Diff of the two buildlogs: -- --- b1/build.log 2024-06-01 18:44:09.361823139 +0000 +++ b2/build.log 2024-06-01 20:08:42.186139701 +0000 @@ -1,6 +1,6 @@ I: pbuilder: network access will be disabled during build -I: Current time: Fri Jul 4 12:45:17 -12 2025 -I: pbuilder-time-stamp: 1751676317 +I: Current time: Sun Jun 2 08:44:12 +14 2024 +I: pbuilder-time-stamp: 1717267452 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/1814947/tmp/hooks/D02_print_environment starting +I: user script /srv/workspace/pbuilder/755909/tmp/hooks/D01_modify_environment starting +debug: Running on ionos11-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 Jun 1 18:44 /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/755909/tmp/hooks/D01_modify_environment finished +I: user script /srv/workspace/pbuilder/755909/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='dbf0bc557cc14cd1990457e97d037a2a' - 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='1814947' - PS1='# ' - PS2='> ' + INVOCATION_ID=a54b410c830744c187cfc8660ee49add + 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=755909 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.s53u0k6t/pbuilderrc_l2y0 --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.s53u0k6t/b1 --logfile b1/build.log librsb_1.3.0.2+dfsg-6.1.dsc' - SUDO_GID='111' - SUDO_UID='106' - 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.s53u0k6t/pbuilderrc_0VqX --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.s53u0k6t/b2 --logfile b2/build.log librsb_1.3.0.2+dfsg-6.1.dsc' + SUDO_GID=111 + SUDO_UID=106 + 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 ionos15-amd64 6.7.12+bpo-amd64 #1 SMP PREEMPT_DYNAMIC Debian 6.7.12-1~bpo12+1 (2024-05-06) 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 29 17:46 /bin -> usr/bin -I: user script /srv/workspace/pbuilder/1814947/tmp/hooks/D02_print_environment finished + lrwxrwxrwx 1 root root 7 Jun 1 11:25 /bin -> usr/bin +I: user script /srv/workspace/pbuilder/755909/tmp/hooks/D02_print_environment finished -> Attempting to satisfy build-dependencies -> Creating pbuilder-satisfydepends-dummy package Package: pbuilder-satisfydepends-dummy @@ -288,7 +320,7 @@ Get: 168 http://deb.debian.org/debian trixie/main amd64 libltdl-dev amd64 2.4.7-7+b1 [164 kB] Get: 169 http://deb.debian.org/debian trixie/main amd64 libhwloc-dev amd64 2.10.0-1+b1 [250 kB] Get: 170 http://deb.debian.org/debian trixie/main amd64 zlib1g-dev amd64 1:1.3.dfsg+really1.3.1-1 [919 kB] -Fetched 358 MB in 4s (86.1 MB/s) +Fetched 358 MB in 7s (47.9 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 ... 19699 files and directories currently installed.) @@ -849,8 +881,8 @@ Setting up tzdata (2024a-4) ... Current default time zone: 'Etc/UTC' -Local time is now: Sat Jul 5 00:46:34 UTC 2025. -Universal Time is now: Sat Jul 5 00:46:34 UTC 2025. +Local time is now: Sat Jun 1 18:46:05 UTC 2024. +Universal Time is now: Sat Jun 1 18:46:05 UTC 2024. Run 'dpkg-reconfigure tzdata' if you wish to change it. Setting up libfontenc1:amd64 (1:1.1.8-1) ... @@ -1016,7 +1048,11 @@ 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/755909/tmp/hooks/A99_set_merged_usr starting +Not re-configuring usrmerge for trixie +I: user script /srv/workspace/pbuilder/755909/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 @@ -1044,62 +1080,62 @@ 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'. @@ -1141,90 +1177,90 @@ 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' @@ -1407,7 +1443,7 @@ 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 @@ -1524,7 +1560,7 @@ 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 @@ -1546,7 +1582,7 @@ 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 @@ -1668,7 +1704,7 @@ 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 @@ -1677,7 +1713,7 @@ 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 @@ -1786,7 +1822,7 @@ 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 @@ -1796,7 +1832,7 @@ 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 @@ -1907,7 +1943,7 @@ 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 @@ -1939,7 +1975,7 @@ ARFLAGS : cru M4 : m4 MAKE : gmake - BASH : /bin/bash + BASH : /bin/sh OCTAVE : false DOXYGEN : doxygen HELP2MAN : help2man @@ -1958,7 +1994,7 @@ 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" @@ -1988,28 +2024,28 @@ 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_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_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 -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 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 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 rsbct rsbct.o ./.libs/librsbpp.a -lpthread -lstdc++fs -fopenmp @@ -2030,241 +2066,235 @@ gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+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 +/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_stropts.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_stropts.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_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_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_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_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_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_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_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.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_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_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_spmv.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_spmv.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_permute.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_permute.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 +/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_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_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_krnl_bcss_u.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_bcss_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_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_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_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_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_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_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_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_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_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_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_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_krnl_bcss_misc_u.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_bcss_misc_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 -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_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_krnl_bcss_u.c -o librsb_nounroll_la-rsb_krnl_bcss_u.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 +/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 +/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 +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.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 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 +/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 +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_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_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 -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 +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_krnl_bcss.c -o librsb_nounroll_la-rsb_krnl_bcss.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_prec.lo `test -f 'rsb_prec.c' || echo './'`rsb_prec.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_is.lo `test -f 'rsb_is.c' || echo './'`rsb_is.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_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_prec.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_prec.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_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 -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/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_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_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_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 +/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 -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/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 +/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 -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_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 -/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/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 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_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 +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 +/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 -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 -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/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 -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/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 +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 -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 -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_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 +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_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_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 +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_csr.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_csr.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_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 +/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_coo_check.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_coo_check.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 -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.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_unroll.c -o librsb_nounroll_la-rsb_unroll.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_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 -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_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_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 -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 -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_vb.c -o librsb_nounroll_la-rsb_krnl_vb.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_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_set.c -o librsb_base_la-rsb_set.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 -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/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 -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_ompio.c -o librsb_nounroll_la-rsb_ompio.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 -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_rec.lo `test -f 'rsb_rec.c' || echo './'`rsb_rec.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_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_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_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_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 +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 -o librsb_base_la-rsb_coo_check.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 +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 +/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 +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 +/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_get.c -o librsb_base_la-rsb_get.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 -fPIC -DPIC -o .libs/librsb_base_la-rsb_src.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_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_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_clone.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_clone.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 -o librsb_nounroll_la-rsb_prec.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 +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_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_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_srt.c -o librsb_base_la-rsb_srt.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_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_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_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_eps.lo `test -f 'rsb_eps.c' || echo './'`rsb_eps.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_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_eps.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_eps.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 -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 -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_set.c -o librsb_base_la-rsb_set.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_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_spmv.c -o librsb_nounroll_la-rsb_spmv.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 -/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 -/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 +/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 +/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 -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_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_sys.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_sys.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 -/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 -/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 +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 -fPIC -DPIC -o .libs/librsb_base_la-rsb_blas_stuff.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_do.lo `test -f 'rsb_do.c' || echo './'`rsb_do.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 -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_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_perf.lo `test -f 'rsb_perf.c' || echo './'`rsb_perf.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_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 -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/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_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_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_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 -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/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_tune.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_tune.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 -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_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_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_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_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 -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/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_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_blas_stuff.c -o librsb_base_la-rsb_blas_stuff.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 +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_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_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_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_rsb.c -o librsb_base_la-rsb_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_do.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_do.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_internals.lo `test -f 'rsb_internals.c' || echo './'`rsb_internals.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_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_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_garbage.lo `test -f 'rsb_garbage.c' || echo './'`rsb_garbage.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_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_internals.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_internals.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_partition.lo `test -f 'rsb_partition.c' || echo './'`rsb_partition.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_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_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_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_test_accuracy.c -o librsb_base_la-rsb_test_accuracy.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_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_blas_stuff.c -o librsb_base_la-rsb_blas_stuff.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_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_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_mmio.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_mmio.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 -fPIC -DPIC -o .libs/librsb_base_la-rsb_partition.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_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 -/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_rsb.c -o librsb_base_la-rsb_rsb.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_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 -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_perf.c -o librsb_base_la-rsb_perf.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_spsum.lo `test -f 'rsb_spsum.c' || echo './'`rsb_spsum.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_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 -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_get.c -o librsb_base_la-rsb_get.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_lock.lo `test -f 'rsb_lock.c' || echo './'`rsb_lock.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_mbw.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_mbw.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_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_limiter.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_limiter.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_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_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_fpb.lo `test -f 'rsb_fpb.c' || echo './'`rsb_fpb.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_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_mbw.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_mbw.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_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_fpb.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_fpb.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_spgemm.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_spgemm.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_spsum.lo `test -f 'rsb_spsum.c' || echo './'`rsb_spsum.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_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_lock.lo `test -f 'rsb_lock.c' || echo './'`rsb_lock.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 -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_fpb.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_fpb.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_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 -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 +/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 -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/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 -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_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 -/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_eps.c -o librsb_base_la-rsb_eps.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_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_dump.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_dump.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_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_swt.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_swt.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_init.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_init.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 -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 -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/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/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_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_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_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_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_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_cpmv.lo `test -f 'rsb_cpmv.c' || echo './'`rsb_cpmv.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_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_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_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_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_mmio.c -o librsb_base_la-rsb_mmio.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_partition.c -o librsb_base_la-rsb_partition.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_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_limiter.c -o librsb_base_la-rsb_limiter.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 +/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 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 -/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_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_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 -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/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 -/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_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_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_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_asm.c -o librsb_base_la-rsb_asm.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 +/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 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/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 +/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 +/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 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 -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/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 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 -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_spgemm.c -o librsb_base_la-rsb_spgemm.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 -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_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 -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/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 -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.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_cpmv.c -o librsb_base_la-rsb_cpmv.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_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_dump.c -o librsb_base_la-rsb_dump.o >/dev/null 2>&1 +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 -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/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_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_rec2coo.c -o librsb_base_la-rsb_rec2coo.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 -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: warning: '-version-info' is ignored for programs +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: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+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 +/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: 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 -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 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 +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: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+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_coo2rec.c -o librsb_base_la-rsb_coo2rec.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 -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 -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/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 -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" ) -/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: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+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 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:"", @@ -2283,12 +2313,20 @@ | ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 32 | __va_arg_pack ()); | ~~~~~~~~~~~~~~~~~ -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: 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_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: 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" ) +/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 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 -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 +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 -o librsb_nounroll_la-rsb_krnl_bcss_misc_u.o >/dev/null 2>&1 rsb_test_matops.c: In function 'rsb__main_block_partitioned_spsv_sxsx': 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:"", @@ -2303,8 +2341,6 @@ | ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 32 | __va_arg_pack ()); | ~~~~~~~~~~~~~~~~~ -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 -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 -o librsb_nounroll_la-rsb_krnl_bcss_misc_u.o >/dev/null 2>&1 rsb_test_matops.c: In function 'rsb__main_block_partitioned_mat_stats': 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:"", @@ -2321,12 +2357,12 @@ | ~~~~~~~~~~~~~~~~~ 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") @@ -2338,7 +2374,7 @@ 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' @@ -2355,27 +2391,27 @@ 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 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 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 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 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 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 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 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/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 +/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 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 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 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 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 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 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 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 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 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/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 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 +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/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/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/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 -/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_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 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 @@ -2394,11 +2430,11 @@ 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 \ +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. @@ -3109,13 +3145,13 @@ 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 -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/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 -/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 +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 +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 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 @@ -3130,25 +3166,25 @@ 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 -/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 -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/assemble assemble.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 render render.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/render render.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 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 span span.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/assemble assemble.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 misc misc.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/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/example example.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/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 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/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/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 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' @@ -3158,7 +3194,7 @@ 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' @@ -3234,7 +3270,7 @@ 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 @@ -3244,15 +3280,15 @@ 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 1751677188 +# beginning run at 1717270860 # /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: 3.68e-08 s -# Will write a final performance record to file rsbench_pr__1751677188_gcc-13.2-1,4th.rpr and periodic checkpoints to rsbench_pr__1751677188_gcc-13.2-1,4th.rpr.tmp +# average timer granularity: 5.49e-07 s +# Will write a final performance record to file rsbench_pr__1717270860_gcc-13.2-1,4th.rpr and periodic checkpoints to rsbench_pr__1717270860_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 @@ -3291,61 +3327,61 @@ # 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: ionos15-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 7.149s +# Memory benchmark took 6.251s # 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 7.151s 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 6.281s 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, 28181 nnz/s ) (0.86 MB/s ) -#pre-sorting (6 elements) took 0.0103619 s -#weeding duplicates (to 6 elements) took 1.90735e-06 s (and check, 9.53674e-07 s ) +# file input of A.mtx took 0.00 s (6 nnz, 23809 nnz/s ) (0.73 MB/s ) +#pre-sorting (6 elements) took 0.0459042 s +#weeding duplicates (to 6 elements) took 1.40667e-05 s (and check, 0 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 0.035s): (3 x 3)[0x5645f959ba20]{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 0.171s): (3 x 3)[0x55729a6119d0]{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 0.02069s; avg 0.006897s ( +/- 17.59/ 9.84 %); best 0.005684s; worst 0.007576s; std dev. 0.0008599 (taking best). -Reference operation time is 0.00568414 s (0.01689 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: 0.005684 Mflops: 0.017) -Merge (3 -> 1 leaves) took w.c.t. of 2.599e-05s, ~9.06e-06s of computing time (of which 1.192e-06s sorting, 8.106e-06s analysis) -3 iterations (1 th.) took 4.697e-05s; avg 1.566e-05s ( +/- 99.76/193.91 %); best 3.711e-08s; worst 4.601e-05s; std dev. 2.147e-05 (taking best). -Reference operation time is 3.71099e-08 s (2587 Mflops) with 1 threads. -After merge step 1: tpop: 3.711e-08 s ~Mflops: 2586.914 nsubm:1 otn:1 -Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 153170.575x: 0.005684s -> 3.711e-08s, so taking this instance. +3 iterations (1 th.) took 0.08802s; avg 0.02934s ( +/- 4.95/ 9.11 %); best 0.02789s; worst 0.03201s; std dev. 0.001893 (taking best). +Reference operation time is 0.0278869 s (0.003442 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: 0.02789 Mflops: 0.003) +Merge (3 -> 1 leaves) took w.c.t. of 2.146e-06s, ~0s of computing time (of which 0s sorting, 0s analysis) +3 iterations (1 th.) took 5.293e-05s; avg 1.764e-05s ( +/- 94.59/183.78 %); best 9.537e-07s; worst 5.007e-05s; std dev. 2.293e-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 29241.500x: 0.02789s -> 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 0.01854s (of which 4.601e-05s partitioning, 0s I/O); computing times: 9.06e-06s in par. loops, 1.192e-06s sorting, 8.106e-06s analyzing) -Total merge + benchmarking process took 0.01854s, equivalent to 499511.7/3.3 new/old ops (0.04491s for 2 clones -- as 1210131.7/7.9 ops, or 605065.9/4.0 ops per clone), SPEEDUP of 153170.575x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 153170.575x (0.005684s -> 3.711e-08s), will amortize in 3.3 ops by saving 0.005684s per op. -In 1 tuning rounds (tot. 0.066s, 0.045s for constructor, 2 clones) obtained a SPEEDUP of 15316957.5% (1.532e+05x) (from 0.01689 to 2587 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.09201s (of which 6.199e-06s partitioning, 0s I/O); computing times: 0s in par. loops, 0s sorting, 0s analyzing) +Total merge + benchmarking process took 0.09201s, equivalent to 96478.5/3.3 new/old ops (0.2077s for 2 clones -- as 217787.0/7.4 ops, or 108893.5/3.7 ops per clone), SPEEDUP of 29241.500x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 29241.500x (0.02789s -> 9.537e-07s), will amortize in 3.3 ops by saving 0.02789s per op. +In 1 tuning rounds (tot. 0.3s, 0.21s for constructor, 2 clones) obtained a SPEEDUP of 2924050.0% (2.924e+04x) (from 0.003442 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 0.0657911 s (5.684e-03 s -> 3.711e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.296056 s (2.789e-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 0.329747 s and estimated a speedup of 1.000000 x (3.711e-08 s -> 3.711e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 1.80388 s and estimated a speedup of 1.000000 x (9.484e-07 s -> 9.484e-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 0.007541 0.011294 0.018835 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 1 3 3 6 0.018835 -%:RSB_SUBDIVISION_TIME:A.mtx S N 1 3 3 6 0.007541 -%:RSB_SHUFFLE_TIME:A.mtx S N 1 3 3 6 0.011294 +%:CONSTRUCTOR_TIMES:A.mtx S N 1 3 3 6 0.000000 0.063076 0.067961 0.131037 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 1 3 3 6 0.131037 +%:RSB_SUBDIVISION_TIME:A.mtx S N 1 3 3 6 0.063076 +%:RSB_SHUFFLE_TIME:A.mtx S N 1 3 3 6 0.067961 %: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 0.018835 +%:SORTEDCOO2RSB_TIME:A.mtx S N 1 3 3 6 0.131037 %: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 @@ -3360,47 +3396,47 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 1 3 3 6 6 6 6 # # Using 4 threads -# Constructed matrix (took 0.048s): (3 x 3)[0x5645f959ba20]{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 0.219s): (3 x 3)[0x55729a6119d0]{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 0.01704s; avg 0.00568s ( +/- 31.14/ 34.03 %); best 0.003911s; worst 0.007613s; std dev. 0.001516 (taking best). -Reference operation time is 0.00391102 s (0.02455 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: 0.003911 Mflops: 0.025) -Merge (3 -> 1 leaves) took w.c.t. of 1.502e-05s, ~5.007e-06s of computing time (of which 9.537e-07s sorting, 3.099e-06s analysis) -3 iterations (4 th.) took 3.815e-06s; avg 1.272e-06s ( +/- 97.08/125.00 %); best 3.711e-08s; worst 2.861e-06s; std dev. 1.189e-06 (taking best). -Reference operation time is 3.71099e-08 s (2587 Mflops) with 4 threads. -After merge step 1: tpop: 3.711e-08 s ~Mflops: 2586.914 nsubm:1 otn:1 -Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 105390.299x: 0.003911s -> 3.711e-08s, so taking this instance. +3 iterations (4 th.) took 0.07998s; avg 0.02666s ( +/- 9.72/ 4.90 %); best 0.02407s; worst 0.02797s; std dev. 0.001833 (taking best). +Reference operation time is 0.0240679 s (0.003989 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: 0.02407 Mflops: 0.004) +Merge (3 -> 1 leaves) took w.c.t. of 5.007e-05s, ~1.407e-05s of computing time (of which 3.099e-06s sorting, 9.06e-06s analysis) +3 iterations (4 th.) took 1.287e-05s; avg 4.292e-06s ( +/- 77.78/155.56 %); best 9.537e-07s; worst 1.097e-05s; std dev. 4.72e-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 25237.000x: 0.02407s -> 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 0.02657s (of which 1.788e-05s partitioning, 0s I/O); computing times: 5.007e-06s in par. loops, 9.537e-07s sorting, 3.099e-06s analyzing) -Total merge + benchmarking process took 0.02657s, equivalent to 716061.7/6.8 new/old ops (0.04654s for 2 clones -- as 1254192.1/11.9 ops, or 627096.0/6.0 ops per clone), SPEEDUP of 105390.299x -Applying multi-merge (3 -> 1 leaves, 1 steps, 1 -> 1 th.sp.) yielded SPEEDUP of 105390.299x (0.003911s -> 3.711e-08s), will amortize in 6.8 ops by saving 0.003911s per op. -In 1 tuning rounds (tot. 0.064s, 0.047s for constructor, 2 clones) obtained a SPEEDUP of 10538929.9% (1.054e+05x) (from 0.02455 to 2587 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.112s (of which 5.698e-05s partitioning, 0s I/O); computing times: 1.407e-05s in par. loops, 3.099e-06s sorting, 9.06e-06s analyzing) +Total merge + benchmarking process took 0.112s, equivalent to 117437.5/4.7 new/old ops (0.2273s for 2 clones -- as 238381.5/9.4 ops, or 119190.8/4.7 ops per clone), SPEEDUP of 25237.000x +Applying multi-merge (3 -> 1 leaves, 1 steps, 1 -> 1 th.sp.) yielded SPEEDUP of 25237.000x (0.02407s -> 9.537e-07s), will amortize in 4.7 ops by saving 0.02407s per op. +In 1 tuning rounds (tot. 0.31s, 0.23s for constructor, 2 clones) obtained a SPEEDUP of 2523600.0% (2.524e+04x) (from 0.003989 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 0.063693 s (3.911e-03 s -> 3.711e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.307555 s (2.407e-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 0.330344 s and estimated a speedup of 1.000000 x (3.711e-08 s -> 3.711e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 1.98796 s and estimated a speedup of 1.000000 x (9.484e-07 s -> 9.484e-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 0.009495 0.024906 0.034401 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 4 3 3 6 0.034401 -%:RSB_SUBDIVISION_TIME:A.mtx S N 4 3 3 6 0.009495 -%:RSB_SHUFFLE_TIME:A.mtx S N 4 3 3 6 0.024906 +%:CONSTRUCTOR_TIMES:A.mtx S N 4 3 3 6 0.000000 0.075457 0.071396 0.146853 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 4 3 3 6 0.146853 +%:RSB_SUBDIVISION_TIME:A.mtx S N 4 3 3 6 0.075457 +%:RSB_SHUFFLE_TIME:A.mtx S N 4 3 3 6 0.071396 %: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 0.034401 +%:SORTEDCOO2RSB_TIME:A.mtx S N 4 3 3 6 0.146853 %: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 0.55 -%:SORTEDCOO2RSB_SCALING:A.mtx S N 4 3 3 6 0.55 -%:RSB_SUBDIVISION_SCALING:A.mtx S N 4 3 3 6 0.79 -%:RSB_SHUFFLE_SCALING:A.mtx S N 4 3 3 6 0.45 -%:CONSTRUCTOR_SCALING:A.mtx S N 4 3 3 6 -nan 0.79 0.45 0.55 +%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 4 3 3 6 0.89 +%:SORTEDCOO2RSB_SCALING:A.mtx S N 4 3 3 6 0.89 +%:RSB_SUBDIVISION_SCALING:A.mtx S N 4 3 3 6 0.84 +%:RSB_SHUFFLE_SCALING:A.mtx S N 4 3 3 6 0.95 +%:CONSTRUCTOR_SCALING:A.mtx S N 4 3 3 6 -nan 0.84 0.95 0.89 #%: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 @@ -3409,56 +3445,56 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 4 3 3 6 6 6 6 # %operation:matrix CONSTRUCTOR[1] SPMV[1] SPMV[4] -%operation:A.mtx 0.034503 1e+09 1e+09 +%operation:A.mtx 0.171086 1e+09 1e+09 %constructor:matrix SORT[1] SCAN[1] SHUFFLE[1] INSERT[1] -%constructor:A.mtx 0 0.00754094 0 0.0112941 +%constructor:A.mtx 0 0.063076 0 0.067961 # 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 0.034s): (3 x 3)[0x5645f959ba20]{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 0.204s): (3 x 3)[0x55729a6119d0]{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 0.02782s; avg 0.009274s ( +/- 39.51/ 52.34 %); best 0.00561s; worst 0.01413s; std dev. 0.003578 (taking best). -Reference operation time is 0.00560999 s (0.03422 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: 0.00561 Mflops: 0.034) -Merge (3 -> 1 leaves) took w.c.t. of 1.287e-05s, ~4.053e-06s of computing time (of which 9.537e-07s sorting, 1.907e-06s analysis) -3 iterations (1 th.) took 6.89e-05s; avg 2.297e-05s ( +/- 95.85/191.70 %); best 9.537e-07s; worst 6.7e-05s; std dev. 3.113e-05 (taking best). +3 iterations (1 th.) took 0.1161s; avg 0.03868s ( +/- 17.33/ 14.01 %); best 0.03198s; worst 0.0441s; std dev. 0.005033 (taking best). +Reference operation time is 0.0319779 s (0.006004 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: 0.03198 Mflops: 0.006) +Merge (3 -> 1 leaves) took w.c.t. of 5.198e-05s, ~1.597e-05s of computing time (of which 5.007e-06s sorting, 1.097e-05s analysis) +3 iterations (1 th.) took 1.693e-05s; avg 5.643e-06s ( +/- 83.10/166.20 %); best 9.537e-07s; worst 1.502e-05s; std dev. 6.631e-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 5882.500x: 0.00561s -> 9.537e-07s, so taking this instance. +Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 33531.250x: 0.03198s -> 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 0.01667s (of which 1.717e-05s partitioning, 0s I/O); computing times: 4.053e-06s in par. loops, 9.537e-07s sorting, 1.907e-06s analyzing) -Total merge + benchmarking process took 0.01667s, equivalent to 17485.0/3.0 new/old ops (0.03488s for 2 clones -- as 36578.5/6.2 ops, or 18289.2/3.1 ops per clone), SPEEDUP of 5882.500x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 5882.500x (0.00561s -> 9.537e-07s), will amortize in 3.0 ops by saving 0.005609s per op. -In 1 tuning rounds (tot. 0.063s, 0.035s for constructor, 2 clones) obtained a SPEEDUP of 588150.0% (5882x) (from 0.03422 to 201.3 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.1119s (of which 5.794e-05s partitioning, 0s I/O); computing times: 1.597e-05s in par. loops, 5.007e-06s sorting, 1.097e-05s analyzing) +Total merge + benchmarking process took 0.1119s, equivalent to 117349.2/3.5 new/old ops (0.2117s for 2 clones -- as 221939.8/6.6 ops, or 110969.9/3.3 ops per clone), SPEEDUP of 33531.250x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 33531.250x (0.03198s -> 9.537e-07s), will amortize in 3.5 ops by saving 0.03198s per op. +In 1 tuning rounds (tot. 0.33s, 0.21s for constructor, 2 clones) obtained a SPEEDUP of 3353025.0% (3.353e+04x) (from 0.006004 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 0.062861 s (5.610e-03 s -> 9.537e-07 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.327991 s (3.198e-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 0.32712 s and estimated a speedup of 1.000000 x (3.711e-08 s -> 3.711e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 1.91192 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 0.009547 0.013139 0.022686 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 1 3 3 6 0.022686 -%:RSB_SUBDIVISION_TIME:A.mtx S N 1 3 3 6 0.009547 -%:RSB_SHUFFLE_TIME:A.mtx S N 1 3 3 6 0.013139 -%: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 0.022686 +%:CONSTRUCTOR_TIMES:A.mtx S N 1 3 3 6 0.000001 0.059635 0.068320 0.127955 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 1 3 3 6 0.127956 +%:RSB_SUBDIVISION_TIME:A.mtx S N 1 3 3 6 0.059635 +%:RSB_SHUFFLE_TIME:A.mtx S N 1 3 3 6 0.068320 +%: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 0.127955 %: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 @@ -3467,47 +3503,47 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 1 3 3 6 6 6 6 # # Using 4 threads -# Constructed matrix (took 0.058s): (3 x 3)[0x5645f959ba20]{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 0.320s): (3 x 3)[0x55729a6119d0]{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 0.02062s; avg 0.006872s ( +/- 18.36/ 35.22 %); best 0.00561s; worst 0.009292s; std dev. 0.001712 (taking best). -Reference operation time is 0.00560999 s (0.03422 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: 0.00561 Mflops: 0.034) -Merge (3 -> 1 leaves) took w.c.t. of 1.597e-05s, ~5.007e-06s of computing time (of which 9.537e-07s sorting, 3.099e-06s analysis) -3 iterations (4 th.) took 5.96e-06s; avg 1.987e-06s ( +/- 98.13/152.00 %); best 3.711e-08s; worst 5.007e-06s; std dev. 2.171e-06 (taking best). -Reference operation time is 3.71099e-08 s (5174 Mflops) with 4 threads. -After merge step 1: tpop: 3.711e-08 s ~Mflops: 5173.828 nsubm:1 otn:1 -Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 151172.502x: 0.00561s -> 3.711e-08s, so taking this instance. +3 iterations (4 th.) took 0.128s; avg 0.04267s ( +/- 14.78/ 11.75 %); best 0.03636s; worst 0.04768s; std dev. 0.004712 (taking best). +Reference operation time is 0.0363591 s (0.005281 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: 0.03636 Mflops: 0.005) +Merge (3 -> 1 leaves) took w.c.t. of 4.601e-05s, ~1.287e-05s of computing time (of which 2.861e-06s sorting, 8.821e-06s analysis) +3 iterations (4 th.) took 1.812e-05s; avg 6.04e-06s ( +/- 84.21/164.47 %); best 9.537e-07s; worst 1.597e-05s; std dev. 7.025e-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 38125.250x: 0.03636s -> 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 0.02674s (of which 1.907e-05s partitioning, 0s I/O); computing times: 5.007e-06s in par. loops, 9.537e-07s sorting, 3.099e-06s analyzing) -Total merge + benchmarking process took 0.02674s, equivalent to 720668.2/4.8 new/old ops (0.04652s for 2 clones -- as 1253703.8/8.3 ops, or 626851.9/4.1 ops per clone), SPEEDUP of 151172.502x -Applying multi-merge (3 -> 1 leaves, 1 steps, 1 -> 1 th.sp.) yielded SPEEDUP of 151172.502x (0.00561s -> 3.711e-08s), will amortize in 4.8 ops by saving 0.00561s per op. -In 1 tuning rounds (tot. 0.067s, 0.047s for constructor, 2 clones) obtained a SPEEDUP of 15117150.2% (1.512e+05x) (from 0.03422 to 5174 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.1601s (of which 5.293e-05s partitioning, 0s I/O); computing times: 1.287e-05s in par. loops, 2.861e-06s sorting, 8.821e-06s analyzing) +Total merge + benchmarking process took 0.1601s, equivalent to 167834.0/4.4 new/old ops (0.3038s for 2 clones -- as 318555.2/8.4 ops, or 159277.6/4.2 ops per clone), SPEEDUP of 38125.250x +Applying multi-merge (3 -> 1 leaves, 1 steps, 1 -> 1 th.sp.) yielded SPEEDUP of 38125.250x (0.03636s -> 9.537e-07s), will amortize in 4.4 ops by saving 0.03636s per op. +In 1 tuning rounds (tot. 0.43s, 0.3s for constructor, 2 clones) obtained a SPEEDUP of 3812425.0% (3.813e+04x) (from 0.005281 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 0.0672538 s (5.610e-03 s -> 3.711e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.432047 s (3.636e-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 0.39685 s and estimated a speedup of 1.000000 x (3.711e-08 s -> 3.711e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 1.70599 s and estimated a speedup of 1.000000 x (9.484e-07 s -> 9.484e-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 0.010837 0.032076 0.042913 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 4 3 3 6 0.042913 -%:RSB_SUBDIVISION_TIME:A.mtx S N 4 3 3 6 0.010837 -%:RSB_SHUFFLE_TIME:A.mtx S N 4 3 3 6 0.032076 -%: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 0.042913 +%:CONSTRUCTOR_TIMES:A.mtx S N 4 3 3 6 0.000001 0.111667 0.148015 0.259682 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 4 3 3 6 0.259683 +%:RSB_SUBDIVISION_TIME:A.mtx S N 4 3 3 6 0.111667 +%:RSB_SHUFFLE_TIME:A.mtx S N 4 3 3 6 0.148015 +%: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 1.250 +%:SORTEDCOO2RSB_TIME:A.mtx S N 4 3 3 6 0.259682 %: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 0.53 -%:SORTEDCOO2RSB_SCALING:A.mtx S N 4 3 3 6 0.53 -%:RSB_SUBDIVISION_SCALING:A.mtx S N 4 3 3 6 0.88 -%:RSB_SHUFFLE_SCALING:A.mtx S N 4 3 3 6 0.41 -%:CONSTRUCTOR_SCALING:A.mtx S N 4 3 3 6 -nan 0.88 0.41 0.53 +%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 4 3 3 6 0.49 +%:SORTEDCOO2RSB_SCALING:A.mtx S N 4 3 3 6 0.49 +%:RSB_SUBDIVISION_SCALING:A.mtx S N 4 3 3 6 0.53 +%:RSB_SHUFFLE_SCALING:A.mtx S N 4 3 3 6 0.46 +%:CONSTRUCTOR_SCALING:A.mtx S N 4 3 3 6 1.25 0.53 0.46 0.49 #%: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 @@ -3516,185 +3552,185 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 4 3 3 6 6 6 6 # %operation:matrix CONSTRUCTOR[1] SPMV[1] SPMV[4] -%operation:A.mtx 0.03403 1e+09 1e+09 +%operation:A.mtx 0.203622 1e+09 1e+09 %constructor:matrix SORT[1] SCAN[1] SHUFFLE[1] INSERT[1] -%constructor:A.mtx 0 0.009547 0 0.013139 +%constructor:A.mtx 1.19209e-06 0.0596352 0 0.06832 # symmetric matrix --- skipping transposed benchmarking -# so far, program took 9.118s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 1.644s/0.000s . +# so far, program took 16.751s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 8.773s/0.000s . getrusage() stats: -ru_maxrss: 28 (maximum resident set size -- MB) -ru_stime : 0.3654s (system CPU time used) -ru_utime : 45.59s (user CPU time used) +ru_maxrss: 11 (maximum resident set size -- MB) +ru_stime : 0.06708s (system CPU time used) +ru_utime : 54.01s (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 2586.91 5.684e-03 0.000e+00 3.711e-08 0.000e+00 6.579e-02 7.22e+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 2586.91 3.911e-03 0.000e+00 3.711e-08 0.000e+00 6.369e-02 7.22e+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 2.789e-02 0.000e+00 9.537e-07 0.000e+00 2.961e-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 2.407e-02 0.000e+00 9.537e-07 0.000e+00 3.076e-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. 12927943.7 % faster, avg. sp. ratio 129280.437x, max sp. ratio 153170.575x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 1744606.5/1716337.9/1772875.0/3489213.0 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 13.9/ 11.6/ 16.3/ 27.9 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 13.9, min. 11.6, max. 16.3 ops) +#pr: (in succ. cases rsb autotuning gave avg. 2723825.0 % faster, avg. sp. ratio 27239.250x, max sp. ratio 29241.500x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 316466.1/310437.2/322495.0/632932.2 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 11.7/ 10.6/ 12.8/ 23.4 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 11.7, min. 10.6, max. 12.8 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 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 5.928/ 5.928/ 5.928,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 14.444/ 7.222/ 7.222,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.: 0.06 s, min 0.06 s, max 0.07 s, tot 0.13 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.06 s, min 0.06 s, max 0.07 s, tot 0.13 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 2.587e+03, min 2.587e+03, max 2.587e+03 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 2.072e-02, min 1.689e-02, max 2.455e-02 (2 samples) -#pr: best tun. rsb operation time was: on avg. 3.711e-08s, min 3.711e-08s, max 3.711e-08s, tot 7.422e-08s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 4.798e-03s, min 3.911e-03s, max 5.684e-03s, tot 9.595e-03s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 3.503e+00 3.503e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.067e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.30 s, min 0.30 s, max 0.31 s, tot 0.60 s (2 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.30 s, min 0.30 s, max 0.31 s, tot 0.60 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. 3.716e-03, min 3.442e-03, max 3.989e-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. 2.598e-02s, min 2.407e-02s, max 2.789e-02s, tot 5.195e-02s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 9.013e+00 9.013e+00 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 2.515e+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 1 201.33 5.610e-03 0.000e+00 9.537e-07 0.000e+00 6.286e-02 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 5173.83 5.610e-03 0.000e+00 3.711e-08 0.000e+00 6.725e-02 1.11e+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 3.198e-02 0.000e+00 9.537e-07 0.000e+00 3.280e-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 3.636e-02 0.000e+00 9.537e-07 0.000e+00 4.320e-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. 7852650.1 % faster, avg. sp. ratio 78527.501x, max sp. ratio 151172.502x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 939102.4/65914.5/1812290.4/1878204.9 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 11.6/ 11.2/ 12.0/ 23.2 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 11.6, min. 11.2, max. 12.0 ops) +#pr: (in succ. cases rsb autotuning gave avg. 3582725.0 % faster, avg. sp. ratio 35828.250x, max sp. ratio 38125.250x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 398478.9/343923.5/453034.2/796957.8 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 11.1/ 10.3/ 11.9/ 22.1 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 11.1, min. 10.3, max. 11.9 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 4.423/ 0.331/ 8.515,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 11.534/ 0.432/ 11.102,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.: 0.07 s, min 0.06 s, max 0.07 s, tot 0.13 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.07 s, min 0.06 s, max 0.07 s, tot 0.13 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 2.688e+03, min 2.013e+02, max 5.174e+03 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 3.422e-02, min 3.422e-02, max 3.422e-02 (2 samples) -#pr: best tun. rsb operation time was: on avg. 4.954e-07s, min 3.711e-08s, max 9.537e-07s, tot 9.908e-07s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 5.610e-03s, min 5.610e-03s, max 5.610e-03s, tot 1.122e-02s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 2.439e+00 6.268e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.067e+00 -#pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 1.039e+00 x, min 7.783e-02 x, max 2.000e+00 x (2 samples, the non-min-nrhs ones) +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.38 s, min 0.33 s, max 0.43 s, tot 0.76 s (2 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.38 s, min 0.33 s, max 0.43 s, tot 0.76 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. 5.642e-03, min 5.281e-03, max 6.004e-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. 3.417e-02s, min 3.198e-02s, max 3.636e-02s, tot 6.834e-02s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 6.275e+00 6.275e+00 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 2.515e+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 2586.91 5.684e-03 0.000e+00 3.711e-08 0.000e+00 6.579e-02 7.22e+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 1 201.33 5.610e-03 0.000e+00 9.537e-07 0.000e+00 6.286e-02 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 2586.91 3.911e-03 0.000e+00 3.711e-08 0.000e+00 6.369e-02 7.22e+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 5173.83 5.610e-03 0.000e+00 3.711e-08 0.000e+00 6.725e-02 1.11e+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 2.789e-02 0.000e+00 9.537e-07 0.000e+00 2.961e-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 3.198e-02 0.000e+00 9.537e-07 0.000e+00 3.280e-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 2.407e-02 0.000e+00 9.537e-07 0.000e+00 3.076e-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 3.636e-02 0.000e+00 9.537e-07 0.000e+00 4.320e-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. 10390296.9 % faster, avg. sp. ratio 103903.969x, max sp. ratio 153170.575x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 1341854.5/65914.5/1812290.4/5367417.9 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 12.8/ 11.2/ 16.3/ 51.1 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 12.8, min. 11.2, max. 16.3 ops) +#pr: (in succ. cases rsb autotuning gave avg. 3153275.0 % faster, avg. sp. ratio 31533.750x, max sp. ratio 38125.250x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 357472.5/310437.2/453034.2/1429890.0 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 11.4/ 10.3/ 12.8/ 45.5 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 11.4, min. 10.3, max. 12.8 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 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 5.176/ 0.331/ 8.515,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 25.978/ 0.432/ 11.102,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.: 0.06 s, min 0.06 s, max 0.07 s, tot 0.26 s (4 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.06 s, min 0.06 s, max 0.07 s, tot 0.26 s (4 samples) -#pr: best tun. rsb canon. mflops were: on avg. 2.637e+03, min 2.013e+02, max 5.174e+03 (4 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 2.747e-02, min 1.689e-02, max 3.422e-02 (4 samples) -#pr: best tun. rsb operation time was: on avg. 2.663e-07s, min 3.711e-08s, max 9.537e-07s, tot 1.065e-06s (4 samples) -#pr: ref. unt. rsb operation time was: on avg. 5.204e-03s, min 3.911e-03s, max 5.684e-03s, tot 2.082e-02s (4 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 2.439e+00 6.268e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.067e+00 -#pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 1.039e+00 x, min 7.783e-02 x, max 2.000e+00 x (2 samples, the non-min-nrhs ones) +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.34 s, min 0.30 s, max 0.43 s, tot 1.36 s (4 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.34 s, min 0.30 s, max 0.43 s, tot 1.36 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. 4.679e-03, min 3.442e-03, max 6.004e-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. 3.007e-02s, min 2.407e-02s, max 3.636e-02s, tot 1.203e-01s (4 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 6.275e+00 9.013e+00 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 2.515e+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 2586.91 5.684e-03 0.000e+00 3.711e-08 0.000e+00 6.579e-02 7.22e+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 2586.91 3.911e-03 0.000e+00 3.711e-08 0.000e+00 6.369e-02 7.22e+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 2.789e-02 0.000e+00 9.537e-07 0.000e+00 2.961e-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 2.407e-02 0.000e+00 9.537e-07 0.000e+00 3.076e-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. 12927943.7 % faster, avg. sp. ratio 129280.437x, max sp. ratio 153170.575x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 1744606.5/1716337.9/1772875.0/3489213.0 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 13.9/ 11.6/ 16.3/ 27.9 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 13.9, min. 11.6, max. 16.3 ops) +#pr: (in succ. cases rsb autotuning gave avg. 2723825.0 % faster, avg. sp. ratio 27239.250x, max sp. ratio 29241.500x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 316466.1/310437.2/322495.0/632932.2 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 11.7/ 10.6/ 12.8/ 23.4 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 11.7, min. 10.6, max. 12.8 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 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 5.928/ 5.928/ 5.928,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 14.444/ 7.222/ 7.222,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.: 0.06 s, min 0.06 s, max 0.07 s, tot 0.13 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.06 s, min 0.06 s, max 0.07 s, tot 0.13 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 2.587e+03, min 2.587e+03, max 2.587e+03 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 2.072e-02, min 1.689e-02, max 2.455e-02 (2 samples) -#pr: best tun. rsb operation time was: on avg. 3.711e-08s, min 3.711e-08s, max 3.711e-08s, tot 7.422e-08s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 4.798e-03s, min 3.911e-03s, max 5.684e-03s, tot 9.595e-03s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 3.503e+00 3.503e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.067e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.30 s, min 0.30 s, max 0.31 s, tot 0.60 s (2 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.30 s, min 0.30 s, max 0.31 s, tot 0.60 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. 3.716e-03, min 3.442e-03, max 3.989e-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. 2.598e-02s, min 2.407e-02s, max 2.789e-02s, tot 5.195e-02s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 9.013e+00 9.013e+00 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 2.515e+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 1 201.33 5.610e-03 0.000e+00 9.537e-07 0.000e+00 6.286e-02 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 5173.83 5.610e-03 0.000e+00 3.711e-08 0.000e+00 6.725e-02 1.11e+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 3.198e-02 0.000e+00 9.537e-07 0.000e+00 3.280e-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 3.636e-02 0.000e+00 9.537e-07 0.000e+00 4.320e-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. 7852650.1 % faster, avg. sp. ratio 78527.501x, max sp. ratio 151172.502x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 939102.4/65914.5/1812290.4/1878204.9 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 11.6/ 11.2/ 12.0/ 23.2 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 11.6, min. 11.2, max. 12.0 ops) +#pr: (in succ. cases rsb autotuning gave avg. 3582725.0 % faster, avg. sp. ratio 35828.250x, max sp. ratio 38125.250x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 398478.9/343923.5/453034.2/796957.8 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 11.1/ 10.3/ 11.9/ 22.1 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 11.1, min. 10.3, max. 11.9 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 4.423/ 0.331/ 8.515,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 11.534/ 0.432/ 11.102,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.: 0.07 s, min 0.06 s, max 0.07 s, tot 0.13 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.07 s, min 0.06 s, max 0.07 s, tot 0.13 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 2.688e+03, min 2.013e+02, max 5.174e+03 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 3.422e-02, min 3.422e-02, max 3.422e-02 (2 samples) -#pr: best tun. rsb operation time was: on avg. 4.954e-07s, min 3.711e-08s, max 9.537e-07s, tot 9.908e-07s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 5.610e-03s, min 5.610e-03s, max 5.610e-03s, tot 1.122e-02s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 2.439e+00 6.268e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.067e+00 -#pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 1.039e+00 x, min 7.783e-02 x, max 2.000e+00 x (2 samples, the non-min-nrhs ones) +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.38 s, min 0.33 s, max 0.43 s, tot 0.76 s (2 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.38 s, min 0.33 s, max 0.43 s, tot 0.76 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. 5.642e-03, min 5.281e-03, max 6.004e-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. 3.417e-02s, min 3.198e-02s, max 3.636e-02s, tot 6.834e-02s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 6.275e+00 6.275e+00 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 2.515e+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. #pr: ======== Limiting to both transA=T and nrhs=1: @@ -3704,44 +3740,44 @@ #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 2586.91 5.684e-03 0.000e+00 3.711e-08 0.000e+00 6.579e-02 7.22e+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 1 201.33 5.610e-03 0.000e+00 9.537e-07 0.000e+00 6.286e-02 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 2586.91 3.911e-03 0.000e+00 3.711e-08 0.000e+00 6.369e-02 7.22e+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 5173.83 5.610e-03 0.000e+00 3.711e-08 0.000e+00 6.725e-02 1.11e+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 2.789e-02 0.000e+00 9.537e-07 0.000e+00 2.961e-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 3.198e-02 0.000e+00 9.537e-07 0.000e+00 3.280e-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 2.407e-02 0.000e+00 9.537e-07 0.000e+00 3.076e-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 3.636e-02 0.000e+00 9.537e-07 0.000e+00 4.320e-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. 10390296.9 % faster, avg. sp. ratio 103903.969x, max sp. ratio 153170.575x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 1341854.5/65914.5/1812290.4/5367417.9 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 12.8/ 11.2/ 16.3/ 51.1 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 12.8, min. 11.2, max. 16.3 ops) +#pr: (in succ. cases rsb autotuning gave avg. 3153275.0 % faster, avg. sp. ratio 31533.750x, max sp. ratio 38125.250x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 357472.5/310437.2/453034.2/1429890.0 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 11.4/ 10.3/ 12.8/ 45.5 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 11.4, min. 10.3, max. 12.8 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 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 5.176/ 0.331/ 8.515,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 25.978/ 0.432/ 11.102,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.: 0.06 s, min 0.06 s, max 0.07 s, tot 0.26 s (4 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.06 s, min 0.06 s, max 0.07 s, tot 0.26 s (4 samples) -#pr: best tun. rsb canon. mflops were: on avg. 2.637e+03, min 2.013e+02, max 5.174e+03 (4 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 2.747e-02, min 1.689e-02, max 3.422e-02 (4 samples) -#pr: best tun. rsb operation time was: on avg. 2.663e-07s, min 3.711e-08s, max 9.537e-07s, tot 1.065e-06s (4 samples) -#pr: ref. unt. rsb operation time was: on avg. 5.204e-03s, min 3.911e-03s, max 5.684e-03s, tot 2.082e-02s (4 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 2.439e+00 6.268e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.067e+00 -#pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 1.039e+00 x, min 7.783e-02 x, max 2.000e+00 x (2 samples, the non-min-nrhs ones) -#pr: Record collection took 1.53 s. +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.34 s, min 0.30 s, max 0.43 s, tot 1.36 s (4 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.34 s, min 0.30 s, max 0.43 s, tot 1.36 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. 4.679e-03, min 3.442e-03, max 6.004e-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. 3.007e-02s, min 2.407e-02s, max 3.636e-02s, tot 1.203e-01s (4 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 6.275e+00 9.013e+00 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 2.515e+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 8.60 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__1751677188_gcc-13.2-1,4th.rpr -# Removing the temporary record file rsbench_pr__1751677188_gcc-13.2-1,4th.rpr.tmp. -# terminating run at 1751677197 (after 9.1s of w.c.t.) +#pr: ======== Saved a performance record of 8 samples to rsbench_pr__1717270860_gcc-13.2-1,4th.rpr +# Removing the temporary record file rsbench_pr__1717270860_gcc-13.2-1,4th.rpr.tmp. +# terminating run at 1717270877 (after 16.7s 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. @@ -3995,67 +4031,45 @@ 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() : 20583998 physical pages -sysconf() : 84312055808 bytes (80406 MB) of physical memory -sysconf() : 14268489 available (free) physical pages -sysconf() : 58443730944 available (free) physical memory -sysconf() , processors : 128 -sysconf() , processors online : 42 -sysconf() : level 1 cache size 32768 -sysconf() : level 1 cache associativity 8 +sysconf() : 20717599 physical pages +sysconf() : 84859285504 bytes (80928 MB) of physical memory +sysconf() : 3679248 available (free) physical pages +sysconf() : 15070199808 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 @@ -4077,33 +4091,30 @@ 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 : 3.71456e-08 s +timing granularity : 1.37805e-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 : 58443730944 -detected total memory : 84312055808 -for array sized 4194304 elems, took 0.00152493 s for linear search and 0 s for binary search for element 4194303, in 45 tries, for a total of 0.102101 s (ignore this:377487270) -for array sized 4194304 elems, took 0.00113487 s for linear search and 0 s for binary search for element 2097151, in 88 tries, for a total of 0.101155 s (ignore this:746585846) -for array sized 4194304 elems, took 0.00049901 s for linear search and 0 s for binary search for element 1048575, in 175 tries, for a total of 0.100182 s (ignore this:1113587096) -for array sized 4194304 elems, took 0.000181913 s for linear search and 0 s for binary search for element 524287, in 353 tries, for a total of 0.100225 s (ignore this:1483733718) -for array sized 4194304 elems, took 0.000140905 s for linear search and 0 s for binary search for element 262143, in 699 tries, for a total of 0.100146 s (ignore this:1850209632) -for array sized 4194304 elems, took 6.98566e-05 s for linear search and 0 s for binary search for element 131071, in 1396 tries, for a total of 0.100008 s (ignore this:-2078807432) -for array sized 4194304 elems, took 3.48091e-05 s for linear search and 0 s for binary search for element 65535, in 2779 tries, for a total of 0.100001 s (ignore this:-1714563902) -for array sized 4194304 elems, took 1.5974e-05 s for linear search and 0 s for binary search for element 32767, in 5557 tries, for a total of 0.100013 s (ignore this:-1350391464) -for array sized 4194304 elems, took 5.00679e-06 s for linear search and 0 s for binary search for element 16383, in 11038 tries, for a total of 0.100006 s (ignore this:-988720356) -for array sized 4194304 elems, took 3.8147e-06 s for linear search and 0 s for binary search for element 8191, in 21645 tries, for a total of 0.100003 s (ignore this:-634131966) -for array sized 4194304 elems, took 9.53674e-07 s for linear search and 0 s for binary search for element 4095, in 42148 tries, for a total of 0.100003 s (ignore this:-288939846) -for array sized 4194304 elems, took 0 s for linear search and 0 s for binary search for element 2047, in 79087 tries, for a total of 0.100002 s (ignore this:34842332) -for array sized 4194304 elems, took 0 s for linear search and 0 s for binary search for element 1023, in 140466 tries, for a total of 0.100000 s (ignore this:322235768) -for array sized 4194304 elems, took 0 s for linear search and 0 s for binary search for element 511, in 232263 tries, for a total of 0.100001 s (ignore this:559608554) -for array sized 4194304 elems, took 0 s for linear search and 0 s for binary search for element 255, in 343825 tries, for a total of 0.100001 s (ignore this:734959304) -for array sized 4194304 elems, took 0 s for linear search and 0 s for binary search for element 127, in 487192 tries, for a total of 0.100001 s (ignore this:858706072) -for array sized 4194304 elems, took 0 s for linear search and 0 s for binary search for element 63, in 543201 tries, for a total of 0.100001 s (ignore this:927149398) -for array sized 4194304 elems, took 0 s for linear search and 0 s for binary search for element 31, in 647289 tries, for a total of 0.100000 s (ignore this:967281316) -for array sized 4194304 elems, took 0 s for linear search and 0 s for binary search for element 15, in 720091 tries, for a total of 0.100093 s (ignore this:988884046) -for array sized 4194304 elems, took 0 s for linear search and 0 s for binary search for element 7, in 718877 tries, for a total of 0.100001 s (ignore this:998948324) +memhinfo : L2:16/64/512K,L1:2/64/64K +detected free memory : 15069683712 +detected total memory : 84859285504 +for array sized 524288 elems, took 0.000669003 s for linear search and 0 s for binary search for element 524287, in 28 tries, for a total of 0.100291 s (ignore this:29360072) +for array sized 524288 elems, took 0.000330925 s for linear search and 0 s for binary search for element 262143, in 78 tries, for a total of 0.100011 s (ignore this:70254380) +for array sized 524288 elems, took 0.000164032 s for linear search and 0 s for binary search for element 131071, in 177 tries, for a total of 0.104227 s (ignore this:116653514) +for array sized 524288 elems, took 8.17776e-05 s for linear search and 0 s for binary search for element 65535, in 365 tries, for a total of 0.107291 s (ignore this:164494064) +for array sized 524288 elems, took 3.09944e-05 s for linear search and 0 s for binary search for element 32767, in 798 tries, for a total of 0.107272 s (ignore this:216790196) +for array sized 524288 elems, took 1.97887e-05 s for linear search and 0 s for binary search for element 16383, in 1508 tries, for a total of 0.106650 s (ignore this:266201324) +for array sized 524288 elems, took 9.77516e-06 s for linear search and 0 s for binary search for element 8191, in 3060 tries, for a total of 0.100005 s (ignore this:316330244) +for array sized 524288 elems, took 4.76837e-06 s for linear search and 0 s for binary search for element 4095, in 5298 tries, for a total of 0.104903 s (ignore this:359720864) +for array sized 524288 elems, took 1.90735e-06 s for linear search and 0 s for binary search for element 2047, in 8009 tries, for a total of 0.101687 s (ignore this:392509710) +for array sized 524288 elems, took 9.53674e-07 s for linear search and 0 s for binary search for element 1023, in 16234 tries, for a total of 0.107448 s (ignore this:425724474) +for array sized 524288 elems, took 9.53674e-07 s for linear search and 0 s for binary search for element 511, in 17425 tries, for a total of 0.102661 s (ignore this:443532824) +for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 255, in 27595 tries, for a total of 0.110919 s (ignore this:457606274) +for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 127, in 29517 tries, for a total of 0.102142 s (ignore this:465103592) +for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 63, in 36461 tries, for a total of 0.100881 s (ignore this:469697678) +for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 31, in 38481 tries, for a total of 0.100002 s (ignore this:472083500) +for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 15, in 37105 tries, for a total of 0.103456 s (ignore this:473196650) +for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 7, in 41821 tries, for a total of 0.100896 s (ignore this:473782144) + ./rsbench -C /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/rsbench version: 1.3.0 format switches:br @@ -4130,7 +4141,7 @@ 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. @@ -4150,17 +4161,17 @@ 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 1751677199 +# beginning run at 1717270881 # /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: 3.83e-08 s -# Will write a final performance record to file rsbench_pr__1751677199_gcc-13.2.rpr and periodic checkpoints to rsbench_pr__1751677199_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: 1.13e-06 s +# Will write a final performance record to file rsbench_pr__1717270881_gcc-13.2.rpr and periodic checkpoints to rsbench_pr__1717270881_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 @@ -4199,834 +4210,835 @@ # 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: ionos15-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 7.209s +# Memory benchmark took 5.530s # 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 7.211s 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 5.572s 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, 52103 nnz/s ) (1.60 MB/s ) -#pre-sorting (6 elements) took 0.0102921 s -#weeding duplicates (to 6 elements) took 1.90735e-06 s (and check, 2.14577e-06 s ) +# file input of A.mtx took 0.00 s (6 nnz, 23719 nnz/s ) (0.73 MB/s ) +#pre-sorting (6 elements) took 0.0461671 s +#weeding duplicates (to 6 elements) took 5.00679e-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 0.055s): (3 x 3)[0x55ed2fd5e2a0]{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 0.280s): (3 x 3)[0x5557ca7271d0]{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 0.01861s; avg 0.006205s ( +/- 18.21/ 26.54 %); best 0.005075s; worst 0.007851s; std dev. 0.001191 (taking best). -Reference operation time is 0.00507498 s (0.004729 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: 0.005075 Mflops: 0.005) -Merge (3 -> 1 leaves) took w.c.t. of 1.788e-05s, ~7.868e-06s of computing time (of which 2.146e-06s sorting, 2.861e-06s analysis) -3 iterations (42 th.) took 5.698e-05s; avg 1.899e-05s ( +/- 99.81/194.98 %); best 3.68e-08s; worst 5.603e-05s; std dev. 2.619e-05 (taking best). -Reference operation time is 3.67999e-08 s (652.2 Mflops) with 42 threads. -After merge step 1: tpop: 3.68e-08 s ~Mflops: 652.176 nsubm:1 otn:42 -Applying merge (3 -> 1 leaves, 42 th.) yielded SPEEDUP of 137907.353x: 0.005075s -> 3.68e-08s, so taking this instance. +3 iterations (20 th.) took 0.148s; avg 0.04932s ( +/- 2.76/ 5.12 %); best 0.04796s; worst 0.05185s; std dev. 0.001788 (taking best). +Reference operation time is 0.0479569 s (0.0005004 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: 0.04796 Mflops: 0.001) +Merge (3 -> 1 leaves) took w.c.t. of 6.413e-05s, ~2.193e-05s of computing time (of which 4.053e-06s sorting, 1.597e-05s analysis) +3 iterations (20 th.) took 3.91e-05s; avg 1.303e-05s ( +/- 92.68/183.54 %); best 9.537e-07s; worst 3.695e-05s; std dev. 1.692e-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 50286.500x: 0.04796s -> 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 0.03186s (of which 2.313e-05s partitioning, 0s I/O); computing times: 7.868e-06s in par. loops, 2.146e-06s sorting, 2.861e-06s analyzing) -Total merge + benchmarking process took 0.03186s, equivalent to 865656.0/6.3 new/old ops (0.06266s for 2 clones -- as 1702747.0/12.3 ops, or 851373.5/6.2 ops per clone), SPEEDUP of 137907.353x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 42 th.sp.) yielded SPEEDUP of 137907.353x (0.005075s -> 3.68e-08s), will amortize in 6.3 ops by saving 0.005075s per op. -In 1 tuning rounds (tot. 0.081s, 0.063s for constructor, 2 clones) obtained a SPEEDUP of 13790635.3% (1.379e+05x) (from 0.004729 to 652.2 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.128s (of which 7.2e-05s partitioning, 0s I/O); computing times: 2.193e-05s in par. loops, 4.053e-06s sorting, 1.597e-05s analyzing) +Total merge + benchmarking process took 0.128s, equivalent to 134200.0/2.7 new/old ops (0.2597s for 2 clones -- as 272332.2/5.4 ops, or 136166.1/2.7 ops per clone), SPEEDUP of 50286.500x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 20 th.sp.) yielded SPEEDUP of 50286.500x (0.04796s -> 9.537e-07s), will amortize in 2.7 ops by saving 0.04796s per op. +In 1 tuning rounds (tot. 0.41s, 0.26s for constructor, 2 clones) obtained a SPEEDUP of 5028550.0% (5.029e+04x) (from 0.0005004 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 0.081444 s (5.075e-03 s -> 3.680e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.407989 s (4.796e-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 0.360177 s and estimated a speedup of 1.000000 x (3.680e-08 s -> 3.680e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 2.43198 s and estimated a speedup of 1.000000 x (9.102e-07 s -> 9.102e-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 0.023999 0.015029 0.039028 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 42 3 3 6 0.039028 -%:RSB_SUBDIVISION_TIME:A.mtx S N 42 3 3 6 0.023999 -%:RSB_SHUFFLE_TIME:A.mtx S N 42 3 3 6 0.015029 -%: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 0.039028 -%: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 0.103462 0.096038 0.199500 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 20 3 3 6 0.199500 +%:RSB_SUBDIVISION_TIME:A.mtx S N 20 3 3 6 0.103462 +%:RSB_SHUFFLE_TIME:A.mtx S N 20 3 3 6 0.096038 +%: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 0.199500 +%: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 0.055191 1e+09 1e+09 -%constructor:matrix SORT[42] SCAN[42] SHUFFLE[42] INSERT[42] -%constructor:A.mtx 0 0.023999 0 0.015029 +%operation:matrix CONSTRUCTOR[20] SPMV[20] SPMV[20] +%operation:A.mtx 0.279482 1e+09 1e+09 +%constructor:matrix SORT[20] SCAN[20] SHUFFLE[20] INSERT[20] +%constructor:A.mtx 0 0.103462 0 0.0960379 # 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 0.038s): (3 x 3)[0x55ed2fd5e2a0]{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 0.323s): (3 x 3)[0x5557ca7271d0]{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 0.01617s; avg 0.00539s ( +/- 9.05/ 14.93 %); best 0.004902s; worst 0.006194s; std dev. 0.0005731 (taking best). -Reference operation time is 0.00490189 s (0.01958 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: 0.004902 Mflops: 0.020) -Merge (3 -> 1 leaves) took w.c.t. of 1.192e-05s, ~5.007e-06s of computing time (of which 2.146e-06s sorting, 2.146e-06s analysis) -3 iterations (42 th.) took 4.506e-05s; avg 1.502e-05s ( +/- 99.75/193.65 %); best 3.68e-08s; worst 4.411e-05s; std dev. 2.057e-05 (taking best). -Reference operation time is 3.67999e-08 s (2609 Mflops) with 42 threads. -After merge step 1: tpop: 3.68e-08 s ~Mflops: 2608.702 nsubm:1 otn:42 -Applying merge (3 -> 1 leaves, 42 th.) yielded SPEEDUP of 133203.758x: 0.004902s -> 3.68e-08s, so taking this instance. +3 iterations (20 th.) took 0.144s; avg 0.04799s ( +/- 25.01/ 41.63 %); best 0.03599s; worst 0.06797s; std dev. 0.01422 (taking best). +Reference operation time is 0.0359879 s (0.002668 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: 0.03599 Mflops: 0.003) +Merge (3 -> 1 leaves) took w.c.t. of 4.196e-05s, ~1.311e-05s of computing time (of which 4.053e-06s sorting, 9.06e-06s analysis) +3 iterations (20 th.) took 3.409e-05s; avg 1.136e-05s ( +/- 91.61/181.12 %); best 9.537e-07s; worst 3.195e-05s; std dev. 1.456e-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 37736.000x: 0.03599s -> 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 0.01933s (of which 1.597e-05s partitioning, 0s I/O); computing times: 5.007e-06s in par. loops, 2.146e-06s sorting, 2.146e-06s analyzing) -Total merge + benchmarking process took 0.01933s, equivalent to 525351.5/3.9 new/old ops (0.0381s for 2 clones -- as 1035218.7/7.8 ops, or 517609.3/3.9 ops per clone), SPEEDUP of 133203.758x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 42 th.sp.) yielded SPEEDUP of 133203.758x (0.004902s -> 3.68e-08s), will amortize in 3.9 ops by saving 0.004902s per op. -In 1 tuning rounds (tot. 0.054s, 0.038s for constructor, 2 clones) obtained a SPEEDUP of 13320275.8% (1.332e+05x) (from 0.01958 to 2609 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.132s (of which 4.697e-05s partitioning, 0s I/O); computing times: 1.311e-05s in par. loops, 4.053e-06s sorting, 9.06e-06s analyzing) +Total merge + benchmarking process took 0.132s, equivalent to 138401.8/3.7 new/old ops (0.2998s for 2 clones -- as 314326.2/8.3 ops, or 157163.1/4.2 ops per clone), SPEEDUP of 37736.000x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 20 th.sp.) yielded SPEEDUP of 37736.000x (0.03599s -> 9.537e-07s), will amortize in 3.7 ops by saving 0.03599s per op. +In 1 tuning rounds (tot. 0.44s, 0.3s for constructor, 2 clones) obtained a SPEEDUP of 3773500.0% (3.774e+04x) (from 0.002668 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 0.0543849 s (4.902e-03 s -> 3.680e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.444019 s (3.599e-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 0.301255 s and estimated a speedup of 1.000000 x (3.680e-08 s -> 3.680e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 2.32394 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 0.014392 0.013121 0.027513 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 42 3 3 6 0.027513 -%:RSB_SUBDIVISION_TIME:A.mtx S N 42 3 3 6 0.014392 -%:RSB_SHUFFLE_TIME:A.mtx S N 42 3 3 6 0.013121 -%: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 0.027513 -%: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 0.127432 0.092006 0.219438 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 20 3 3 6 0.219438 +%:RSB_SUBDIVISION_TIME:A.mtx S N 20 3 3 6 0.127432 +%:RSB_SHUFFLE_TIME:A.mtx S N 20 3 3 6 0.092006 +%: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 0.219438 +%: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 0.038408 1e+09 1e+09 -%constructor:matrix SORT[42] SCAN[42] SHUFFLE[42] INSERT[42] -%constructor:A.mtx 0 0.0143919 0 0.0131211 +%operation:matrix CONSTRUCTOR[20] SPMV[20] SPMV[20] +%operation:A.mtx 0.323432 1e+09 1e+09 +%constructor:matrix SORT[20] SCAN[20] SHUFFLE[20] INSERT[20] +%constructor:A.mtx 0 0.127432 0 0.092006 # symmetric matrix --- skipping transposed benchmarking -# so far, program took 8.191s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.797s/0.000s . +# so far, program took 12.390s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 5.608s/0.000s . getrusage() stats: -ru_maxrss: 28 (maximum resident set size -- MB) -ru_stime : 0.2211s (system CPU time used) -ru_utime : 26.72s (user CPU time used) +ru_maxrss: 7 (maximum resident set size -- MB) +ru_stime : 0.1127s (system CPU time used) +ru_utime : 37.21s (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 8.191s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.797s/0.000s . +# Cache block size total 524288 bytes, per-thread 26214 bytes +# so far, program took 12.390s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 5.608s/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 0.032s): (3 x 3)[0x55ed2fd5e2a0]{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 0.428s): (3 x 3)[0x5557ca7271d0]{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 0.01536s; avg 0.005121s ( +/- 26.95/ 52.69 %); best 0.003741s; worst 0.00782s; std dev. 0.001908 (taking best). -Reference operation time is 0.00374103 s (0.006415 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: 0.003741 Mflops: 0.006) -Merge (3 -> 1 leaves) took w.c.t. of 1.216e-05s, ~5.007e-06s of computing time (of which 9.537e-07s sorting, 2.146e-06s analysis) -3 iterations (42 th.) took 5.698e-05s; avg 1.899e-05s ( +/- 99.81/193.72 %); best 3.68e-08s; worst 5.579e-05s; std dev. 2.602e-05 (taking best). -Reference operation time is 3.67999e-08 s (652.2 Mflops) with 42 threads. -After merge step 1: tpop: 3.68e-08 s ~Mflops: 652.176 nsubm:1 otn:42 -Applying merge (3 -> 1 leaves, 42 th.) yielded SPEEDUP of 101658.568x: 0.003741s -> 3.68e-08s, so taking this instance. +3 iterations (20 th.) took 0.144s; avg 0.04799s ( +/- 17.62/ 16.35 %); best 0.03953s; worst 0.05583s; std dev. 0.006669 (taking best). +Reference operation time is 0.03953 s (0.0006071 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: 0.03953 Mflops: 0.001) +Merge (3 -> 1 leaves) took w.c.t. of 7.868e-06s, ~0s of computing time (of which 0s sorting, 7.868e-06s analysis) +3 iterations (20 th.) took 8.392e-05s; avg 2.797e-05s ( +/- 96.75/160.80 %); best 9.102e-07s; worst 7.296e-05s; std dev. 3.212e-05 (taking best). +Reference operation time is 9.10199e-07 s (26.37 Mflops) with 20 threads. +After merge step 1: tpop: 9.102e-07 s ~Mflops: 26.368 nsubm:1 otn:20 +Applying merge (3 -> 1 leaves, 20 th.) yielded SPEEDUP of 43430.121x: 0.03953s -> 9.102e-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 0.02069s (of which 1.502e-05s partitioning, 0s I/O); computing times: 5.007e-06s in par. loops, 9.537e-07s sorting, 2.146e-06s analyzing) -Total merge + benchmarking process took 0.02069s, equivalent to 562202.8/5.5 new/old ops (0.03372s for 2 clones -- as 916229.3/9.0 ops, or 458114.7/4.5 ops per clone), SPEEDUP of 101658.568x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 42 th.sp.) yielded SPEEDUP of 101658.568x (0.003741s -> 3.68e-08s), will amortize in 5.5 ops by saving 0.003741s per op. -In 1 tuning rounds (tot. 0.049s, 0.034s for constructor, 2 clones) obtained a SPEEDUP of 10165756.8% (1.017e+05x) (from 0.006415 to 652.2 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.124s (of which 7.868e-06s partitioning, 0s I/O); computing times: 0s in par. loops, 0s sorting, 7.868e-06s analyzing) +Total merge + benchmarking process took 0.124s, equivalent to 136215.2/3.1 new/old ops (0.2597s for 2 clones -- as 285357.5/6.6 ops, or 142678.7/3.3 ops per clone), SPEEDUP of 43430.121x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 20 th.sp.) yielded SPEEDUP of 43430.121x (0.03953s -> 9.102e-07s), will amortize in 3.1 ops by saving 0.03953s per op. +In 1 tuning rounds (tot. 0.4s, 0.26s for constructor, 2 clones) obtained a SPEEDUP of 4342912.1% (4.343e+04x) (from 0.0006071 to 26.37 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 0.049341 s (3.741e-03 s -> 3.680e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.404154 s (3.953e-02 s -> 9.102e-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 0.313289 s and estimated a speedup of 1.000000 x (3.680e-08 s -> 3.680e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 2.15177 s and estimated a speedup of 1.000000 x (9.102e-07 s -> 9.102e-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 0.012828 0.010061 0.022889 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 42 3 3 6 0.022889 -%:RSB_SUBDIVISION_TIME:A.mtx S N 42 3 3 6 0.012828 -%:RSB_SHUFFLE_TIME:A.mtx S N 42 3 3 6 0.010061 -%: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 0.022889 -%: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 0.135505 0.140004 0.275509 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 20 3 3 6 0.275509 +%:RSB_SUBDIVISION_TIME:A.mtx S N 20 3 3 6 0.135505 +%:RSB_SHUFFLE_TIME:A.mtx S N 20 3 3 6 0.140004 +%: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 0.275509 +%: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 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 0.03248 1e+09 1e+09 -%constructor:matrix SORT[42] SCAN[42] SHUFFLE[42] INSERT[42] -%constructor:A.mtx 0 0.0128279 0 0.010061 +%operation:matrix CONSTRUCTOR[20] SPMV[20] SPMV[20] +%operation:A.mtx 0.427533 1e+09 1e+09 +%constructor:matrix SORT[20] SCAN[20] SHUFFLE[20] INSERT[20] +%constructor:A.mtx 0 0.135505 0 0.140004 # 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 0.039s): (3 x 3)[0x55ed2fd5e2a0]{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 0.292s): (3 x 3)[0x5557ca7271d0]{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 0.01973s; avg 0.006578s ( +/- 15.70/ 25.50 %); best 0.005545s; worst 0.008255s; std dev. 0.001197 (taking best). -Reference operation time is 0.0055449 s (0.01731 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: 0.005545 Mflops: 0.017) -Merge (3 -> 1 leaves) took w.c.t. of 1.097e-05s, ~5.007e-06s of computing time (of which 9.537e-07s sorting, 1.907e-06s analysis) -3 iterations (42 th.) took 2.289e-05s; avg 7.629e-06s ( +/- 99.52/200.00 %); best 3.68e-08s; worst 2.289e-05s; std dev. 1.079e-05 (taking best). -Reference operation time is 3.67999e-08 s (2609 Mflops) with 42 threads. -After merge step 1: tpop: 3.68e-08 s ~Mflops: 2608.702 nsubm:1 otn:42 -Applying merge (3 -> 1 leaves, 42 th.) yielded SPEEDUP of 150677.033x: 0.005545s -> 3.68e-08s, so taking this instance. +3 iterations (20 th.) took 0.128s; avg 0.04266s ( +/- 25.00/ 12.54 %); best 0.032s; worst 0.04801s; std dev. 0.007542 (taking best). +Reference operation time is 0.031996 s (0.003 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: 0.032 Mflops: 0.003) +Merge (3 -> 1 leaves) took w.c.t. of 4.911e-05s, ~1.287e-05s of computing time (of which 1.907e-06s sorting, 1.502e-05s analysis) +3 iterations (20 th.) took 7.868e-06s; avg 2.623e-06s ( +/- 65.29/200.00 %); best 9.102e-07s; worst 7.868e-06s; std dev. 3.709e-06 (taking best). +Reference operation time is 9.10199e-07 s (105.5 Mflops) with 20 threads. +After merge step 1: tpop: 9.102e-07 s ~Mflops: 105.471 nsubm:1 otn:20 +Applying merge (3 -> 1 leaves, 20 th.) yielded SPEEDUP of 35152.777x: 0.032s -> 9.102e-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 0.02011s (of which 1.621e-05s partitioning, 0s I/O); computing times: 5.007e-06s in par. loops, 9.537e-07s sorting, 1.907e-06s analyzing) -Total merge + benchmarking process took 0.02011s, equivalent to 546472.3/3.6 new/old ops (0.04045s for 2 clones -- as 1099209.6/7.3 ops, or 549604.8/3.6 ops per clone), SPEEDUP of 150677.033x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 42 th.sp.) yielded SPEEDUP of 150677.033x (0.005545s -> 3.68e-08s), will amortize in 3.6 ops by saving 0.005545s per op. -In 1 tuning rounds (tot. 0.06s, 0.04s for constructor, 2 clones) obtained a SPEEDUP of 15067603.3% (1.507e+05x) (from 0.01731 to 2609 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.1241s (of which 4.911e-05s partitioning, 0s I/O); computing times: 1.287e-05s in par. loops, 1.907e-06s sorting, 1.502e-05s analyzing) +Total merge + benchmarking process took 0.1241s, equivalent to 136344.9/3.9 new/old ops (0.2518s for 2 clones -- as 276659.2/7.9 ops, or 138329.6/3.9 ops per clone), SPEEDUP of 35152.777x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 20 th.sp.) yielded SPEEDUP of 35152.777x (0.032s -> 9.102e-07s), will amortize in 3.9 ops by saving 0.032s per op. +In 1 tuning rounds (tot. 0.38s, 0.25s for constructor, 2 clones) obtained a SPEEDUP of 3515177.7% (3.515e+04x) (from 0.003 to 105.5 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 0.0603931 s (5.545e-03 s -> 3.680e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.380078 s (3.200e-02 s -> 9.102e-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 0.300907 s and estimated a speedup of 1.000000 x (3.680e-08 s -> 3.680e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 2.18789 s and estimated a speedup of 1.047765 x (9.537e-07 s -> 9.102e-07 s per op) in new matrix (1 -> 1 lsubm) +RSB Autotuner suggested a new matrix: freeing the old one. #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 0.015049 0.013133 0.028182 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 42 3 3 6 0.028182 -%:RSB_SUBDIVISION_TIME:A.mtx S N 42 3 3 6 0.015049 -%:RSB_SHUFFLE_TIME:A.mtx S N 42 3 3 6 0.013133 -%: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 0.028182 -%: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 0.103764 0.096006 0.199770 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 20 3 3 6 0.199771 +%:RSB_SUBDIVISION_TIME:A.mtx S N 20 3 3 6 0.103764 +%:RSB_SHUFFLE_TIME:A.mtx S N 20 3 3 6 0.096006 +%: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 0.199770 +%: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 0.0389481 1e+09 1e+09 -%constructor:matrix SORT[42] SCAN[42] SHUFFLE[42] INSERT[42] -%constructor:A.mtx 0 0.015049 0 0.013133 +%operation:matrix CONSTRUCTOR[20] SPMV[20] SPMV[20] +%operation:A.mtx 0.291817 1e+09 1e+09 +%constructor:matrix SORT[20] SCAN[20] SHUFFLE[20] INSERT[20] +%constructor:A.mtx 9.53674e-07 0.103764 0 0.0960062 # symmetric matrix --- skipping transposed benchmarking -# so far, program took 9.062s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 1.521s/0.000s . +# so far, program took 18.650s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 10.732s/0.000s . getrusage() stats: -ru_maxrss: 28 (maximum resident set size -- MB) -ru_stime : 0.2521s (system CPU time used) -ru_utime : 44.26s (user CPU time used) +ru_maxrss: 7 (maximum resident set size -- MB) +ru_stime : 0.1328s (system CPU time used) +ru_utime : 65.46s (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 9.062s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 1.521s/0.000s . +# Cache block size total 524288 bytes, per-thread 26214 bytes +# so far, program took 18.650s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 10.732s/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 0.050s): (3 x 3)[0x55ed2fd615e0]{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 0.348s): (3 x 3)[0x5557ca72a4e0]{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 0.01905s; avg 0.006351s ( +/- 38.53/ 48.98 %); best 0.003904s; worst 0.009462s; std dev. 0.002317 (taking best). -Reference operation time is 0.0039041 s (0.02459 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: 0.003904 Mflops: 0.025) -Merge (3 -> 1 leaves) took w.c.t. of 1.311e-05s, ~5.007e-06s of computing time (of which 9.537e-07s sorting, 2.146e-06s analysis) -3 iterations (42 th.) took 2.313e-05s; avg 7.709e-06s ( +/- 99.52/200.00 %); best 3.68e-08s; worst 2.313e-05s; std dev. 1.09e-05 (taking best). -Reference operation time is 3.67999e-08 s (2609 Mflops) with 42 threads. -After merge step 1: tpop: 3.68e-08 s ~Mflops: 2608.702 nsubm:1 otn:42 -Applying merge (3 -> 1 leaves, 42 th.) yielded SPEEDUP of 106090.055x: 0.003904s -> 3.68e-08s, so taking this instance. +3 iterations (20 th.) took 0.136s; avg 0.04532s ( +/- 29.18/ 23.26 %); best 0.03209s; worst 0.05586s; std dev. 0.009887 (taking best). +Reference operation time is 0.0320928 s (0.002991 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: 0.03209 Mflops: 0.003) +Merge (3 -> 1 leaves) took w.c.t. of 3.791e-05s, ~1.097e-05s of computing time (of which 4.053e-06s sorting, 1.001e-05s analysis) +3 iterations (20 th.) took 4.792e-05s; avg 1.597e-05s ( +/- 94.03/188.06 %); best 9.537e-07s; worst 4.601e-05s; std dev. 2.124e-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 33651.750x: 0.03209s -> 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 0.01777s (of which 1.693e-05s partitioning, 0s I/O); computing times: 5.007e-06s in par. loops, 9.537e-07s sorting, 2.146e-06s analyzing) -Total merge + benchmarking process took 0.01777s, equivalent to 482772.9/4.6 new/old ops (0.04396s for 2 clones -- as 1194596.7/11.3 ops, or 597298.3/5.6 ops per clone), SPEEDUP of 106090.055x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 42 th.sp.) yielded SPEEDUP of 106090.055x (0.003904s -> 3.68e-08s), will amortize in 4.6 ops by saving 0.003904s per op. -In 1 tuning rounds (tot. 0.063s, 0.044s for constructor, 2 clones) obtained a SPEEDUP of 10608905.5% (1.061e+05x) (from 0.02459 to 2609 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.1801s (of which 4.292e-05s partitioning, 0s I/O); computing times: 1.097e-05s in par. loops, 4.053e-06s sorting, 1.001e-05s analyzing) +Total merge + benchmarking process took 0.1801s, equivalent to 188813.0/5.6 new/old ops (0.3078s for 2 clones -- as 322720.2/9.6 ops, or 161360.1/4.8 ops per clone), SPEEDUP of 33651.750x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 20 th.sp.) yielded SPEEDUP of 33651.750x (0.03209s -> 9.537e-07s), will amortize in 5.6 ops by saving 0.03209s per op. +In 1 tuning rounds (tot. 0.44s, 0.31s for constructor, 2 clones) obtained a SPEEDUP of 3365075.0% (3.365e+04x) (from 0.002991 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 0.063118 s (3.904e-03 s -> 3.680e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.443997 s (3.209e-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 0.321383 s and estimated a speedup of 1.000000 x (3.680e-08 s -> 3.680e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 2.21988 s and estimated a speedup of 1.000000 x (9.102e-07 s -> 9.102e-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 0.000001 0.017416 0.015608 0.033024 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 42 3 3 6 0.033025 -%:RSB_SUBDIVISION_TIME:A.mtx S N 42 3 3 6 0.017416 -%:RSB_SHUFFLE_TIME:A.mtx S N 42 3 3 6 0.015608 -%:ROW_MAJOR_SORT_TIME:A.mtx S N 42 3 3 6 0.000001 -%:ROW_MAJOR_SORT_SCALING:A.mtx S N 42 3 3 6 1.000 -%:SORTEDCOO2RSB_TIME:A.mtx S N 42 3 3 6 0.033024 -%: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 1.00 1.00 1.00 1.00 +%:CONSTRUCTOR_TIMES:A.mtx S N 20 3 3 6 0.000000 0.163684 0.079943 0.243627 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 20 3 3 6 0.243627 +%:RSB_SUBDIVISION_TIME:A.mtx S N 20 3 3 6 0.163684 +%:RSB_SHUFFLE_TIME:A.mtx S N 20 3 3 6 0.079943 +%: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 0.243627 +%: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 0.049988 1e+09 1e+09 -%constructor:matrix SORT[42] SCAN[42] SHUFFLE[42] INSERT[42] -%constructor:A.mtx 9.53674e-07 0.017416 0 0.0156078 +%operation:matrix CONSTRUCTOR[20] SPMV[20] SPMV[20] +%operation:A.mtx 0.34783 1e+09 1e+09 +%constructor:matrix SORT[20] SCAN[20] SHUFFLE[20] INSERT[20] +%constructor:A.mtx 0 0.163684 0 0.0799432 # 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 0.052s): (3 x 3)[0x55ed2fd615e0]{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 0.232s): (3 x 3)[0x5557ca72a4e0]{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 0.02495s; avg 0.008318s ( +/- 3.55/ 6.84 %); best 0.008023s; worst 0.008887s; std dev. 0.0004023 (taking best). -Reference operation time is 0.00802302 s (0.04786 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: 0.008023 Mflops: 0.048) -Merge (3 -> 1 leaves) took w.c.t. of 1.216e-05s, ~5.007e-06s of computing time (of which 9.537e-07s sorting, 2.146e-06s analysis) -3 iterations (42 th.) took 1.884e-05s; avg 6.278e-06s ( +/- 99.41/184.81 %); best 3.68e-08s; worst 1.788e-05s; std dev. 8.214e-06 (taking best). -Reference operation time is 3.67999e-08 s (1.043e+04 Mflops) with 42 threads. -After merge step 1: tpop: 3.68e-08 s ~Mflops: 10434.809 nsubm:1 otn:42 -Applying merge (3 -> 1 leaves, 42 th.) yielded SPEEDUP of 218017.493x: 0.008023s -> 3.68e-08s, so taking this instance. +3 iterations (20 th.) took 0.124s; avg 0.04132s ( +/- 12.92/ 25.74 %); best 0.03598s; worst 0.05195s; std dev. 0.00752 (taking best). +Reference operation time is 0.0359788 s (0.01067 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: 0.03598 Mflops: 0.011) +Merge (3 -> 1 leaves) took w.c.t. of 4.506e-05s, ~1.597e-05s of computing time (of which 5.96e-06s sorting, 7.868e-06s analysis) +3 iterations (20 th.) took 1.502e-05s; avg 5.007e-06s ( +/- 80.95/161.90 %); best 9.537e-07s; worst 1.311e-05s; std dev. 5.732e-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 37726.500x: 0.03598s -> 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 0.02305s (of which 1.502e-05s partitioning, 0s I/O); computing times: 5.007e-06s in par. loops, 9.537e-07s sorting, 2.146e-06s analyzing) -Total merge + benchmarking process took 0.02305s, equivalent to 626336.2/2.9 new/old ops (0.03985s for 2 clones -- as 1082883.1/5.0 ops, or 541441.5/2.5 ops per clone), SPEEDUP of 218017.493x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 42 th.sp.) yielded SPEEDUP of 218017.493x (0.008023s -> 3.68e-08s), will amortize in 2.9 ops by saving 0.008023s per op. -In 1 tuning rounds (tot. 0.065s, 0.04s for constructor, 2 clones) obtained a SPEEDUP of 21801649.3% (2.18e+05x) (from 0.04786 to 1.043e+04 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.09198s (of which 5.007e-05s partitioning, 0s I/O); computing times: 1.597e-05s in par. loops, 5.96e-06s sorting, 7.868e-06s analyzing) +Total merge + benchmarking process took 0.09198s, equivalent to 96451.0/2.6 new/old ops (0.2037s for 2 clones -- as 213615.0/5.7 ops, or 106807.5/2.8 ops per clone), SPEEDUP of 37726.500x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 20 th.sp.) yielded SPEEDUP of 37726.500x (0.03598s -> 9.537e-07s), will amortize in 2.6 ops by saving 0.03598s per op. +In 1 tuning rounds (tot. 0.33s, 0.2s for constructor, 2 clones) obtained a SPEEDUP of 3772550.0% (3.773e+04x) (from 0.01067 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 0.0649068 s (8.023e-03 s -> 3.680e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.327909 s (3.598e-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 0.357583 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 1.74393 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 0.014165 0.017550 0.031715 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 42 3 3 6 0.031715 -%:RSB_SUBDIVISION_TIME:A.mtx S N 42 3 3 6 0.014165 -%:RSB_SHUFFLE_TIME:A.mtx S N 42 3 3 6 0.017550 -%: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 0.031715 -%: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 0.071714 0.072010 0.143724 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 20 3 3 6 0.143725 +%:RSB_SUBDIVISION_TIME:A.mtx S N 20 3 3 6 0.071714 +%:RSB_SHUFFLE_TIME:A.mtx S N 20 3 3 6 0.072010 +%: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 0.143724 +%: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 0.0523481 1e+09 1e+09 -%constructor:matrix SORT[42] SCAN[42] SHUFFLE[42] INSERT[42] -%constructor:A.mtx 0 0.0141649 0 0.01755 +%operation:matrix CONSTRUCTOR[20] SPMV[20] SPMV[20] +%operation:A.mtx 0.2318 1e+09 1e+09 +%constructor:matrix SORT[20] SCAN[20] SHUFFLE[20] INSERT[20] +%constructor:A.mtx 9.53674e-07 0.0717139 0 0.0720098 # symmetric matrix --- skipping transposed benchmarking -# so far, program took 10.040s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 2.328s/0.000s . +# so far, program took 24.370s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 15.468s/0.000s . getrusage() stats: -ru_maxrss: 28 (maximum resident set size -- MB) -ru_stime : 0.2885s (system CPU time used) -ru_utime : 64s (user CPU time used) +ru_maxrss: 7 (maximum resident set size -- MB) +ru_stime : 0.2139s (system CPU time used) +ru_utime : 95.28s (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 10.040s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 2.328s/0.000s . +# Cache block size total 524288 bytes, per-thread 26214 bytes +# so far, program took 24.370s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 15.468s/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 0.043s): (3 x 3)[0x55ed2fd615e0]{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 0.228s): (3 x 3)[0x5557ca72a4e0]{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 0.02621s; avg 0.008737s ( +/- 36.28/ 29.08 %); best 0.005567s; worst 0.01128s; std dev. 0.002374 (taking best). -Reference operation time is 0.00556707 s (0.01724 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: 0.005567 Mflops: 0.017) -Merge (3 -> 1 leaves) took w.c.t. of 1.812e-05s, ~5.007e-06s of computing time (of which 9.537e-07s sorting, 2.146e-06s analysis) -3 iterations (42 th.) took 2.098e-05s; avg 6.994e-06s ( +/- 99.47/182.95 %); best 3.68e-08s; worst 1.979e-05s; std dev. 9.061e-06 (taking best). -Reference operation time is 3.67999e-08 s (2609 Mflops) with 42 threads. -After merge step 1: tpop: 3.68e-08 s ~Mflops: 2608.702 nsubm:1 otn:42 -Applying merge (3 -> 1 leaves, 42 th.) yielded SPEEDUP of 151279.559x: 0.005567s -> 3.68e-08s, so taking this instance. +3 iterations (20 th.) took 0.1119s; avg 0.03729s ( +/- 3.46/ 6.81 %); best 0.036s; worst 0.03983s; std dev. 0.001797 (taking best). +Reference operation time is 0.035995 s (0.002667 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: 0.036 Mflops: 0.003) +Merge (3 -> 1 leaves) took w.c.t. of 4.315e-05s, ~1.192e-05s of computing time (of which 3.099e-06s sorting, 7.868e-06s analysis) +3 iterations (20 th.) took 3.695e-05s; avg 1.232e-05s ( +/- 92.26/184.52 %); best 9.537e-07s; worst 3.505e-05s; std dev. 1.607e-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 37743.500x: 0.036s -> 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 0.02306s (of which 2.193e-05s partitioning, 0s I/O); computing times: 5.007e-06s in par. loops, 9.537e-07s sorting, 2.146e-06s analyzing) -Total merge + benchmarking process took 0.02306s, equivalent to 626498.2/4.1 new/old ops (0.03999s for 2 clones -- as 1086601.9/7.2 ops, or 543300.9/3.6 ops per clone), SPEEDUP of 151279.559x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 42 th.sp.) yielded SPEEDUP of 151279.559x (0.005567s -> 3.68e-08s), will amortize in 4.1 ops by saving 0.005567s per op. -In 1 tuning rounds (tot. 0.066s, 0.04s for constructor, 2 clones) obtained a SPEEDUP of 15127855.9% (1.513e+05x) (from 0.01724 to 2609 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.09601s (of which 5.102e-05s partitioning, 0s I/O); computing times: 1.192e-05s in par. loops, 3.099e-06s sorting, 7.868e-06s analyzing) +Total merge + benchmarking process took 0.09601s, equivalent to 100668.8/2.7 new/old ops (0.2118s for 2 clones -- as 222040.0/5.9 ops, or 111020.0/2.9 ops per clone), SPEEDUP of 37743.500x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 20 th.sp.) yielded SPEEDUP of 37743.500x (0.036s -> 9.537e-07s), will amortize in 2.7 ops by saving 0.03599s per op. +In 1 tuning rounds (tot. 0.32s, 0.21s for constructor, 2 clones) obtained a SPEEDUP of 3774250.0% (3.774e+04x) (from 0.002667 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 0.0663109 s (5.567e-03 s -> 3.680e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.323875 s (3.600e-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 0.398052 s and estimated a speedup of 1.000000 x (3.680e-08 s -> 3.680e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 2.63194 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 0.017804 0.011183 0.028987 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 42 3 3 6 0.028987 -%:RSB_SUBDIVISION_TIME:A.mtx S N 42 3 3 6 0.017804 -%:RSB_SHUFFLE_TIME:A.mtx S N 42 3 3 6 0.011183 -%: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 0.028987 -%: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 0.087512 0.071926 0.159438 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 20 3 3 6 0.159439 +%:RSB_SUBDIVISION_TIME:A.mtx S N 20 3 3 6 0.087512 +%:RSB_SHUFFLE_TIME:A.mtx S N 20 3 3 6 0.071926 +%: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 0.159438 +%: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 0.0427918 1e+09 1e+09 -%constructor:matrix SORT[42] SCAN[42] SHUFFLE[42] INSERT[42] -%constructor:A.mtx 0 0.0178041 0 0.011183 +%operation:matrix CONSTRUCTOR[20] SPMV[20] SPMV[20] +%operation:A.mtx 0.227608 1e+09 1e+09 +%constructor:matrix SORT[20] SCAN[20] SHUFFLE[20] INSERT[20] +%constructor:A.mtx 9.53674e-07 0.087512 0 0.0719259 # 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 0.055s): (3 x 3)[0x55ed2fd615e0]{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 0.480s): (3 x 3)[0x5557ca72a4e0]{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 0.01876s; avg 0.006255s ( +/- 11.12/ 20.74 %); best 0.005559s; worst 0.007552s; std dev. 0.0009181 (taking best). -Reference operation time is 0.00555897 s (0.06908 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: 0.005559 Mflops: 0.069) -Merge (3 -> 1 leaves) took w.c.t. of 1.121e-05s, ~4.053e-06s of computing time (of which 9.537e-07s sorting, 2.146e-06s analysis) -3 iterations (42 th.) took 5.007e-06s; avg 1.669e-06s ( +/- 97.80/142.86 %); best 3.68e-08s; worst 4.053e-06s; std dev. 1.73e-06 (taking best). -Reference operation time is 3.67999e-08 s (1.043e+04 Mflops) with 42 threads. -After merge step 1: tpop: 3.68e-08 s ~Mflops: 10434.809 nsubm:1 otn:42 -Applying merge (3 -> 1 leaves, 42 th.) yielded SPEEDUP of 151059.281x: 0.005559s -> 3.68e-08s, so taking this instance. +3 iterations (20 th.) took 0.2039s; avg 0.06795s ( +/- 11.65/ 17.50 %); best 0.06003s; worst 0.07985s; std dev. 0.008562 (taking best). +Reference operation time is 0.060034 s (0.006396 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: 0.06003 Mflops: 0.006) +Merge (3 -> 1 leaves) took w.c.t. of 4.411e-05s, ~1.192e-05s of computing time (of which 5.007e-06s sorting, 8.821e-06s analysis) +3 iterations (20 th.) took 1.717e-05s; avg 5.722e-06s ( +/- 83.33/162.50 %); best 9.537e-07s; worst 1.502e-05s; std dev. 6.576e-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 62950.250x: 0.06003s -> 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 0.01728s (of which 1.502e-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 0.01728s, equivalent to 469433.1/3.1 new/old ops (0.04034s for 2 clones -- as 1096255.3/7.3 ops, or 548127.6/3.6 ops per clone), SPEEDUP of 151059.281x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 42 th.sp.) yielded SPEEDUP of 151059.281x (0.005559s -> 3.68e-08s), will amortize in 3.1 ops by saving 0.005559s per op. -In 1 tuning rounds (tot. 0.059s, 0.04s for constructor, 2 clones) obtained a SPEEDUP of 15105828.1% (1.511e+05x) (from 0.06908 to 1.043e+04 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.1682s (of which 4.792e-05s partitioning, 0s I/O); computing times: 1.192e-05s in par. loops, 5.007e-06s sorting, 8.821e-06s analyzing) +Total merge + benchmarking process took 0.1682s, equivalent to 176378.8/2.8 new/old ops (0.3793s for 2 clones -- as 397736.2/6.3 ops, or 198868.1/3.2 ops per clone), SPEEDUP of 62950.250x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 20 th.sp.) yielded SPEEDUP of 62950.250x (0.06003s -> 9.537e-07s), will amortize in 2.8 ops by saving 0.06003s per op. +In 1 tuning rounds (tot. 0.58s, 0.38s for constructor, 2 clones) obtained a SPEEDUP of 6294925.0% (6.295e+04x) (from 0.006396 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 0.0594361 s (5.559e-03 s -> 3.680e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.583584 s (6.003e-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 0.370104 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 2.25548 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 0.020436 0.019339 0.039775 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 42 3 3 6 0.039775 -%:RSB_SUBDIVISION_TIME:A.mtx S N 42 3 3 6 0.020436 -%:RSB_SHUFFLE_TIME:A.mtx S N 42 3 3 6 0.019339 -%: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 0.039775 -%: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 0.163490 0.148045 0.311535 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 20 3 3 6 0.311535 +%:RSB_SUBDIVISION_TIME:A.mtx S N 20 3 3 6 0.163490 +%:RSB_SHUFFLE_TIME:A.mtx S N 20 3 3 6 0.148045 +%: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 0.311535 +%: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 0.05474 1e+09 1e+09 -%constructor:matrix SORT[42] SCAN[42] SHUFFLE[42] INSERT[42] -%constructor:A.mtx 0 0.020436 0 0.0193391 +%operation:matrix CONSTRUCTOR[20] SPMV[20] SPMV[20] +%operation:A.mtx 0.480286 1e+09 1e+09 +%constructor:matrix SORT[20] SCAN[20] SHUFFLE[20] INSERT[20] +%constructor:A.mtx 0 0.16349 0 0.148045 # symmetric matrix --- skipping transposed benchmarking -# so far, program took 11.111s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 3.222s/0.000s . +# so far, program took 31.402s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 21.262s/0.000s . getrusage() stats: -ru_maxrss: 28 (maximum resident set size -- MB) -ru_stime : 0.3444s (system CPU time used) -ru_utime : 84.32s (user CPU time used) +ru_maxrss: 7 (maximum resident set size -- MB) +ru_stime : 0.2487s (system CPU time used) +ru_utime : 131.4s (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 1 652.18 5.075e-03 0.000e+00 3.680e-08 0.000e+00 8.144e-02 4.02e+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 2608.70 4.902e-03 0.000e+00 3.680e-08 0.000e+00 5.438e-02 9.89e+00 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 4.796e-02 0.000e+00 9.537e-07 0.000e+00 4.080e-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 3.599e-02 0.000e+00 9.537e-07 0.000e+00 4.440e-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. 13555455.6 % faster, avg. sp. ratio 135555.556x, max sp. ratio 137907.353x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 1845507.0/1477855.5/2213158.4/3691013.9 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 13.6/ 11.1/ 16.0/ 27.1 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 13.6, min. 11.1, max. 16.0 ops) +#pr: (in succ. cases rsb autotuning gave avg. 4401025.0 % faster, avg. sp. ratio 44011.250x, max sp. ratio 50286.500x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 446697.6/427807.5/465587.8/893395.2 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 10.4/ 8.5/ 12.3/ 20.8 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 10.4, min. 8.5, max. 12.3 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 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 5.326/ 3.370/ 7.283,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 13.913/ 4.022/ 9.891,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.: 0.07 s, min 0.05 s, max 0.08 s, tot 0.14 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.07 s, min 0.05 s, max 0.08 s, tot 0.14 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 1.630e+03, min 6.522e+02, max 2.609e+03 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 1.216e-02, min 4.729e-03, max 1.958e-02 (2 samples) -#pr: best tun. rsb operation time was: on avg. 3.680e-08s, min 3.680e-08s, max 3.680e-08s, tot 7.360e-08s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 4.988e-03s, min 4.902e-03s, max 5.075e-03s, tot 9.977e-03s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 2.884e+00 6.234e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.031e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.43 s, min 0.41 s, max 0.44 s, tot 0.85 s (2 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.43 s, min 0.41 s, max 0.44 s, tot 0.85 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. 1.584e-03, min 5.004e-04, max 2.668e-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. 4.197e-02s, min 3.599e-02s, max 4.796e-02s, tot 8.394e-02s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 8.755e+00 1.892e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 2.106e+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 1 652.18 3.741e-03 0.000e+00 3.680e-08 0.000e+00 4.934e-02 2.39e+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 2608.70 5.545e-03 0.000e+00 3.680e-08 0.000e+00 6.039e-02 5.33e+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 26.37 3.953e-02 0.000e+00 9.102e-07 0.000e+00 4.042e-01 9.67e-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 1 105.47 3.200e-02 0.000e+00 9.102e-07 0.000e+00 3.801e-01 2.15e-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. 12616680.0 % faster, avg. sp. ratio 126167.800x, max sp. ratio 150677.033x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 1490955.6/1340790.4/1641120.8/2981911.2 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 12.0/ 10.9/ 13.2/ 24.1 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 12.0, min. 10.9, max. 13.2 ops) +#pr: (in succ. cases rsb autotuning gave avg. 3929044.9 % faster, avg. sp. ratio 39291.449x, max sp. ratio 43430.121x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 430802.5/417576.8/444028.1/861604.9 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 11.1/ 10.2/ 11.9/ 22.1 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 11.1, min. 10.2, max. 11.9 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 3.043/ 2.065/ 4.022,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 7.717/ 2.391/ 5.326,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 0.123/ 0.083/ 0.163,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 0.312/ 0.097/ 0.215,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.: 0.05 s, min 0.05 s, max 0.06 s, tot 0.11 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.05 s, min 0.05 s, max 0.06 s, tot 0.11 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 1.630e+03, min 6.522e+02, max 2.609e+03 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 1.186e-02, min 6.415e-03, max 1.731e-02 (2 samples) -#pr: best tun. rsb operation time was: on avg. 3.680e-08s, min 3.680e-08s, max 3.680e-08s, tot 7.360e-08s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 4.643e-03s, min 3.741e-03s, max 5.545e-03s, tot 9.286e-03s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 5.223e+00 1.017e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.031e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.39 s, min 0.38 s, max 0.40 s, tot 0.78 s (2 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.39 s, min 0.38 s, max 0.40 s, tot 0.78 s (2 samples) +#pr: best tun. rsb canon. mflops were: on avg. 6.592e+01, min 2.637e+01, max 1.055e+02 (2 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 1.804e-03, min 6.071e-04, max 3.000e-03 (2 samples) +#pr: best tun. rsb operation time was: on avg. 9.102e-07s, min 9.102e-07s, max 9.102e-07s, tot 1.820e-06s (2 samples) +#pr: ref. unt. rsb operation time was: on avg. 3.576e-02s, min 3.200e-02s, max 3.953e-02s, tot 7.153e-02s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.513e+01 2.946e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 2.106e+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 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 2608.70 3.904e-03 0.000e+00 3.680e-08 0.000e+00 6.312e-02 4.02e+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 10434.81 8.023e-03 0.000e+00 3.680e-08 0.000e+00 6.491e-02 9.89e+00 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 3.209e-02 0.000e+00 9.537e-07 0.000e+00 4.440e-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 3.598e-02 0.000e+00 9.537e-07 0.000e+00 3.279e-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. 16205277.4 % faster, avg. sp. ratio 162053.774x, max sp. ratio 218017.493x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 1739472.0/1715166.8/1763777.1/3478944.0 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 12.1/ 8.1/ 16.2/ 24.3 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 12.1, min. 8.1, max. 16.2 ops) +#pr: (in succ. cases rsb autotuning gave avg. 3568812.5 % faster, avg. sp. ratio 35689.125x, max sp. ratio 37726.500x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 404701.0/343837.5/465564.5/809402.0 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 11.5/ 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: (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 5.326/ 3.370/ 7.283,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 13.913/ 4.022/ 9.891,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.: 0.06 s, min 0.06 s, max 0.06 s, tot 0.13 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.06 s, min 0.06 s, max 0.06 s, tot 0.13 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 6.522e+03, min 2.609e+03, max 1.043e+04 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 3.623e-02, min 2.459e-02, max 4.786e-02 (2 samples) -#pr: best tun. rsb operation time was: on avg. 3.680e-08s, min 3.680e-08s, max 3.680e-08s, tot 7.360e-08s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 5.964e-03s, min 3.904e-03s, max 8.023e-03s, tot 1.193e-02s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 2.884e+00 6.234e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.031e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.39 s, min 0.33 s, max 0.44 s, tot 0.77 s (2 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.39 s, min 0.33 s, max 0.44 s, tot 0.77 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. 6.832e-03, min 2.991e-03, max 1.067e-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. 3.404e-02s, min 3.209e-02s, max 3.598e-02s, tot 6.807e-02s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 8.755e+00 1.892e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 2.106e+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 2608.70 5.567e-03 0.000e+00 3.680e-08 0.000e+00 6.631e-02 7.28e+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 10434.81 5.559e-03 0.000e+00 3.680e-08 0.000e+00 5.944e-02 1.90e+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 3.600e-02 0.000e+00 9.537e-07 0.000e+00 3.239e-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 6.003e-02 0.000e+00 9.537e-07 0.000e+00 5.836e-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. 15116842.0 % faster, avg. sp. ratio 151169.420x, max sp. ratio 151279.559x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 1708522.8/1615115.0/1801930.7/3417045.7 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 11.3/ 10.7/ 11.9/ 22.6 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 11.3, min. 10.7, max. 11.9 ops) +#pr: (in succ. cases rsb autotuning gave avg. 5034587.5 % faster, avg. sp. ratio 50346.875x, max sp. ratio 62950.250x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 475769.9/339607.8/611932.0/951539.8 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 9.4/ 9.0/ 9.7/ 18.7 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 9.4, min. 9.0, max. 9.7 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 9.891/ 5.978/ 13.804,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 26.304/ 7.283/ 19.022,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.: 0.06 s, min 0.06 s, max 0.07 s, tot 0.13 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.06 s, min 0.06 s, max 0.07 s, tot 0.13 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 6.522e+03, min 2.609e+03, max 1.043e+04 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 4.316e-02, min 1.724e-02, max 6.908e-02 (2 samples) -#pr: best tun. rsb operation time was: on avg. 3.680e-08s, min 3.680e-08s, max 3.680e-08s, tot 7.360e-08s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 5.563e-03s, min 5.559e-03s, max 5.567e-03s, tot 1.113e-02s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.522e+00 3.514e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.031e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.45 s, min 0.32 s, max 0.58 s, tot 0.91 s (2 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.45 s, min 0.32 s, max 0.58 s, tot 0.91 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. 4.532e-03, min 2.667e-03, max 6.396e-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. 4.801e-02s, min 3.600e-02s, max 6.003e-02s, tot 9.603e-02s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 4.619e+00 1.066e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 2.106e+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 1 652.18 5.075e-03 0.000e+00 3.680e-08 0.000e+00 8.144e-02 4.02e+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 1 652.18 3.741e-03 0.000e+00 3.680e-08 0.000e+00 4.934e-02 2.39e+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 2608.70 3.904e-03 0.000e+00 3.680e-08 0.000e+00 6.312e-02 4.02e+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 2608.70 5.567e-03 0.000e+00 3.680e-08 0.000e+00 6.631e-02 7.28e+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 4.796e-02 0.000e+00 9.537e-07 0.000e+00 4.080e-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 26.37 3.953e-02 0.000e+00 9.102e-07 0.000e+00 4.042e-01 9.67e-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 3.209e-02 0.000e+00 9.537e-07 0.000e+00 4.440e-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 3.600e-02 0.000e+00 9.537e-07 0.000e+00 3.239e-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. 12423288.4 % faster, avg. sp. ratio 124233.884x, max sp. ratio 151279.559x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 1767761.6/1340790.4/2213158.4/7071046.3 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 14.3/ 11.9/ 16.2/ 57.3 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 14.3, min. 11.9, max. 16.2 ops) +#pr: (in succ. cases rsb autotuning gave avg. 4127696.8 % faster, avg. sp. ratio 41277.968x, max sp. ratio 50286.500x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 419252.0/339607.8/465564.5/1677007.9 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 10.4/ 8.5/ 13.8/ 41.6 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 10.4, min. 8.5, max. 13.8 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 3.696/ 2.065/ 5.978,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 17.717/ 2.391/ 7.283,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 0.144/ 0.083/ 0.231,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 0.688/ 0.097/ 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.: 0.07 s, min 0.05 s, max 0.08 s, tot 0.26 s (4 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.07 s, min 0.05 s, max 0.08 s, tot 0.26 s (4 samples) -#pr: best tun. rsb canon. mflops were: on avg. 1.630e+03, min 6.522e+02, max 2.609e+03 (4 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 1.324e-02, min 4.729e-03, max 2.459e-02 (4 samples) -#pr: best tun. rsb operation time was: on avg. 3.680e-08s, min 3.680e-08s, max 3.680e-08s, tot 1.472e-07s (4 samples) -#pr: ref. unt. rsb operation time was: on avg. 4.572e-03s, min 3.741e-03s, max 5.567e-03s, tot 1.829e-02s (4 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 3.514e+00 1.017e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.031e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.40 s, min 0.32 s, max 0.44 s, tot 1.58 s (4 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.40 s, min 0.32 s, max 0.44 s, tot 1.58 s (4 samples) +#pr: best tun. rsb canon. mflops were: on avg. 6.322e+01, min 2.517e+01, max 1.007e+02 (4 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 1.691e-03, min 5.004e-04, max 2.991e-03 (4 samples) +#pr: best tun. rsb operation time was: on avg. 9.428e-07s, min 9.102e-07s, max 9.537e-07s, tot 3.771e-06s (4 samples) +#pr: ref. unt. rsb operation time was: on avg. 3.889e-02s, min 3.209e-02s, max 4.796e-02s, tot 1.556e-01s (4 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.066e+01 2.946e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 2.106e+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 2608.70 4.902e-03 0.000e+00 3.680e-08 0.000e+00 5.438e-02 9.89e+00 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 2608.70 5.545e-03 0.000e+00 3.680e-08 0.000e+00 6.039e-02 5.33e+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 10434.81 8.023e-03 0.000e+00 3.680e-08 0.000e+00 6.491e-02 9.89e+00 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 10434.81 5.559e-03 0.000e+00 3.680e-08 0.000e+00 5.944e-02 1.90e+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 3.599e-02 0.000e+00 9.537e-07 0.000e+00 4.440e-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 1 105.47 3.200e-02 0.000e+00 9.102e-07 0.000e+00 3.801e-01 2.15e-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 3.598e-02 0.000e+00 9.537e-07 0.000e+00 3.279e-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 6.003e-02 0.000e+00 9.537e-07 0.000e+00 5.836e-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. 16323839.1 % faster, avg. sp. ratio 163239.391x, max sp. ratio 218017.493x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 1624467.1/1477855.5/1763777.1/6497868.5 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 10.2/ 8.1/ 11.1/ 40.8 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 10.2, min. 8.1, max. 11.1 ops) +#pr: (in succ. cases rsb autotuning gave avg. 4339038.2 % faster, avg. sp. ratio 43391.382x, max sp. ratio 62950.250x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 459733.5/343837.5/611932.0/1838934.0 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 10.8/ 9.1/ 12.3/ 43.1 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 10.8, min. 9.1, max. 12.3 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 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 8.098/ 4.022/ 13.804,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 44.131/ 5.326/ 19.022,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 0.314/ 0.163/ 0.533,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 1.713/ 0.215/ 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.: 0.06 s, min 0.05 s, max 0.06 s, tot 0.24 s (4 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.06 s, min 0.05 s, max 0.06 s, tot 0.24 s (4 samples) -#pr: best tun. rsb canon. mflops were: on avg. 6.522e+03, min 2.609e+03, max 1.043e+04 (4 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 3.846e-02, min 1.731e-02, max 6.908e-02 (4 samples) -#pr: best tun. rsb operation time was: on avg. 3.680e-08s, min 3.680e-08s, max 3.680e-08s, tot 1.472e-07s (4 samples) -#pr: ref. unt. rsb operation time was: on avg. 6.007e-03s, min 4.902e-03s, max 8.023e-03s, tot 2.403e-02s (4 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.522e+00 5.223e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.031e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.43 s, min 0.33 s, max 0.58 s, tot 1.74 s (4 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.43 s, min 0.33 s, max 0.58 s, tot 1.74 s (4 samples) +#pr: best tun. rsb canon. mflops were: on avg. 2.529e+02, min 1.007e+02, max 4.027e+02 (4 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 5.684e-03, min 2.668e-03, max 1.067e-02 (4 samples) +#pr: best tun. rsb operation time was: on avg. 9.428e-07s, min 9.102e-07s, max 9.537e-07s, tot 3.771e-06s (4 samples) +#pr: ref. unt. rsb operation time was: on avg. 4.100e-02s, min 3.200e-02s, max 6.003e-02s, tot 1.640e-01s (4 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 4.619e+00 1.513e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 2.106e+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 (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 1 652.18 5.075e-03 0.000e+00 3.680e-08 0.000e+00 8.144e-02 4.02e+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 1 652.18 3.741e-03 0.000e+00 3.680e-08 0.000e+00 4.934e-02 2.39e+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 2608.70 3.904e-03 0.000e+00 3.680e-08 0.000e+00 6.312e-02 4.02e+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 2608.70 5.567e-03 0.000e+00 3.680e-08 0.000e+00 6.631e-02 7.28e+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 2608.70 4.902e-03 0.000e+00 3.680e-08 0.000e+00 5.438e-02 9.89e+00 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 2608.70 5.545e-03 0.000e+00 3.680e-08 0.000e+00 6.039e-02 5.33e+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 10434.81 8.023e-03 0.000e+00 3.680e-08 0.000e+00 6.491e-02 9.89e+00 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 10434.81 5.559e-03 0.000e+00 3.680e-08 0.000e+00 5.944e-02 1.90e+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 4.796e-02 0.000e+00 9.537e-07 0.000e+00 4.080e-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 26.37 3.953e-02 0.000e+00 9.102e-07 0.000e+00 4.042e-01 9.67e-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 3.209e-02 0.000e+00 9.537e-07 0.000e+00 4.440e-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 3.600e-02 0.000e+00 9.537e-07 0.000e+00 3.239e-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 3.599e-02 0.000e+00 9.537e-07 0.000e+00 4.440e-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 1 105.47 3.200e-02 0.000e+00 9.102e-07 0.000e+00 3.801e-01 2.15e-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 3.598e-02 0.000e+00 9.537e-07 0.000e+00 3.279e-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 6.003e-02 0.000e+00 9.537e-07 0.000e+00 5.836e-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. 14373563.8 % faster, avg. sp. ratio 143736.638x, max sp. ratio 218017.493x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 1696114.4/1340790.4/2213158.4/13568914.8 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 12.3/ 8.1/ 16.2/ 98.1 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 12.3, min. 8.1, max. 16.2 ops) +#pr: (in succ. cases rsb autotuning gave avg. 4233367.5 % faster, avg. sp. ratio 42334.675x, max sp. ratio 62950.250x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 439492.7/339607.8/611932.0/3515941.9 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 10.6/ 8.5/ 13.8/ 84.6 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 10.6, min. 8.5, max. 13.8 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 5.897/ 2.065/ 13.804,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 61.848/ 2.391/ 19.022,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 0.229/ 0.083/ 0.533,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 2.401/ 0.097/ 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.: 0.06 s, min 0.05 s, max 0.08 s, tot 0.50 s (8 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.06 s, min 0.05 s, max 0.08 s, tot 0.50 s (8 samples) -#pr: best tun. rsb canon. mflops were: on avg. 4.076e+03, min 6.522e+02, max 1.043e+04 (8 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 2.585e-02, min 4.729e-03, max 6.908e-02 (8 samples) -#pr: best tun. rsb operation time was: on avg. 3.680e-08s, min 3.680e-08s, max 3.680e-08s, tot 2.944e-07s (8 samples) -#pr: ref. unt. rsb operation time was: on avg. 5.289e-03s, min 3.741e-03s, max 8.023e-03s, tot 4.232e-02s (8 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.522e+00 1.017e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.031e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.41 s, min 0.32 s, max 0.58 s, tot 3.32 s (8 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.41 s, min 0.32 s, max 0.58 s, tot 3.32 s (8 samples) +#pr: best tun. rsb canon. mflops were: on avg. 1.580e+02, min 2.517e+01, max 4.027e+02 (8 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 3.688e-03, min 5.004e-04, max 1.067e-02 (8 samples) +#pr: best tun. rsb operation time was: on avg. 9.428e-07s, min 9.102e-07s, max 9.537e-07s, tot 7.542e-06s (8 samples) +#pr: ref. unt. rsb operation time was: on avg. 3.995e-02s, min 3.200e-02s, max 6.003e-02s, tot 3.196e-01s (8 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 4.619e+00 2.946e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 2.106e+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 (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 1 652.18 5.075e-03 0.000e+00 3.680e-08 0.000e+00 8.144e-02 4.02e+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 1 652.18 3.741e-03 0.000e+00 3.680e-08 0.000e+00 4.934e-02 2.39e+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 2608.70 3.904e-03 0.000e+00 3.680e-08 0.000e+00 6.312e-02 4.02e+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 2608.70 5.567e-03 0.000e+00 3.680e-08 0.000e+00 6.631e-02 7.28e+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 4.796e-02 0.000e+00 9.537e-07 0.000e+00 4.080e-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 26.37 3.953e-02 0.000e+00 9.102e-07 0.000e+00 4.042e-01 9.67e-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 3.209e-02 0.000e+00 9.537e-07 0.000e+00 4.440e-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 3.600e-02 0.000e+00 9.537e-07 0.000e+00 3.239e-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. 12423288.4 % faster, avg. sp. ratio 124233.884x, max sp. ratio 151279.559x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 1767761.6/1340790.4/2213158.4/7071046.3 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 14.3/ 11.9/ 16.2/ 57.3 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 14.3, min. 11.9, max. 16.2 ops) +#pr: (in succ. cases rsb autotuning gave avg. 4127696.8 % faster, avg. sp. ratio 41277.968x, max sp. ratio 50286.500x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 419252.0/339607.8/465564.5/1677007.9 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 10.4/ 8.5/ 13.8/ 41.6 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 10.4, min. 8.5, max. 13.8 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 3.696/ 2.065/ 5.978,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 17.717/ 2.391/ 7.283,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 0.144/ 0.083/ 0.231,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 0.688/ 0.097/ 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.: 0.07 s, min 0.05 s, max 0.08 s, tot 0.26 s (4 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.07 s, min 0.05 s, max 0.08 s, tot 0.26 s (4 samples) -#pr: best tun. rsb canon. mflops were: on avg. 1.630e+03, min 6.522e+02, max 2.609e+03 (4 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 1.324e-02, min 4.729e-03, max 2.459e-02 (4 samples) -#pr: best tun. rsb operation time was: on avg. 3.680e-08s, min 3.680e-08s, max 3.680e-08s, tot 1.472e-07s (4 samples) -#pr: ref. unt. rsb operation time was: on avg. 4.572e-03s, min 3.741e-03s, max 5.567e-03s, tot 1.829e-02s (4 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 3.514e+00 1.017e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.031e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.40 s, min 0.32 s, max 0.44 s, tot 1.58 s (4 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.40 s, min 0.32 s, max 0.44 s, tot 1.58 s (4 samples) +#pr: best tun. rsb canon. mflops were: on avg. 6.322e+01, min 2.517e+01, max 1.007e+02 (4 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 1.691e-03, min 5.004e-04, max 2.991e-03 (4 samples) +#pr: best tun. rsb operation time was: on avg. 9.428e-07s, min 9.102e-07s, max 9.537e-07s, tot 3.771e-06s (4 samples) +#pr: ref. unt. rsb operation time was: on avg. 3.889e-02s, min 3.209e-02s, max 4.796e-02s, tot 1.556e-01s (4 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.066e+01 2.946e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 2.106e+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 2608.70 4.902e-03 0.000e+00 3.680e-08 0.000e+00 5.438e-02 9.89e+00 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 2608.70 5.545e-03 0.000e+00 3.680e-08 0.000e+00 6.039e-02 5.33e+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 10434.81 8.023e-03 0.000e+00 3.680e-08 0.000e+00 6.491e-02 9.89e+00 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 10434.81 5.559e-03 0.000e+00 3.680e-08 0.000e+00 5.944e-02 1.90e+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 3.599e-02 0.000e+00 9.537e-07 0.000e+00 4.440e-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 1 105.47 3.200e-02 0.000e+00 9.102e-07 0.000e+00 3.801e-01 2.15e-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 3.598e-02 0.000e+00 9.537e-07 0.000e+00 3.279e-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 6.003e-02 0.000e+00 9.537e-07 0.000e+00 5.836e-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. 16323839.1 % faster, avg. sp. ratio 163239.391x, max sp. ratio 218017.493x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 1624467.1/1477855.5/1763777.1/6497868.5 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 10.2/ 8.1/ 11.1/ 40.8 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 10.2, min. 8.1, max. 11.1 ops) +#pr: (in succ. cases rsb autotuning gave avg. 4339038.2 % faster, avg. sp. ratio 43391.382x, max sp. ratio 62950.250x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 459733.5/343837.5/611932.0/1838934.0 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 10.8/ 9.1/ 12.3/ 43.1 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 10.8, min. 9.1, max. 12.3 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 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 8.098/ 4.022/ 13.804,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 44.131/ 5.326/ 19.022,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 0.314/ 0.163/ 0.533,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 1.713/ 0.215/ 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.: 0.06 s, min 0.05 s, max 0.06 s, tot 0.24 s (4 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.06 s, min 0.05 s, max 0.06 s, tot 0.24 s (4 samples) -#pr: best tun. rsb canon. mflops were: on avg. 6.522e+03, min 2.609e+03, max 1.043e+04 (4 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 3.846e-02, min 1.731e-02, max 6.908e-02 (4 samples) -#pr: best tun. rsb operation time was: on avg. 3.680e-08s, min 3.680e-08s, max 3.680e-08s, tot 1.472e-07s (4 samples) -#pr: ref. unt. rsb operation time was: on avg. 6.007e-03s, min 4.902e-03s, max 8.023e-03s, tot 2.403e-02s (4 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.522e+00 5.223e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.031e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.43 s, min 0.33 s, max 0.58 s, tot 1.74 s (4 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.43 s, min 0.33 s, max 0.58 s, tot 1.74 s (4 samples) +#pr: best tun. rsb canon. mflops were: on avg. 2.529e+02, min 1.007e+02, max 4.027e+02 (4 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 5.684e-03, min 2.668e-03, max 1.067e-02 (4 samples) +#pr: best tun. rsb operation time was: on avg. 9.428e-07s, min 9.102e-07s, max 9.537e-07s, tot 3.771e-06s (4 samples) +#pr: ref. unt. rsb operation time was: on avg. 4.100e-02s, min 3.200e-02s, max 6.003e-02s, tot 1.640e-01s (4 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 4.619e+00 1.513e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 2.106e+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 (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. @@ -5037,65 +5049,65 @@ #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 1 652.18 5.075e-03 0.000e+00 3.680e-08 0.000e+00 8.144e-02 4.02e+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 1 652.18 3.741e-03 0.000e+00 3.680e-08 0.000e+00 4.934e-02 2.39e+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 2608.70 3.904e-03 0.000e+00 3.680e-08 0.000e+00 6.312e-02 4.02e+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 2608.70 5.567e-03 0.000e+00 3.680e-08 0.000e+00 6.631e-02 7.28e+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 2608.70 4.902e-03 0.000e+00 3.680e-08 0.000e+00 5.438e-02 9.89e+00 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 2608.70 5.545e-03 0.000e+00 3.680e-08 0.000e+00 6.039e-02 5.33e+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 10434.81 8.023e-03 0.000e+00 3.680e-08 0.000e+00 6.491e-02 9.89e+00 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 10434.81 5.559e-03 0.000e+00 3.680e-08 0.000e+00 5.944e-02 1.90e+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 4.796e-02 0.000e+00 9.537e-07 0.000e+00 4.080e-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 26.37 3.953e-02 0.000e+00 9.102e-07 0.000e+00 4.042e-01 9.67e-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 3.209e-02 0.000e+00 9.537e-07 0.000e+00 4.440e-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 3.600e-02 0.000e+00 9.537e-07 0.000e+00 3.239e-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 3.599e-02 0.000e+00 9.537e-07 0.000e+00 4.440e-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 1 105.47 3.200e-02 0.000e+00 9.102e-07 0.000e+00 3.801e-01 2.15e-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 3.598e-02 0.000e+00 9.537e-07 0.000e+00 3.279e-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 6.003e-02 0.000e+00 9.537e-07 0.000e+00 5.836e-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. 14373563.8 % faster, avg. sp. ratio 143736.638x, max sp. ratio 218017.493x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 1696114.4/1340790.4/2213158.4/13568914.8 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 12.3/ 8.1/ 16.2/ 98.1 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 12.3, min. 8.1, max. 16.2 ops) +#pr: (in succ. cases rsb autotuning gave avg. 4233367.5 % faster, avg. sp. ratio 42334.675x, max sp. ratio 62950.250x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 439492.7/339607.8/611932.0/3515941.9 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 10.6/ 8.5/ 13.8/ 84.6 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 10.6, min. 8.5, max. 13.8 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 5.897/ 2.065/ 13.804,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 61.848/ 2.391/ 19.022,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 0.229/ 0.083/ 0.533,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 2.401/ 0.097/ 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.: 0.06 s, min 0.05 s, max 0.08 s, tot 0.50 s (8 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.06 s, min 0.05 s, max 0.08 s, tot 0.50 s (8 samples) -#pr: best tun. rsb canon. mflops were: on avg. 4.076e+03, min 6.522e+02, max 1.043e+04 (8 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 2.585e-02, min 4.729e-03, max 6.908e-02 (8 samples) -#pr: best tun. rsb operation time was: on avg. 3.680e-08s, min 3.680e-08s, max 3.680e-08s, tot 2.944e-07s (8 samples) -#pr: ref. unt. rsb operation time was: on avg. 5.289e-03s, min 3.741e-03s, max 8.023e-03s, tot 4.232e-02s (8 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.522e+00 1.017e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.031e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.41 s, min 0.32 s, max 0.58 s, tot 3.32 s (8 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.41 s, min 0.32 s, max 0.58 s, tot 3.32 s (8 samples) +#pr: best tun. rsb canon. mflops were: on avg. 1.580e+02, min 2.517e+01, max 4.027e+02 (8 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 3.688e-03, min 5.004e-04, max 1.067e-02 (8 samples) +#pr: best tun. rsb operation time was: on avg. 9.428e-07s, min 9.102e-07s, max 9.537e-07s, tot 7.542e-06s (8 samples) +#pr: ref. unt. rsb operation time was: on avg. 3.995e-02s, min 3.200e-02s, max 6.003e-02s, tot 3.196e-01s (8 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 4.619e+00 2.946e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 2.106e+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 (4 samples, the non-min-nrhs ones) -#pr: Record collection took 3.49 s. +#pr: Record collection took 23.34 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__1751677199_gcc-13.2.rpr -# Removing the temporary record file rsbench_pr__1751677199_gcc-13.2.rpr.tmp. -# terminating run at 1751677211 (after 11.1s 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__1717270881_gcc-13.2.rpr +# Removing the temporary record file rsbench_pr__1717270881_gcc-13.2.rpr.tmp. +# terminating run at 1717270913 (after 31.4s 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 -+ grep '^.\{71,\}' + 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 ++ grep '^.\{71,\}' + true -+ cat /build/reproducible-path/librsb-1.3.0.2+dfsg/README + grep '^[^ ].\{80,\}' ++ cat /build/reproducible-path/librsb-1.3.0.2+dfsg/README + true -++ /build/reproducible-path/librsb-1.3.0.2+dfsg/rsbench -h ++ wc -l +++ /build/reproducible-path/librsb-1.3.0.2+dfsg/rsbench -h + test 63 -ge 61 ++ 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 @@ -5133,7 +5145,7 @@ 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 @@ -5143,15 +5155,15 @@ 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 1751677211 +# beginning run at 1717270915 # /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: 3.67e-08 s +# average timer granularity: 1.98e-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 @@ -5190,15 +5202,15 @@ # 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: ionos15-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 @@ -5210,40 +5222,40 @@ # 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 7.272s +# Memory benchmark took 6.170s # 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 7.274s 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 6.308s 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 6.380e-02 s (100.00 %) - analyzed arrays in 1.481e-02 s (23.22 %) - cleaned-up arrays in 1.121e-05 s (0.02 %) - deduplicated arrays in 1.287e-05 s (0.02 %) - sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 3.022e-02 s (47.37 %) - memory allocations took 2.074e-05 s (0.03 %) - leafs setup took 4.768e-06 s (0.01 %) - halfword conversion took 1.871e-02 s (29.32 %) -Built (100 x 100)[0x556d0c3934e0]{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 0.064s): (100 x 100)[0x556d0c3934e0]{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 2.402e-01 s (100.00 %) + analyzed arrays in 7.621e-02 s (31.73 %) + cleaned-up arrays in 1.597e-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 1.120e-01 s (46.61 %) + memory allocations took 4.292e-05 s (0.02 %) + leafs setup took 1.597e-05 s (0.01 %) + halfword conversion took 5.195e-02 s (21.63 %) +Built (100 x 100)[0x55abeeb83510]{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 0.240s): (100 x 100)[0x55abeeb83510]{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 @@ -5254,11 +5266,11 @@ # 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 @@ -5269,11 +5281,11 @@ # 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 @@ -5283,16 +5295,16 @@ # 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 0.02284s; avg 0.007612s ( +/- 0.83/ 1.09 %); best 0.007549s; worst 0.007695s; std dev. 6.123e-05 (taking best). -Reference operation time is 0.00754905 s (2.676 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: 0.007549 Mflops: 2.676) -Merge (3 -> 1 leaves) took w.c.t. of 5.794e-05s, ~4.601e-05s of computing time (of which 1.788e-05s sorting, 4.053e-06s analysis) +3 iterations (1 th.) took 0.1039s; avg 0.03465s ( +/- 7.60/ 3.85 %); best 0.03202s; worst 0.03598s; std dev. 0.001863 (taking best). +Reference operation time is 0.0320151 s (0.631 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: 0.03202 Mflops: 0.631) +Merge (3 -> 1 leaves) took w.c.t. of 0.00021s, ~0.000154s of computing time (of which 8.607e-05s sorting, 1.812e-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 @@ -5303,11 +5315,11 @@ # 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 @@ -5317,14 +5329,14 @@ # 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 3.91e-05s; avg 1.303e-05s ( +/- 8.54/ 15.24 %); best 1.192e-05s; worst 1.502e-05s; std dev. 1.408e-06 (taking best). -Reference operation time is 1.19209e-05 s (1694 Mflops) with 1 threads. +3 iterations (1 th.) took 6.104e-05s; avg 2.035e-05s ( +/- 21.48/ 42.97 %); best 1.597e-05s; worst 2.909e-05s; std dev. 6.182e-06 (taking best). +Reference operation time is 1.5974e-05 s (1265 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 @@ -5334,25 +5346,25 @@ # 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 633.260x: 0.007549s -> 1.192e-05s, so taking this instance. +After merge step 1: tpop: 1.597e-05 s ~Mflops: 1264.551 nsubm:1 otn:1 +Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 2004.194x: 0.03202s -> 1.597e-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 0.06735s (of which 6.199e-05s partitioning, 0.04316s I/O); computing times: 4.601e-05s in par. loops, 1.788e-05s sorting, 4.053e-06s analyzing) -Total merge + benchmarking process took 0.06735s, equivalent to 5649.8/8.9 new/old ops (0.04662s for 2 clones -- as 3910.8/6.2 ops, or 1955.4/3.1 ops per clone), SPEEDUP of 633.260x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 633.260x (0.007549s -> 1.192e-05s), will amortize in 8.9 ops by saving 0.007537s per op. -In 1 tuning rounds (tot. 0.11s, 0.047s for constructor, 2 clones) obtained a SPEEDUP of 63226.0% (633.3x) (from 2.676 to 1694 Mflops). Employed 0.051s for I/O of matrix plots. +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.2841s (of which 0.0002189s partitioning, 0.1882s I/O); computing times: 0.000154s in par. loops, 8.607e-05s sorting, 1.812e-05s analyzing) +Total merge + benchmarking process took 0.2841s, equivalent to 17786.9/8.9 new/old ops (0.1947s for 2 clones -- as 12186.0/6.1 ops, or 6093.0/3.0 ops per clone), SPEEDUP of 2004.194x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 2004.194x (0.03202s -> 1.597e-05s), will amortize in 8.9 ops by saving 0.032s per op. +In 1 tuning rounds (tot. 0.49s, 0.19s for constructor, 2 clones) obtained a SPEEDUP of 200319.4% (2004x) (from 0.631 to 1265 Mflops). Employed 0.22s 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 0.164396 s (7.549e-03 s -> 1.192e-05 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.708065 s (3.202e-02 s -> 1.597e-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 @@ -5363,11 +5375,11 @@ # 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 @@ -5378,13 +5390,13 @@ # 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 @@ -5395,11 +5407,11 @@ # 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 @@ -5409,27 +5421,27 @@ # 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 3.791e-05s; avg 1.264e-05s ( +/- 5.66/ 9.43 %); best 1.192e-05s; worst 1.383e-05s; std dev. 8.485e-07 (taking best). -Reference operation time is 1.19209e-05 s (1694 Mflops) with 1 threads. +3 iterations (1 th.) took 8.607e-05s; avg 2.869e-05s ( +/- 51.80/102.77 %); best 1.383e-05s; worst 5.817e-05s; std dev. 2.085e-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 2.664e-02 s (100.00 %) - analyzed arrays in 1.435e-02 s (53.87 %) - cleaned-up arrays in 8.106e-06 s (0.03 %) - deduplicated arrays in 1.287e-05 s (0.05 %) + converted COO to RSB in 1.310e-01 s (100.00 %) + analyzed arrays in 4.293e-02 s (32.77 %) + 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 1.226e-02 s (46.02 %) - memory allocations took 2.146e-06 s (0.01 %) - leafs setup took 9.537e-07 s (0.00 %) - halfword conversion took 5.007e-06 s (0.02 %) -Built (100 x 100)[0x556d0c3a2230]{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 8.798e-02 s (67.15 %) + memory allocations took 9.775e-06 s (0.01 %) + leafs setup took 1.502e-05 s (0.01 %) + halfword conversion took 3.910e-05 s (0.03 %) +Built (100 x 100)[0x55abeeb8ef60]{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 @@ -5440,12 +5452,12 @@ # 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 @@ -5456,22 +5468,22 @@ # 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 2.612e-02 s (100.00 %) - analyzed arrays in 3.858e-03 s (14.77 %) - cleaned-up arrays in 7.868e-06 s (0.03 %) - deduplicated arrays in 1.311e-05 s (0.05 %) - sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.125e-02 s (43.07 %) - memory allocations took 2.146e-06 s (0.01 %) - leafs setup took 9.537e-07 s (0.00 %) - halfword conversion took 1.099e-02 s (42.06 %) -Built (100 x 100)[0x556d0c393810]{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 + converted COO to RSB in 1.519e-01 s (100.00 %) + analyzed arrays in 4.777e-02 s (31.46 %) + cleaned-up arrays in 1.407e-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 5.196e-02 s (34.21 %) + memory allocations took 1.383e-05 s (0.01 %) + leafs setup took 9.060e-06 s (0.01 %) + halfword conversion took 5.207e-02 s (34.29 %) +Built (100 x 100)[0x55abeeb83860]{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 @@ -5482,11 +5494,11 @@ # 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 @@ -5497,11 +5509,11 @@ # 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 @@ -5511,16 +5523,16 @@ # 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 0.02558s; avg 0.008527s ( +/- 15.34/ 26.60 %); best 0.007219s; worst 0.01079s; std dev. 0.00161 (taking best). -Reference operation time is 0.00721908 s (2.798 Mflops) with 1 threads. -Challenging best inner round reference (1.19209e-05 s/1 threads) with: subdivision 0.25, 3 leaves, 2.121 bytes/nz, 0.00721908 s/0 threads (speedup 0.00165131 x), same?n. +3 iterations (1 th.) took 0.0992s; avg 0.03307s ( +/- 5.34/ 8.63 %); best 0.0313s; worst 0.03592s; std dev. 0.002036 (taking best). +Reference operation time is 0.0313022 s (0.6453 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, 0.0313022 s/0 threads (speedup 0.000441767 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 @@ -5531,12 +5543,12 @@ # 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 @@ -5547,22 +5559,22 @@ # 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 4.652e-02 s (100.00 %) - analyzed arrays in 1.230e-02 s (26.44 %) - cleaned-up arrays in 8.106e-06 s (0.02 %) - deduplicated arrays in 1.192e-05 s (0.03 %) + converted COO to RSB in 2.038e-01 s (100.00 %) + analyzed arrays in 8.775e-02 s (43.06 %) + cleaned-up arrays in 1.502e-05 s (0.01 %) + deduplicated arrays in 1.287e-05 s (0.01 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.351e-02 s (29.05 %) - memory allocations took 3.815e-06 s (0.01 %) - leafs setup took 1.907e-06 s (0.00 %) - halfword conversion took 2.068e-02 s (44.46 %) -Built (100 x 100)[0x556d0c394200]{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 + shuffled partitions in 6.803e-02 s (33.38 %) + memory allocations took 2.289e-05 s (0.01 %) + leafs setup took 1.502e-05 s (0.01 %) + halfword conversion took 4.792e-02 s (23.52 %) +Built (100 x 100)[0x55abeeb84370]{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 @@ -5573,11 +5585,11 @@ # 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 @@ -5588,11 +5600,11 @@ # 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 @@ -5602,16 +5614,16 @@ # 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 0.02319s; avg 0.007731s ( +/- 26.18/ 26.62 %); best 0.005707s; worst 0.009789s; std dev. 0.001667 (taking best). -Reference operation time is 0.00570679 s (3.54 Mflops) with 1 threads. -Challenging best inner round reference (1.19209e-05 s/1 threads) with: subdivision 0.5, 10 leaves, 2.206 bytes/nz, 0.00570679 s/0 threads (speedup 0.0020889 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 0.09992s; avg 0.03331s ( +/- 51.72/ 55.92 %); best 0.01608s; worst 0.05193s; std dev. 0.01467 (taking best). +Reference operation time is 0.0160801 s (1.256 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, 0.0160801 s/0 threads (speedup 0.00085996 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 @@ -5622,12 +5634,12 @@ # 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 @@ -5638,22 +5650,22 @@ # 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 4.391e-02 s (100.00 %) - analyzed arrays in 1.155e-02 s (26.31 %) - cleaned-up arrays in 7.868e-06 s (0.02 %) - deduplicated arrays in 1.192e-05 s (0.03 %) + converted COO to RSB in 2.038e-01 s (100.00 %) + analyzed arrays in 8.375e-02 s (41.09 %) + 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 1.480e-02 s (33.70 %) - memory allocations took 5.245e-06 s (0.01 %) - leafs setup took 3.099e-06 s (0.01 %) - halfword conversion took 1.753e-02 s (39.92 %) -Built (100 x 100)[0x556d0c3a2350]{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' + shuffled partitions in 5.206e-02 s (25.54 %) + memory allocations took 1.907e-05 s (0.01 %) + leafs setup took 1.311e-05 s (0.01 %) + halfword conversion took 6.796e-02 s (33.34 %) +Built (100 x 100)[0x55abeeb8f080]{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: 26, 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 @@ -5664,11 +5676,11 @@ # 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 @@ -5679,11 +5691,11 @@ # 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 @@ -5693,16 +5705,16 @@ # 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 0.02642s; avg 0.008807s ( +/- 32.20/ 26.93 %); best 0.005971s; worst 0.01118s; std dev. 0.002151 (taking best). -Reference operation time is 0.00597095 s (3.383 Mflops) with 1 threads. -Challenging best inner round reference (1.19209e-05 s/1 threads) with: subdivision 1, 22 leaves, 2.295 bytes/nz, 0.00597095 s/0 threads (speedup 0.00199649 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 0.1553s; avg 0.05178s ( +/- 0.89/ 0.47 %); best 0.05132s; worst 0.05202s; std dev. 0.0003263 (taking best). +Reference operation time is 0.0513201 s (0.3936 Mflops) with 1 threads. +Challenging best inner round reference (1.38283e-05 s/1 threads) with: subdivision 1, 26 leaves, 2.317 bytes/nz, 0.0513201 s/0 threads (speedup 0.000269452 x), same?n. +New candidate clone performs slowly; discarding it: 100 x 100, type D, 5050 nnz, 50 nnz/r, 36 subms, 26 lsubms, 2.3168 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 @@ -5713,12 +5725,12 @@ # 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 @@ -5729,22 +5741,22 @@ # 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 5.194e-02 s (100.00 %) - analyzed arrays in 1.779e-02 s (34.26 %) - cleaned-up arrays in 8.106e-06 s (0.02 %) - deduplicated arrays in 1.192e-05 s (0.02 %) - sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.706e-02 s (32.84 %) - memory allocations took 5.960e-06 s (0.01 %) - leafs setup took 5.007e-06 s (0.01 %) - halfword conversion took 1.706e-02 s (32.85 %) -Built (100 x 100)[0x556d0c3c8fc0]{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: 48, 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 3.397e-01 s (100.00 %) + analyzed arrays in 1.037e-01 s (30.52 %) + cleaned-up arrays in 1.907e-05 s (0.01 %) + deduplicated arrays in 1.693e-05 s (0.00 %) + sorted arrays in 9.537e-07 s (0.00 %) + shuffled partitions in 1.090e-01 s (32.08 %) + memory allocations took 3.695e-05 s (0.01 %) + leafs setup took 1.407e-05 s (0.00 %) + halfword conversion took 1.269e-01 s (37.37 %) +Built (100 x 100)[0x55abeebb5d20]{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 @@ -5755,11 +5767,11 @@ # 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 @@ -5770,11 +5782,11 @@ # 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 @@ -5784,16 +5796,16 @@ # 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 0.0234s; avg 0.0078s ( +/- 27.59/ 28.34 %); best 0.005648s; worst 0.01001s; std dev. 0.001781 (taking best). -Reference operation time is 0.0056479 s (3.577 Mflops) with 1 threads. -Challenging best inner round reference (1.19209e-05 s/1 threads) with: subdivision 2, 48 leaves, 2.434 bytes/nz, 0.0056479 s/0 threads (speedup 0.00211068 x), same?n. -New candidate clone performs slowly; discarding it: 100 x 100, type D, 5050 nnz, 50 nnz/r, 66 subms, 48 lsubms, 2.4341 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 0.09585s; avg 0.03195s ( +/- 12.79/ 12.61 %); best 0.02787s; worst 0.03598s; std dev. 0.003313 (taking best). +Reference operation time is 0.0278661 s (0.7249 Mflops) with 1 threads. +Challenging best inner round reference (1.38283e-05 s/1 threads) with: subdivision 2, 57 leaves, 2.471 bytes/nz, 0.0278661 s/0 threads (speedup 0.00049624 x), same?n. +New candidate clone performs slowly; discarding it: 100 x 100, type D, 5050 nnz, 50 nnz/r, 78 subms, 57 lsubms, 2.4713 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 @@ -5804,12 +5816,12 @@ # 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 @@ -5820,22 +5832,22 @@ # 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 3.773e-02 s (100.00 %) - analyzed arrays in 1.682e-02 s (44.57 %) - cleaned-up arrays in 8.106e-06 s (0.02 %) - deduplicated arrays in 1.287e-05 s (0.03 %) - sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 9.596e-03 s (25.43 %) - memory allocations took 5.960e-06 s (0.02 %) - leafs setup took 5.960e-06 s (0.02 %) - halfword conversion took 1.129e-02 s (29.91 %) -Built (100 x 100)[0x556d0c3c8fc0]{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 1.759e-01 s (100.00 %) + analyzed arrays in 6.787e-02 s (38.58 %) + cleaned-up arrays in 1.788e-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 6.003e-02 s (34.12 %) + memory allocations took 2.241e-05 s (0.01 %) + leafs setup took 0.000e+00 s (0.00 %) + halfword conversion took 4.798e-02 s (27.27 %) +Built (100 x 100)[0x55abeebb5d20]{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 @@ -5846,11 +5858,11 @@ # 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 @@ -5861,11 +5873,11 @@ # 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 @@ -5875,17 +5887,17 @@ # 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 0.01715s; avg 0.005718s ( +/- 1.18/ 2.32 %); best 0.00565s; worst 0.00585s; std dev. 9.363e-05 (taking best). -Reference operation time is 0.00565004 s (3.575 Mflops) with 1 threads. -Challenging best inner round reference (1.19209e-05 s/1 threads) with: subdivision 4, 102 leaves, 2.653 bytes/nz, 0.00565004 s/0 threads (speedup 0.00210988 x), same?n. -New candidate clone performs slowly; discarding it: 100 x 100, type D, 5050 nnz, 50 nnz/r, 138 subms, 102 lsubms, 2.6535 bpnz -Best sparse multiply performance with subdivision multiplier of 1: 1694.5 Mflops. +3 iterations (1 th.) took 0.07948s; avg 0.02649s ( +/- 9.34/ 5.61 %); best 0.02402s; worst 0.02798s; std dev. 0.001762 (taking best). +Reference operation time is 0.024018 s (0.841 Mflops) with 1 threads. +Challenging best inner round reference (1.38283e-05 s/1 threads) with: subdivision 4, 120 leaves, 2.726 bytes/nz, 0.024018 s/0 threads (speedup 0.000575745 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 @@ -5895,29 +5907,29 @@ # 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 0.34935 s (eq. to 3e+04/ 3e+04 old/new op.times), gained local/global speedup 1 x (1.19209e-05 : 1.19209e-05) / 1 x (1.19209e-05 : 1.19209e-05). This is not amortizable ! +Last tuner inner round (1 of 1) took 1.74366 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. 0.35s, 0.23s for constructor, 0 clones) obtained NO speedup (best stays 1694 Mflops). -Second run of RSB Autotuner took 0.349383 s and estimated a speedup of 1.000000 x (1.192e-05 s -> 1.192e-05 s per op) in same matrix (1 -> 1 lsubm) +In 1 tuning rounds (tot. 1.7s, 1.2s for constructor, 0 clones) obtained NO speedup (best stays 1461 Mflops). +Second run of RSB Autotuner took 1.74379 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 0.014812 0.030223 0.045035 -%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.045035 -%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.014812 -%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.030223 -%: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 0.045035 +%:CONSTRUCTOR_TIMES:lower-100x100-5050nz S N 1 100 100 5050 0.000001 0.076214 0.111957 0.188171 +%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.188172 +%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.076214 +%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.111957 +%: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 0.188171 %: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 @@ -5926,45 +5938,45 @@ %: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 0.0637958 1e+09 1e+09 +%operation:lower-100x100-5050nz 0.240219 1e+09 1e+09 %constructor:matrix SORT[1] SCAN[1] SHUFFLE[1] INSERT[1] -%constructor:lower-100x100-5050nz 0 0.014812 0 0.0302231 -# so far, program took 7.884s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.514s/0.000s . +%constructor:lower-100x100-5050nz 9.53674e-07 0.0762141 0 0.111957 +# so far, program took 9.153s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 2.452s/0.000s . getrusage() stats: -ru_maxrss: 30 (maximum resident set size -- MB) -ru_stime : 0.19s (system CPU time used) -ru_utime : 18.48s (user CPU time used) +ru_maxrss: 7 (maximum resident set size -- MB) +ru_stime : 0.04751s (system CPU time used) +ru_utime : 16.98s (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 7.884s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.514s/0.000s . +# Cache block size total 524288 bytes, per-thread 524288 bytes +# so far, program took 9.153s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 2.452s/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 4.876e-02 s (100.00 %) - analyzed arrays in 9.281e-03 s (19.03 %) - cleaned-up arrays in 7.868e-06 s (0.02 %) - deduplicated arrays in 1.311e-05 s (0.03 %) - sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 2.628e-02 s (53.90 %) - memory allocations took 3.099e-06 s (0.01 %) - leafs setup took 1.907e-06 s (0.00 %) - halfword conversion took 1.317e-02 s (27.01 %) -Built (100 x 100)[0x556d0c3a2350]{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 0.049s): (100 x 100)[0x556d0c3a2350]{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 2.033e-01 s (100.00 %) + analyzed arrays in 4.331e-02 s (21.31 %) + cleaned-up arrays in 1.383e-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 1.119e-01 s (55.07 %) + memory allocations took 5.960e-06 s (0.00 %) + leafs setup took 7.153e-06 s (0.00 %) + halfword conversion took 4.798e-02 s (23.60 %) +Built (100 x 100)[0x55abeeb8f080]{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 0.203s): (100 x 100)[0x55abeeb8f080]{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 @@ -5975,11 +5987,11 @@ # 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 @@ -5990,11 +6002,11 @@ # 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 @@ -6004,16 +6016,16 @@ # 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 0.02254s; avg 0.007512s ( +/- 0.16/ 0.17 %); best 0.0075s; worst 0.007525s; std dev. 1.013e-05 (taking best). -Reference operation time is 0.00750017 s (2.693 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: 0.0075 Mflops: 2.693) -Merge (3 -> 1 leaves) took w.c.t. of 4.911e-05s, ~4.101e-05s of computing time (of which 1.597e-05s sorting, 2.146e-06s analysis) +3 iterations (1 th.) took 0.1079s; avg 0.03598s ( +/- 33.22/ 33.36 %); best 0.02403s; worst 0.04798s; std dev. 0.009779 (taking best). +Reference operation time is 0.0240262 s (0.8408 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: 0.02403 Mflops: 0.841) +Merge (3 -> 1 leaves) took w.c.t. of 0.000133s, ~0.0001121s of computing time (of which 0s sorting, 2.098e-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 @@ -6024,11 +6036,11 @@ # 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 @@ -6038,14 +6050,14 @@ # 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 3.791e-05s; avg 1.264e-05s ( +/- 5.66/ 11.32 %); best 1.192e-05s; worst 1.407e-05s; std dev. 1.012e-06 (taking best). -Reference operation time is 1.19209e-05 s (1694 Mflops) with 1 threads. +3 iterations (1 th.) took 0s; avg 0s ( +/- -inf/ -nan %); best 4.856e-06s; worst 0s; std dev. 0 (taking best). +Reference operation time is 4.85625e-06 s (4160 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 @@ -6055,25 +6067,25 @@ # 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 629.160x: 0.0075s -> 1.192e-05s, so taking this instance. +After merge step 1: tpop: 4.856e-06 s ~Mflops: 4159.586 nsubm:1 otn:1 +Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 4947.468x: 0.02403s -> 4.856e-06s, 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 0.06048s (of which 5.198e-05s partitioning, 0.03777s I/O); computing times: 4.101e-05s in par. loops, 1.597e-05s sorting, 2.146e-06s analyzing) -Total merge + benchmarking process took 0.06048s, equivalent to 5073.5/8.1 new/old ops (0.04139s for 2 clones -- as 3472.0/5.5 ops, or 1736.0/2.8 ops per clone), SPEEDUP of 629.160x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 629.160x (0.0075s -> 1.192e-05s), will amortize in 8.1 ops by saving 0.007488s per op. -In 1 tuning rounds (tot. 0.1s, 0.041s for constructor, 2 clones) obtained a SPEEDUP of 62816.0% (629.2x) (from 2.693 to 1694 Mflops). Employed 0.036s for I/O of matrix plots. +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.2884s (of which 0.0001459s partitioning, 0.1798s I/O); computing times: 0.0001121s in par. loops, 0s sorting, 2.098e-05s analyzing) +Total merge + benchmarking process took 0.2884s, equivalent to 59383.9/12.0 new/old ops (0.2036s for 2 clones -- as 41934.7/8.5 ops, or 20967.4/4.2 ops per clone), SPEEDUP of 4947.468x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 4947.468x (0.02403s -> 4.856e-06s), will amortize in 12.0 ops by saving 0.02402s per op. +In 1 tuning rounds (tot. 0.49s, 0.2s for constructor, 2 clones) obtained a SPEEDUP of 494646.8% (4947x) (from 0.8408 to 4160 Mflops). Employed 0.2s 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 0.137545 s (7.500e-03 s -> 1.192e-05 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.692403 s (2.403e-02 s -> 4.856e-06 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 @@ -6084,11 +6096,11 @@ # 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 @@ -6099,13 +6111,13 @@ # 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 @@ -6116,11 +6128,11 @@ # 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 @@ -6130,27 +6142,27 @@ # 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 3.791e-05s; avg 1.264e-05s ( +/- 5.66/ 9.43 %); best 1.192e-05s; worst 1.383e-05s; std dev. 8.485e-07 (taking best). +3 iterations (1 th.) took 4.911e-05s; avg 1.637e-05s ( +/- 27.18/ 52.91 %); best 1.192e-05s; worst 2.503e-05s; std dev. 6.126e-06 (taking best). Reference operation time is 1.19209e-05 s (1694 Mflops) with 1 threads. Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 2.101e-02 s (100.00 %) - analyzed arrays in 7.758e-03 s (36.93 %) - cleaned-up arrays in 7.868e-06 s (0.04 %) - deduplicated arrays in 1.192e-05 s (0.06 %) - sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.317e-02 s (62.70 %) - memory allocations took 5.341e-05 s (0.25 %) - leafs setup took 2.146e-06 s (0.01 %) - halfword conversion took 2.861e-06 s (0.01 %) -Built (100 x 100)[0x556d0c3a2230]{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 + converted COO to RSB in 1.053e-01 s (100.00 %) + analyzed arrays in 4.732e-02 s (44.92 %) + cleaned-up arrays in 1.383e-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 5.797e-02 s (55.04 %) + memory allocations took 1.121e-05 s (0.01 %) + leafs setup took 0.000e+00 s (0.00 %) + halfword conversion took 0.000e+00 s (0.00 %) +Built (100 x 100)[0x55abeeb8ef60]{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 @@ -6161,12 +6173,12 @@ # 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 @@ -6177,22 +6189,22 @@ # 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 1.625e-02 s (100.00 %) - analyzed arrays in 1.064e-02 s (65.45 %) - cleaned-up arrays in 7.868e-06 s (0.05 %) - deduplicated arrays in 1.311e-05 s (0.08 %) - sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 5.588e-03 s (34.39 %) - memory allocations took 9.537e-07 s (0.01 %) + converted COO to RSB in 1.496e-01 s (100.00 %) + analyzed arrays in 4.961e-02 s (33.15 %) + cleaned-up arrays in 1.383e-05 s (0.01 %) + deduplicated arrays in 1.383e-05 s (0.01 %) + sorted arrays in 1.192e-06 s (0.00 %) + shuffled partitions in 4.795e-02 s (32.05 %) + memory allocations took 6.199e-06 s (0.00 %) leafs setup took 0.000e+00 s (0.00 %) - halfword conversion took 3.815e-06 s (0.02 %) -Built (100 x 100)[0x556d0c394200]{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' + halfword conversion took 5.203e-02 s (34.77 %) +Built (100 x 100)[0x55abeeb84370]{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 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 @@ -6203,11 +6215,11 @@ # 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 @@ -6218,11 +6230,11 @@ # 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 @@ -6232,16 +6244,16 @@ # 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 3.791e-05s; avg 1.264e-05s ( +/- 5.66/ 11.32 %); best 1.192e-05s; worst 1.407e-05s; std dev. 1.012e-06 (taking best). -Reference operation time is 1.19209e-05 s (1694 Mflops) with 1 threads. -Challenging best inner round reference (1.19209e-05 s/1 threads) with: subdivision 0.25, 1 leaves, 2.08 bytes/nz, 1.19209e-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 0.08002s; avg 0.02667s ( +/- 40.03/ 20.08 %); best 0.016s; worst 0.03203s; std dev. 0.00755 (taking best). +Reference operation time is 0.015996 s (1.263 Mflops) with 1 threads. +Challenging best inner round reference (1.19209e-05 s/1 threads) with: subdivision 0.25, 3 leaves, 2.121 bytes/nz, 0.015996 s/0 threads (speedup 0.000745245 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 @@ -6252,12 +6264,12 @@ # 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 @@ -6268,22 +6280,22 @@ # 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 2.740e-02 s (100.00 %) - analyzed arrays in 3.967e-03 s (14.48 %) - cleaned-up arrays in 8.106e-06 s (0.03 %) - deduplicated arrays in 1.192e-05 s (0.04 %) + converted COO to RSB in 1.838e-01 s (100.00 %) + analyzed arrays in 3.988e-02 s (21.70 %) + cleaned-up arrays in 0.000e+00 s (0.00 %) + deduplicated arrays in 0.000e+00 s (0.00 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 9.692e-03 s (35.37 %) - memory allocations took 2.861e-06 s (0.01 %) - leafs setup took 2.861e-06 s (0.01 %) - halfword conversion took 1.372e-02 s (50.05 %) -Built (100 x 100)[0x556d0c394200]{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 6.465e-02 s (35.17 %) + memory allocations took 0.000e+00 s (0.00 %) + leafs setup took 2.217e-05 s (0.01 %) + halfword conversion took 7.926e-02 s (43.12 %) +Built (100 x 100)[0x55abeeb84370]{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 @@ -6294,11 +6306,11 @@ # 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 @@ -6309,11 +6321,11 @@ # 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 @@ -6323,16 +6335,16 @@ # 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 0.0244s; avg 0.008132s ( +/- 7.01/ 8.76 %); best 0.007562s; worst 0.008845s; std dev. 0.0005334 (taking best). -Reference operation time is 0.00756192 s (2.671 Mflops) with 1 threads. -Challenging best inner round reference (1.19209e-05 s/1 threads) with: subdivision 0.5, 6 leaves, 2.163 bytes/nz, 0.00756192 s/0 threads (speedup 0.00157644 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 0.09945s; avg 0.03315s ( +/- 27.67/ 20.98 %); best 0.02398s; worst 0.0401s; std dev. 0.006769 (taking best). +Reference operation time is 0.023977 s (0.8425 Mflops) with 1 threads. +Challenging best inner round reference (1.19209e-05 s/1 threads) with: subdivision 0.5, 8 leaves, 2.185 bytes/nz, 0.023977 s/0 threads (speedup 0.000497181 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 @@ -6343,12 +6355,12 @@ # 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 @@ -6359,22 +6371,22 @@ # 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 3.912e-02 s (100.00 %) - analyzed arrays in 1.176e-02 s (30.05 %) - cleaned-up arrays in 8.106e-06 s (0.02 %) - deduplicated arrays in 1.192e-05 s (0.03 %) + converted COO to RSB in 2.118e-01 s (100.00 %) + analyzed arrays in 8.380e-02 s (39.57 %) + cleaned-up arrays in 1.383e-05 s (0.01 %) + deduplicated arrays in 1.311e-05 s (0.01 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.163e-02 s (29.72 %) - memory allocations took 3.815e-06 s (0.01 %) - leafs setup took 1.907e-06 s (0.00 %) - halfword conversion took 1.571e-02 s (40.17 %) -Built (100 x 100)[0x556d0c3a2350]{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 5.588e-02 s (26.38 %) + memory allocations took 2.289e-05 s (0.01 %) + leafs setup took 1.311e-05 s (0.01 %) + halfword conversion took 7.205e-02 s (34.02 %) +Built (100 x 100)[0x55abeeb8f080]{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 @@ -6385,11 +6397,11 @@ # 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 @@ -6400,11 +6412,11 @@ # 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 @@ -6414,16 +6426,16 @@ # 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 0.02475s; avg 0.008251s ( +/- 6.64/ 4.52 %); best 0.007703s; worst 0.008624s; std dev. 0.0003956 (taking best). -Reference operation time is 0.00770307 s (2.622 Mflops) with 1 threads. -Challenging best inner round reference (1.19209e-05 s/1 threads) with: subdivision 1, 16 leaves, 2.25 bytes/nz, 0.00770307 s/0 threads (speedup 0.00154756 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 0.136s; avg 0.04534s ( +/- 11.93/ 6.25 %); best 0.03993s; worst 0.04818s; std dev. 0.003828 (taking best). +Reference operation time is 0.039932 s (0.5059 Mflops) with 1 threads. +Challenging best inner round reference (1.19209e-05 s/1 threads) with: subdivision 1, 19 leaves, 2.272 bytes/nz, 0.039932 s/0 threads (speedup 0.000298531 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 @@ -6434,12 +6446,12 @@ # 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 @@ -6450,22 +6462,22 @@ # 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 5.086e-02 s (100.00 %) - analyzed arrays in 2.237e-02 s (43.98 %) - cleaned-up arrays in 7.868e-06 s (0.02 %) - deduplicated arrays in 1.311e-05 s (0.03 %) - sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.612e-02 s (31.70 %) - memory allocations took 4.053e-06 s (0.01 %) - leafs setup took 4.053e-06 s (0.01 %) - halfword conversion took 1.234e-02 s (24.25 %) -Built (100 x 100)[0x556d0c3a2350]{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 2.997e-01 s (100.00 %) + analyzed arrays in 8.336e-02 s (27.82 %) + cleaned-up arrays in 1.192e-05 s (0.00 %) + deduplicated arrays in 1.192e-05 s (0.00 %) + sorted arrays in 9.537e-07 s (0.00 %) + shuffled partitions in 1.162e-01 s (38.78 %) + memory allocations took 2.527e-05 s (0.01 %) + leafs setup took 1.693e-05 s (0.01 %) + halfword conversion took 1.000e-01 s (33.38 %) +Built (100 x 100)[0x55abeeba2160]{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 @@ -6476,11 +6488,11 @@ # 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 @@ -6491,11 +6503,11 @@ # 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 @@ -6505,16 +6517,16 @@ # 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 0.01714s; avg 0.005713s ( +/- 34.44/ 35.72 %); best 0.003745s; worst 0.007753s; std dev. 0.001637 (taking best). -Reference operation time is 0.00374508 s (5.394 Mflops) with 1 threads. -Challenging best inner round reference (1.19209e-05 s/1 threads) with: subdivision 2, 37 leaves, 2.385 bytes/nz, 0.00374508 s/0 threads (speedup 0.00318309 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 0.1197s; avg 0.03989s ( +/- 29.97/ 30.26 %); best 0.02794s; worst 0.05196s; std dev. 0.009809 (taking best). +Reference operation time is 0.027936 s (0.7231 Mflops) with 1 threads. +Challenging best inner round reference (1.19209e-05 s/1 threads) with: subdivision 2, 42 leaves, 2.409 bytes/nz, 0.027936 s/0 threads (speedup 0.000426723 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 @@ -6525,12 +6537,12 @@ # 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 @@ -6541,22 +6553,22 @@ # 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 4.453e-02 s (100.00 %) - analyzed arrays in 2.202e-02 s (49.46 %) - cleaned-up arrays in 8.106e-06 s (0.02 %) - deduplicated arrays in 1.287e-05 s (0.03 %) - sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 9.500e-03 s (21.33 %) - memory allocations took 5.007e-06 s (0.01 %) - leafs setup took 5.960e-06 s (0.01 %) - halfword conversion took 1.297e-02 s (29.13 %) -Built (100 x 100)[0x556d0c3b5400]{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: 80, 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 2.879e-01 s (100.00 %) + analyzed arrays in 1.078e-01 s (37.45 %) + cleaned-up arrays in 1.407e-05 s (0.00 %) + deduplicated arrays in 1.287e-05 s (0.00 %) + sorted arrays in 9.537e-07 s (0.00 %) + shuffled partitions in 8.405e-02 s (29.20 %) + memory allocations took 2.718e-05 s (0.01 %) + leafs setup took 2.313e-05 s (0.01 %) + halfword conversion took 9.591e-02 s (33.32 %) +Built (100 x 100)[0x55abeeba2160]{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 @@ -6567,11 +6579,11 @@ # 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 @@ -6582,11 +6594,11 @@ # 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 @@ -6596,17 +6608,17 @@ # 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 0.02068s; avg 0.006892s ( +/- 18.95/ 36.91 %); best 0.005586s; worst 0.009436s; std dev. 0.001799 (taking best). -Reference operation time is 0.00558615 s (3.616 Mflops) with 1 threads. -Challenging best inner round reference (1.19209e-05 s/1 threads) with: subdivision 4, 80 leaves, 2.558 bytes/nz, 0.00558615 s/0 threads (speedup 0.00213402 x), same?n. -New candidate clone performs slowly; discarding it: 100 x 100, type S, 5050 nnz, 50 nnz/r, 108 subms, 80 lsubms, 2.5584 bpnz +3 iterations (1 th.) took 0.128s; avg 0.04265s ( +/- 15.81/ 12.59 %); best 0.03591s; worst 0.04802s; std dev. 0.00504 (taking best). +Reference operation time is 0.0359089 s (0.5625 Mflops) with 1 threads. +Challenging best inner round reference (1.19209e-05 s/1 threads) with: subdivision 4, 90 leaves, 2.606 bytes/nz, 0.0359089 s/0 threads (speedup 0.000331977 x), same?n. +New candidate clone performs slowly; discarding it: 100 x 100, type S, 5050 nnz, 50 nnz/r, 122 subms, 90 lsubms, 2.6059 bpnz Best sparse multiply performance with subdivision multiplier of 1: 1694.5 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 @@ -6616,29 +6628,29 @@ # 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 0.286988 s (eq. to 2e+04/ 2e+04 old/new op.times), gained local/global speedup 1 x (1.19209e-05 : 1.19209e-05) / 1 x (1.19209e-05 : 1.19209e-05). This is not amortizable ! +Last tuner inner round (1 of 1) took 1.8125 s (eq. to 2e+05/ 2e+05 old/new op.times), gained local/global speedup 1 x (1.19209e-05 : 1.19209e-05) / 1 x (1.19209e-05 : 1.19209e-05). This is not amortizable ! Auto tuning inner round 1 did not find a configuration better than the original. -In 1 tuning rounds (tot. 0.29s, 0.2s for constructor, 0 clones) obtained NO speedup (best stays 1694 Mflops). -Second run of RSB Autotuner took 0.287018 s and estimated a speedup of 1.000000 x (1.192e-05 s -> 1.192e-05 s per op) in same matrix (1 -> 1 lsubm) +In 1 tuning rounds (tot. 1.8s, 1.2s for constructor, 0 clones) obtained NO speedup (best stays 1694 Mflops). +Second run of RSB Autotuner took 1.81258 s and estimated a speedup of 1.000000 x (1.192e-05 s -> 1.192e-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 0.009281 0.026280 0.035561 -%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.035561 -%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.009281 -%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.026280 -%: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 0.035561 +%:CONSTRUCTOR_TIMES:lower-100x100-5050nz S N 1 100 100 5050 0.000001 0.043315 0.111945 0.155260 +%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.155261 +%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.043315 +%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.111945 +%: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 0.155260 %: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 @@ -6647,45 +6659,45 @@ %: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 0.048759 1e+09 1e+09 +%operation:lower-100x100-5050nz 0.203288 1e+09 1e+09 %constructor:matrix SORT[1] SCAN[1] SHUFFLE[1] INSERT[1] -%constructor:lower-100x100-5050nz 0 0.00928092 0 0.0262802 -# so far, program took 8.394s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.938s/0.000s . +%constructor:lower-100x100-5050nz 9.53674e-07 0.0433149 0 0.111945 +# so far, program took 12.068s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 4.957s/0.000s . getrusage() stats: -ru_maxrss: 30 (maximum resident set size -- MB) -ru_stime : 0.1997s (system CPU time used) -ru_utime : 28.66s (user CPU time used) +ru_maxrss: 7 (maximum resident set size -- MB) +ru_stime : 0.0506s (system CPU time used) +ru_utime : 32.47s (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 8.394s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.938s/0.000s . +# Cache block size total 524288 bytes, per-thread 524288 bytes +# so far, program took 12.068s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 4.957s/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 4.994e-02 s (100.00 %) - analyzed arrays in 9.871e-03 s (19.76 %) - cleaned-up arrays in 7.868e-06 s (0.02 %) - deduplicated arrays in 1.311e-05 s (0.03 %) + converted COO to RSB in 3.034e-01 s (100.00 %) + analyzed arrays in 5.587e-02 s (18.41 %) + cleaned-up arrays in 1.502e-05 s (0.00 %) + deduplicated arrays in 1.287e-05 s (0.00 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 3.249e-02 s (65.05 %) - memory allocations took 4.053e-06 s (0.01 %) - leafs setup took 9.537e-07 s (0.00 %) - halfword conversion took 7.557e-03 s (15.13 %) -Built (100 x 100)[0x556d0c3a2350]{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 0.050s): (100 x 100)[0x556d0c3a2350]{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' + shuffled partitions in 1.515e-01 s (49.93 %) + memory allocations took 1.621e-05 s (0.01 %) + leafs setup took 8.821e-06 s (0.00 %) + halfword conversion took 9.598e-02 s (31.64 %) +Built (100 x 100)[0x55abeeb8f080]{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 0.303s): (100 x 100)[0x55abeeb8f080]{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 @@ -6696,11 +6708,11 @@ # 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 @@ -6711,11 +6723,11 @@ # 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 @@ -6725,16 +6737,16 @@ # 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 0.01532s; avg 0.005108s ( +/- 61.49/ 50.90 %); best 0.001967s; worst 0.007708s; std dev. 0.002375 (taking best). -Reference operation time is 0.00196695 s (41.08 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: 0.001967 Mflops: 41.079) -Merge (3 -> 1 leaves) took w.c.t. of 5.102e-05s, ~4.315e-05s of computing time (of which 1.693e-05s sorting, 1.907e-06s analysis) +3 iterations (1 th.) took 0.1201s; avg 0.04003s ( +/- 10.09/ 9.78 %); best 0.03599s; worst 0.04395s; std dev. 0.00325 (taking best). +Reference operation time is 0.035989 s (2.245 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: 0.03599 Mflops: 2.245) +Merge (3 -> 1 leaves) took w.c.t. of 0.0001221s, ~9.108e-05s of computing time (of which 4.101e-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 @@ -6745,11 +6757,11 @@ # 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 @@ -6759,14 +6771,14 @@ # 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 0.0001099s; avg 3.664e-05s ( +/- 4.34/ 3.47 %); best 3.505e-05s; worst 3.791e-05s; std dev. 1.189e-06 (taking best). -Reference operation time is 3.50475e-05 s (2305 Mflops) with 1 threads. +3 iterations (1 th.) took 0.0001109s; avg 3.695e-05s ( +/- 16.13/ 29.68 %); best 3.099e-05s; worst 4.792e-05s; std dev. 7.765e-06 (taking best). +Reference operation time is 3.09944e-05 s (2607 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 @@ -6776,25 +6788,25 @@ # 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: 3.505e-05 s ~Mflops: 2305.441 nsubm:1 otn:1 -Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 56.122x: 0.001967s -> 3.505e-05s, so taking this instance. +After merge step 1: tpop: 3.099e-05 s ~Mflops: 2606.921 nsubm:1 otn:1 +Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 1161.146x: 0.03599s -> 3.099e-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 0.04774s (of which 5.412e-05s partitioning, 0.02784s I/O); computing times: 4.315e-05s in par. loops, 1.693e-05s sorting, 1.907e-06s analyzing) -Total merge + benchmarking process took 0.04774s, equivalent to 1362.1/24.3 new/old ops (0.0373s for 2 clones -- as 1064.1/19.0 ops, or 532.1/9.5 ops per clone), SPEEDUP of 56.122x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 56.122x (0.001967s -> 3.505e-05s), will amortize in 24.7 ops by saving 0.001932s per op. -In 1 tuning rounds (tot. 0.081s, 0.037s for constructor, 2 clones) obtained a SPEEDUP of 5512.2% (56.12x) (from 41.08 to 2305 Mflops). Employed 0.037s for I/O of matrix plots. +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.3s (of which 0.000128s partitioning, 0.1961s I/O); computing times: 9.108e-05s in par. loops, 4.101e-05s sorting, 7.868e-06s analyzing) +Total merge + benchmarking process took 0.3s, equivalent to 9678.0/8.3 new/old ops (0.2025s for 2 clones -- as 6533.9/5.6 ops, or 3266.9/2.8 ops per clone), SPEEDUP of 1161.146x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 1161.146x (0.03599s -> 3.099e-05s), will amortize in 8.3 ops by saving 0.03596s per op. +In 1 tuning rounds (tot. 0.52s, 0.2s for constructor, 2 clones) obtained a SPEEDUP of 116014.6% (1161x) (from 2.245 to 2607 Mflops). Employed 0.21s 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 0.117645 s (1.967e-03 s -> 3.505e-05 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.728092 s (3.599e-02 s -> 3.099e-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 @@ -6805,11 +6817,11 @@ # 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 @@ -6820,13 +6832,13 @@ # 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 @@ -6837,11 +6849,11 @@ # 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 @@ -6851,27 +6863,27 @@ # 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 ( +/- 2.53/ 4.51 %); best 4.292e-05s; worst 4.601e-05s; std dev. 1.408e-06 (taking best). -Reference operation time is 4.29153e-05 s (1883 Mflops) with 1 threads. +3 iterations (1 th.) took 0.000113s; avg 3.767e-05s ( +/- 17.72/ 35.44 %); best 3.099e-05s; worst 5.102e-05s; std dev. 9.441e-06 (taking best). +Reference operation time is 3.09944e-05 s (2607 Mflops) with 1 threads. Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 2.486e-02 s (100.00 %) - analyzed arrays in 6.861e-03 s (27.59 %) - cleaned-up arrays in 8.106e-06 s (0.03 %) - deduplicated arrays in 1.192e-05 s (0.05 %) - sorted arrays in 9.537e-07 s (0.00 %) - shuffled partitions in 1.798e-02 s (72.30 %) - memory allocations took 1.907e-06 s (0.01 %) - leafs setup took 9.537e-07 s (0.00 %) - halfword conversion took 2.861e-06 s (0.01 %) -Built (100 x 100)[0x556d0c3a2230]{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 + converted COO to RSB in 1.311e-01 s (100.00 %) + analyzed arrays in 5.510e-02 s (42.03 %) + cleaned-up arrays in 1.287e-05 s (0.01 %) + deduplicated arrays in 1.311e-05 s (0.01 %) + sorted arrays in 0.000e+00 s (0.00 %) + shuffled partitions in 7.594e-02 s (57.92 %) + memory allocations took 8.821e-06 s (0.01 %) + leafs setup took 7.868e-06 s (0.01 %) + halfword conversion took 2.217e-05 s (0.02 %) +Built (100 x 100)[0x55abeeb8ef60]{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 @@ -6882,12 +6894,12 @@ # 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 @@ -6898,22 +6910,22 @@ # 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 4.290e-02 s (100.00 %) - analyzed arrays in 1.117e-02 s (26.05 %) - cleaned-up arrays in 7.868e-06 s (0.02 %) - deduplicated arrays in 1.216e-05 s (0.03 %) + converted COO to RSB in 1.798e-01 s (100.00 %) + analyzed arrays in 4.785e-02 s (26.61 %) + cleaned-up arrays in 1.383e-05 s (0.01 %) + deduplicated arrays in 1.311e-05 s (0.01 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.426e-02 s (33.24 %) - memory allocations took 2.861e-06 s (0.01 %) - leafs setup took 9.537e-07 s (0.00 %) - halfword conversion took 1.744e-02 s (40.65 %) -Built (100 x 100)[0x556d0c394200]{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 6.835e-02 s (38.02 %) + memory allocations took 1.621e-05 s (0.01 %) + leafs setup took 7.868e-06 s (0.00 %) + halfword conversion took 6.354e-02 s (35.34 %) +Built (100 x 100)[0x55abeeb84990]{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 @@ -6924,11 +6936,11 @@ # 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 @@ -6939,11 +6951,11 @@ # 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 @@ -6953,16 +6965,16 @@ # 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 0.02302s; avg 0.007672s ( +/- 25.67/ 25.05 %); best 0.005703s; worst 0.009594s; std dev. 0.001589 (taking best). -Reference operation time is 0.00570297 s (14.17 Mflops) with 1 threads. -Challenging best inner round reference (4.29153e-05 s/1 threads) with: subdivision 0.25, 3 leaves, 2.121 bytes/nz, 0.00570297 s/0 threads (speedup 0.00752508 x), same?n. +3 iterations (1 th.) took 0.1159s; avg 0.03863s ( +/- 17.93/ 23.85 %); best 0.03171s; worst 0.04784s; std dev. 0.006785 (taking best). +Reference operation time is 0.0317061 s (2.548 Mflops) with 1 threads. +Challenging best inner round reference (3.09944e-05 s/1 threads) with: subdivision 0.25, 3 leaves, 2.121 bytes/nz, 0.0317061 s/0 threads (speedup 0.000977554 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 @@ -6973,12 +6985,12 @@ # 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 @@ -6989,22 +7001,22 @@ # 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 4.396e-02 s (100.00 %) - analyzed arrays in 1.176e-02 s (26.75 %) - cleaned-up arrays in 7.868e-06 s (0.02 %) - deduplicated arrays in 1.311e-05 s (0.03 %) + converted COO to RSB in 2.075e-01 s (100.00 %) + analyzed arrays in 7.547e-02 s (36.37 %) + cleaned-up arrays in 1.502e-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 1.586e-02 s (36.07 %) - memory allocations took 2.861e-06 s (0.01 %) - leafs setup took 2.146e-06 s (0.00 %) - halfword conversion took 1.632e-02 s (37.12 %) -Built (100 x 100)[0x556d0c394200]{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 6.798e-02 s (32.76 %) + memory allocations took 1.788e-05 s (0.01 %) + leafs setup took 1.001e-05 s (0.00 %) + halfword conversion took 6.400e-02 s (30.84 %) +Built (100 x 100)[0x55abeeb8f080]{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 @@ -7015,11 +7027,11 @@ # 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 @@ -7030,11 +7042,11 @@ # 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 @@ -7044,16 +7056,16 @@ # 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 0.02383s; avg 0.007944s ( +/- 29.47/ 34.18 %); best 0.005603s; worst 0.01066s; std dev. 0.002081 (taking best). -Reference operation time is 0.00560308 s (14.42 Mflops) with 1 threads. -Challenging best inner round reference (4.29153e-05 s/1 threads) with: subdivision 0.5, 10 leaves, 2.206 bytes/nz, 0.00560308 s/0 threads (speedup 0.00765925 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 0.1037s; avg 0.03455s ( +/- 7.29/ 4.59 %); best 0.03203s; worst 0.03613s; std dev. 0.0018 (taking best). +Reference operation time is 0.032032 s (2.522 Mflops) with 1 threads. +Challenging best inner round reference (3.09944e-05 s/1 threads) with: subdivision 0.5, 12 leaves, 2.217 bytes/nz, 0.032032 s/0 threads (speedup 0.000967607 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 @@ -7064,12 +7076,12 @@ # 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 @@ -7080,22 +7092,22 @@ # 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 4.084e-02 s (100.00 %) - analyzed arrays in 1.317e-02 s (32.26 %) - cleaned-up arrays in 8.106e-06 s (0.02 %) - deduplicated arrays in 1.192e-05 s (0.03 %) - sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.374e-02 s (33.64 %) - memory allocations took 3.815e-06 s (0.01 %) - leafs setup took 3.099e-06 s (0.01 %) - halfword conversion took 1.390e-02 s (34.03 %) -Built (100 x 100)[0x556d0c3a2350]{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 2.213e-01 s (100.00 %) + analyzed arrays in 8.385e-02 s (37.88 %) + cleaned-up arrays in 1.311e-05 s (0.01 %) + deduplicated arrays in 1.192e-05 s (0.01 %) + sorted arrays in 9.537e-07 s (0.00 %) + shuffled partitions in 6.774e-02 s (30.60 %) + memory allocations took 1.788e-05 s (0.01 %) + leafs setup took 1.478e-05 s (0.01 %) + halfword conversion took 6.969e-02 s (31.49 %) +Built (100 x 100)[0x55abeeb8f080]{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: 27, 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 @@ -7106,11 +7118,11 @@ # 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 @@ -7121,11 +7133,11 @@ # 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 @@ -7135,16 +7147,16 @@ # 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 0.0212s; avg 0.007067s ( +/- 19.30/ 36.13 %); best 0.005703s; worst 0.00962s; std dev. 0.001807 (taking best). -Reference operation time is 0.00570297 s (14.17 Mflops) with 1 threads. -Challenging best inner round reference (4.29153e-05 s/1 threads) with: subdivision 1, 22 leaves, 2.295 bytes/nz, 0.00570297 s/0 threads (speedup 0.00752508 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 0.106s; avg 0.03533s ( +/- 31.79/ 19.07 %); best 0.0241s; worst 0.04206s; std dev. 0.007993 (taking best). +Reference operation time is 0.024096 s (3.353 Mflops) with 1 threads. +Challenging best inner round reference (3.09944e-05 s/1 threads) with: subdivision 1, 27 leaves, 2.328 bytes/nz, 0.024096 s/0 threads (speedup 0.00128629 x), same?n. +New candidate clone performs slowly; discarding it: 100 x 100, type C, 5050 nnz, 50 nnz/r, 37 subms, 27 lsubms, 2.3279 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 @@ -7155,12 +7167,12 @@ # 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 @@ -7171,22 +7183,22 @@ # 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 3.936e-02 s (100.00 %) - analyzed arrays in 1.511e-02 s (38.38 %) - cleaned-up arrays in 7.868e-06 s (0.02 %) - deduplicated arrays in 1.216e-05 s (0.03 %) + converted COO to RSB in 2.197e-01 s (100.00 %) + analyzed arrays in 8.369e-02 s (38.10 %) + cleaned-up arrays in 1.311e-05 s (0.01 %) + deduplicated arrays in 1.287e-05 s (0.01 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 9.532e-03 s (24.22 %) - memory allocations took 8.106e-06 s (0.02 %) - leafs setup took 5.007e-06 s (0.01 %) - halfword conversion took 1.469e-02 s (37.32 %) -Built (100 x 100)[0x556d0c3c8fc0]{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: 50, 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 6.795e-02 s (30.93 %) + memory allocations took 3.004e-05 s (0.01 %) + leafs setup took 1.788e-05 s (0.01 %) + halfword conversion took 6.797e-02 s (30.94 %) +Built (100 x 100)[0x55abeebb5d20]{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 @@ -7197,11 +7209,11 @@ # 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 @@ -7212,11 +7224,11 @@ # 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 @@ -7226,16 +7238,16 @@ # 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 0.01487s; avg 0.004958s ( +/- 26.40/ 15.03 %); best 0.003649s; worst 0.005703s; std dev. 0.0009285 (taking best). -Reference operation time is 0.003649 s (22.14 Mflops) with 1 threads. -Challenging best inner round reference (4.29153e-05 s/1 threads) with: subdivision 2, 50 leaves, 2.436 bytes/nz, 0.003649 s/0 threads (speedup 0.0117609 x), same?n. -New candidate clone performs slowly; discarding it: 100 x 100, type C, 5050 nnz, 50 nnz/r, 68 subms, 50 lsubms, 2.4364 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 0.1356s; avg 0.04521s ( +/- 21.54/ 14.98 %); best 0.03548s; worst 0.05199s; std dev. 0.007059 (taking best). +Reference operation time is 0.0354772 s (2.278 Mflops) with 1 threads. +Challenging best inner round reference (3.09944e-05 s/1 threads) with: subdivision 2, 57 leaves, 2.47 bytes/nz, 0.0354772 s/0 threads (speedup 0.000873644 x), same?n. +New candidate clone performs slowly; discarding it: 100 x 100, type C, 5050 nnz, 50 nnz/r, 78 subms, 57 lsubms, 2.4705 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 @@ -7246,12 +7258,12 @@ # 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 @@ -7262,22 +7274,22 @@ # 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 3.393e-02 s (100.00 %) - analyzed arrays in 1.138e-02 s (33.55 %) - cleaned-up arrays in 9.060e-06 s (0.03 %) - deduplicated arrays in 1.879e-03 s (5.54 %) - sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.221e-02 s (35.98 %) - memory allocations took 7.868e-06 s (0.02 %) - leafs setup took 8.106e-06 s (0.02 %) - halfword conversion took 8.432e-03 s (24.85 %) -Built (100 x 100)[0x556d0c3c8fc0]{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: 101, 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 2.036e-01 s (100.00 %) + analyzed arrays in 8.757e-02 s (43.01 %) + cleaned-up arrays in 1.502e-05 s (0.01 %) + deduplicated arrays in 1.192e-05 s (0.01 %) + sorted arrays in 9.537e-07 s (0.00 %) + shuffled partitions in 4.801e-02 s (23.58 %) + memory allocations took 3.314e-05 s (0.02 %) + leafs setup took 2.193e-05 s (0.01 %) + halfword conversion took 6.795e-02 s (33.37 %) +Built (100 x 100)[0x55abeebb5d20]{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 @@ -7288,11 +7300,11 @@ # 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 @@ -7303,11 +7315,11 @@ # 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 @@ -7317,17 +7329,17 @@ # 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 0.01389s; avg 0.00463s ( +/- 15.98/ 28.48 %); best 0.00389s; worst 0.005948s; std dev. 0.0009345 (taking best). -Reference operation time is 0.00389004 s (20.77 Mflops) with 1 threads. -Challenging best inner round reference (4.29153e-05 s/1 threads) with: subdivision 4, 101 leaves, 2.642 bytes/nz, 0.00389004 s/0 threads (speedup 0.0110321 x), same?n. -New candidate clone performs slowly; discarding it: 100 x 100, type C, 5050 nnz, 50 nnz/r, 138 subms, 101 lsubms, 2.6416 bpnz -Best sparse multiply performance with subdivision multiplier of 1: 1882.78 Mflops. +3 iterations (1 th.) took 0.0835s; avg 0.02783s ( +/- 42.47/ 29.38 %); best 0.01601s; worst 0.03601s; std dev. 0.00856 (taking best). +Reference operation time is 0.0160129 s (5.046 Mflops) with 1 threads. +Challenging best inner round reference (3.09944e-05 s/1 threads) with: subdivision 4, 120 leaves, 2.726 bytes/nz, 0.0160129 s/0 threads (speedup 0.00193559 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: 2606.92 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 @@ -7337,23 +7349,23 @@ # 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 0.325755 s (eq. to 8e+03/ 8e+03 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 1.71181 s (eq. to 6e+04/ 6e+04 old/new op.times), gained local/global speedup 1 x (3.09944e-05 : 3.09944e-05) / 1 x (3.09944e-05 : 3.09944e-05). This is not amortizable ! Auto tuning inner round 1 did not find a configuration better than the original. -In 1 tuning rounds (tot. 0.33s, 0.23s for constructor, 0 clones) obtained NO speedup (best stays 1883 Mflops). -Second run of RSB Autotuner took 0.325789 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. 1.7s, 1.2s for constructor, 0 clones) obtained NO speedup (best stays 2607 Mflops). +Second run of RSB Autotuner took 1.71193 s and estimated a speedup of 1.000000 x (3.099e-05 s -> 3.099e-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 0.009871 0.032490 0.042361 -%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.042361 -%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.009871 -%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.032490 +%:CONSTRUCTOR_TIMES:lower-100x100-5050nz S N 1 100 100 5050 0.000000 0.055866 0.151486 0.207352 +%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.207352 +%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.055866 +%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.151486 %: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 0.042361 +%:SORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.207352 %: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 @@ -7368,45 +7380,45 @@ %: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 0.0499439 1e+09 1e+09 +%operation:lower-100x100-5050nz 0.303385 1e+09 1e+09 %constructor:matrix SORT[1] SCAN[1] SHUFFLE[1] INSERT[1] -%constructor:lower-100x100-5050nz 0 0.00987101 0 0.03249 -# so far, program took 8.919s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 1.382s/0.000s . +%constructor:lower-100x100-5050nz 0 0.055866 0 0.151486 +# so far, program took 14.968s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 7.397s/0.000s . getrusage() stats: -ru_maxrss: 30 (maximum resident set size -- MB) -ru_stime : 0.2225s (system CPU time used) -ru_utime : 39.66s (user CPU time used) +ru_maxrss: 7 (maximum resident set size -- MB) +ru_stime : 0.0624s (system CPU time used) +ru_utime : 47.66s (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 8.919s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 1.382s/0.000s . +# Cache block size total 524288 bytes, per-thread 524288 bytes +# so far, program took 14.968s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 7.397s/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 3.367e-02 s (100.00 %) - analyzed arrays in 5.337e-03 s (15.85 %) - cleaned-up arrays in 9.060e-06 s (0.03 %) - deduplicated arrays in 1.287e-05 s (0.04 %) + converted COO to RSB in 2.478e-01 s (100.00 %) + analyzed arrays in 4.149e-02 s (16.75 %) + cleaned-up arrays in 1.502e-05 s (0.01 %) + deduplicated arrays in 1.311e-05 s (0.01 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.861e-02 s (55.26 %) - memory allocations took 7.153e-06 s (0.02 %) - leafs setup took 1.907e-06 s (0.01 %) - halfword conversion took 9.694e-03 s (28.79 %) -Built (100 x 100)[0x556d0c3a2350]{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 0.034s): (100 x 100)[0x556d0c3a2350]{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' + shuffled partitions in 1.382e-01 s (55.77 %) + memory allocations took 1.478e-05 s (0.01 %) + leafs setup took 1.097e-05 s (0.00 %) + halfword conversion took 6.805e-02 s (27.46 %) +Built (100 x 100)[0x55abeeb8f080]{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 0.248s): (100 x 100)[0x55abeeb8f080]{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 @@ -7417,11 +7429,11 @@ # 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 @@ -7432,11 +7444,11 @@ # 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 @@ -7446,16 +7458,16 @@ # 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 0.01525s; avg 0.005084s ( +/- 25.09/ 14.27 %); best 0.003808s; worst 0.005809s; std dev. 0.0009048 (taking best). -Reference operation time is 0.00380802 s (21.22 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: 0.003808 Mflops: 21.218) -Merge (3 -> 1 leaves) took w.c.t. of 6.104e-05s, ~5.198e-05s of computing time (of which 2.599e-05s sorting, 1.907e-06s analysis) +3 iterations (1 th.) took 0.1199s; avg 0.03998s ( +/- 20.04/ 29.93 %); best 0.03197s; worst 0.05195s; std dev. 0.008623 (taking best). +Reference operation time is 0.0319681 s (2.528 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: 0.03197 Mflops: 2.528) +Merge (3 -> 1 leaves) took w.c.t. of 0.0001349s, ~0.0001059s of computing time (of which 5.984e-05s sorting, 9.06e-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 @@ -7466,11 +7478,11 @@ # 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 @@ -7480,14 +7492,14 @@ # 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 0.0001318s; avg 4.395e-05s ( +/- 1.81/ 1.99 %); best 4.315e-05s; worst 4.482e-05s; std dev. 6.837e-07 (taking best). -Reference operation time is 4.31538e-05 s (1872 Mflops) with 1 threads. +3 iterations (1 th.) took 0.0001109s; avg 3.695e-05s ( +/- 19.35/ 35.48 %); best 2.98e-05s; worst 5.007e-05s; std dev. 9.285e-06 (taking best). +Reference operation time is 2.98023e-05 s (2711 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 @@ -7497,25 +7509,25 @@ # 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 88.243x: 0.003808s -> 4.315e-05s, so taking this instance. +After merge step 1: tpop: 2.98e-05 s ~Mflops: 2711.198 nsubm:1 otn:1 +Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 1072.672x: 0.03197s -> 2.98e-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 0.04303s (of which 6.413e-05s partitioning, 0.0296s I/O); computing times: 5.198e-05s in par. loops, 2.599e-05s sorting, 1.907e-06s analyzing) -Total merge + benchmarking process took 0.04303s, equivalent to 997.0/11.3 new/old ops (0.03322s for 2 clones -- as 769.9/8.7 ops, or 384.9/4.4 ops per clone), SPEEDUP of 88.243x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 88.243x (0.003808s -> 4.315e-05s), will amortize in 11.4 ops by saving 0.003765s per op. -In 1 tuning rounds (tot. 0.078s, 0.033s for constructor, 2 clones) obtained a SPEEDUP of 8724.3% (88.24x) (from 21.22 to 1872 Mflops). Employed 0.04s for I/O of matrix plots. +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.4282s (of which 0.0001411s partitioning, 0.2602s I/O); computing times: 0.0001059s in par. loops, 5.984e-05s sorting, 9.06e-06s analyzing) +Total merge + benchmarking process took 0.4282s, equivalent to 14367.6/13.4 new/old ops (0.2911s for 2 clones -- as 9767.9/9.1 ops, or 4884.0/4.6 ops per clone), SPEEDUP of 1072.672x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 1072.672x (0.03197s -> 2.98e-05s), will amortize in 13.4 ops by saving 0.03194s per op. +In 1 tuning rounds (tot. 0.67s, 0.29s for constructor, 2 clones) obtained a SPEEDUP of 107167.2% (1073x) (from 2.528 to 2711 Mflops). Employed 0.21s 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 0.118869 s (3.808e-03 s -> 4.315e-05 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.880625 s (3.197e-02 s -> 2.980e-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 @@ -7526,11 +7538,11 @@ # 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 @@ -7541,13 +7553,13 @@ # 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 @@ -7558,11 +7570,11 @@ # 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 @@ -7572,27 +7584,27 @@ # 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 0.000133s; avg 4.435e-05s ( +/- 2.69/ 3.76 %); best 4.315e-05s; worst 4.601e-05s; std dev. 1.216e-06 (taking best). -Reference operation time is 4.31538e-05 s (1872 Mflops) with 1 threads. +3 iterations (1 th.) took 0.000149s; avg 4.967e-05s ( +/- 39.52/ 75.20 %); best 3.004e-05s; worst 8.702e-05s; std dev. 2.642e-05 (taking best). +Reference operation time is 3.00407e-05 s (2690 Mflops) with 1 threads. Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 1.538e-02 s (100.00 %) - analyzed arrays in 8.688e-03 s (56.50 %) - cleaned-up arrays in 9.060e-06 s (0.06 %) - deduplicated arrays in 1.192e-05 s (0.08 %) + converted COO to RSB in 1.628e-01 s (100.00 %) + analyzed arrays in 6.270e-02 s (38.52 %) + cleaned-up arrays in 1.502e-05 s (0.01 %) + deduplicated arrays in 1.311e-05 s (0.01 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 6.660e-03 s (43.31 %) - memory allocations took 4.053e-06 s (0.03 %) - leafs setup took 9.537e-07 s (0.01 %) - halfword conversion took 4.053e-06 s (0.03 %) -Built (100 x 100)[0x556d0c3a2230]{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 + shuffled partitions in 1.000e-01 s (61.44 %) + memory allocations took 9.775e-06 s (0.01 %) + leafs setup took 9.060e-06 s (0.01 %) + halfword conversion took 1.597e-05 s (0.01 %) +Built (100 x 100)[0x55abeeb8ef60]{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 @@ -7603,12 +7615,12 @@ # 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 @@ -7619,22 +7631,22 @@ # 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 3.528e-02 s (100.00 %) - analyzed arrays in 7.662e-03 s (21.72 %) - cleaned-up arrays in 8.106e-06 s (0.02 %) - deduplicated arrays in 1.192e-05 s (0.03 %) + converted COO to RSB in 1.873e-01 s (100.00 %) + analyzed arrays in 5.578e-02 s (29.78 %) + 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 1.621e-02 s (45.95 %) - memory allocations took 2.861e-06 s (0.01 %) - leafs setup took 9.537e-07 s (0.00 %) - halfword conversion took 1.138e-02 s (32.27 %) -Built (100 x 100)[0x556d0c3a2350]{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 + shuffled partitions in 5.955e-02 s (31.79 %) + memory allocations took 1.335e-05 s (0.01 %) + leafs setup took 9.060e-06 s (0.00 %) + halfword conversion took 7.196e-02 s (38.41 %) +Built (100 x 100)[0x55abeeb8f080]{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 @@ -7645,11 +7657,11 @@ # 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 @@ -7660,11 +7672,11 @@ # 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 @@ -7674,16 +7686,16 @@ # 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 0.01944s; avg 0.006482s ( +/- 14.70/ 17.53 %); best 0.005529s; worst 0.007618s; std dev. 0.0008628 (taking best). -Reference operation time is 0.00552893 s (14.61 Mflops) with 1 threads. -Challenging best inner round reference (4.31538e-05 s/1 threads) with: subdivision 0.25, 6 leaves, 2.163 bytes/nz, 0.00552893 s/0 threads (speedup 0.00780509 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 0.08793s; avg 0.02931s ( +/- 31.64/ 22.76 %); best 0.02004s; worst 0.03598s; std dev. 0.006765 (taking best). +Reference operation time is 0.020036 s (4.033 Mflops) with 1 threads. +Challenging best inner round reference (3.00407e-05 s/1 threads) with: subdivision 0.25, 8 leaves, 2.185 bytes/nz, 0.020036 s/0 threads (speedup 0.00149934 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 @@ -7694,12 +7706,12 @@ # 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 @@ -7710,22 +7722,22 @@ # 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 3.721e-02 s (100.00 %) - analyzed arrays in 1.323e-02 s (35.56 %) - cleaned-up arrays in 8.106e-06 s (0.02 %) - deduplicated arrays in 1.287e-05 s (0.03 %) + converted COO to RSB in 1.834e-01 s (100.00 %) + analyzed arrays in 8.347e-02 s (45.51 %) + cleaned-up arrays in 1.383e-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 1.353e-02 s (36.35 %) - memory allocations took 5.245e-06 s (0.01 %) - leafs setup took 3.099e-06 s (0.01 %) - halfword conversion took 1.042e-02 s (28.01 %) -Built (100 x 100)[0x556d0c3a2350]{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 5.186e-02 s (28.28 %) + memory allocations took 1.931e-05 s (0.01 %) + leafs setup took 1.311e-05 s (0.01 %) + halfword conversion took 4.801e-02 s (26.18 %) +Built (100 x 100)[0x55abeeb8f080]{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 @@ -7736,11 +7748,11 @@ # 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 @@ -7751,11 +7763,11 @@ # 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 @@ -7765,16 +7777,16 @@ # 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 0.01588s; avg 0.005294s ( +/- 25.98/ 19.52 %); best 0.003918s; worst 0.006327s; std dev. 0.001013 (taking best). -Reference operation time is 0.00391817 s (20.62 Mflops) with 1 threads. -Challenging best inner round reference (4.31538e-05 s/1 threads) with: subdivision 0.5, 16 leaves, 2.25 bytes/nz, 0.00391817 s/0 threads (speedup 0.0110138 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 0.08789s; avg 0.0293s ( +/- 31.79/ 63.49 %); best 0.01998s; worst 0.0479s; std dev. 0.01315 (taking best). +Reference operation time is 0.0199821 s (4.044 Mflops) with 1 threads. +Challenging best inner round reference (3.00407e-05 s/1 threads) with: subdivision 0.5, 19 leaves, 2.272 bytes/nz, 0.0199821 s/0 threads (speedup 0.00150338 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 @@ -7785,12 +7797,12 @@ # 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 @@ -7801,22 +7813,22 @@ # 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 4.548e-02 s (100.00 %) - analyzed arrays in 2.133e-02 s (46.90 %) - cleaned-up arrays in 8.106e-06 s (0.02 %) - deduplicated arrays in 1.287e-05 s (0.03 %) - sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.254e-02 s (27.56 %) - memory allocations took 6.914e-06 s (0.02 %) - leafs setup took 5.007e-06 s (0.01 %) - halfword conversion took 1.158e-02 s (25.46 %) -Built (100 x 100)[0x556d0c3a2350]{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 2.034e-01 s (100.00 %) + analyzed arrays in 7.119e-02 s (35.01 %) + cleaned-up arrays in 1.287e-05 s (0.01 %) + deduplicated arrays in 1.216e-05 s (0.01 %) + sorted arrays in 9.537e-07 s (0.00 %) + shuffled partitions in 5.709e-02 s (28.08 %) + memory allocations took 2.694e-05 s (0.01 %) + leafs setup took 1.383e-05 s (0.01 %) + halfword conversion took 7.500e-02 s (36.88 %) +Built (100 x 100)[0x55abeebdd470]{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: 40, 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 @@ -7827,11 +7839,11 @@ # 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 @@ -7842,11 +7854,11 @@ # 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 @@ -7856,16 +7868,16 @@ # 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 0.02211s; avg 0.00737s ( +/- 26.31/ 17.48 %); best 0.005431s; worst 0.008658s; std dev. 0.001395 (taking best). -Reference operation time is 0.00543094 s (14.88 Mflops) with 1 threads. -Challenging best inner round reference (4.31538e-05 s/1 threads) with: subdivision 1, 36 leaves, 2.383 bytes/nz, 0.00543094 s/0 threads (speedup 0.00794592 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 0.09183s; avg 0.03061s ( +/- 9.17/ 17.62 %); best 0.0278s; worst 0.036s; std dev. 0.003815 (taking best). +Reference operation time is 0.027801 s (2.906 Mflops) with 1 threads. +Challenging best inner round reference (3.00407e-05 s/1 threads) with: subdivision 1, 40 leaves, 2.398 bytes/nz, 0.027801 s/0 threads (speedup 0.00108056 x), same?n. +New candidate clone performs slowly; discarding it: 100 x 100, type Z, 5050 nnz, 50 nnz/r, 55 subms, 40 lsubms, 2.3976 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 @@ -7876,12 +7888,12 @@ # 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 @@ -7892,22 +7904,22 @@ # 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 4.971e-02 s (100.00 %) - analyzed arrays in 1.777e-02 s (35.74 %) - cleaned-up arrays in 8.106e-06 s (0.02 %) - deduplicated arrays in 1.311e-05 s (0.03 %) - sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.856e-02 s (37.33 %) - memory allocations took 7.868e-06 s (0.02 %) - leafs setup took 7.153e-06 s (0.01 %) - halfword conversion took 1.334e-02 s (26.85 %) -Built (100 x 100)[0x556d0c3f0710]{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: 75, 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 1.994e-01 s (100.00 %) + analyzed arrays in 7.930e-02 s (39.78 %) + cleaned-up arrays in 1.311e-05 s (0.01 %) + deduplicated arrays in 1.192e-05 s (0.01 %) + sorted arrays in 9.537e-07 s (0.00 %) + shuffled partitions in 6.006e-02 s (30.13 %) + memory allocations took 2.718e-05 s (0.01 %) + leafs setup took 2.193e-05 s (0.01 %) + halfword conversion took 5.993e-02 s (30.06 %) +Built (100 x 100)[0x55abeebdd470]{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 @@ -7918,11 +7930,11 @@ # 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 @@ -7933,11 +7945,11 @@ # 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 @@ -7947,16 +7959,16 @@ # 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 0.0174s; avg 0.0058s ( +/- 60.24/ 65.52 %); best 0.002306s; worst 0.0096s; std dev. 0.002986 (taking best). -Reference operation time is 0.00230598 s (35.04 Mflops) with 1 threads. -Challenging best inner round reference (4.31538e-05 s/1 threads) with: subdivision 2, 75 leaves, 2.544 bytes/nz, 0.00230598 s/0 threads (speedup 0.0187138 x), same?n. -New candidate clone performs slowly; discarding it: 100 x 100, type Z, 5050 nnz, 50 nnz/r, 102 subms, 75 lsubms, 2.5442 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 0.1079s; avg 0.03596s ( +/- 0.13/ 0.07 %); best 0.03591s; worst 0.03599s; std dev. 3.329e-05 (taking best). +Reference operation time is 0.0359149 s (2.25 Mflops) with 1 threads. +Challenging best inner round reference (3.00407e-05 s/1 threads) with: subdivision 2, 84 leaves, 2.581 bytes/nz, 0.0359149 s/0 threads (speedup 0.000836442 x), same?n. +New candidate clone performs slowly; discarding it: 100 x 100, type Z, 5050 nnz, 50 nnz/r, 114 subms, 84 lsubms, 2.5814 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 @@ -7967,12 +7979,12 @@ # 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 @@ -7983,22 +7995,22 @@ # 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 4.629e-02 s (100.00 %) - analyzed arrays in 2.370e-02 s (51.19 %) - cleaned-up arrays in 8.106e-06 s (0.02 %) - deduplicated arrays in 1.287e-05 s (0.03 %) - sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.280e-02 s (27.66 %) - memory allocations took 9.775e-06 s (0.02 %) - leafs setup took 1.001e-05 s (0.02 %) - halfword conversion took 9.748e-03 s (21.06 %) -Built (100 x 100)[0x556d0c3f0710]{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 + converted COO to RSB in 2.113e-01 s (100.00 %) + analyzed arrays in 8.327e-02 s (39.40 %) + cleaned-up arrays in 1.311e-05 s (0.01 %) + deduplicated arrays in 1.192e-05 s (0.01 %) + sorted arrays in 9.537e-07 s (0.00 %) + shuffled partitions in 6.013e-02 s (28.45 %) + memory allocations took 3.099e-05 s (0.01 %) + leafs setup took 2.408e-05 s (0.01 %) + halfword conversion took 6.785e-02 s (32.11 %) +Built (100 x 100)[0x55abeebdd470]{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 @@ -8009,11 +8021,11 @@ # 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 @@ -8024,11 +8036,11 @@ # 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 @@ -8038,17 +8050,17 @@ # 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 0.02097s; avg 0.006991s ( +/- 18.36/ 36.44 %); best 0.005708s; worst 0.009539s; std dev. 0.001801 (taking best). -Reference operation time is 0.00570798 s (14.16 Mflops) with 1 threads. -Challenging best inner round reference (4.31538e-05 s/1 threads) with: subdivision 4, 136 leaves, 2.776 bytes/nz, 0.00570798 s/0 threads (speedup 0.00756025 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: 1872.37 Mflops. +3 iterations (1 th.) took 0.1039s; avg 0.03465s ( +/- 7.61/ 3.94 %); best 0.03201s; worst 0.03601s; std dev. 0.001865 (taking best). +Reference operation time is 0.032011 s (2.524 Mflops) with 1 threads. +Challenging best inner round reference (3.00407e-05 s/1 threads) with: subdivision 4, 120 leaves, 2.726 bytes/nz, 0.032011 s/0 threads (speedup 0.00093845 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: 2689.68 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 @@ -8058,23 +8070,23 @@ # 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 0.327244 s (eq. to 8e+03/ 8e+03 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 1.63158 s (eq. to 5e+04/ 5e+04 old/new op.times), gained local/global speedup 1 x (3.00407e-05 : 3.00407e-05) / 1 x (3.00407e-05 : 3.00407e-05). This is not amortizable ! Auto tuning inner round 1 did not find a configuration better than the original. -In 1 tuning rounds (tot. 0.33s, 0.23s for constructor, 0 clones) obtained NO speedup (best stays 1872 Mflops). -Second run of RSB Autotuner took 0.32731 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. 1.6s, 1.1s for constructor, 0 clones) obtained NO speedup (best stays 2690 Mflops). +Second run of RSB Autotuner took 1.63176 s and estimated a speedup of 1.000000 x (3.004e-05 s -> 3.004e-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 0.005337 0.018606 0.023943 -%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.023943 -%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.005337 -%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.018606 +%:CONSTRUCTOR_TIMES:lower-100x100-5050nz S N 1 100 100 5050 0.000000 0.041488 0.138174 0.179662 +%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.179662 +%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.041488 +%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.138174 %: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 0.023943 +%:SORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.179662 %: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 @@ -8089,68 +8101,70 @@ %: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 0.033668 1e+09 1e+09 +%operation:lower-100x100-5050nz 0.247764 1e+09 1e+09 %constructor:matrix SORT[1] SCAN[1] SHUFFLE[1] INSERT[1] -%constructor:lower-100x100-5050nz 0 0.005337 0 0.0186059 -# so far, program took 9.432s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 1.828s/0.000s . +%constructor:lower-100x100-5050nz 0 0.0414882 0 0.138174 +# so far, program took 17.900s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 9.909s/0.000s . getrusage() stats: -ru_maxrss: 30 (maximum resident set size -- MB) -ru_stime : 0.2993s (system CPU time used) -ru_utime : 50.64s (user CPU time used) +ru_maxrss: 7 (maximum resident set size -- MB) +ru_stime : 0.0659s (system CPU time used) +ru_utime : 63.37s (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 7.549e-03 0.000e+00 1.192e-05 0.000e+00 1.644e-01 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 7.500e-03 0.000e+00 1.192e-05 0.000e+00 1.375e-01 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 2305.44 1.967e-03 0.000e+00 3.505e-05 0.000e+00 1.176e-01 1.52e+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 3.808e-03 0.000e+00 4.315e-05 0.000e+00 1.189e-01 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 1264.55 3.202e-02 0.000e+00 1.597e-05 0.000e+00 7.081e-01 3.34e+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 4159.59 2.403e-02 0.000e+00 4.856e-06 0.000e+00 6.924e-01 6.57e+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 2606.92 3.599e-02 0.000e+00 3.099e-05 0.000e+00 7.281e-01 1.72e+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 2711.20 3.197e-02 0.000e+00 2.980e-05 0.000e+00 8.806e-01 3.22e+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. 35069.6 % faster, avg. sp. ratio 351.696x, max sp. ratio 633.260x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 7860.0/2754.5/13790.5/31439.9 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 32.8/ 18.3/ 59.8/131.1 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 33.2, min. 18.4, max. 60.9 ops) +#pr: (in succ. cases rsb autotuning gave avg. 229537.0 % faster, avg. sp. ratio 2296.370x, max sp. ratio 4947.468x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 59986.4/23491.1/142579.7/239945.6 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 24.7/ 20.2/ 28.8/ 98.7 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 24.7, min. 20.2, max. 28.8 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 2.684/ 1.498/ 4.404,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 10.896/ 1.521/ 4.471,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 3.660/ 1.694/ 6.487,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 14.851/ 1.720/ 6.570,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.: 0.13 s, min 0.12 s, max 0.16 s, tot 0.54 s (4 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.13 s, min 0.12 s, max 0.16 s, tot 0.54 s (4 samples) -#pr: best tun. rsb canon. mflops were: on avg. 1.892e+03, min 1.694e+03, max 2.305e+03 (4 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 1.692e+01, min 2.676e+00, max 4.108e+01 (4 samples) -#pr: best tun. rsb operation time was: on avg. 2.551e-05s, min 1.192e-05s, max 4.315e-05s, tot 1.020e-04s (4 samples) -#pr: ref. unt. rsb operation time was: on avg. 5.206e-03s, min 1.967e-03s, max 7.549e-03s, tot 2.082e-02s (4 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 4.721e+00 1.388e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 3.129e+00 -#pr: Record collection took 1.80 s. +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.75 s, min 0.69 s, max 0.88 s, tot 3.01 s (4 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.75 s, min 0.69 s, max 0.88 s, tot 3.01 s (4 samples) +#pr: best tun. rsb canon. mflops were: on avg. 2.686e+03, min 1.265e+03, max 4.160e+03 (4 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 1.561e+00, min 6.310e-01, max 2.528e+00 (4 samples) +#pr: best tun. rsb operation time was: on avg. 2.041e-05s, min 4.856e-06s, max 3.099e-05s, tot 8.163e-05s (4 samples) +#pr: ref. unt. rsb operation time was: on avg. 3.100e-02s, min 2.403e-02s, max 3.599e-02s, tot 1.240e-01s (4 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.150e+00 4.403e+00 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 8.227e-01 +#pr: min / max ratio of in-cache MEMSET bandwidth to extrapolated read bandwidth ratio: 9.458e-01 3.622e+00 +#pr: # Warning: extrapolated memory I/O bandwidth exceeds cache bandwidth! +#pr: Record collection took 9.79 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 1751677220 (after 9.4s of w.c.t.) +# terminating run at 1717270932 (after 17.8s 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 Jul 4 13:00 test-tuning-lower-100x100-5050nz--D-N-1--base.eps --rw-r--r-- 1 pbuilder1 pbuilder1 84556 Jul 4 13:00 test-tuning-lower-100x100-5050nz--D-N-1--mv-tuned_merge1_1x1th.eps --rw-r--r-- 1 pbuilder1 pbuilder1 85633 Jul 4 13:00 test-tuning-lower-100x100-5050nz--S-N-1--base.eps --rw-r--r-- 1 pbuilder1 pbuilder1 84556 Jul 4 13:00 test-tuning-lower-100x100-5050nz--S-N-1--mv-tuned_merge1_1x1th.eps --rw-r--r-- 1 pbuilder1 pbuilder1 85633 Jul 4 13:00 test-tuning-lower-100x100-5050nz--C-N-1--base.eps --rw-r--r-- 1 pbuilder1 pbuilder1 84556 Jul 4 13:00 test-tuning-lower-100x100-5050nz--C-N-1--mv-tuned_merge1_1x1th.eps --rw-r--r-- 1 pbuilder1 pbuilder1 85634 Jul 4 13:00 test-tuning-lower-100x100-5050nz--Z-N-1--base.eps --rw-r--r-- 1 pbuilder1 pbuilder1 84556 Jul 4 13:00 test-tuning-lower-100x100-5050nz--Z-N-1--mv-tuned_merge1_1x1th.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 85642 Jun 2 09:42 test-tuning-lower-100x100-5050nz--D-N-1--base.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 84564 Jun 2 09:42 test-tuning-lower-100x100-5050nz--D-N-1--mv-tuned_merge1_1x1th.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 85642 Jun 2 09:42 test-tuning-lower-100x100-5050nz--S-N-1--base.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 84563 Jun 2 09:42 test-tuning-lower-100x100-5050nz--S-N-1--mv-tuned_merge1_1x1th.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 85642 Jun 2 09:42 test-tuning-lower-100x100-5050nz--C-N-1--base.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 84564 Jun 2 09:42 test-tuning-lower-100x100-5050nz--C-N-1--mv-tuned_merge1_1x1th.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 85642 Jun 2 09:42 test-tuning-lower-100x100-5050nz--Z-N-1--base.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 84564 Jun 2 09:42 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 4097 Jul 4 13:00 test.txt +-rw-r--r-- 1 pbuilder2 pbuilder2 4288 Jun 2 09:42 test.txt + RSB_PR_WLTC=2 + RSB_PR_SR=0 + rsbench --read-performance-record test.rpr @@ -8160,29 +8174,29 @@ /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 @@ -8197,7 +8211,7 @@ This error may be safely ignored. Correctly allocated a matrix. Summary information of the matrix: -(3 x 3)[0x555ae35914a0]{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)[0x55a19bcc54a0]{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. @@ -8212,7 +8226,7 @@ This error may be safely ignored. Correctly allocated a matrix. Summary information of the matrix: -(3 x 3)[0x55e4604dc4a0]{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)[0x55c61557b4a0]{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. @@ -8276,51 +8290,51 @@ Done. Building a matrix with 5 nnz, 5 x 5 Duplicates check: 5 - 0 = 5 - converted COO to RSB in 5.303e-02 s (100.00 %) - analyzed arrays in 1.818e-02 s (34.28 %) - cleaned-up arrays in 1.192e-06 s (0.00 %) - deduplicated arrays in 0.000e+00 s (0.00 %) - sorted arrays in 4.708e-03 s (8.88 %) - shuffled partitions in 1.527e-02 s (28.79 %) - memory allocations took 5.960e-06 s (0.01 %) - leafs setup took 2.146e-06 s (0.00 %) - halfword conversion took 1.487e-02 s (28.03 %) -Built (5 x 5)[0x55e4604e2f60]{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 3.663e-01 s (100.00 %) + analyzed arrays in 1.159e-01 s (31.65 %) + cleaned-up arrays in 1.907e-06 s (0.00 %) + deduplicated arrays in 3.099e-06 s (0.00 %) + sorted arrays in 1.831e-02 s (5.00 %) + shuffled partitions in 7.999e-02 s (21.84 %) + memory allocations took 4.101e-05 s (0.01 %) + leafs setup took 9.060e-06 s (0.00 %) + halfword conversion took 1.520e-01 s (41.50 %) +Built (5 x 5)[0x55c61557eb20]{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)[0x55e4604e2f60]{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)[0x55c61557eb20]{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 0.697705s. +Before auto-tuning, 100 multiplications took 4.147936s. 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.=3.67999e-08), 42 suggested as starting thread count(default). -3 iterations (42 th.) took 0.01688s; avg 0.005627s ( +/- 32.65/ 33.30 %); best 0.00379s; worst 0.007501s; std dev. 0.001515 (taking best). -Reference operation time is 0.0037899 s (0.005277 Mflops) with 42 threads. -3 iterations (42 th.) took 0.01513s; avg 0.005042s ( +/- 22.91/ 11.86 %); best 0.003887s; worst 0.00564s; std dev. 0.0008169 (taking best). -Reference operation time is 0.00388694 s (0.005145 Mflops) with 42 threads. -After 0.032078s, autotuning routine did not find a better threads count configuration. -(5 x 5)[0x55e4604e2f60]{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 0.647533s -- effective speedup of 1.07748 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.=2.04794e-06), 20 suggested as starting thread count(default). +3 iterations (20 th.) took 0.07988s; avg 0.02663s ( +/- 40.20/ 20.48 %); best 0.01592s; worst 0.03208s; std dev. 0.00757 (taking best). +Reference operation time is 0.0159221 s (0.001256 Mflops) with 20 threads. +3 iterations (20 th.) took 0.09595s; avg 0.03198s ( +/- 0.07/ 0.06 %); best 0.03196s; worst 0.032s; std dev. 1.651e-05 (taking best). +Reference operation time is 0.0319638 s (0.0006257 Mflops) with 20 threads. +After 0.175998s, autotuning routine did not find a better threads count configuration. +(5 x 5)[0x55c61557eb20]{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 2.943973s -- effective speedup of 1.40896 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.=3.67999e-08), 42 suggested as starting thread count. -3 iterations (42 th.) took 0.02129s; avg 0.007095s ( +/- 31.53/ 19.11 %); best 0.004858s; worst 0.008451s; std dev. 0.001594 (taking best). -Reference operation time is 0.00485802 s (0.004117 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: 0.004858 Mflops: 0.004) -Merge (2 -> 1 leaves) took w.c.t. of 3.099e-05s, ~6.914e-06s of computing time (of which 9.537e-07s sorting, 5.007e-06s analysis) -3 iterations (42 th.) took 3.099e-06s; avg 1.033e-06s ( +/- 96.44/107.69 %); best 3.68e-08s; worst 2.146e-06s; std dev. 8.778e-07 (taking best). -Reference operation time is 3.67999e-08 s (543.5 Mflops) with 42 threads. -After merge step 1: tpop: 3.68e-08 s ~Mflops: 543.480 nsubm:1 otn:42 -Applying merge (2 -> 1 leaves, 42 th.) yielded SPEEDUP of 132011.662x: 0.004858s -> 3.68e-08s, so taking this instance. +Starting autotuning (15 x 0.1 s stages, transA=N, nrhs=2, timer gran.=2.04794e-06), 20 suggested as starting thread count. +3 iterations (20 th.) took 0.08396s; avg 0.02799s ( +/- 14.79/ 28.96 %); best 0.02385s; worst 0.03609s; std dev. 0.005732 (taking best). +Reference operation time is 0.0238471 s (0.0008387 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: 0.02385 Mflops: 0.001) +Merge (2 -> 1 leaves) took w.c.t. of 4.506e-05s, ~9.06e-06s of computing time (of which 1.192e-06s sorting, 9.06e-06s analysis) +3 iterations (20 th.) took 4.053e-06s; avg 1.351e-06s ( +/- -51.58/ 58.82 %); best 2.048e-06s; worst 2.146e-06s; std dev. 5.62e-07 (taking best). +Reference operation time is 2.04794e-06 s (9.766 Mflops) with 20 threads. +After merge step 1: tpop: 2.048e-06 s ~Mflops: 9.766 nsubm:1 otn:20 +Applying merge (2 -> 1 leaves, 20 th.) yielded SPEEDUP of 11644.411x: 0.02385s -> 2.048e-06s, 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 0.01467s (of which 6.89e-05s partitioning, 0s I/O); computing times: 6.914e-06s in par. loops, 9.537e-07s sorting, 5.007e-06s analyzing) -Total merge + benchmarking process took 0.01467s, equivalent to 398620.0/3.0 new/old ops (0.03737s for 2 clones -- as 1015516.7/7.7 ops, or 507758.3/3.8 ops per clone), SPEEDUP of 132011.662x -Applying multi-merge (2 -> 1 leaves, 1 steps, 42 -> 42 th.sp.) yielded SPEEDUP of 132011.662x (0.004858s -> 3.68e-08s), will amortize in 3.0 ops by saving 0.004858s per op. -In 1 tuning rounds (tot. 0.059s, 0.037s for constructor, 2 clones) obtained a SPEEDUP of 13201066.2% (1.32e+05x) (from 0.004117 to 543.5 Mflops). -After 0.058841s, autotuning routine declared speedup of 132012 x, when using threads count of 42. -(5 x 5)[0x55e4604e6590]{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 0.000031s -- further speedup of 20891.9 x +A total of 1 merge steps (of max 6) (2 -> 1 subms) took 0.1s (of which 0.0004151s partitioning, 0s I/O); computing times: 9.06e-06s in par. loops, 1.192e-06s sorting, 9.06e-06s analyzing) +Total merge + benchmarking process took 0.1s, equivalent to 48846.6/4.2 new/old ops (0.1955s for 2 clones -- as 95451.3/8.2 ops, or 47725.6/4.1 ops per clone), SPEEDUP of 11644.411x +Applying multi-merge (2 -> 1 leaves, 1 steps, 20 -> 20 th.sp.) yielded SPEEDUP of 11644.411x (0.02385s -> 2.048e-06s), will amortize in 4.2 ops by saving 0.02385s per op. +In 1 tuning rounds (tot. 0.28s, 0.2s for constructor, 2 clones) obtained a SPEEDUP of 1164341.1% (1.164e+04x) (from 0.0008387 to 9.766 Mflops). +After 0.280016s, autotuning routine declared speedup of 11644.4 x, when using threads count of 20. +(5 x 5)[0x55c6155821e0]{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 0.000032s -- further speedup of 92148.6 x 0/2 0 0 -> 0 1/2 1 0 -> 5 0/2 0 3 -> 0 @@ -8331,7 +8345,7 @@ Correctly initialized the library. Correctly allocated a matrix with 7 nonzeroes. Summary information of the matrix: -(6 x 6)[0x55e4604e2f60]{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)[0x55c61557eb20]{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 @@ -8482,56 +8496,73 @@ 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 1.038e-01 s (100.00 %) - analyzed arrays in 1.865e-02 s (17.97 %) - cleaned-up arrays in 9.704e-05 s (0.09 %) - deduplicated arrays in 1.352e-04 s (0.13 %) - sorted arrays in 3.813e-02 s (36.75 %) - shuffled partitions in 2.988e-02 s (28.80 %) - memory allocations took 4.101e-05 s (0.04 %) - leafs setup took 9.775e-06 s (0.01 %) - halfword conversion took 1.682e-02 s (16.21 %) -Built (500 x 500)[0x5616f1bc82d0]{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 3.720e-01 s (100.00 %) + analyzed arrays in 7.549e-02 s (20.29 %) + cleaned-up arrays in 2.651e-04 s (0.07 %) + deduplicated arrays in 1.931e-04 s (0.05 %) + sorted arrays in 1.439e-01 s (38.69 %) + shuffled partitions in 1.040e-01 s (27.95 %) + memory allocations took 1.488e-04 s (0.04 %) + leafs setup took 2.503e-05 s (0.01 %) + halfword conversion took 4.797e-02 s (12.90 %) +Built (500 x 500)[0x55638230e2d0]{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)[0x5616f1bc82d0]{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)[0x55638230e2d0]{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 0.715353s. +Before auto-tuning, 100 multiplications took 2.895596s. 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.=3.69072e-08), 42 suggested as starting thread count(default). -3 iterations (42 th.) took 0.01921s; avg 0.006403s ( +/- 12.28/ 6.15 %); best 0.005617s; worst 0.006797s; std dev. 0.0005559 (taking best). -Reference operation time is 0.00561714 s (44.51 Mflops) with 42 threads. -3 iterations (42 th.) took 0.01885s; avg 0.006284s ( +/- 32.76/ 41.34 %); best 0.004225s; worst 0.008881s; std dev. 0.001939 (taking best). -Reference operation time is 0.00422502 s (59.17 Mflops) with 42 threads. -After 0.038137s, autotuning routine did not find a better threads count configuration. -(500 x 500)[0x5616f1bc82d0]{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 0.780070s -- effective speedup of 0.917037 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.=8.47352e-07), 20 suggested as starting thread count(default). +3 iterations (20 th.) took 0.1119s; avg 0.0373s ( +/- 14.45/ 28.64 %); best 0.03191s; worst 0.04798s; std dev. 0.007553 (taking best). +Reference operation time is 0.0319109 s (7.834 Mflops) with 20 threads. +3 iterations (20 th.) took 0.09597s; avg 0.03199s ( +/- 0.21/ 0.20 %); best 0.03192s; worst 0.03205s; std dev. 5.27e-05 (taking best). +Reference operation time is 0.0319231 s (7.831 Mflops) with 20 threads. +After 0.208072s, autotuning routine did not find a better threads count configuration. +(500 x 500)[0x55638230e2d0]{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 3.852335s -- effective speedup of 0.751647 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.=3.69072e-08), 42 suggested as starting thread count. -3 iterations (42 th.) took 0.01783s; avg 0.005943s ( +/- 23.23/ 23.79 %); best 0.004562s; worst 0.007356s; std dev. 0.001141 (taking best). -Reference operation time is 0.0045619 s (54.8 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: 0.004562 Mflops: 54.802) -Merge (37 -> 28 leaves) took w.c.t. of 0.002489s, ~0.0004249s of computing time (of which 9.608e-05s sorting, 8.106e-06s analysis) -3 iterations (42 th.) took 0.05265s; avg 0.01755s ( +/- 78.86/135.05 %); best 0.003711s; worst 0.04125s; std dev. 0.01684 (taking best). -Reference operation time is 0.00371099 s (67.37 Mflops) with 42 threads. -After merge step 1: tpop: 0.003711 s ~Mflops: 67.368 nsubm:28 otn:42 -Applying merge (37 -> 28 leaves, 42 th.) yielded SPEEDUP of 1.229x: 0.004562s -> 0.003711s, so taking this instance. -Merge (28 -> 22 leaves) took w.c.t. of 0.002107s, ~0.000149s of computing time (of which 8.106e-05s sorting, 6.914e-06s analysis) -3 iterations (42 th.) took 0.0249s; avg 0.008301s ( +/- 22.78/ 30.64 %); best 0.00641s; worst 0.01084s; std dev. 0.001868 (taking best). -Reference operation time is 0.00640988 s (39 Mflops) with 42 threads. -After merge step 2: tpop: 0.00641 s ~Mflops: 39.002 nsubm:22 otn:42 -Applying merge (28 -> 22 leaves, 42 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.727x: 0.003711s -> 0.00641s. +Starting autotuning (15 x 0.1 s stages, transA=N, nrhs=2, timer gran.=8.47352e-07), 20 suggested as starting thread count. +3 iterations (20 th.) took 0.0768s; avg 0.0256s ( +/- 20.36/ 12.48 %); best 0.02039s; worst 0.02879s; std dev. 0.003717 (taking best). +Reference operation time is 0.0203869 s (12.26 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: 0.02039 Mflops: 12.263) +Merge (64 -> 40 leaves) took w.c.t. of 0.1079s, ~0.4931s of computing time (of which 0.0253s sorting, 2.098e-05s analysis) +3 iterations (20 th.) took 0.1359s; avg 0.0453s ( +/- 20.45/ 30.16 %); best 0.03604s; worst 0.05897s; std dev. 0.009864 (taking best). +Reference operation time is 0.0360389 s (6.937 Mflops) with 20 threads. +After merge step 1: tpop: 0.03604 s ~Mflops: 6.937 nsubm:40 otn:20 +Applying merge (64 -> 40 leaves, 20 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.768x: 0.02039s -> 0.03604s. Skipping further merge based tests after 1 definite performance degradations in a row (and last exceeding limit). -A total of 2 merge steps (of max 6) (37 -> 22 subms) took 0.1047s (of which 0.004609s partitioning, 0s I/O); computing times: 0.0005739s in par. loops, 0.0001771s sorting, 1.502e-05s analyzing) -Total merge + benchmarking process took 0.1047s, equivalent to 28.2/22.9 new/old ops (0.04465s for 2 clones -- as 12.0/9.8 ops, or 6.0/4.9 ops per clone), SPEEDUP of 1.229x -Applying multi-merge (37 -> 28 leaves, 1 steps, 42 -> 42 th.sp.) yielded SPEEDUP of 1.229x (0.004562s -> 0.003711s), will amortize in 123.0 ops by saving 0.0008509s per op. -In 1 tuning rounds (tot. 0.15s, 0.045s for constructor, 2 clones) obtained a SPEEDUP of 22.9% (1.229x) (from 54.8 to 67.37 Mflops). -After 0.145320s, autotuning routine declared speedup of 1.2293 x, when using threads count of 42. -(500 x 500)[0x5616f1bd32d0]{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: 28, symflags:'' -After threads auto-tuning, 100 multiplications took 0.679114s -- further speedup of 1.14866 x +A total of 1 merge steps (of max 6) (64 -> 40 subms) took 0.2439s (of which 0.108s partitioning, 0s I/O); computing times: 0.4931s in par. loops, 0.0253s sorting, 2.098e-05s analyzing) +Total merge + benchmarking process took 0.2439s, equivalent to 12.0/12.0 new/old ops (0.1107s for 1 clones -- as 5.4/5.4 ops, or 5.4/5.4 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 0.1079s; avg 0.03597s ( +/- 32.56/ 32.90 %); best 0.02426s; worst 0.0478s; std dev. 0.009611 (taking best). +Reference operation time is 0.024256 s (10.31 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: 0.02426 Mflops: 10.307) +Split (64 -> 160 leaves, 87 -> 215 subms) took 0.04772s (of which: 1.407e-05s analysis, -5.495e+10s mem.mgmt); compute time: 0.001976s overall, 0.000325s searches, 0.001651s shuffle, 0.0006385s switch, 0.0001295s quadrants. +3 iterations (20 th.) took 0.08389s; avg 0.02796s ( +/- 16.39/ 28.85 %); best 0.02338s; worst 0.03603s; std dev. 0.005722 (taking best). +Reference operation time is 0.0233791 s (10.69 Mflops) with 20 threads. +After split step 1: tpop: 0.02338 s ~Mflops: 10.693 nsubm:160 otn:20 +Applying split (64 -> 160 leaves, 20 th.) yielded SPEEDUP of 1.038x: 0.02426s -> 0.02338s, so taking this instance. +Split (160 -> 400 leaves, 215 -> 535 subms) took 0.03573s (of which: 3.982e-05s analysis, -1.374e+11s mem.mgmt); compute time: 0.00545s overall, 0.0005596s searches, 0.004891s shuffle, 0.002603s switch, 0.0005109s quadrants. +3 iterations (20 th.) took 0.1635s; avg 0.0545s ( +/- 56.94/112.82 %); best 0.02347s; worst 0.116s; std dev. 0.04348 (taking best). +Reference operation time is 0.0234671 s (10.65 Mflops) with 20 threads. +After split step 2: tpop: 0.02347 s ~Mflops: 10.653 nsubm:400 otn:20 +Applying split (160 -> 400 leaves, 20 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=0.99625x): 0.02338s -> 0.02347s, so IGNORING this instance. +Split (400 -> 1000 leaves, 535 -> 1335 subms) took 0.04786s (of which: 6.294e-05s analysis, -3.435e+11s mem.mgmt); compute time: 0.005983s overall, 0.0007246s searches, 0.005259s shuffle, 0.001521s switch, 0.001063s quadrants. +3 iterations (20 th.) took 0.3111s; avg 0.1037s ( +/- 43.08/ 31.27 %); best 0.05903s; worst 0.1361s; std dev. 0.03265 (taking best). +Reference operation time is 0.059027 s (4.235 Mflops) with 20 threads. +After split step 3: tpop: 0.05903 s ~Mflops: 4.235 nsubm:1000 otn:20 +Applying split (400 -> 1000 leaves, 20 th.) yielded SLOWDOWN (1th of 3 tolerable) of 2.525x: 0.02338s -> 0.05903s. +Skipping further split based tests after 1 definite performance degradations in a row (and last exceeding limit). +A total of 3 split steps (of max 6) (64 -> 1000 subms) took 0.7877s (of which 0.1334s partitioning, 0s I/O); computing times: 0.01341s in par. loops, 0.001609s sorting, 0.0001168s analyzing) +Total split + benchmarking process took 0.7877s, equivalent to 33.7/32.5 new/old ops (0.1956s for 2 clones -- as 8.4/8.1 ops, or 4.2/4.0 ops per clone), SPEEDUP of 1.038x +Applying multi-split (64 -> 160 leaves, 1 steps, 20 -> 20 th.sp.) yielded SPEEDUP of 1.038x (0.02426s -> 0.02338s), will amortize in 898.2 ops by saving 0.0008769s per op. +In 1 tuning rounds (tot. 1.4s, 0.31s for constructor, 3 clones) obtained a SPEEDUP of 3.8% (1.038x) (from 10.31 to 10.69 Mflops). +After 1.428266s, autotuning routine declared speedup of 1.03751 x, when using threads count of 20. +(500 x 500)[0x556382416bf0]{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 3.311338s -- further speedup of 1.16338 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! @@ -8539,19 +8570,19 @@ Correctly initialized the library. Building a matrix with 7 nnz, 6 x 6 Duplicates check: 1 - 0 = 1 - converted COO to RSB in 2.608e-02 s (100.00 %) - analyzed arrays in 1.843e-02 s (70.69 %) - cleaned-up arrays in 5.960e-06 s (0.02 %) - deduplicated arrays in 1.192e-06 s (0.00 %) - sorted arrays in 9.537e-07 s (0.00 %) - shuffled partitions in 7.604e-03 s (29.16 %) - memory allocations took 1.788e-05 s (0.07 %) - leafs setup took 3.099e-06 s (0.01 %) - halfword conversion took 6.914e-06 s (0.03 %) -Built (6 x 6)[0x5588fe0344d0]{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 1.344e-01 s (100.00 %) + analyzed arrays in 1.055e-01 s (78.51 %) + cleaned-up arrays in 1.001e-05 s (0.01 %) + deduplicated arrays in 1.907e-06 s (0.00 %) + sorted arrays in 4.053e-06 s (0.00 %) + shuffled partitions in 2.880e-02 s (21.43 %) + memory allocations took 3.600e-05 s (0.03 %) + leafs setup took 1.311e-05 s (0.01 %) + halfword conversion took 1.502e-05 s (0.01 %) +Built (6 x 6)[0x5654b2c844d0]{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)[0x5588fe0344d0]{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)[0x5654b2c844d0]{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 @@ -8577,55 +8608,55 @@ 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:3.736e-08 -3 iterations (42 th.) took 3.29e-05s; avg 1.097e-05s ( +/- 99.66/191.30 %); best 3.736e-08s; worst 3.195e-05s; std dev. 1.484e-05 (taking best). -Reference operation time is 3.73602e-08 s (53.53 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: 3.736e-08 Mflops: 53.533) -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 ( +/- 88.25/200.00 %); best 3.736e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). -Reference operation time is 3.73602e-08 s (53.53 Mflops) with 42 threads. -After merge step 1: tpop: 3.736e-08 s ~Mflops: 53.533 nsubm:1 otn:42 -Applying merge (1 -> 1 leaves, 42 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=1.00000x): 3.736e-08s -> 3.736e-08s, so IGNORING this instance. +Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:1.253e-06 +3 iterations (20 th.) took 5.698e-05s; avg 1.899e-05s ( +/- 93.41/173.64 %); best 1.253e-06s; worst 5.198e-05s; std dev. 2.336e-05 (taking best). +Reference operation time is 1.25265e-06 s (1.597 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: 1.253e-06 Mflops: 1.597) +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 3.815e-06s; avg 1.272e-06s ( +/- 1.49/ 50.00 %); best 1.253e-06s; worst 1.907e-06s; std dev. 4.496e-07 (taking best). +Reference operation time is 1.25265e-06 s (1.597 Mflops) with 20 threads. +After merge step 1: tpop: 1.253e-06 s ~Mflops: 1.597 nsubm:1 otn:20 +Applying merge (1 -> 1 leaves, 20 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=1.00000x): 1.253e-06s -> 1.253e-06s, 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 1.693e-05s (of which 3.815e-06s partitioning, 0s I/O); computing times: 0s in par. loops, 0s sorting, 0s analyzing) -Total merge + benchmarking process took 1.693e-05s, equivalent to 453.1/453.1 new/old ops (0.01492s for 1 clones -- as 399304.4/399304.4 ops, or 399304.4/399304.4 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) +A total of 1 merge steps (of max 6) (1 -> 1 subms) took 2.789e-05s (of which 6.914e-06s partitioning, 0s I/O); computing times: 0s in par. loops, 0s sorting, 0s analyzing) +Total merge + benchmarking process took 2.789e-05s, equivalent to 22.3/22.3 new/old ops (0.1056s for 1 clones -- as 84307.6/84307.6 ops, or 84307.6/84307.6 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 ( +/- 96.38/107.69 %); best 3.736e-08s; worst 2.146e-06s; std dev. 8.778e-07 (taking best). -Reference operation time is 3.73602e-08 s (53.53 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: 3.736e-08 Mflops: 53.533) -Split (1 -> 1 leaves, 1 -> 1 subms) took 3.695e-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 1.907e-06s; avg 6.358e-07s ( +/- 94.12/ 50.00 %); best 3.736e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). -Reference operation time is 3.73602e-08 s (53.53 Mflops) with 42 threads. -After split step 1: tpop: 3.736e-08 s ~Mflops: 53.533 nsubm:1 otn:42 -Applying split (1 -> 1 leaves, 42 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=1.00000x): 3.736e-08s -> 3.736e-08s, so IGNORING this instance. -Split (1 -> 1 leaves, 1 -> 1 subms) took 3.099e-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 2.861e-06s; avg 9.537e-07s ( +/- 96.08/200.00 %); best 3.736e-08s; worst 2.861e-06s; std dev. 1.349e-06 (taking best). -Reference operation time is 3.73602e-08 s (53.53 Mflops) with 42 threads. -After split step 2: tpop: 3.736e-08 s ~Mflops: 53.533 nsubm:1 otn:42 -Applying split (1 -> 1 leaves, 42 th.) yielded NEGLIGIBLE change (2th in a row) (old/new=1.00000x): 3.736e-08s -> 3.736e-08s, so IGNORING this instance. +3 iterations (20 th.) took 2.193e-05s; avg 7.312e-06s ( +/- 82.87/160.87 %); best 1.253e-06s; worst 1.907e-05s; std dev. 8.326e-06 (taking best). +Reference operation time is 1.25265e-06 s (1.597 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: 1.253e-06 Mflops: 1.597) +Split (1 -> 1 leaves, 1 -> 1 subms) took 4.911e-05s (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 2.861e-06s; avg 9.537e-07s ( +/- -31.35/ 0.00 %); best 1.253e-06s; worst 9.537e-07s; std dev. 0 (taking best). +Reference operation time is 1.25265e-06 s (1.597 Mflops) with 20 threads. +After split step 1: tpop: 1.253e-06 s ~Mflops: 1.597 nsubm:1 otn:20 +Applying split (1 -> 1 leaves, 20 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=1.00000x): 1.253e-06s -> 1.253e-06s, 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 (20 th.) took 3.099e-06s; avg 1.033e-06s ( +/- -21.25/107.69 %); best 1.253e-06s; worst 2.146e-06s; std dev. 8.778e-07 (taking best). +Reference operation time is 1.25265e-06 s (1.597 Mflops) with 20 threads. +After split step 2: tpop: 1.253e-06 s ~Mflops: 1.597 nsubm:1 otn:20 +Applying split (1 -> 1 leaves, 20 th.) yielded NEGLIGIBLE change (2th in a row) (old/new=1.00000x): 1.253e-06s -> 1.253e-06s, so IGNORING this instance. +Split (1 -> 1 leaves, 1 -> 1 subms) took 8.106e-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 3.099e-06s; avg 1.033e-06s ( +/- -21.25/ 15.38 %); best 1.253e-06s; worst 1.192e-06s; std dev. 1.124e-07 (taking best). +Reference operation time is 1.25265e-06 s (1.597 Mflops) with 20 threads. +After split step 3: tpop: 1.253e-06 s ~Mflops: 1.597 nsubm:1 otn:20 +Applying split (1 -> 1 leaves, 20 th.) yielded NEGLIGIBLE change (3th in a row) (old/new=1.00000x): 1.253e-06s -> 1.253e-06s, 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 (42 th.) took 1.192e-06s; avg 3.974e-07s ( +/- 90.60/200.00 %); best 3.736e-08s; worst 1.192e-06s; std dev. 5.62e-07 (taking best). -Reference operation time is 3.73602e-08 s (53.53 Mflops) with 42 threads. -After split step 3: tpop: 3.736e-08 s ~Mflops: 53.533 nsubm:1 otn:42 -Applying split (1 -> 1 leaves, 42 th.) yielded NEGLIGIBLE change (3th in a row) (old/new=1.00000x): 3.736e-08s -> 3.736e-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 0s; avg 0s ( +/- -inf/ -nan %); best 3.736e-08s; worst 0s; std dev. 0 (taking best). -Reference operation time is 3.73602e-08 s (53.53 Mflops) with 42 threads. -After split step 4: tpop: 3.736e-08 s ~Mflops: 53.533 nsubm:1 otn:42 -Applying split (1 -> 1 leaves, 42 th.) yielded NEGLIGIBLE change (4th in a row) (old/new=1.00000x): 3.736e-08s -> 3.736e-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 ( +/- 88.25/200.00 %); best 3.736e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). -Reference operation time is 3.73602e-08 s (53.53 Mflops) with 42 threads. -After split step 5: tpop: 3.736e-08 s ~Mflops: 53.533 nsubm:1 otn:42 -Applying split (1 -> 1 leaves, 42 th.) yielded NEGLIGIBLE change (5th in a row) (old/new=1.00000x): 3.736e-08s -> 3.736e-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 ( +/- 90.60/200.00 %); best 3.736e-08s; worst 1.192e-06s; std dev. 5.62e-07 (taking best). -Reference operation time is 3.73602e-08 s (53.53 Mflops) with 42 threads. -After split step 6: tpop: 3.736e-08 s ~Mflops: 53.533 nsubm:1 otn:42 -Applying split (1 -> 1 leaves, 42 th.) yielded NEGLIGIBLE change (6th in a row) (old/new=1.00000x): 3.736e-08s -> 3.736e-08s, so IGNORING this instance. -A total of 6 split steps (of max 6) (1 -> 1 subms) took 0.002289s (of which 0.002228s partitioning, 0s I/O); computing times: 0s in par. loops, 0s sorting, 5.96e-06s analyzing) -Total split + benchmarking process took 0.002289s, equivalent to 61269.9/61269.9 new/old ops (0.02088s for 1 clones -- as 558800.3/558800.3 ops, or 558800.3/558800.3 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) -In 1 tuning rounds (tot. 0.038s, 0.036s for constructor, 2 clones) obtained NO speedup (best stays 53.53 Mflops). +3 iterations (20 th.) took 1.383e-05s; avg 4.609e-06s ( +/- 72.82/117.24 %); best 1.253e-06s; worst 1.001e-05s; std dev. 4.126e-06 (taking best). +Reference operation time is 1.25265e-06 s (1.597 Mflops) with 20 threads. +After split step 4: tpop: 1.253e-06 s ~Mflops: 1.597 nsubm:1 otn:20 +Applying split (1 -> 1 leaves, 20 th.) yielded NEGLIGIBLE change (4th in a row) (old/new=1.00000x): 1.253e-06s -> 1.253e-06s, so IGNORING this instance. +Split (1 -> 1 leaves, 1 -> 1 subms) took 4.053e-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 1.907e-06s; avg 6.358e-07s ( +/- -97.02/ 50.00 %); best 1.253e-06s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). +Reference operation time is 1.25265e-06 s (1.597 Mflops) with 20 threads. +After split step 5: tpop: 1.253e-06 s ~Mflops: 1.597 nsubm:1 otn:20 +Applying split (1 -> 1 leaves, 20 th.) yielded NEGLIGIBLE change (5th in a row) (old/new=1.00000x): 1.253e-06s -> 1.253e-06s, 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 (20 th.) took 1.907e-06s; avg 6.358e-07s ( +/- -97.02/ 50.00 %); best 1.253e-06s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). +Reference operation time is 1.25265e-06 s (1.597 Mflops) with 20 threads. +After split step 6: tpop: 1.253e-06 s ~Mflops: 1.597 nsubm:1 otn:20 +Applying split (1 -> 1 leaves, 20 th.) yielded NEGLIGIBLE change (6th in a row) (old/new=1.00000x): 1.253e-06s -> 1.253e-06s, so IGNORING this instance. +A total of 6 split steps (of max 6) (1 -> 1 subms) took 0.0002611s (of which 0.00016s partitioning, 0s I/O); computing times: 0s in par. loops, 0s sorting, 1.407e-05s analyzing) +Total split + benchmarking process took 0.0002611s, equivalent to 208.4/208.4 new/old ops (0.1097s for 1 clones -- as 87583.2/87583.2 ops, or 87583.2/87583.2 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) +In 1 tuning rounds (tot. 0.22s, 0.22s for constructor, 2 clones) obtained NO speedup (best stays 1.597 Mflops). Backsolving we should get a unitary vector: %%MatrixMarket matrix array real general @@ -8660,128 +8691,101 @@ /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 4.580e-02 s (100.00 %) - analyzed arrays in 5.849e-03 s (12.77 %) - cleaned-up arrays in 9.537e-07 s (0.00 %) - deduplicated arrays in 1.907e-06 s (0.00 %) - sorted arrays in 8.797e-03 s (19.21 %) - shuffled partitions in 1.588e-02 s (34.68 %) - memory allocations took 3.576e-05 s (0.08 %) - leafs setup took 5.007e-06 s (0.01 %) - halfword conversion took 1.521e-02 s (33.22 %) -Built (20 x 20)[0x55b0c55be9f0]{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:3.71e-08 -Starting autotuning (16 x 3.70979e-08 s stages, transA=N, nrhs=1, timer gran.=3.70979e-08), 42 suggested as starting thread count(default). -3 iterations (42 th.) took 0.0187s; avg 0.006232s ( +/- 12.85/ 21.29 %); best 0.005431s; worst 0.007559s; std dev. 0.0009451 (taking best). -Reference operation time is 0.00543094 s (0.1547 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: 0.005431 Mflops: 0.155) -Merge (22 -> 16 leaves) took w.c.t. of 0.005775s, ~0.002122s of computing time (of which 1.907e-06s sorting, 5.007e-06s analysis) -3 iterations (42 th.) took 0.03629s; avg 0.0121s ( +/- 53.36/ 75.75 %); best 0.005641s; worst 0.02126s; std dev. 0.006657 (taking best). -Reference operation time is 0.00564098 s (0.1489 Mflops) with 42 threads. -After merge step 1: tpop: 0.005641 s ~Mflops: 0.149 nsubm:16 otn:42 -Applying merge (22 -> 16 leaves, 42 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.039x: 0.005431s -> 0.005641s. -Merge (16 -> 10 leaves) took w.c.t. of 0.003779s, ~1.097e-05s of computing time (of which 1.907e-06s sorting, 5.007e-06s analysis) -3 iterations (42 th.) took 0.0485s; avg 0.01617s ( +/- 41.59/ 66.94 %); best 0.009443s; worst 0.02699s; std dev. 0.007727 (taking best). -Reference operation time is 0.00944304 s (0.08895 Mflops) with 42 threads. -After merge step 2: tpop: 0.009443 s ~Mflops: 0.089 nsubm:10 otn:42 -Applying merge (16 -> 10 leaves, 42 th.) yielded SLOWDOWN (2th of 3 tolerable) of 1.739x: 0.005431s -> 0.009443s. -Skipping further merge based tests after 2 definite performance degradations in a row (and last exceeding limit). -A total of 2 merge steps (of max 6) (22 -> 10 subms) took 0.0944s (of which 0.009568s partitioning, 0s I/O); computing times: 0.002133s in par. loops, 3.815e-06s sorting, 1.001e-05s analyzing) -Total merge + benchmarking process took 0.0944s, equivalent to 17.4/17.4 new/old ops (0.02308s for 1 clones -- as 4.2/4.2 ops, or 4.2/4.2 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 0.02179s; avg 0.007262s ( +/- 21.33/ 18.22 %); best 0.005713s; worst 0.008585s; std dev. 0.001183 (taking best). -Reference operation time is 0.00571299 s (0.147 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: 0.005713 Mflops: 0.147) -Split (22 -> 51 leaves, 30 -> 70 subms) took 0.02647s (of which: 4.053e-06s analysis, -1.927e+10s mem.mgmt); compute time: 0.1396s overall, 7.153e-06s searches, 0.1396s shuffle, 0.1396s switch, 1.073e-05s quadrants. -3 iterations (42 th.) took 0.02605s; avg 0.008682s ( +/- 30.64/ 40.47 %); best 0.006022s; worst 0.0122s; std dev. 0.002592 (taking best). -Reference operation time is 0.00602198 s (0.1395 Mflops) with 42 threads. -After split step 1: tpop: 0.006022 s ~Mflops: 0.139 nsubm:51 otn:42 -Applying split (22 -> 51 leaves, 42 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.054x: 0.005713s -> 0.006022s. -Split (51 -> 122 leaves, 70 -> 166 subms) took 0.009784s (of which: 7.153e-06s analysis, -4.379e+10s mem.mgmt); compute time: 0.1078s overall, 1.597e-05s searches, 0.1077s shuffle, 0.09894s switch, 0.0004711s quadrants. -3 iterations (42 th.) took 0.02375s; avg 0.007916s ( +/- 18.05/ 9.52 %); best 0.006487s; worst 0.00867s; std dev. 0.001011 (taking best). -Reference operation time is 0.00648713 s (0.1295 Mflops) with 42 threads. -After split step 2: tpop: 0.006487 s ~Mflops: 0.129 nsubm:122 otn:42 -Applying split (51 -> 122 leaves, 42 th.) yielded SLOWDOWN (2th of 3 tolerable) of 1.136x: 0.005713s -> 0.006487s. -Split (122 -> 146 leaves, 166 -> 198 subms) took 0.009639s (of which: 1.097e-05s analysis, -1.401e+10s mem.mgmt); compute time: 0.01603s overall, 5.96e-06s searches, 0.01602s shuffle, 0.0157s switch, 0.0001671s quadrants. -3 iterations (42 th.) took 0.02793s; avg 0.009309s ( +/- 12.76/ 7.20 %); best 0.008121s; worst 0.009979s; std dev. 0.0008423 (taking best). -Reference operation time is 0.00812101 s (0.1034 Mflops) with 42 threads. -After split step 3: tpop: 0.008121 s ~Mflops: 0.103 nsubm:146 otn:42 -Applying split (122 -> 146 leaves, 42 th.) yielded SLOWDOWN (3th of 3 tolerable) of 1.422x: 0.005713s -> 0.008121s. -Skipping further split based tests after 3 definite performance degradations in a row (and last exceeding limit). -A total of 3 split steps (of max 6) (22 -> 146 subms) took 0.1241s (of which 0.04629s partitioning, 0s I/O); computing times: 0.2634s in par. loops, 2.909e-05s sorting, 2.217e-05s analyzing) -Total split + benchmarking process took 0.1241s, equivalent to 21.7/21.7 new/old ops (0.02093s for 1 clones -- as 3.7/3.7 ops, or 3.7/3.7 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) -In 1 tuning rounds (tot. 0.3s, 0.044s for constructor, 2 clones) obtained NO speedup (best stays 0.147 Mflops). - autotuner chose 42 threads + converted COO to RSB in 2.482e-01 s (100.00 %) + analyzed arrays in 8.166e-02 s (32.90 %) + cleaned-up arrays in 3.099e-06 s (0.00 %) + deduplicated arrays in 2.861e-06 s (0.00 %) + sorted arrays in 5.047e-02 s (20.33 %) + shuffled partitions in 4.801e-02 s (19.34 %) + memory allocations took 8.798e-05 s (0.04 %) + leafs setup took 1.812e-05 s (0.01 %) + halfword conversion took 6.797e-02 s (27.38 %) +Built (20 x 20)[0x55877e7f09f0]{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:3.71e-08 -Starting autotuning (16 x 3.70979e-08 s stages, transA=N, nrhs=1, timer gran.=3.70979e-08), 42 suggested as starting thread count(default). -3 iterations (42 th.) took 0.02533s; avg 0.008445s ( +/- 11.99/ 7.30 %); best 0.007432s; worst 0.009061s; std dev. 0.0007216 (taking best). -~ 42 threads: 0.007432s (0.11 Mflops) (0/2 degradations so far) - -3 iterations (41 th.) took 0.02818s; avg 0.009393s ( +/- 45.71/ 26.51 %); best 0.0051s; worst 0.01188s; std dev. 0.003049 (taking best). - 41 threads: 0.0051s (0.16 Mflops) (0/2 degradations so far) - -3 iterations (40 th.) took 0.02743s; avg 0.009143s ( +/- 32.18/ 16.83 %); best 0.006201s; worst 0.01068s; std dev. 0.002081 (taking best). - 40 threads: 0.006201s (0.14 Mflops) (1/2 degradations so far) - -3 iterations (39 th.) took 0.02219s; avg 0.007398s ( +/- 24.13/ 46.08 %); best 0.005613s; worst 0.01081s; std dev. 0.002411 (taking best). - 39 threads: 0.005613s (0.15 Mflops) (2/2 degradations so far) - -Best threads choice is 41; starting threads were 42; max speed gap is 1.5x; search took 0.1s. -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: 0.0051 Mflops: 0.165) -Merge (22 -> 16 leaves) took w.c.t. of 0.005608s, ~1.907e-05s of computing time (of which 2.861e-06s sorting, 6.199e-06s analysis) -3 iterations (42 th.) took 0.03628s; avg 0.01209s ( +/- 37.75/ 54.21 %); best 0.007527s; worst 0.01865s; std dev. 0.004753 (taking best). -~ 42 threads: 0.007527s (0.11 Mflops) (0/2 degradations so far) - -3 iterations (41 th.) took 0.01755s; avg 0.005848s ( +/- 47.66/ 29.69 %); best 0.003061s; worst 0.007585s; std dev. 0.001991 (taking best). - 41 threads: 0.003061s (0.27 Mflops) (0/2 degradations so far) - -3 iterations (40 th.) took 0.0206s; avg 0.006865s ( +/- 19.03/ 9.84 %); best 0.005559s; worst 0.007541s; std dev. 0.0009239 (taking best). - 40 threads: 0.005559s (0.15 Mflops) (1/2 degradations so far) - -3 iterations (39 th.) took 0.02413s; avg 0.008045s ( +/- 8.91/ 13.49 %); best 0.007328s; worst 0.00913s; std dev. 0.0007805 (taking best). - 39 threads: 0.007328s (0.11 Mflops) (2/2 degradations so far) - -Best threads choice is 41; starting threads were 42; max speed gap is 2.5x; search took 0.099s. -After merge step 1: tpop: 0.003061 s ~Mflops: 0.274 nsubm:16 otn:41 -Applying merge (22 -> 16 leaves, 41 th.) yielded SPEEDUP of 1.666x: 0.0051s -> 0.003061s, so taking this instance. -Merge (16 -> 10 leaves) took w.c.t. of 0.003771s, ~1.478e-05s of computing time (of which 1.907e-06s sorting, 5.007e-06s analysis) -3 iterations (42 th.) took 0.03531s; avg 0.01177s ( +/- 33.52/ 66.80 %); best 0.007824s; worst 0.01963s; std dev. 0.005559 (taking best). -~ 42 threads: 0.007824s (0.11 Mflops) (0/2 degradations so far) - -3 iterations (41 th.) took 0.02309s; avg 0.007696s ( +/- 32.72/ 35.46 %); best 0.005178s; worst 0.01043s; std dev. 0.002147 (taking best). - 41 threads: 0.005178s (0.16 Mflops) (0/2 degradations so far) - -3 iterations (40 th.) took 0.0293s; avg 0.009767s ( +/- 22.98/ 45.68 %); best 0.007522s; worst 0.01423s; std dev. 0.003155 (taking best). - 40 threads: 0.007522s (0.11 Mflops) (1/2 degradations so far) - -3 iterations (39 th.) took 0.02474s; avg 0.008247s ( +/- 52.74/ 80.61 %); best 0.003898s; worst 0.01489s; std dev. 0.004775 (taking best). - 39 threads: 0.003898s (0.22 Mflops) (0/2 degradations so far) - -3 iterations (38 th.) took 0.02259s; avg 0.00753s ( +/- 16.70/ 25.19 %); best 0.006273s; worst 0.009427s; std dev. 0.001365 (taking best). - 38 threads: 0.006273s (0.13 Mflops) (1/2 degradations so far) - -3 iterations (37 th.) took 0.01973s; avg 0.006576s ( +/- 33.18/ 45.69 %); best 0.004394s; worst 0.00958s; std dev. 0.002196 (taking best). - 37 threads: 0.004394s (0.19 Mflops) (2/2 degradations so far) - -Best threads choice is 39; starting threads were 42; max speed gap is 2x; search took 0.16s. -After merge step 2: tpop: 0.003898 s ~Mflops: 0.216 nsubm:10 otn:39 -Applying merge (16 -> 10 leaves, 39 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.273x: 0.003061s -> 0.003898s. +Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:7.678e-07 +Starting autotuning (16 x 7.67803e-07 s stages, transA=N, nrhs=1, timer gran.=7.67803e-07), 20 suggested as starting thread count(default). +3 iterations (20 th.) took 0.108s; avg 0.03601s ( +/- 33.23/ 55.45 %); best 0.02404s; worst 0.05598s; std dev. 0.01421 (taking best). +Reference operation time is 0.024045 s (0.03493 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, 30 subms, 22 lsubms, 3.7524 bpnz (tpop: 0.02404 Mflops: 0.035) +Merge (22 -> 16 leaves) took w.c.t. of 0.02027s, ~0.0001791s of computing time (of which 6.199e-06s sorting, 1.884e-05s analysis) +3 iterations (20 th.) took 0.1316s; avg 0.04388s ( +/- 63.51/ 81.44 %); best 0.01601s; worst 0.07961s; std dev. 0.02655 (taking best). +Reference operation time is 0.016011 s (0.05246 Mflops) with 20 threads. +After merge step 1: tpop: 0.01601 s ~Mflops: 0.052 nsubm:16 otn:20 +Applying merge (22 -> 16 leaves, 20 th.) yielded SPEEDUP of 1.502x: 0.02404s -> 0.01601s, so taking this instance. +Merge (16 -> 10 leaves) took w.c.t. of 0.012s, ~5.198e-05s of computing time (of which 9.06e-06s sorting, 1.717e-05s analysis) +3 iterations (20 th.) took 0.1689s; avg 0.05629s ( +/- 21.72/ 34.89 %); best 0.04406s; worst 0.07592s; std dev. 0.01402 (taking best). +Reference operation time is 0.0440612 s (0.01906 Mflops) with 20 threads. +After merge step 2: tpop: 0.04406 s ~Mflops: 0.019 nsubm:10 otn:20 +Applying merge (16 -> 10 leaves, 20 th.) yielded SLOWDOWN (1th of 3 tolerable) of 2.752x: 0.01601s -> 0.04406s. +Skipping further merge based tests after 1 definite performance degradations in a row (and last exceeding limit). +A total of 2 merge steps (of max 6) (22 -> 10 subms) took 0.4489s (of which 0.03232s partitioning, 0s I/O); computing times: 0.000231s in par. loops, 1.526e-05s sorting, 3.6e-05s analyzing) +Total merge + benchmarking process took 0.4489s, equivalent to 28.0/18.7 new/old ops (0.2198s for 2 clones -- as 13.7/9.1 ops, or 6.9/4.6 ops per clone), SPEEDUP of 1.502x +Applying multi-merge (22 -> 16 leaves, 1 steps, 0 -> 20 th.sp.) yielded SPEEDUP of 1.502x (0.02404s -> 0.01601s), will amortize in 55.9 ops by saving 0.008034s per op. +In 1 tuning rounds (tot. 0.66s, 0.22s for constructor, 2 clones) obtained a SPEEDUP of 50.2% (1.502x) (from 0.03493 to 0.05246 Mflops). + autotuner chose 20 threads +Will autotune matrix: 20 x 20, type D, 210 nnz, 10 nnz/r, 22 subms, 16 lsubms, 3.4476 bpnz. +Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:7.678e-07 +Starting autotuning (16 x 7.67803e-07 s stages, transA=N, nrhs=1, timer gran.=7.67803e-07), 20 suggested as starting thread count(default). +3 iterations (20 th.) took 0.12s; avg 0.04s ( +/- 0.08/ 0.06 %); best 0.03997s; worst 0.04002s; std dev. 2.265e-05 (taking best). +~ 20 threads: 0.03997s (0.021 Mflops) (0/2 degradations so far) - +3 iterations (19 th.) took 0.1041s; avg 0.0347s ( +/- 42.40/ 26.71 %); best 0.01999s; worst 0.04397s; std dev. 0.01052 (taking best). + 19 threads: 0.01999s (0.042 Mflops) (0/2 degradations so far) - +3 iterations (18 th.) took 0.1398s; avg 0.0466s ( +/- 5.99/ 3.01 %); best 0.04381s; worst 0.048s; std dev. 0.001975 (taking best). + 18 threads: 0.04381s (0.019 Mflops) (1/2 degradations so far) - +3 iterations (17 th.) took 0.12s; avg 0.03999s ( +/- 0.06/ 0.03 %); best 0.03997s; worst 0.04s; std dev. 1.585e-05 (taking best). + 17 threads: 0.03997s (0.021 Mflops) (2/2 degradations so far) - +Best threads choice is 19; starting threads were 20; max speed gap is 2.2x; search took 0.48s. +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, 22 subms, 16 lsubms, 3.4476 bpnz (tpop: 0.01999 Mflops: 0.042) +Merge (16 -> 10 leaves) took w.c.t. of 0.02002s, ~5.698e-05s of computing time (of which 1.597e-05s sorting, 1.192e-05s analysis) +3 iterations (20 th.) took 0.1359s; avg 0.04529s ( +/- 64.70/ 76.39 %); best 0.01599s; worst 0.07989s; std dev. 0.02635 (taking best). +~ 20 threads: 0.01599s (0.053 Mflops) (0/2 degradations so far) - +3 iterations (19 th.) took 0.07998s; avg 0.02666s ( +/- 39.98/ 20.01 %); best 0.016s; worst 0.032s; std dev. 0.007537 (taking best). + 19 threads: 0.016s (0.052 Mflops) (1/2 degradations so far) - +3 iterations (18 th.) took 0.07997s; avg 0.02666s ( +/- 39.94/ 20.13 %); best 0.01601s; worst 0.03202s; std dev. 0.007529 (taking best). + 18 threads: 0.01601s (0.052 Mflops) (2/2 degradations so far) - +Best threads choice is 20; starting threads were 20; max speed gap is 1x; search took 0.3s. +After merge step 1: tpop: 0.01599 s ~Mflops: 0.053 nsubm:10 otn:20 +Applying merge (16 -> 10 leaves, 20 th.) yielded SPEEDUP of 1.250x: 0.01999s -> 0.01599s, so taking this instance. +Merge (10 -> 8 leaves) took w.c.t. of 4.601e-05s, ~1.383e-05s of computing time (of which 3.099e-06s sorting, 1.502e-05s analysis) +3 iterations (20 th.) took 0.09887s; avg 0.03296s ( +/- 18.32/ 21.20 %); best 0.02692s; worst 0.03994s; std dev. 0.005359 (taking best). +~ 20 threads: 0.02692s (0.031 Mflops) (0/2 degradations so far) - +3 iterations (19 th.) took 0.08396s; avg 0.02799s ( +/- 14.40/ 28.68 %); best 0.02396s; worst 0.03601s; std dev. 0.005676 (taking best). + 19 threads: 0.02396s (0.035 Mflops) (0/2 degradations so far) - +3 iterations (18 th.) took 0.09593s; avg 0.03198s ( +/- 24.98/ 43.87 %); best 0.02399s; worst 0.04601s; std dev. 0.009952 (taking best). + 18 threads: 0.02399s (0.035 Mflops) (1/2 degradations so far) - +3 iterations (17 th.) took 0.07602s; avg 0.02534s ( +/- 4.94/ 9.87 %); best 0.02409s; worst 0.02784s; std dev. 0.001768 (taking best). + 17 threads: 0.02409s (0.035 Mflops) (2/2 degradations so far) - +Best threads choice is 19; starting threads were 20; max speed gap is 1.1x; search took 0.35s. +After merge step 2: tpop: 0.02396 s ~Mflops: 0.035 nsubm:8 otn:19 +Applying merge (10 -> 8 leaves, 19 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.498x: 0.01599s -> 0.02396s. Skipping further merge based tests after 1 definite performance degradations in a row (and last exceeding limit). -A total of 2 merge steps (of max 6) (22 -> 10 subms) took 0.2875s (of which 0.009397s partitioning, 0s I/O); computing times: 3.386e-05s in par. loops, 4.768e-06s sorting, 1.121e-05s analyzing) -Total merge + benchmarking process took 0.2875s, equivalent to 93.9/56.4 new/old ops (0.04246s for 2 clones -- as 13.9/8.3 ops, or 6.9/4.2 ops per clone), SPEEDUP of 1.666x -Applying multi-merge (22 -> 16 leaves, 1 steps, 41 -> 41 th.sp.) yielded SPEEDUP of 1.666x (0.0051s -> 0.003061s), will amortize in 141.0 ops by saving 0.002039s per op. -In 1 tuning rounds (tot. 0.41s, 0.042s for constructor, 2 clones) obtained a SPEEDUP of 66.6% (1.666x) (from 0.1647 to 0.2744 Mflops). +A total of 2 merge steps (of max 6) (16 -> 8 subms) took 0.736s (of which 0.02009s partitioning, 0s I/O); computing times: 7.081e-05s in par. loops, 1.907e-05s sorting, 2.694e-05s analyzing) +Total merge + benchmarking process took 0.736s, equivalent to 46.0/36.8 new/old ops (0.1729s for 2 clones -- as 10.8/8.6 ops, or 5.4/4.3 ops per clone), SPEEDUP of 1.250x +Applying multi-merge (16 -> 10 leaves, 1 steps, 19 -> 20 th.sp.) yielded SPEEDUP of 1.250x (0.01999s -> 0.01599s), will amortize in 183.9 ops by saving 0.004003s per op. +In 1 tuning rounds (tot. 1.3s, 0.17s for constructor, 2 clones) obtained a SPEEDUP of 25.0% (1.25x) (from 0.04202 to 0.05254 Mflops). check results are ok Building a matrix with 36 nnz, 6 x 6 Duplicates check: 36 - 0 = 36 - converted COO to RSB in 2.384e-02 s (100.00 %) - analyzed arrays in 1.175e-02 s (49.29 %) - cleaned-up arrays in 9.537e-07 s (0.00 %) - deduplicated arrays in 1.192e-06 s (0.00 %) - sorted arrays in 7.391e-03 s (31.00 %) - shuffled partitions in 4.690e-03 s (19.67 %) - memory allocations took 4.768e-06 s (0.02 %) - leafs setup took 1.192e-06 s (0.00 %) - halfword conversion took 1.907e-06 s (0.01 %) -Built (6 x 6)[0x55b0c55c8a70]{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 1.076e-01 s (100.00 %) + analyzed arrays in 3.199e-02 s (29.73 %) + cleaned-up arrays in 2.146e-06 s (0.00 %) + deduplicated arrays in 2.861e-06 s (0.00 %) + sorted arrays in 4.358e-02 s (40.50 %) + shuffled partitions in 3.197e-02 s (29.71 %) + memory allocations took 3.195e-05 s (0.03 %) + leafs setup took 9.060e-06 s (0.01 %) + halfword conversion took 8.821e-06 s (0.01 %) +Built (6 x 6)[0x55877e7f6980]{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 0.8082E-04 s -A single USMM took 0.5317E-04 s -USMM-to-USMV speed ratio is is 1.520 x +Repeated USMV took 0.4697E-04 s +A single USMM took 0.3386E-04 s +USMM-to-USMV speed ratio is is 1.387 x Call auto-tuning routine.. Repeat measurement. -Tuned USMM took 0.6914E-05 s -Tuned-to-untuned speed ratio is is 7.690 x +Tuned USMM took 0.9060E-05 s +Tuned-to-untuned speed ratio is is 3.737 x FAILED: 0 PASSED: 2 /build/reproducible-path/librsb-1.3.0.2+dfsg/examples/fortran_rsb_fi @@ -8830,252 +8834,210 @@ 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 4.879e-02 s (100.00 %) - analyzed arrays in 1.126e-02 s (23.07 %) - cleaned-up arrays in 5.960e-06 s (0.01 %) - deduplicated arrays in 1.192e-06 s (0.00 %) - sorted arrays in 1.007e-02 s (20.64 %) - shuffled partitions in 1.056e-02 s (21.64 %) - memory allocations took 1.001e-05 s (0.02 %) - leafs setup took 4.053e-06 s (0.01 %) - halfword conversion took 1.687e-02 s (34.58 %) -Built (6 x 6)[0x55fc1fef1a20]{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 2.727e-01 s (100.00 %) + analyzed arrays in 7.189e-02 s (26.36 %) + cleaned-up arrays in 1.001e-05 s (0.00 %) + deduplicated arrays in 3.815e-06 s (0.00 %) + sorted arrays in 4.874e-02 s (17.87 %) + shuffled partitions in 7.215e-02 s (26.46 %) + memory allocations took 4.530e-05 s (0.02 %) + leafs setup took 1.907e-05 s (0.01 %) + halfword conversion took 7.983e-02 s (29.27 %) +Built (6 x 6)[0x55b39df99a20]{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)[0x55fc1fefa060]{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)[0x55b39df9ee10]{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 0.01957s; avg 0.006523s ( +/- 40.32/ 52.23 %); best 0.003893s; worst 0.00993s; std dev. 0.002525 (taking best). -Reference operation time is 0.00389314 s (0.03699 Mflops) with 42 threads. -After 0.019612s, autotuning routine did not find a better threads count configuration. +3 iterations (20 th.) took 0.09977s; avg 0.03326s ( +/- 4.44/ 8.30 %); best 0.03178s; worst 0.03602s; std dev. 0.001954 (taking best). +Reference operation time is 0.0317771 s (0.004532 Mflops) with 20 threads. +After 0.099885s, 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 0.02215s; avg 0.007385s ( +/- 30.34/ 51.76 %); best 0.005144s; worst 0.01121s; std dev. 0.002716 (taking best). -Reference operation time is 0.00514388 s (0.02799 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: 0.005144 Mflops: 0.028) -Merge (22 -> 16 leaves) took w.c.t. of 0.0005171s, ~0.0002329s of computing time (of which 3.815e-06s sorting, 5.007e-06s analysis) -3 iterations (42 th.) took 0.04009s; avg 0.01336s ( +/- 42.46/ 71.24 %); best 0.00769s; worst 0.02288s; std dev. 0.006773 (taking best). -Reference operation time is 0.00768995 s (0.01873 Mflops) with 42 threads. -After merge step 1: tpop: 0.00769 s ~Mflops: 0.019 nsubm:16 otn:42 -Applying merge (22 -> 16 leaves, 42 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.495x: 0.005144s -> 0.00769s. -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 0.04063s (of which 0.0005231s partitioning, 0s I/O); computing times: 0.0002329s in par. loops, 3.815e-06s sorting, 5.007e-06s analyzing) -Total merge + benchmarking process took 0.04063s, equivalent to 7.9/7.9 new/old ops (0.01357s for 1 clones -- as 2.6/2.6 ops, or 2.6/2.6 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) +3 iterations (20 th.) took 0.08816s; avg 0.02939s ( +/- 5.42/ 10.19 %); best 0.02779s; worst 0.03238s; std dev. 0.002119 (taking best). +Reference operation time is 0.0277929 s (0.005181 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: 0.02779 Mflops: 0.005) +Merge (22 -> 16 leaves) took w.c.t. of 0.03166s, ~0.000216s of computing time (of which 7.868e-06s sorting, 1.287e-05s analysis) +3 iterations (20 th.) took 0.1359s; avg 0.04528s ( +/- 29.76/ 58.93 %); best 0.03181s; worst 0.07197s; std dev. 0.01887 (taking best). +Reference operation time is 0.031806 s (0.004527 Mflops) with 20 threads. +After merge step 1: tpop: 0.03181 s ~Mflops: 0.005 nsubm:16 otn:20 +Applying merge (22 -> 16 leaves, 20 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.144x: 0.02779s -> 0.03181s. +Merge (16 -> 10 leaves) took w.c.t. of 0.02018s, ~5.794e-05s of computing time (of which 7.153e-06s sorting, 1.407e-05s analysis) +3 iterations (20 th.) took 0.1596s; avg 0.05321s ( +/- 32.61/ 65.15 %); best 0.03586s; worst 0.08788s; std dev. 0.02451 (taking best). +Reference operation time is 0.0358589 s (0.004016 Mflops) with 20 threads. +After merge step 2: tpop: 0.03586 s ~Mflops: 0.004 nsubm:10 otn:20 +Applying merge (16 -> 10 leaves, 20 th.) yielded SLOWDOWN (2th of 3 tolerable) of 1.290x: 0.02779s -> 0.03586s. +Skipping further merge based tests after 2 definite performance degradations in a row (and last exceeding limit). +A total of 2 merge steps (of max 6) (22 -> 10 subms) took 0.3475s (of which 0.0519s partitioning, 0s I/O); computing times: 0.0002739s in par. loops, 1.502e-05s sorting, 2.694e-05s analyzing) +Total merge + benchmarking process took 0.3475s, equivalent to 12.5/12.5 new/old ops (0.08827s for 1 clones -- as 3.2/3.2 ops, or 3.2/3.2 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 0.0272s; avg 0.009066s ( +/- 4.58/ 7.68 %); best 0.008651s; worst 0.009763s; std dev. 0.0004957 (taking best). -Reference operation time is 0.00865078 s (0.01665 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: 0.008651 Mflops: 0.017) -Split (22 -> 28 leaves, 29 -> 37 subms) took 0.008698s (of which: 4.053e-06s analysis, -3.503e+09s mem.mgmt); compute time: 0.000396s overall, 2.861e-06s searches, 0.0003932s shuffle, 0.0001991s switch, 1.907e-06s quadrants. -3 iterations (42 th.) took 0.02094s; avg 0.006981s ( +/- 19.00/ 12.18 %); best 0.005655s; worst 0.007832s; std dev. 0.0009503 (taking best). -Reference operation time is 0.00565505 s (0.02546 Mflops) with 42 threads. -After split step 1: tpop: 0.005655 s ~Mflops: 0.025 nsubm:28 otn:42 -Applying split (22 -> 28 leaves, 42 th.) yielded SPEEDUP of 1.530x: 0.008651s -> 0.005655s, so taking this instance. -Split (28 -> 28 leaves, 37 -> 37 subms) took 0.005381s (of which: 6.199e-06s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. -3 iterations (42 th.) took 0.02582s; avg 0.008607s ( +/- 52.79/ 54.08 %); best 0.004064s; worst 0.01326s; std dev. 0.003756 (taking best). -Reference operation time is 0.00406384 s (0.03543 Mflops) with 42 threads. -After split step 2: tpop: 0.004064 s ~Mflops: 0.035 nsubm:28 otn:42 -Applying split (28 -> 28 leaves, 42 th.) yielded SPEEDUP of 1.392x: 0.005655s -> 0.004064s, so taking this instance. -Split (28 -> 28 leaves, 37 -> 37 subms) took 0.009269s (of which: 3.815e-06s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. -3 iterations (42 th.) took 0.03644s; avg 0.01215s ( +/- 34.97/ 55.66 %); best 0.0079s; worst 0.01891s; std dev. 0.004833 (taking best). -Reference operation time is 0.0079 s (0.01823 Mflops) with 42 threads. -After split step 3: tpop: 0.0079 s ~Mflops: 0.018 nsubm:28 otn:42 -Applying split (28 -> 28 leaves, 42 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.944x: 0.004064s -> 0.0079s. +3 iterations (20 th.) took 0.1001s; avg 0.03336s ( +/- 39.77/ 31.99 %); best 0.02009s; worst 0.04403s; std dev. 0.009943 (taking best). +Reference operation time is 0.020092 s (0.007167 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 D, 36 nnz, 6 nnz/r, 29 subms, 22 lsubms, 4.6667 bpnz (tpop: 0.02009 Mflops: 0.007) +Split (22 -> 28 leaves, 29 -> 37 subms) took 0.05178s (of which: 1.001e-05s analysis, -3.435e+09s mem.mgmt); compute time: 0.02825s overall, 4.053e-06s searches, 0.02825s shuffle, 0.02821s switch, 5.96e-06s quadrants. +3 iterations (20 th.) took 0.1078s; avg 0.03593s ( +/- 22.96/ 33.77 %); best 0.02768s; worst 0.04807s; std dev. 0.008763 (taking best). +Reference operation time is 0.0276821 s (0.005202 Mflops) with 20 threads. +After split step 1: tpop: 0.02768 s ~Mflops: 0.005 nsubm:28 otn:20 +Applying split (22 -> 28 leaves, 20 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.378x: 0.02009s -> 0.02768s. Skipping further split based tests after 1 definite performance degradations in a row (and last exceeding limit). -A total of 3 split steps (of max 6) (22 -> 28 subms) took 0.1515s (of which 0.02354s partitioning, 0s I/O); computing times: 0.000396s in par. loops, 2.861e-06s sorting, 1.407e-05s analyzing) -Total split + benchmarking process took 0.1515s, equivalent to 37.3/17.5 new/old ops (0.06739s for 3 clones -- as 16.6/7.8 ops, or 5.5/2.6 ops per clone), SPEEDUP of 2.129x -Applying multi-split (22 -> 28 leaves, 2 steps, 0 -> 42 th.sp.) yielded SPEEDUP of 2.129x (0.008651s -> 0.004064s), will amortize in 33.0 ops by saving 0.004587s per op. -In 1 tuning rounds (tot. 0.28s, 0.081s for constructor, 4 clones) obtained a SPEEDUP of 112.9% (2.129x) (from 0.01665 to 0.03543 Mflops). -After 0.278118s, global autotuning declared speedup of 2.12872 x, when using threads count of 42 and a new matrix: -(6 x 6)[0x55fc1ff0b440]{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 1 split steps (of max 6) (22 -> 28 subms) took 0.1599s (of which 0.05206s partitioning, 0s I/O); computing times: 0.02825s in par. loops, 4.053e-06s sorting, 1.001e-05s analyzing) +Total split + benchmarking process took 0.1599s, equivalent to 8.0/8.0 new/old ops (0.1079s for 1 clones -- as 5.4/5.4 ops, or 5.4/5.4 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) +In 1 tuning rounds (tot. 0.89s, 0.2s for constructor, 2 clones) obtained NO speedup (best stays 0.007167 Mflops). +After 0.892036s, global autotuning found old matrix optimal, with declared speedup 1 x when using 20 threads Considering S clone. Building a matrix with 36 nnz, 6 x 6 Duplicates check: 36 - 0 = 36 - converted COO to RSB in 3.829e-02 s (100.00 %) - analyzed arrays in 1.133e-02 s (29.60 %) + converted COO to RSB in 1.799e-01 s (100.00 %) + analyzed arrays in 8.382e-02 s (46.59 %) cleaned-up arrays in 1.907e-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 1.408e-02 s (36.79 %) - memory allocations took 4.053e-06 s (0.01 %) - leafs setup took 3.099e-06 s (0.01 %) - halfword conversion took 1.286e-02 s (33.58 %) -Built (6 x 6)[0x55fc1fefa060]{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:'' + deduplicated arrays in 1.192e-06 s (0.00 %) + sorted arrays in 9.537e-07 s (0.00 %) + shuffled partitions in 4.802e-02 s (26.69 %) + memory allocations took 1.478e-05 s (0.01 %) + leafs setup took 6.914e-06 s (0.00 %) + halfword conversion took 4.803e-02 s (26.70 %) +Built (6 x 6)[0x55b39df9ee10]{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)[0x55fc1fefa060]{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)[0x55b39df9ee10]{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 0.02334s; avg 0.007781s ( +/- 12.35/ 17.45 %); best 0.00682s; worst 0.009139s; std dev. 0.0009873 (taking best). -Reference operation time is 0.0068202 s (0.02111 Mflops) with 42 threads. -After 0.023371s, autotuning routine did not find a better threads count configuration. +3 iterations (20 th.) took 0.0839s; avg 0.02797s ( +/- 42.71/ 56.99 %); best 0.01602s; worst 0.04391s; std dev. 0.01173 (taking best). +Reference operation time is 0.0160239 s (0.008987 Mflops) with 20 threads. +After 0.083979s, 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 0.02173s; avg 0.007244s ( +/- 32.34/ 54.76 %); best 0.004901s; worst 0.01121s; std dev. 0.00282 (taking best). -Reference operation time is 0.00490117 s (0.02938 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: 0.004901 Mflops: 0.029) -Merge (16 -> 10 leaves) took w.c.t. of 0.003616s, ~2.003e-05s of computing time (of which 3.099e-06s sorting, 5.96e-06s analysis) -3 iterations (42 th.) took 0.04315s; avg 0.01438s ( +/- 61.36/109.58 %); best 0.005559s; worst 0.03015s; std dev. 0.01117 (taking best). -Reference operation time is 0.00555897 s (0.0259 Mflops) with 42 threads. -After merge step 1: tpop: 0.005559 s ~Mflops: 0.026 nsubm:10 otn:42 -Applying merge (16 -> 10 leaves, 42 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.134x: 0.004901s -> 0.005559s. -Merge (10 -> 7 leaves) took w.c.t. of 1.287e-05s, ~5.007e-06s of computing time (of which 1.192e-06s sorting, 3.099e-06s analysis) -3 iterations (42 th.) took 0.02263s; avg 0.007542s ( +/- 0.57/ 0.90 %); best 0.007499s; worst 0.00761s; std dev. 4.867e-05 (taking best). -Reference operation time is 0.00749898 s (0.0192 Mflops) with 42 threads. -After merge step 2: tpop: 0.007499 s ~Mflops: 0.019 nsubm:7 otn:42 -Applying merge (10 -> 7 leaves, 42 th.) yielded SLOWDOWN (2th of 3 tolerable) of 1.530x: 0.004901s -> 0.007499s. -Skipping further merge based tests after 2 definite performance degradations in a row (and last exceeding limit). -A total of 2 merge steps (of max 6) (16 -> 7 subms) took 0.06946s (of which 0.003644s partitioning, 0s I/O); computing times: 2.503e-05s in par. loops, 4.292e-06s sorting, 9.06e-06s analyzing) -Total merge + benchmarking process took 0.06946s, equivalent to 14.2/14.2 new/old ops (0.02245s for 1 clones -- as 4.6/4.6 ops, or 4.6/4.6 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 0.02438s; avg 0.008125s ( +/- 30.25/ 15.65 %); best 0.005667s; worst 0.009397s; std dev. 0.001738 (taking best). -Reference operation time is 0.00566721 s (0.02541 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 S, 36 nnz, 6 nnz/r, 21 subms, 16 lsubms, 4.8889 bpnz (tpop: 0.005667 Mflops: 0.025) -Split (16 -> 28 leaves, 21 -> 37 subms) took 0.007509s (of which: 3.099e-06s analysis, -7.007e+09s mem.mgmt); compute time: 4.315e-05s overall, 1.907e-06s searches, 4.125e-05s shuffle, 9.06e-06s switch, 3.099e-06s quadrants. -3 iterations (42 th.) took 0.04452s; avg 0.01484s ( +/- 61.16/102.93 %); best 0.005764s; worst 0.03012s; std dev. 0.01087 (taking best). -Reference operation time is 0.00576401 s (0.02498 Mflops) with 42 threads. -After split step 1: tpop: 0.005764 s ~Mflops: 0.025 nsubm:28 otn:42 -Applying split (16 -> 28 leaves, 42 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=0.98321x): 0.005667s -> 0.005764s, so IGNORING this instance. -Split (28 -> 28 leaves, 37 -> 37 subms) took 0.005423s (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 0.04476s; avg 0.01492s ( +/- 62.62/111.45 %); best 0.005578s; worst 0.03155s; std dev. 0.01179 (taking best). -Reference operation time is 0.00557804 s (0.02582 Mflops) with 42 threads. -After split step 2: tpop: 0.005578 s ~Mflops: 0.026 nsubm:28 otn:42 -Applying split (28 -> 28 leaves, 42 th.) yielded SPEEDUP of 1.016x: 0.005667s -> 0.005578s, so taking this instance. -Split (28 -> 28 leaves, 37 -> 37 subms) took 0.007508s (of which: 3.815e-06s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. -3 iterations (42 th.) took 0.03352s; avg 0.01117s ( +/- 16.42/ 9.76 %); best 0.009339s; worst 0.01226s; std dev. 0.001305 (taking best). -Reference operation time is 0.00933909 s (0.01542 Mflops) with 42 threads. -After split step 3: tpop: 0.009339 s ~Mflops: 0.015 nsubm:28 otn:42 -Applying split (28 -> 28 leaves, 42 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.674x: 0.005578s -> 0.009339s. -Skipping further split based tests after 1 definite performance degradations in a row (and last exceeding limit). -A total of 3 split steps (of max 6) (16 -> 28 subms) took 0.1602s (of which 0.02051s partitioning, 0s I/O); computing times: 4.315e-05s in par. loops, 1.907e-06s sorting, 1.097e-05s analyzing) -Total split + benchmarking process took 0.1602s, equivalent to 28.7/28.3 new/old ops (0.03936s for 2 clones -- as 7.1/6.9 ops, or 3.5/3.5 ops per clone), SPEEDUP of 1.016x -Applying multi-split (16 -> 28 leaves, 2 steps, 0 -> 42 th.sp.) yielded SPEEDUP of 1.016x (0.005667s -> 0.005578s), will amortize in 1796.9 ops by saving 8.917e-05s per op. -In 1 tuning rounds (tot. 0.32s, 0.062s for constructor, 3 clones) obtained a SPEEDUP of 1.6% (1.016x) (from 0.02541 to 0.02582 Mflops). -After 0.322082s, global autotuning declared speedup of 1.01599 x, when using threads count of 42 and a new matrix: -(6 x 6)[0x55fc1ff0b3a0]{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:'' +3 iterations (20 th.) took 0.1119s; avg 0.03731s ( +/- 14.42/ 28.62 %); best 0.03193s; worst 0.04799s; std dev. 0.00755 (taking best). +Reference operation time is 0.0319328 s (0.004509 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: 0.03193 Mflops: 0.005) +Merge (16 -> 10 leaves) took w.c.t. of 0.02008s, ~6.08e-05s of computing time (of which 7.868e-06s sorting, 7.868e-06s analysis) +3 iterations (20 th.) took 0.1199s; avg 0.03996s ( +/- 59.86/ 79.89 %); best 0.01604s; worst 0.07188s; std dev. 0.02349 (taking best). +Reference operation time is 0.0160389 s (0.008978 Mflops) with 20 threads. +After merge step 1: tpop: 0.01604 s ~Mflops: 0.009 nsubm:10 otn:20 +Applying merge (16 -> 10 leaves, 20 th.) yielded SPEEDUP of 1.991x: 0.03193s -> 0.01604s, so taking this instance. +Merge (10 -> 7 leaves) took w.c.t. of 6.39e-05s, ~2.313e-05s of computing time (of which 2.861e-06s sorting, 2.861e-06s analysis) +3 iterations (20 th.) took 0.09593s; avg 0.03198s ( +/- 4.92/ 5.10 %); best 0.0304s; worst 0.03361s; std dev. 0.001309 (taking best). +Reference operation time is 0.0304029 s (0.004736 Mflops) with 20 threads. +After merge step 2: tpop: 0.0304 s ~Mflops: 0.005 nsubm:7 otn:20 +Applying merge (10 -> 7 leaves, 20 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.896x: 0.01604s -> 0.0304s. +Skipping further merge based tests after 1 definite performance degradations in a row (and last exceeding limit). +A total of 2 merge steps (of max 6) (16 -> 7 subms) took 0.3482s (of which 0.02017s partitioning, 0s I/O); computing times: 8.392e-05s in par. loops, 1.073e-05s sorting, 1.073e-05s analyzing) +Total merge + benchmarking process took 0.3482s, equivalent to 21.7/10.9 new/old ops (0.1919s for 2 clones -- as 12.0/6.0 ops, or 6.0/3.0 ops per clone), SPEEDUP of 1.991x +Applying multi-merge (16 -> 10 leaves, 1 steps, 0 -> 20 th.sp.) yielded SPEEDUP of 1.991x (0.03193s -> 0.01604s), will amortize in 21.9 ops by saving 0.01589s per op. +In 1 tuning rounds (tot. 0.54s, 0.19s for constructor, 2 clones) obtained a SPEEDUP of 99.1% (1.991x) (from 0.004509 to 0.008978 Mflops). +After 0.540227s, global autotuning declared speedup of 1.99096 x, when using threads count of 20 and a new matrix: +(6 x 6)[0x55b39df9c0c0]{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: 10, symflags:'' Considering C clone. Building a matrix with 36 nnz, 6 x 6 Duplicates check: 36 - 0 = 36 - converted COO to RSB in 4.367e-02 s (100.00 %) - analyzed arrays in 1.552e-02 s (35.55 %) - cleaned-up arrays in 9.537e-07 s (0.00 %) - deduplicated arrays in 1.192e-06 s (0.00 %) + converted COO to RSB in 2.357e-01 s (100.00 %) + analyzed arrays in 9.166e-02 s (38.89 %) + cleaned-up arrays in 1.216e-05 s (0.01 %) + deduplicated arrays in 0.000e+00 s (0.00 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.315e-02 s (30.12 %) - memory allocations took 6.199e-06 s (0.01 %) - leafs setup took 2.146e-06 s (0.00 %) - halfword conversion took 1.498e-02 s (34.30 %) -Built (6 x 6)[0x55fc1fefe780]{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 8.000e-02 s (33.95 %) + memory allocations took 1.383e-05 s (0.01 %) + leafs setup took 1.907e-06 s (0.00 %) + halfword conversion took 6.398e-02 s (27.15 %) +Built (6 x 6)[0x55b39dfa6670]{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)[0x55fc1fefe780]{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)[0x55b39dfa6670]{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 0.02851s; avg 0.009503s ( +/- 25.47/ 26.67 %); best 0.007083s; worst 0.01204s; std dev. 0.002024 (taking best). -Reference operation time is 0.00708294 s (0.08132 Mflops) with 42 threads. -After 0.028532s, autotuning routine did not find a better threads count configuration. +3 iterations (20 th.) took 0.09188s; avg 0.03063s ( +/- 10.26/ 5.94 %); best 0.02749s; worst 0.03245s; std dev. 0.002231 (taking best). +Reference operation time is 0.0274851 s (0.02096 Mflops) with 20 threads. +After 0.091968s, 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 0.0207s; avg 0.0069s ( +/- 69.87/ 36.11 %); best 0.002079s; worst 0.009391s; std dev. 0.003409 (taking best). -Reference operation time is 0.00207901 s (0.2771 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: 0.002079 Mflops: 0.277) -Merge (22 -> 16 leaves) took w.c.t. of 0.003839s, ~1.097e-05s of computing time (of which 1.907e-06s sorting, 7.153e-06s analysis) -3 iterations (42 th.) took 0.03217s; avg 0.01072s ( +/- 47.31/ 94.12 %); best 0.005651s; worst 0.02082s; std dev. 0.007137 (taking best). -Reference operation time is 0.005651 s (0.1019 Mflops) with 42 threads. -After merge step 1: tpop: 0.005651 s ~Mflops: 0.102 nsubm:16 otn:42 -Applying merge (22 -> 16 leaves, 42 th.) yielded SLOWDOWN (1th of 3 tolerable) of 2.718x: 0.002079s -> 0.005651s. +3 iterations (20 th.) took 0.08799s; avg 0.02933s ( +/- 19.18/ 10.14 %); best 0.02371s; worst 0.03231s; std dev. 0.003979 (taking best). +Reference operation time is 0.0237069 s (0.0243 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: 0.02371 Mflops: 0.024) +Merge (22 -> 16 leaves) took w.c.t. of 0.01601s, ~0.008051s of computing time (of which 0.007992s sorting, 0s analysis) +3 iterations (20 th.) took 0.1199s; avg 0.03997s ( +/- 59.99/ 79.92 %); best 0.01599s; worst 0.07191s; std dev. 0.02351 (taking best). +Reference operation time is 0.01599 s (0.03602 Mflops) with 20 threads. +After merge step 1: tpop: 0.01599 s ~Mflops: 0.036 nsubm:16 otn:20 +Applying merge (22 -> 16 leaves, 20 th.) yielded SPEEDUP of 1.483x: 0.02371s -> 0.01599s, so taking this instance. +Merge (16 -> 10 leaves) took w.c.t. of 0.01596s, ~5.698e-05s of computing time (of which 6.914e-06s sorting, 1.407e-05s analysis) +3 iterations (20 th.) took 0.0999s; avg 0.0333s ( +/- 4.00/ 7.91 %); best 0.03197s; worst 0.03593s; std dev. 0.001862 (taking best). +Reference operation time is 0.0319681 s (0.01802 Mflops) with 20 threads. +After merge step 2: tpop: 0.03197 s ~Mflops: 0.018 nsubm:10 otn:20 +Applying merge (16 -> 10 leaves, 20 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.999x: 0.01599s -> 0.03197s. 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 0.03604s (of which 0.003846s partitioning, 0s I/O); computing times: 1.097e-05s in par. loops, 1.907e-06s sorting, 7.153e-06s analyzing) -Total merge + benchmarking process took 0.03604s, equivalent to 17.3/17.3 new/old ops (0.01773s for 1 clones -- as 8.5/8.5 ops, or 8.5/8.5 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 0.02139s; avg 0.007131s ( +/- 20.29/ 11.36 %); best 0.005684s; worst 0.007941s; std dev. 0.001025 (taking best). -Reference operation time is 0.00568414 s (0.1013 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 C, 36 nnz, 6 nnz/r, 29 subms, 22 lsubms, 4.6667 bpnz (tpop: 0.005684 Mflops: 0.101) -Split (22 -> 28 leaves, 29 -> 37 subms) took 0.001891s (of which: 5.96e-06s analysis, -3.503e+09s mem.mgmt); compute time: 2.289e-05s overall, 2.861e-06s searches, 2.003e-05s shuffle, 7.153e-06s switch, 3.338e-06s quadrants. -3 iterations (42 th.) took 0.05658s; avg 0.01886s ( +/- 59.85/100.97 %); best 0.007572s; worst 0.0379s; std dev. 0.01354 (taking best). -Reference operation time is 0.00757217 s (0.07607 Mflops) with 42 threads. -After split step 1: tpop: 0.007572 s ~Mflops: 0.076 nsubm:28 otn:42 -Applying split (22 -> 28 leaves, 42 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.332x: 0.005684s -> 0.007572s. -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 -> 28 subms) took 0.05852s (of which 0.00191s partitioning, 0s I/O); computing times: 2.289e-05s in par. loops, 2.861e-06s sorting, 5.96e-06s analyzing) -Total split + benchmarking process took 0.05852s, equivalent to 10.3/10.3 new/old ops (0.01877s for 1 clones -- as 3.3/3.3 ops, or 3.3/3.3 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) -In 1 tuning rounds (tot. 0.17s, 0.037s for constructor, 2 clones) obtained NO speedup (best stays 0.1013 Mflops). -After 0.173356s, global autotuning found old matrix optimal, with declared speedup 1 x when using 42 threads +A total of 2 merge steps (of max 6) (22 -> 10 subms) took 0.3484s (of which 0.03209s partitioning, 0s I/O); computing times: 0.008108s in par. loops, 0.007999s sorting, 1.407e-05s analyzing) +Total merge + benchmarking process took 0.3484s, equivalent to 21.8/14.7 new/old ops (0.1919s for 2 clones -- as 12.0/8.1 ops, or 6.0/4.0 ops per clone), SPEEDUP of 1.483x +Applying multi-merge (22 -> 16 leaves, 1 steps, 0 -> 20 th.sp.) yielded SPEEDUP of 1.483x (0.02371s -> 0.01599s), will amortize in 45.2 ops by saving 0.007717s per op. +In 1 tuning rounds (tot. 0.53s, 0.19s for constructor, 2 clones) obtained a SPEEDUP of 48.3% (1.483x) (from 0.0243 to 0.03602 Mflops). +After 0.532455s, global autotuning declared speedup of 1.48261 x, when using threads count of 20 and a new matrix: +(6 x 6)[0x55b39df9ee10]{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: 16, symflags:'' Considering Z clone. Building a matrix with 36 nnz, 6 x 6 Duplicates check: 36 - 0 = 36 - converted COO to RSB in 4.848e-02 s (100.00 %) - analyzed arrays in 1.669e-02 s (34.42 %) - cleaned-up arrays in 9.537e-07 s (0.00 %) - deduplicated arrays in 1.192e-06 s (0.00 %) - sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.514e-02 s (31.24 %) - memory allocations took 6.914e-06 s (0.01 %) - leafs setup took 4.053e-06 s (0.01 %) - halfword conversion took 1.663e-02 s (34.31 %) -Built (6 x 6)[0x55fc1ff043e0]{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 1.955e-01 s (100.00 %) + analyzed arrays in 7.147e-02 s (36.56 %) + cleaned-up arrays in 1.192e-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 5.999e-02 s (30.69 %) + memory allocations took 2.170e-05 s (0.01 %) + leafs setup took 2.003e-05 s (0.01 %) + halfword conversion took 6.394e-02 s (32.71 %) +Built (6 x 6)[0x55b39dfa6650]{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)[0x55fc1ff043e0]{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)[0x55b39dfa6650]{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 0.0203s; avg 0.006766s ( +/- 34.29/ 22.43 %); best 0.004446s; worst 0.008283s; std dev. 0.001666 (taking best). -Reference operation time is 0.00444603 s (0.1296 Mflops) with 42 threads. -After 0.020329s, autotuning routine did not find a better threads count configuration. +3 iterations (20 th.) took 0.08397s; avg 0.02799s ( +/- 14.46/ 28.56 %); best 0.02394s; worst 0.03598s; std dev. 0.005653 (taking best). +Reference operation time is 0.023941 s (0.02406 Mflops) with 20 threads. +After 0.084039s, 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 0.02173s; avg 0.007245s ( +/- 36.44/ 31.86 %); best 0.004605s; worst 0.009553s; std dev. 0.002034 (taking best). -Reference operation time is 0.00460505 s (0.1251 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: 0.004605 Mflops: 0.125) -Merge (28 -> 22 leaves) took w.c.t. of 0.001885s, ~1.097e-05s of computing time (of which 9.537e-07s sorting, 5.007e-06s analysis) -3 iterations (42 th.) took 0.05371s; avg 0.0179s ( +/- 67.93/121.92 %); best 0.005742s; worst 0.03973s; std dev. 0.01547 (taking best). -Reference operation time is 0.00574207 s (0.1003 Mflops) with 42 threads. -After merge step 1: tpop: 0.005742 s ~Mflops: 0.100 nsubm:22 otn:42 -Applying merge (28 -> 22 leaves, 42 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.247x: 0.004605s -> 0.005742s. +3 iterations (20 th.) took 0.06563s; avg 0.02188s ( +/- 19.33/ 9.69 %); best 0.01765s; worst 0.024s; std dev. 0.00299 (taking best). +Reference operation time is 0.0176489 s (0.03264 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: 0.01765 Mflops: 0.033) +Merge (28 -> 22 leaves) took w.c.t. of 0.01433s, ~4.792e-05s of computing time (of which 2.217e-05s sorting, 1.001e-05s analysis) +3 iterations (20 th.) took 0.152s; avg 0.05065s ( +/- 37.07/ 73.67 %); best 0.03187s; worst 0.08796s; std dev. 0.02638 (taking best). +Reference operation time is 0.031873 s (0.01807 Mflops) with 20 threads. +After merge step 1: tpop: 0.03187 s ~Mflops: 0.018 nsubm:22 otn:20 +Applying merge (28 -> 22 leaves, 20 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.806x: 0.01765s -> 0.03187s. 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) (28 -> 22 subms) took 0.05562s (of which 0.001892s partitioning, 0s I/O); computing times: 1.097e-05s in par. loops, 9.537e-07s sorting, 5.007e-06s analyzing) -Total merge + benchmarking process took 0.05562s, equivalent to 12.1/12.1 new/old ops (0.02416s for 1 clones -- as 5.2/5.2 ops, or 5.2/5.2 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) +A total of 1 merge steps (of max 6) (28 -> 22 subms) took 0.1664s (of which 0.01436s partitioning, 0s I/O); computing times: 4.792e-05s in par. loops, 2.217e-05s sorting, 1.001e-05s analyzing) +Total merge + benchmarking process took 0.1664s, equivalent to 9.4/9.4 new/old ops (0.08788s for 1 clones -- as 5.0/5.0 ops, or 5.0/5.0 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 0.0197s; avg 0.006566s ( +/- 19.04/ 15.50 %); best 0.005316s; worst 0.007584s; std dev. 0.0009403 (taking best). -Reference operation time is 0.00531602 s (0.1084 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 Z, 36 nnz, 6 nnz/r, 37 subms, 28 lsubms, 4.4444 bpnz (tpop: 0.005316 Mflops: 0.108) -Split (28 -> 28 leaves, 37 -> 37 subms) took 0.003557s (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 0.02743s; avg 0.009142s ( +/- 39.74/ 40.81 %); best 0.005509s; worst 0.01287s; std dev. 0.003007 (taking best). -Reference operation time is 0.0055089 s (0.1046 Mflops) with 42 threads. -After split step 1: tpop: 0.005509 s ~Mflops: 0.105 nsubm:28 otn:42 -Applying split (28 -> 28 leaves, 42 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.036x: 0.005316s -> 0.005509s. -Split (28 -> 28 leaves, 37 -> 37 subms) took 0.007657s (of which: 5.96e-06s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. -3 iterations (42 th.) took 0.03429s; avg 0.01143s ( +/- 49.79/ 67.70 %); best 0.005739s; worst 0.01917s; std dev. 0.005671 (taking best). -Reference operation time is 0.00573897 s (0.1004 Mflops) with 42 threads. -After split step 2: tpop: 0.005739 s ~Mflops: 0.100 nsubm:28 otn:42 -Applying split (28 -> 28 leaves, 42 th.) yielded SLOWDOWN (2th of 3 tolerable) of 1.080x: 0.005316s -> 0.005739s. -Split (28 -> 28 leaves, 37 -> 37 subms) took 0.005457s (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 0.02644s; avg 0.008815s ( +/- 36.81/ 50.57 %); best 0.00557s; worst 0.01327s; std dev. 0.003259 (taking best). -Reference operation time is 0.00556993 s (0.1034 Mflops) with 42 threads. -After split step 3: tpop: 0.00557 s ~Mflops: 0.103 nsubm:28 otn:42 -Applying split (28 -> 28 leaves, 42 th.) yielded SLOWDOWN (3th of 3 tolerable) of 1.048x: 0.005316s -> 0.00557s. -Split (28 -> 28 leaves, 37 -> 37 subms) took 0.002298s (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 0.03408s; avg 0.01136s ( +/- 53.55/100.71 %); best 0.005277s; worst 0.0228s; std dev. 0.008095 (taking best). -Reference operation time is 0.00527716 s (0.1091 Mflops) with 42 threads. -After split step 4: tpop: 0.005277 s ~Mflops: 0.109 nsubm:28 otn:42 -Applying split (28 -> 28 leaves, 42 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=1.00736x): 0.005316s -> 0.005277s, so IGNORING this instance. -Split (28 -> 28 leaves, 37 -> 37 subms) took 0.001909s (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 0.03713s; avg 0.01238s ( +/- 54.14/ 96.89 %); best 0.005676s; worst 0.02437s; std dev. 0.008498 (taking best). -Reference operation time is 0.00567603 s (0.1015 Mflops) with 42 threads. -After split step 5: tpop: 0.005676 s ~Mflops: 0.101 nsubm:28 otn:42 -Applying split (28 -> 28 leaves, 42 th.) yielded SLOWDOWN (4th of 3 tolerable) of 1.068x: 0.005316s -> 0.005676s. -Skipping further split based tests after 4 definite performance degradations in a row. -A total of 5 split steps (of max 6) (28 -> 28 subms) took 0.1804s (of which 0.02095s partitioning, 0s I/O); computing times: 0s in par. loops, 0s sorting, 2.217e-05s analyzing) -Total split + benchmarking process took 0.1804s, equivalent to 33.9/33.9 new/old ops (0.02307s for 1 clones -- as 4.3/4.3 ops, or 4.3/4.3 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) -In 1 tuning rounds (tot. 0.33s, 0.047s for constructor, 2 clones) obtained NO speedup (best stays 0.1084 Mflops). -After 0.326885s, global autotuning found old matrix optimal, with declared speedup 1 x when using 42 threads +3 iterations (20 th.) took 0.07987s; avg 0.02662s ( +/- 39.85/ 20.00 %); best 0.01602s; worst 0.03195s; std dev. 0.007502 (taking best). +Reference operation time is 0.0160151 s (0.03597 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: 0.01602 Mflops: 0.036) +Split (28 -> 28 leaves, 37 -> 37 subms) took 0.03154s (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 0.07979s; avg 0.0266s ( +/- 40.00/ 20.48 %); best 0.01596s; worst 0.03204s; std dev. 0.007523 (taking best). +Reference operation time is 0.0159581 s (0.03609 Mflops) with 20 threads. +After split step 1: tpop: 0.01596 s ~Mflops: 0.036 nsubm:28 otn:20 +Applying split (28 -> 28 leaves, 20 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=1.00357x): 0.01602s -> 0.01596s, so IGNORING this instance. +Split (28 -> 28 leaves, 37 -> 37 subms) took 0.03197s (of which: 3.099e-06s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. +3 iterations (20 th.) took 0.09194s; avg 0.03065s ( +/- 61.15/ 56.87 %); best 0.01191s; worst 0.04807s; std dev. 0.01479 (taking best). +Reference operation time is 0.0119069 s (0.04838 Mflops) with 20 threads. +After split step 2: tpop: 0.01191 s ~Mflops: 0.048 nsubm:28 otn:20 +Applying split (28 -> 28 leaves, 20 th.) yielded SPEEDUP of 1.345x: 0.01602s -> 0.01191s, so taking this instance. +Split (28 -> 28 leaves, 37 -> 37 subms) took 0.03188s (of which: 1.121e-05s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. +3 iterations (20 th.) took 0.09199s; avg 0.03066s ( +/- 9.11/ 4.60 %); best 0.02787s; worst 0.03207s; std dev. 0.001976 (taking best). +Reference operation time is 0.0278699 s (0.02067 Mflops) with 20 threads. +After split step 3: tpop: 0.02787 s ~Mflops: 0.021 nsubm:28 otn:20 +Applying split (28 -> 28 leaves, 20 th.) yielded SLOWDOWN (1th of 3 tolerable) of 2.341x: 0.01191s -> 0.02787s. +Skipping further split based tests after 1 definite performance degradations in a row (and last exceeding limit). +A total of 3 split steps (of max 6) (28 -> 28 subms) took 0.4396s (of which 0.09564s partitioning, 0s I/O); computing times: 0s in par. loops, 0s sorting, 2.527e-05s analyzing) +Total split + benchmarking process took 0.4396s, equivalent to 36.9/27.4 new/old ops (0.16s for 2 clones -- as 13.4/10.0 ops, or 6.7/5.0 ops per clone), SPEEDUP of 1.345x +Applying multi-split (28 -> 28 leaves, 2 steps, 0 -> 20 th.sp.) yielded SPEEDUP of 1.345x (0.01602s -> 0.01191s), will amortize in 107.0 ops by saving 0.004108s per op. +In 1 tuning rounds (tot. 0.92s, 0.25s for constructor, 3 clones) obtained a SPEEDUP of 34.5% (1.345x) (from 0.03597 to 0.04838 Mflops). +After 0.920048s, global autotuning declared speedup of 1.34503 x, when using threads count of 20 and a new matrix: +(6 x 6)[0x55b39dfa9da0]{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' @@ -9206,9 +9168,9 @@ 4 0 DIFF PRINT TEST END Beginning large binary search test. -Detected 84312055808 bytes of memory, comprehensive of 58613551104 of free memory. +Detected 84859285504 bytes of memory, comprehensive of 17034919936 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 (17592186037187 MB) than on the maximal coordinate indices array (18446744066130107392) allows. +Will perform the test using less memory (17592186040216 MB) than on the maximal coordinate indices array (18446744069305872384) allows. Skipping test: too little memory. Skipping large binary search test. BASIC SPARSE BLAS TEST: BEGIN @@ -9217,7 +9179,7 @@ got RSB_IO_WANT_IS_INITIALIZED_MARKER: 1 INIT INTERFACE TEST: END (SUCCESS) DEVEL PRINT TEST: BEGIN -(4 x 4)[0x55bf49d7ae70]{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)[0x562bf5136740]{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 | @@ -9226,8 +9188,8 @@ RSB_FLAG_ASSEMBLED_IN_COO_ARRAYS | RSB_FLAG_OWN_PARTITIONING_ARRAYS | RSB_FLAG_SORT_INPUT -(2 x 2)[0x55bf49d7af80]{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)[0x55bf49d7b090]{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)[0x562bf5136850]{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)[0x562bf5136960]{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%) @@ -9235,9 +9197,9 @@ ( 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)[0x55bf49d7af80]{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)[0x55bf49d7b090]{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)[0x55bf49d7ae70]{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)[0x562bf5136850]{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)[0x562bf5136960]{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)[0x562bf5136740]{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 | @@ -9255,8 +9217,8 @@ 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 30.010221 s, max allowed was 30.000000. - PASSED:3319 +Terminating testing earlier due to user timeout request: test took 30.011937 s, max allowed was 30.000000. + PASSED:586 FAILED:0 ADVANCED SPARSE BLAS TEST: END (SUCCESS) gmake qtests -C librsbpp @@ -9265,99 +9227,99 @@ 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 -++ grep Z-sort +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 ++ wc -l +++ grep Z-sort +++ ./rsbpp Td,s G.mtx + test 54 = 54 -++ ./rsbpp Td G.mtx ++ grep Z-sort +++ ./rsbpp Td G.mtx ++ wc -l + test 27 = 27 ++ ./rsbpp Td,z G.mtx -++ wc -l -++ grep Z-sort -+ test 54 = 54 -++ ./rsbpp vTd,z G.mtx ++ grep Z-sort ++ wc -l + test 54 = 54 -++ ./rsbpp vTd,z G.mtx +++ wc -l ++ grep Z-sort +++ ./rsbpp vTd,z G.mtx ++ test 54 = 54 ++ wc -l +++ grep Z-sort +++ ./rsbpp vTd,z G.mtx + test 54 = 54 -++ ./rsbpp vvvTd,z G.mtx -++ grep Zorted ++ wc -l +++ grep Zorted +++ ./rsbpp vvvTd,z G.mtx + test 8 = 8 -++ ./rsbpp vvTd,z G.mtx ++ grep Z-sort ++ wc -l -+ test 54 = 54 ++ ./rsbpp vvTd,z G.mtx ++ test 54 = 54 ++ grep Range +++ ./rsbpp vvTd,z G.mtx ++ wc -l + test 0 = 0 -++ ./rsbpp vvvTd,z G.mtx ++ wc -l ++ grep Range +++ ./rsbpp vvvTd,z G.mtx + test 258 -gt 0 -++ ./rsbpp vvvTd,z S.mtx -++ grep Range ++ wc -l +++ grep Range +++ ./rsbpp vvvTd,z S.mtx + test 0 -eq 0 ++ ./rsbpp vvvTd,z G.mtx -++ grep Range ++ wc -l +++ grep Range + test 258 = 258 +++ grep spmm- ++ OMP_NUM_THREADS=1 ++ ./rsbpp m10M10I1r1,4,8sFv -++ grep spmm- ++ wc -l + test 9 = 9 -++ wc -l +++ grep spmm- ++ OMP_NUM_THREADS=1 +++ wc -l ++ ./rsbpp C1000m100M100I1r1,4,8sFv -++ grep spmm- + test 9 = 9 ++ wc -l ++ grep spmm- ++ OMP_NUM_THREADS=1 ++ ./rsbpp C1000m100M100I1r1sFvtN,T + test 3 = 3 -++ grep spmm- ++ wc -l +++ grep spmm- ++ OMP_NUM_THREADS=1 ++ ./rsbpp C1000m100M100I1r1vtN,TsF + test 2 = 2 +++ wc -l +++ grep spmm- ++ OMP_NUM_THREADS=1 ++ ./rsbpp C1000m100M100I1r0vtN,TsF -++ grep spmm- -++ wc -l + test 0 = 0 -++ grep Recursing ++ OMP_NUM_THREADS=1 -++ wc -l ++ RSB_NUM_THREADS=1 ++ ./rsbpp vvvC1000m100M100I1r1vtN,TorsF +++ grep Recursing +++ wc -l + test 4 = 4 +++ grep Recursing +++ wc -l ++ OMP_NUM_THREADS=2 ++ RSB_NUM_THREADS=2 ++ ./rsbpp vvvC1000m100M100I1r1vtN,TorsF -++ grep Recursing -++ wc -l + test 4 = 4 -++ grep Recursing ++ OMP_NUM_THREADS=1 ++ RSB_NUM_THREADS=1 ++ ./rsbpp vvvC1000m100M100I1r1vtN,ToRsF ++ wc -l +++ grep Recursing + test 208 = 208 ++ OMP_NUM_THREADS=2 ++ RSB_NUM_THREADS=2 ++ ./rsbpp vvvC1000m100M100I1r1vtN,ToRsF -++ grep Recursing ++ wc -l +++ grep Recursing + 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) @@ -9404,7 +9366,7 @@ 0 0 0 0 before tuning for SPMV: -(3 x 3)[0x55e9e27b6b50]{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)[0x55a5cf7e8390]{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 @@ -9493,18 +9455,18 @@ BEGIN Rsb_Matrix_test_multimatrix_ms_mnrhs BEGIN -(3 x 3)[0x55e9e27cce90]{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)[0x55e9e27cce90]{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)[0x55e9e27d9bf0]{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 1.07638: -(3 x 3)[0x55e9e27f6a00]{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)[0x55e9e27cce90]{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)[0x55e9e27cce90]{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)[0x55e9e27d9bf0]{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 1.49151: -(3 x 3)[0x55e9e27fa380]{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)[0x55a5cf80a200]{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 1.25113: +(3 x 3)[0x55a5cf820f10]{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)[0x55a5cf80a200]{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 1.46153: +(3 x 3)[0x55a5cf81e8c0]{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)[0x55a5cf80a200]{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 1.12514: +(3 x 3)[0x55a5cf825ba0]{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)[0x55a5cf80a200]{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 1.60517: +(3 x 3)[0x55a5cf81e8c0]{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 ! @@ -9521,10 +9483,10 @@ ./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 ionos15-amd64 +running on i-capture-the-hostname Built without the MKL. ( ! ./rsbtest --unrecognized-option-triggers-abort ) -running on ionos15-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 ) @@ -9533,7 +9495,7 @@ ( ! ./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 ionos15-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! @@ -9585,7 +9547,7 @@ 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; }; }) @@ -9595,7 +9557,7 @@ 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' @@ -9722,12 +9684,12 @@ 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 'librsb-doc' in '../librsb-doc_1.3.0.2+dfsg-6.1_all.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-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' in '../librsb0t64_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 dpkg-genchanges: info: binary-only upload (no source code included) @@ -9736,12 +9698,14 @@ 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/755909/tmp/hooks/B01_cleanup starting +I: user script /srv/workspace/pbuilder/755909/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/1814947 and its subdirectories -I: Current time: Fri Jul 4 13:07:08 -12 2025 -I: pbuilder-time-stamp: 1751677628 +I: removing directory /srv/workspace/pbuilder/755909 and its subdirectories +I: Current time: Sun Jun 2 10:08:41 +14 2024 +I: pbuilder-time-stamp: 1717272521