 0.04797s; std dev. 0.01412 (taking best). +Reference operation time is 0.01599 s (0.03602 Mflops) with 20 threads. +After split step 5: tpop: 0.01599 s ~Mflops: 0.036 nsubm:28 otn:20 +Applying split (28 -> 28 leaves, 20 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.317x: 0.01215s -> 0.01599s. +Skipping further split based tests after 1 definite performance degradations in a row (and last exceeding limit). +A total of 5 split steps (of max 6) (22 -> 28 subms) took 0.9323s (of which 0.2119s partitioning, 0s I/O); computing times: 8.774e-05s in par. loops, 5.007e-06s sorting, 6.199e-05s analyzing) +Total split + benchmarking process took 0.9323s, equivalent to 76.8/27.3 new/old ops (0.3853s for 4 clones -- as 31.7/11.3 ops, or 7.9/2.8 ops per clone), SPEEDUP of 2.816x +Applying multi-split (22 -> 28 leaves, 4 steps, 0 -> 20 th.sp.) yielded SPEEDUP of 2.816x (0.0342s -> 0.01215s), will amortize in 42.3 ops by saving 0.02205s per op. +In 1 tuning rounds (tot. 1.5s, 0.47s for constructor, 5 clones) obtained a SPEEDUP of 181.6% (2.816x) (from 0.01684 to 0.04743 Mflops). +After 1.492558s, global autotuning declared speedup of 2.81563 x, when using threads count of 20 and a new matrix: +(6 x 6)[0x557aea7dbc40]{C} @ (0(0..0),0(0..0)) (36 nnz, 6 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 28, symflags:'' Considering Z clone. Building a matrix with 36 nnz, 6 x 6 Duplicates check: 36 - 0 = 36 - converted COO to RSB in 2.477e-02 s (100.00 %) - analyzed arrays in 9.340e-03 s (37.70 %) - cleaned-up arrays in 1.192e-06 s (0.00 %) - deduplicated arrays in 0.000e+00 s (0.00 %) - sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 7.676e-03 s (30.99 %) - memory allocations took 9.775e-06 s (0.04 %) - leafs setup took 5.007e-06 s (0.02 %) - halfword conversion took 7.737e-03 s (31.23 %) -Built (6 x 6)[0x562201493780]{Z} @ (0(0..0),0(0..0)) (36 nnz, 6 nnz/r) flags 0x42046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 28, symflags:'' + converted COO to RSB in 1.913e-01 s (100.00 %) + analyzed arrays in 7.130e-02 s (37.27 %) + cleaned-up arrays in 2.146e-06 s (0.00 %) + deduplicated arrays in 9.537e-07 s (0.00 %) + sorted arrays in 9.537e-07 s (0.00 %) + shuffled partitions in 5.600e-02 s (29.27 %) + memory allocations took 1.597e-05 s (0.01 %) + leafs setup took 1.121e-05 s (0.01 %) + halfword conversion took 6.397e-02 s (33.44 %) +Built (6 x 6)[0x557aea7c3340]{Z} @ (0(0..0),0(0..0)) (36 nnz, 6 nnz/r) flags 0x42046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 28, symflags:'' Base matrix: -(6 x 6)[0x562201493780]{Z} @ (0(0..0),0(0..0)) (36 nnz, 6 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 28, symflags:'' +(6 x 6)[0x557aea7c3340]{Z} @ (0(0..0),0(0..0)) (36 nnz, 6 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 28, symflags:'' Will use autotuning routine to sample matrix: 6 x 6, type Z, 36 nnz, 6 nnz/r, 37 subms, 28 lsubms, 4.4444 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:0.1 -3 iterations (42 th.) took 0.012s; avg 0.004001s ( +/- 1.24/ 1.01 %); best 0.003951s; worst 0.004041s; std dev. 3.728e-05 (taking best). -Reference operation time is 0.00395107 s (0.1458 Mflops) with 42 threads. -After 0.012029s, autotuning routine did not find a better threads count configuration. +3 iterations (20 th.) took 0.09994s; avg 0.03331s ( +/- 40.11/ 32.01 %); best 0.01995s; worst 0.04397s; std dev. 0.009992 (taking best). +Reference operation time is 0.0199511 s (0.02887 Mflops) with 20 threads. +After 0.100007s, autotuning routine did not find a better threads count configuration. Will autotune matrix: 6 x 6, type Z, 36 nnz, 6 nnz/r, 37 subms, 28 lsubms, 4.4444 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:0.1 -3 iterations (42 th.) took 0.01188s; avg 0.00396s ( +/- 0.83/ 0.99 %); best 0.003927s; worst 0.003999s; std dev. 2.97e-05 (taking best). -Reference operation time is 0.00392699 s (0.1467 Mflops) with 42 threads. -Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=2, order=cols) (max 6 steps, inclusive 3 grace steps) on: 6 x 6, type Z, 36 nnz, 6 nnz/r, 37 subms, 28 lsubms, 4.4444 bpnz (tpop: 0.003927 Mflops: 0.147) -Merge (28 -> 22 leaves) took w.c.t. of 0.001915s, ~1.812e-05s of computing time (of which 2.861e-06s sorting, 4.053e-06s analysis) -3 iterations (42 th.) took 0.01382s; avg 0.004606s ( +/- 21.58/ 35.78 %); best 0.003612s; worst 0.006254s; std dev. 0.001174 (taking best). -Reference operation time is 0.00361204 s (0.1595 Mflops) with 42 threads. -After merge step 1: tpop: 0.003612 s ~Mflops: 0.159 nsubm:22 otn:42 -Applying merge (28 -> 22 leaves, 42 th.) yielded SPEEDUP of 1.087x: 0.003927s -> 0.003612s, so taking this instance. -Merge (22 -> 16 leaves) took w.c.t. of 0.001929s, ~1.431e-05s of computing time (of which 5.007e-06s sorting, 5.007e-06s analysis) -3 iterations (42 th.) took 0.01365s; avg 0.00455s ( +/- 17.94/ 32.95 %); best 0.003734s; worst 0.006049s; std dev. 0.001061 (taking best). -Reference operation time is 0.00373387 s (0.1543 Mflops) with 42 threads. -After merge step 2: tpop: 0.003734 s ~Mflops: 0.154 nsubm:16 otn:42 -Applying merge (22 -> 16 leaves, 42 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.034x: 0.003612s -> 0.003734s. -Merge (16 -> 10 leaves) took w.c.t. of 0.001996s, ~1.192e-05s of computing time (of which 2.146e-06s sorting, 3.815e-06s analysis) -3 iterations (42 th.) took 0.01324s; avg 0.004412s ( +/- 16.36/ 29.22 %); best 0.00369s; worst 0.005701s; std dev. 0.0009137 (taking best). -Reference operation time is 0.00369 s (0.1561 Mflops) with 42 threads. -After merge step 3: tpop: 0.00369 s ~Mflops: 0.156 nsubm:10 otn:42 -Applying merge (16 -> 10 leaves, 42 th.) yielded SLOWDOWN (2th of 3 tolerable) of 1.022x: 0.003612s -> 0.00369s. -Merge (10 -> 7 leaves) took w.c.t. of 1.287e-05s, ~5.007e-06s of computing time (of which 9.537e-07s sorting, 2.861e-06s analysis) -3 iterations (42 th.) took 0.01126s; avg 0.003752s ( +/- 1.06/ 0.86 %); best 0.003712s; worst 0.003784s; std dev. 2.987e-05 (taking best). -Reference operation time is 0.00371194 s (0.1552 Mflops) with 42 threads. -After merge step 4: tpop: 0.003712 s ~Mflops: 0.155 nsubm:7 otn:42 -Applying merge (10 -> 7 leaves, 42 th.) yielded SLOWDOWN (3th of 3 tolerable) of 1.028x: 0.003612s -> 0.003712s. -Merge (7 -> 4 leaves) took w.c.t. of 1.097e-05s, ~5.007e-06s of computing time (of which 0s sorting, 2.146e-06s analysis) -3 iterations (42 th.) took 0.01138s; avg 0.003794s ( +/- 1.01/ 1.41 %); best 0.003756s; worst 0.003848s; std dev. 3.901e-05 (taking best). -Reference operation time is 0.00375605 s (0.1534 Mflops) with 42 threads. -After merge step 5: tpop: 0.003756 s ~Mflops: 0.153 nsubm:4 otn:42 -Applying merge (7 -> 4 leaves, 42 th.) yielded SLOWDOWN (4th of 3 tolerable) of 1.040x: 0.003612s -> 0.003756s. -Skipping further merge based tests after 4 definite performance degradations in a row. -A total of 5 merge steps (of max 6) (28 -> 4 subms) took 0.08073s (of which 0.005899s partitioning, 0s I/O); computing times: 5.436e-05s in par. loops, 1.097e-05s sorting, 1.788e-05s analyzing) -Total merge + benchmarking process took 0.08073s, equivalent to 22.4/20.6 new/old ops (0.02277s for 2 clones -- as 6.3/5.8 ops, or 3.2/2.9 ops per clone), SPEEDUP of 1.087x -Applying multi-merge (28 -> 22 leaves, 1 steps, 0 -> 42 th.sp.) yielded SPEEDUP of 1.087x (0.003927s -> 0.003612s), will amortize in 256.3 ops by saving 0.000315s per op. -In 1 tuning rounds (tot. 0.1s, 0.023s for constructor, 2 clones) obtained a SPEEDUP of 8.7% (1.087x) (from 0.1467 to 0.1595 Mflops). -After 0.104040s, global autotuning declared speedup of 1.08719 x, when using threads count of 42 and a new matrix: -(6 x 6)[0x56220149ad20]{Z} @ (0(0..0),0(0..0)) (36 nnz, 6 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 22, symflags:'' +3 iterations (20 th.) took 0.06804s; avg 0.02268s ( +/- 29.26/ 58.47 %); best 0.01604s; worst 0.03594s; std dev. 0.009378 (taking best). +Reference operation time is 0.0160441 s (0.0359 Mflops) with 20 threads. +Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=2, order=cols) (max 6 steps, inclusive 3 grace steps) on: 6 x 6, type Z, 36 nnz, 6 nnz/r, 37 subms, 28 lsubms, 4.4444 bpnz (tpop: 0.01604 Mflops: 0.036) +Merge (28 -> 22 leaves) took w.c.t. of 0.02s, ~4.101e-05s of computing time (of which 1.597e-05s sorting, 1.001e-05s analysis) +3 iterations (20 th.) took 0.1279s; avg 0.04263s ( +/- 62.44/ 49.86 %); best 0.01601s; worst 0.06389s; std dev. 0.01991 (taking best). +Reference operation time is 0.0160131 s (0.03597 Mflops) with 20 threads. +After merge step 1: tpop: 0.01601 s ~Mflops: 0.036 nsubm:22 otn:20 +Applying merge (28 -> 22 leaves, 20 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=1.00194x): 0.01604s -> 0.01601s, so IGNORING this instance. +Merge (22 -> 16 leaves) took w.c.t. of 0.02373s, ~3.314e-05s of computing time (of which 9.06e-06s sorting, 1.478e-05s analysis) +3 iterations (20 th.) took 0.1158s; avg 0.03862s ( +/- 58.57/117.07 %); best 0.016s; worst 0.08382s; std dev. 0.03197 (taking best). +Reference operation time is 0.0159969 s (0.03601 Mflops) with 20 threads. +After merge step 2: tpop: 0.016 s ~Mflops: 0.036 nsubm:16 otn:20 +Applying merge (22 -> 16 leaves, 20 th.) yielded NEGLIGIBLE change (2th in a row) (old/new=1.00295x): 0.01604s -> 0.016s, so IGNORING this instance. +Merge (16 -> 10 leaves) took w.c.t. of 0.01626s, ~5.007e-05s of computing time (of which 2.861e-06s sorting, 8.821e-06s analysis) +3 iterations (20 th.) took 0.1557s; avg 0.0519s ( +/- 38.35/ 68.93 %); best 0.032s; worst 0.08768s; std dev. 0.02535 (taking best). +Reference operation time is 0.0319979 s (0.018 Mflops) with 20 threads. +After merge step 3: tpop: 0.032 s ~Mflops: 0.018 nsubm:10 otn:20 +Applying merge (16 -> 10 leaves, 20 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.994x: 0.01604s -> 0.032s. +Skipping further merge based tests after 1 definite performance degradations in a row (and last exceeding limit). +A total of 3 merge steps (of max 6) (28 -> 10 subms) took 0.46s (of which 0.06007s partitioning, 0s I/O); computing times: 0.0001242s in par. loops, 2.789e-05s sorting, 3.362e-05s analyzing) +Total merge + benchmarking process took 0.46s, equivalent to 28.7/28.7 new/old ops (0.08393s for 1 clones -- as 5.2/5.2 ops, or 5.2/5.2 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) +Merging based autotuning FAILED (=NO SPEEDUP); let's try splitting then... +3 iterations (20 th.) took 0.09999s; avg 0.03333s ( +/- 16.00/ 8.00 %); best 0.028s; worst 0.036s; std dev. 0.00377 (taking best). +Reference operation time is 0.0279992 s (0.02057 Mflops) with 20 threads. +Starting split (same threads) based auto-tuning procedure (transA=N, nrhs=2, order=cols) (max 6 steps, inclusive 3 grace steps) on: 6 x 6, type Z, 36 nnz, 6 nnz/r, 37 subms, 28 lsubms, 4.4444 bpnz (tpop: 0.028 Mflops: 0.021) +Split (28 -> 28 leaves, 37 -> 37 subms) took 0.05192s (of which: 8.821e-06s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. +3 iterations (20 th.) took 0.08401s; avg 0.028s ( +/- 57.02/ 28.54 %); best 0.01203s; worst 0.036s; std dev. 0.01129 (taking best). +Reference operation time is 0.0120349 s (0.04786 Mflops) with 20 threads. +After split step 1: tpop: 0.01203 s ~Mflops: 0.048 nsubm:28 otn:20 +Applying split (28 -> 28 leaves, 20 th.) yielded SPEEDUP of 2.326x: 0.028s -> 0.01203s, so taking this instance. +Split (28 -> 28 leaves, 37 -> 37 subms) took 0.02s (of which: 7.868e-06s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. +3 iterations (20 th.) took 0.08404s; avg 0.02801s ( +/- 28.49/ 42.76 %); best 0.02003s; worst 0.03999s; std dev. 0.008625 (taking best). +Reference operation time is 0.02003 s (0.02876 Mflops) with 20 threads. +After split step 2: tpop: 0.02003 s ~Mflops: 0.029 nsubm:28 otn:20 +Applying split (28 -> 28 leaves, 20 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.664x: 0.01203s -> 0.02003s. +Skipping further split based tests after 1 definite performance degradations in a row (and last exceeding limit). +A total of 2 split steps (of max 6) (28 -> 28 subms) took 0.308s (of which 0.07198s partitioning, 0s I/O); computing times: 0s in par. loops, 0s sorting, 1.669e-05s analyzing) +Total split + benchmarking process took 0.308s, equivalent to 25.6/11.0 new/old ops (0.1638s for 2 clones -- as 13.6/5.9 ops, or 6.8/2.9 ops per clone), SPEEDUP of 2.326x +Applying multi-split (28 -> 28 leaves, 1 steps, 0 -> 20 th.sp.) yielded SPEEDUP of 2.326x (0.028s -> 0.01203s), will amortize in 19.3 ops by saving 0.01596s per op. +In 1 tuning rounds (tot. 1.1s, 0.25s for constructor, 3 clones) obtained a SPEEDUP of 132.6% (2.326x) (from 0.02057 to 0.04786 Mflops). +After 1.116086s, global autotuning declared speedup of 2.3265 x, when using threads count of 20 and a new matrix: +(6 x 6)[0x557aea7ca9b0]{Z} @ (0(0..0),0(0..0)) (36 nnz, 6 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 28, symflags:'' gmake[4]: Leaving directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/examples' gmake[3]: Leaving directory '/build/reproducible-path/librsb-1.3.0.2+dfsg' @@ -9262,19 +9264,18 @@ 4 0 DIFF PRINT TEST END Beginning large binary search test. -Detected 84312158208 bytes of memory, comprehensive of 53781069824 of free memory. +Detected 84590833664 bytes of memory, comprehensive of 40341262336 of free memory. On this system, maximal array of coordinates can have 2147483137 elements and occupy 8589932548 bytes. -Will perform the test using less memory (5699 MB) than on the maximal coordinate indices array (5976064000) allows. -(c)allocated 1494016000 nnz (5976064000 bytes) -Succeeded retrieving array last element. -Successfully performed large binary search test. +Will perform the test using less memory (17592186040502 MB) than on the maximal coordinate indices array (18446744069605760000) allows. +Skipping test: too little memory. +Skipping large binary search test. BASIC SPARSE BLAS TEST: BEGIN INIT INTERFACE TEST: BEGIN got RSB_IO_WANT_EXTRA_VERBOSE_INTERFACE: -1 got RSB_IO_WANT_IS_INITIALIZED_MARKER: 1 INIT INTERFACE TEST: END (SUCCESS) DEVEL PRINT TEST: BEGIN -(4 x 4)[0x55d3f480ae70]{S} @ (0(0..0),0(0..0)) (4 nnz, 1 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 2, symflags:'' +(4 x 4)[0x555dca5ac740]{S} @ (0(0..0),0(0..0)) (4 nnz, 1 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 2, symflags:'' RSB_FLAG_USE_HALFWORD_INDICES | RSB_FLAG_SORTED_INPUT | RSB_FLAG_WANT_COO_STORAGE | @@ -9283,8 +9284,8 @@ RSB_FLAG_ASSEMBLED_IN_COO_ARRAYS | RSB_FLAG_OWN_PARTITIONING_ARRAYS | RSB_FLAG_SORT_INPUT -(2 x 2)[0x55d3f480af80]{S} @ (0(0..2),0(0..2)) (2 nnz, 1 nnz/r) flags 0x2144386 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 0, symflags:'' -(2 x 2)[0x55d3f480b090]{S} @ (2(2..4),2(2..4)) (2 nnz, 1 nnz/r) flags 0x2144386 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 0, symflags:'' +(2 x 2)[0x555dca5ac850]{S} @ (0(0..2),0(0..2)) (2 nnz, 1 nnz/r) flags 0x2144386 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 0, symflags:'' +(2 x 2)[0x555dca5ac960]{S} @ (2(2..4),2(2..4)) (2 nnz, 1 nnz/r) flags 0x2144386 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 0, symflags:'' #R 4 x 4, 4 nnz (16 bytes), 16 index space for bytes, 544 bytes for 2 structs (2 of which are on the diagonal) (1e+02% of nnz are on the diagonal) #N at 0 0, 4 x 4, 4 nnz ( 25%) #T at 0 0, 2 x 2, 2 nnz ( 50%) @@ -9292,9 +9293,9 @@ ( 0x2046186 = { rec:1 coo:1 css:1 hw:1 ic:1 fi:0 symflags: } ) DEVEL PRINT TEST: END PRINT TEST: BEGIN [QUIET] -(2 x 2)[0x55d3f480af80]{S} @ (0(0..2),0(0..2)) (2 nnz, 1 nnz/r) flags 0x2144386 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 0, symflags:'' -(2 x 2)[0x55d3f480b090]{S} @ (2(2..4),2(2..4)) (2 nnz, 1 nnz/r) flags 0x2144386 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 0, symflags:'' -(4 x 4)[0x55d3f480ae70]{S} @ (0(0..0),0(0..0)) (4 nnz, 1 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 2, symflags:'' +(2 x 2)[0x555dca5ac850]{S} @ (0(0..2),0(0..2)) (2 nnz, 1 nnz/r) flags 0x2144386 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 0, symflags:'' +(2 x 2)[0x555dca5ac960]{S} @ (2(2..4),2(2..4)) (2 nnz, 1 nnz/r) flags 0x2144386 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 0, symflags:'' +(4 x 4)[0x555dca5ac740]{S} @ (0(0..0),0(0..0)) (4 nnz, 1 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 2, symflags:'' RSB_FLAG_USE_HALFWORD_INDICES | RSB_FLAG_SORTED_INPUT | RSB_FLAG_WANT_COO_STORAGE | @@ -9312,8 +9313,8 @@ BASIC PRIMITIVES TEST: BEGIN BASIC PRIMITIVES TEST: END (SUCCESS) ADVANCED SPARSE BLAS TEST: BEGIN [limit 30.000000s] [QUIET] -Terminating testing earlier due to user timeout request: test took 30.044642 s, max allowed was 30.000000. - PASSED:19847 +Terminating testing earlier due to user timeout request: test took 30.019802 s, max allowed was 30.000000. + PASSED:689 FAILED:0 ADVANCED SPARSE BLAS TEST: END (SUCCESS) gmake qtests -C librsbpp @@ -9322,99 +9323,99 @@ gmake[4]: Entering directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp' gmake[4]: Leaving directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp' ./rsbtt -if ! test -f G.mtx ; then cp -p /build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp/G.mtx . ; fi ; /bin/bash /build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp/test.sh -++ ./rsbpp Td,s G.mtx +if ! test -f G.mtx ; then cp -p /build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp/G.mtx . ; fi ; /bin/sh /build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp/test.sh ++ grep Z-sort ++ wc -l +++ ./rsbpp Td,s G.mtx + test 54 = 54 ++ ./rsbpp Td G.mtx -++ grep Z-sort ++ wc -l +++ grep Z-sort + test 27 = 27 ++ ./rsbpp Td,z G.mtx -++ grep Z-sort ++ wc -l -+ test 54 = 54 -++ ./rsbpp vTd,z G.mtx ++ grep Z-sort -++ wc -l + test 54 = 54 +++ wc -l +++ grep Z-sort ++ ./rsbpp vTd,z G.mtx ++ test 54 = 54 ++ grep Z-sort +++ ./rsbpp vTd,z G.mtx ++ wc -l + test 54 = 54 -++ ./rsbpp vvvTd,z G.mtx ++ grep Zorted +++ ./rsbpp vvvTd,z G.mtx ++ wc -l + test 8 = 8 -++ ./rsbpp vvTd,z G.mtx -++ grep Z-sort ++ wc -l +++ grep Z-sort +++ ./rsbpp vvTd,z G.mtx + test 54 = 54 ++ ./rsbpp vvTd,z G.mtx -++ grep Range ++ wc -l -+ test 0 = 0 -++ ./rsbpp vvvTd,z G.mtx ++ grep Range ++ test 0 = 0 ++ wc -l +++ grep Range +++ ./rsbpp vvvTd,z G.mtx + test 258 -gt 0 -++ ./rsbpp vvvTd,z S.mtx ++ grep Range ++ wc -l +++ ./rsbpp vvvTd,z S.mtx + test 0 -eq 0 -++ ./rsbpp vvvTd,z G.mtx -++ grep Range ++ wc -l +++ grep Range +++ ./rsbpp vvvTd,z G.mtx + test 258 = 258 ++ OMP_NUM_THREADS=1 +++ wc -l +++ grep spmm- ++ ./rsbpp m10M10I1r1,4,8sFv ++ test 9 = 9 ++ grep spmm- ++ wc -l -+ test 9 = 9 ++ OMP_NUM_THREADS=1 ++ ./rsbpp C1000m100M100I1r1,4,8sFv -++ grep spmm- -++ wc -l + test 9 = 9 ++ OMP_NUM_THREADS=1 +++ wc -l +++ grep spmm- ++ ./rsbpp C1000m100M100I1r1sFvtN,T ++ test 3 = 3 ++ grep spmm- ++ wc -l -+ test 3 = 3 ++ OMP_NUM_THREADS=1 ++ ./rsbpp C1000m100M100I1r1vtN,TsF ++ test 2 = 2 ++ grep spmm- ++ wc -l -+ test 2 = 2 ++ OMP_NUM_THREADS=1 ++ ./rsbpp C1000m100M100I1r0vtN,TsF -++ grep spmm- -++ wc -l + test 0 = 0 +++ wc -l +++ grep Recursing ++ OMP_NUM_THREADS=1 ++ RSB_NUM_THREADS=1 ++ ./rsbpp vvvC1000m100M100I1r1vtN,TorsF -++ grep Recursing -++ wc -l + test 4 = 4 ++ OMP_NUM_THREADS=2 +++ grep Recursing ++ RSB_NUM_THREADS=2 +++ wc -l ++ ./rsbpp vvvC1000m100M100I1r1vtN,TorsF ++ test 4 = 4 ++ grep Recursing ++ wc -l -+ test 4 = 4 ++ OMP_NUM_THREADS=1 ++ RSB_NUM_THREADS=1 ++ ./rsbpp vvvC1000m100M100I1r1vtN,ToRsF -++ grep Recursing -++ wc -l + test 208 = 208 +++ wc -l +++ grep Recursing ++ OMP_NUM_THREADS=2 ++ RSB_NUM_THREADS=2 ++ ./rsbpp vvvC1000m100M100I1r1vtN,ToRsF -++ grep Recursing -++ wc -l + test 410 = 410 echo "Skipping tests based on Google Test (not detected at configure time)" Skipping tests based on Google Test (not detected at configure time) @@ -9461,7 +9462,7 @@ 0 0 0 0 before tuning for SPMV: -(3 x 3)[0x55db064fe290]{D} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'' +(3 x 3)[0x55c192c1ab50]{D} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'' ** x: 1.1 @@ -9550,18 +9551,18 @@ BEGIN Rsb_Matrix_test_multimatrix_ms_mnrhs BEGIN -(3 x 3)[0x55db065137b0]{D} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x204619e (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LT' -Tuned with speedup factor of 1: -(3 x 3)[0x55db065137b0]{D} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x204619e (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LT' -(3 x 3)[0x55db06508290]{D} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x204619e (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LT' -Tuned with speedup factor of 1.57764: -(3 x 3)[0x55db06531f80]{D} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x204619e (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LT' -(3 x 3)[0x55db065137b0]{D} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x204619e (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LT' -Tuned with speedup factor of 1.05001: -(3 x 3)[0x55db065358e0]{D} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x204619e (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LT' -(3 x 3)[0x55db065137b0]{D} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x204619e (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LT' -Tuned with speedup factor of 1.08655: -(3 x 3)[0x55db06530c50]{D} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x204619e (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LT' +(3 x 3)[0x55c192c40690]{D} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x204619e (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LT' +Tuned with speedup factor of 1.00088: +(3 x 3)[0x55c192c57e10]{D} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x204619e (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LT' +(3 x 3)[0x55c192c40690]{D} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x204619e (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LT' +Tuned with speedup factor of 1.4616: +(3 x 3)[0x55c192c587b0]{D} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x204619e (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LT' +(3 x 3)[0x55c192c40690]{D} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x204619e (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LT' +Tuned with speedup factor of 1.97843: +(3 x 3)[0x55c192c587b0]{D} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x204619e (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LT' +(3 x 3)[0x55c192c40690]{D} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x204619e (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LT' +Tuned with speedup factor of 1.16723: +(3 x 3)[0x55c192c587b0]{D} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x204619e (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LT' END OK: terminating with no allocations registered in librsb [*] tests terminated successfully ! @@ -9578,10 +9579,10 @@ ./rsbtest --no-tune --max_t 0.01 --serial | dd if=/dev/stdin of=/dev/stdout bs=16M status=none iflag=fullblock | grep -q Building ./rsbtest --no-tune --max_t 0.01 --max 1 --nrhs 1 --beta 1 --incy 1 --incx 1 --no-trans --alpha 1 --type d --rand --serial . | dd if=/dev/stdin of=/dev/stdout bs=16M status=none iflag=fullblock | grep -q adding ! ./rsbtest --mkl A.mkl -running on ionos5-amd64 +running on i-capture-the-hostname Built without the MKL. ( ! ./rsbtest --unrecognized-option-triggers-abort ) -running on ionos5-amd64 +running on i-capture-the-hostname /build/reproducible-path/librsb-1.3.0.2+dfsg/rsbtest/.libs/rsbtest: unrecognized option '--unrecognized-option-triggers-abort' unrecognized option, aborting. ( ./rsbtest --no-tune --max_t 0.01 --skip-loading-hermitian-matrices --skip-loading-unsymmetric-matrices --tune-maxt 10 --tune-maxr 10 --verbose-tuning --extra-verbose-interface --min_t 0.01 --max_t 0.01 --mintimes 1 --maxtimes 1 --verbose --skip-loading-symmetric-matrices A.mtx | dd if=/dev/stdin of=/dev/stdout bs=16M status=none iflag=fullblock | grep -q skip ) @@ -9590,7 +9591,7 @@ ( ! ./rsbtest --no-tune --max_t 0.01 --quiet --types all --nthreads 1,2 --maxtimes 1 -+ A.mtx | dd if=/dev/stdin of=/dev/stdout bs=16M status=none iflag=fullblock | grep -q 2.threads ) ( ! ./rsbtest --no-tune --max_t 0.01 --quiet --render-only A.mtx > /dev/null ) ! ./rsbtest --no-tune --max_t 0.01 --quiet --max 1 --nrhs 1 --beta 1 --incy 1 --incx 1 --render --no-trans --alpha 1 --type all A.mtx -running on ionos5-amd64 +running on i-capture-the-hostname Will not invoke autotuning routine. Benchmark will sample for at most 0.01 s Built without render support! @@ -9642,7 +9643,7 @@ gmake[4]: Entering directory '/build/reproducible-path/librsb-1.3.0.2+dfsg' gmake[5]: Entering directory '/build/reproducible-path/librsb-1.3.0.2+dfsg' /usr/bin/mkdir -p '/build/reproducible-path/librsb-1.3.0.2+dfsg/debian/tmp/usr/lib/x86_64-linux-gnu' - /bin/bash ./libtool --mode=install /usr/bin/install -c librsb.la '/build/reproducible-path/librsb-1.3.0.2+dfsg/debian/tmp/usr/lib/x86_64-linux-gnu' + /bin/sh ./libtool --mode=install /usr/bin/install -c librsb.la '/build/reproducible-path/librsb-1.3.0.2+dfsg/debian/tmp/usr/lib/x86_64-linux-gnu' libtool: install: /usr/bin/install -c .libs/librsb.so.0.0.0 /build/reproducible-path/librsb-1.3.0.2+dfsg/debian/tmp/usr/lib/x86_64-linux-gnu/librsb.so.0.0.0 libtool: install: (cd /build/reproducible-path/librsb-1.3.0.2+dfsg/debian/tmp/usr/lib/x86_64-linux-gnu && { ln -s -f librsb.so.0.0.0 librsb.so.0 || { rm -f librsb.so.0 && ln -s librsb.so.0.0.0 librsb.so.0; }; }) libtool: install: (cd /build/reproducible-path/librsb-1.3.0.2+dfsg/debian/tmp/usr/lib/x86_64-linux-gnu && { ln -s -f librsb.so.0.0.0 librsb.so || { rm -f librsb.so && ln -s librsb.so.0.0.0 librsb.so; }; }) @@ -9652,7 +9653,7 @@ libtool: install: ranlib /build/reproducible-path/librsb-1.3.0.2+dfsg/debian/tmp/usr/lib/x86_64-linux-gnu/librsb.a libtool: warning: remember to run 'libtool --finish /usr/lib/x86_64-linux-gnu' /usr/bin/mkdir -p '/build/reproducible-path/librsb-1.3.0.2+dfsg/debian/tmp/usr/bin' - /bin/bash ./libtool --mode=install /usr/bin/install -c rsbench '/build/reproducible-path/librsb-1.3.0.2+dfsg/debian/tmp/usr/bin' + /bin/sh ./libtool --mode=install /usr/bin/install -c rsbench '/build/reproducible-path/librsb-1.3.0.2+dfsg/debian/tmp/usr/bin' libtool: warning: 'librsb.la' has not been installed in '/usr/lib/x86_64-linux-gnu' libtool: install: /usr/bin/install -c .libs/rsbench /build/reproducible-path/librsb-1.3.0.2+dfsg/debian/tmp/usr/bin/rsbench /usr/bin/mkdir -p '/build/reproducible-path/librsb-1.3.0.2+dfsg/debian/tmp/usr/bin' @@ -9779,11 +9780,11 @@ dh_gencontrol dh_md5sums dh_builddeb -dpkg-deb: building package 'librsb-dev' in '../librsb-dev_1.3.0.2+dfsg-6.1_amd64.deb'. -dpkg-deb: building package 'librsb0t64-dbgsym' in '../librsb0t64-dbgsym_1.3.0.2+dfsg-6.1_amd64.deb'. dpkg-deb: building package 'librsb0t64' in '../librsb0t64_1.3.0.2+dfsg-6.1_amd64.deb'. dpkg-deb: building package 'librsb-tools' in '../librsb-tools_1.3.0.2+dfsg-6.1_amd64.deb'. dpkg-deb: building package 'librsb-tools-dbgsym' in '../librsb-tools-dbgsym_1.3.0.2+dfsg-6.1_amd64.deb'. +dpkg-deb: building package 'librsb0t64-dbgsym' in '../librsb0t64-dbgsym_1.3.0.2+dfsg-6.1_amd64.deb'. +dpkg-deb: building package 'librsb-dev' in '../librsb-dev_1.3.0.2+dfsg-6.1_amd64.deb'. dpkg-deb: building package 'librsb-doc' in '../librsb-doc_1.3.0.2+dfsg-6.1_all.deb'. dpkg-genbuildinfo --build=binary -O../librsb_1.3.0.2+dfsg-6.1_amd64.buildinfo dpkg-genchanges --build=binary -O../librsb_1.3.0.2+dfsg-6.1_amd64.changes @@ -9793,12 +9794,14 @@ dpkg-buildpackage: info: binary-only upload (no source included) dpkg-genchanges: info: not including original source code in upload I: copying local configuration +I: user script /srv/workspace/pbuilder/1797627/tmp/hooks/B01_cleanup starting +I: user script /srv/workspace/pbuilder/1797627/tmp/hooks/B01_cleanup finished I: unmounting dev/ptmx filesystem I: unmounting dev/pts filesystem I: unmounting dev/shm filesystem I: unmounting proc filesystem I: unmounting sys filesystem I: cleaning the build env -I: removing directory /srv/workspace/pbuilder/1314568 and its subdirectories -I: Current time: Sat Jun 14 14:54:44 -12 2025 -I: pbuilder-time-stamp: 1749956084 +I: removing directory /srv/workspace/pbuilder/1797627 and its subdirectories +I: Current time: Mon May 13 11:55:57 +14 2024 +I: pbuilder-time-stamp: 1715550957