Diff of the two buildlogs: -- --- b1/build.log 2024-05-16 04:04:07.812955257 +0000 +++ b2/build.log 2024-05-16 04:22:32.013993501 +0000 @@ -1,6 +1,6 @@ I: pbuilder: network access will be disabled during build -I: Current time: Wed May 15 15:36:24 -12 2024 -I: pbuilder-time-stamp: 1715830584 +I: Current time: Thu Jun 19 00:27:12 +14 2025 +I: pbuilder-time-stamp: 1750242432 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/1272415/tmp/hooks/D02_print_environment starting +I: user script /srv/workspace/pbuilder/2591390/tmp/hooks/D01_modify_environment starting +debug: Running on codethink01-arm64. +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 18 10:27 /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/2591390/tmp/hooks/D01_modify_environment finished +I: user script /srv/workspace/pbuilder/2591390/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='arm64' - DEBIAN_FRONTEND='noninteractive' + 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]="aarch64-unknown-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=arm64 + DEBIAN_FRONTEND=noninteractive DEB_BUILD_OPTIONS='buildinfo=+all reproducible=+all parallel=12 ' - DISTRIBUTION='trixie' - HOME='/root' - HOST_ARCH='arm64' + DIRSTACK=() + DISTRIBUTION=trixie + EUID=0 + FUNCNAME=([0]="Echo" [1]="main") + GROUPS=() + HOME=/root + HOSTNAME=i-capture-the-hostname + HOSTTYPE=aarch64 + HOST_ARCH=arm64 IFS=' ' - INVOCATION_ID='ba2ab633fbef4663af033b764ed61dd4' - 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='1272415' - PS1='# ' - PS2='> ' + INVOCATION_ID=c63dcb88b6ec4082a3ca8055f53e1dad + LANG=C + LANGUAGE=nl_BE:nl + LC_ALL=C + MACHTYPE=aarch64-unknown-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=2591390 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.I41USMiz/pbuilderrc_jmdp --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.I41USMiz/b1 --logfile b1/build.log librsb_1.3.0.2+dfsg-6.1.dsc' - SUDO_GID='109' - SUDO_UID='104' - SUDO_USER='jenkins' - TERM='unknown' - TZ='/usr/share/zoneinfo/Etc/GMT+12' - USER='root' - _='/usr/bin/systemd-run' - http_proxy='http://192.168.101.4:3128' + 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.I41USMiz/pbuilderrc_uh9N --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.I41USMiz/b2 --logfile b2/build.log librsb_1.3.0.2+dfsg-6.1.dsc' + SUDO_GID=109 + SUDO_UID=104 + SUDO_USER=jenkins + TERM=unknown + TZ=/usr/share/zoneinfo/Etc/GMT-14 + UID=0 + USER=root + _='I: set' + http_proxy=http://192.168.101.4:3128 I: uname -a - Linux codethink04-arm64 6.1.0-21-cloud-arm64 #1 SMP Debian 6.1.90-1 (2024-05-03) aarch64 GNU/Linux + Linux i-capture-the-hostname 6.1.0-21-cloud-arm64 #1 SMP Debian 6.1.90-1 (2024-05-03) aarch64 GNU/Linux I: ls -l /bin - lrwxrwxrwx 1 root root 7 May 14 11:23 /bin -> usr/bin -I: user script /srv/workspace/pbuilder/1272415/tmp/hooks/D02_print_environment finished + lrwxrwxrwx 1 root root 7 Jun 16 17:48 /bin -> usr/bin +I: user script /srv/workspace/pbuilder/2591390/tmp/hooks/D02_print_environment finished -> Attempting to satisfy build-dependencies -> Creating pbuilder-satisfydepends-dummy package Package: pbuilder-satisfydepends-dummy @@ -289,7 +321,7 @@ Get: 169 http://deb.debian.org/debian trixie/main arm64 libltdl-dev arm64 2.4.7-7+b1 [165 kB] Get: 170 http://deb.debian.org/debian trixie/main arm64 libhwloc-dev arm64 2.10.0-1+b1 [234 kB] Get: 171 http://deb.debian.org/debian trixie/main arm64 zlib1g-dev arm64 1:1.3.dfsg-3.1 [915 kB] -Fetched 348 MB in 2s (155 MB/s) +Fetched 348 MB in 4s (81.7 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 ... 19744 files and directories currently installed.) @@ -853,8 +885,8 @@ Setting up tzdata (2024a-4) ... Current default time zone: 'Etc/UTC' -Local time is now: Thu May 16 03:37:35 UTC 2024. -Universal Time is now: Thu May 16 03:37:35 UTC 2024. +Local time is now: Wed Jun 18 10:29:12 UTC 2025. +Universal Time is now: Wed Jun 18 10:29:12 UTC 2025. Run 'dpkg-reconfigure tzdata' if you wish to change it. Setting up libfontenc1:arm64 (1:1.1.8-1) ... @@ -1021,7 +1053,11 @@ Building tag database... -> Finished parsing the build-deps I: Building the package -I: Running cd /build/reproducible-path/librsb-1.3.0.2+dfsg/ && env PATH="/usr/sbin:/usr/bin:/sbin:/bin:/usr/games" HOME="/nonexistent/first-build" dpkg-buildpackage -us -uc -b && env PATH="/usr/sbin:/usr/bin:/sbin:/bin:/usr/games" HOME="/nonexistent/first-build" dpkg-genchanges -S > ../librsb_1.3.0.2+dfsg-6.1_source.changes +I: user script /srv/workspace/pbuilder/2591390/tmp/hooks/A99_set_merged_usr starting +Not re-configuring usrmerge for trixie +I: user script /srv/workspace/pbuilder/2591390/tmp/hooks/A99_set_merged_usr finished +hostname: Name or service not known +I: Running cd /build/reproducible-path/librsb-1.3.0.2+dfsg/ && env PATH="/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/i/capture/the/path" HOME="/nonexistent/second-build" dpkg-buildpackage -us -uc -b && env PATH="/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/i/capture/the/path" HOME="/nonexistent/second-build" dpkg-genchanges -S > ../librsb_1.3.0.2+dfsg-6.1_source.changes dpkg-buildpackage: info: source package librsb dpkg-buildpackage: info: source version 1.3.0.2+dfsg-6.1 dpkg-buildpackage: info: source distribution unstable @@ -1049,62 +1085,62 @@ cp: warning: behavior of -n is non-portable and may change in future; use --update=none instead cp: warning: behavior of -n is non-portable and may change in future; use --update=none instead dh_autoreconf -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found libtoolize: putting auxiliary files in '.'. libtoolize: copying file './ltmain.sh' libtoolize: putting macros in AC_CONFIG_MACRO_DIRS, 'm4'. @@ -1146,90 +1182,90 @@ libtoolize: copying file 'm4/ltsugar.m4' libtoolize: copying file 'm4/ltversion.m4' libtoolize: copying file 'm4/lt~obsolete.m4' -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found +sh: line 1: git: command not found configure.ac:66: installing './compile' configure.ac:65: installing './missing' Makefile.am: installing './depcomp' @@ -1412,7 +1448,7 @@ checking for m4... m4 checking for gmake... gmake checking for ggrep... /usr/bin/grep -checking for bash... /bin/bash +checking for bash... /bin/sh checking for gsed... /usr/bin/sed checking for cmp... cmp checking for basename... basename @@ -1529,7 +1565,7 @@ configure: It appears that Fortran programs can be linked without using the Fortran linker. configure: Using OPENMP_CFLAGS ok for linking an OpenMP program: adding it to LIBS. checking if your have a usable getrusage() ... 1 -checking for /bin/bash... /bin/bash +checking for /bin/sh... /bin/sh configure: Will not use Google Test. configure: You seem to not have GNU Octave or have disabled 'int' type. Part of the test suite will not be generated. If you want more testing capabilities, you should enable the 'int' type as well. checking that generated files are newer than configure... done @@ -1551,7 +1587,7 @@ config.status: executing depfiles commands config.status: executing libtool commands === configuring in librsbpp (/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp) -configure: running /bin/bash ./configure --disable-option-checking '--prefix=/usr' '--build=aarch64-linux-gnu' '--includedir=${prefix}/include' '--mandir=${prefix}/share/man' '--infodir=${prefix}/share/info' '--sysconfdir=/etc' '--localstatedir=/var' '--disable-silent-rules' '--libdir=${prefix}/lib/aarch64-linux-gnu' '--runstatedir=/run' '--disable-maintainer-mode' '--disable-dependency-tracking' '--with-memhinfo=L2:4/64/512K,L1:8/64/24K' '--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=aarch64-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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard' 'BASH=/bin/bash' --cache-file=/dev/null --srcdir=. +configure: running /bin/sh ./configure --disable-option-checking '--prefix=/usr' '--build=aarch64-linux-gnu' '--includedir=${prefix}/include' '--mandir=${prefix}/share/man' '--infodir=${prefix}/share/info' '--sysconfdir=/etc' '--localstatedir=/var' '--disable-silent-rules' '--libdir=${prefix}/lib/aarch64-linux-gnu' '--runstatedir=/run' '--disable-maintainer-mode' '--disable-dependency-tracking' '--with-memhinfo=L2:4/64/512K,L1:8/64/24K' '--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=aarch64-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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard' 'BASH=/bin/sh' --cache-file=/dev/null --srcdir=. checking for a BSD-compatible install... /usr/bin/install -c checking whether build environment is sane... yes checking for a race-free mkdir -p... /usr/bin/mkdir -p @@ -1673,7 +1709,7 @@ configure: Will not use Google Test. checking whether you have std::thread... yes checking whether you have std::mutex... yes -/bin/bash +/bin/sh checking that generated files are newer than configure... done configure: creating ./config.status config.status: creating Makefile @@ -1682,7 +1718,7 @@ config.status: executing libtool commands configure: Successfully created a Makefile. === configuring in rsblib (/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib) -configure: running /bin/bash ./configure --disable-option-checking '--prefix=/usr' '--build=aarch64-linux-gnu' '--includedir=${prefix}/include' '--mandir=${prefix}/share/man' '--infodir=${prefix}/share/info' '--sysconfdir=/etc' '--localstatedir=/var' '--disable-silent-rules' '--libdir=${prefix}/lib/aarch64-linux-gnu' '--runstatedir=/run' '--disable-maintainer-mode' '--disable-dependency-tracking' '--with-memhinfo=L2:4/64/512K,L1:8/64/24K' '--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=aarch64-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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard' 'BASH=/bin/bash' --cache-file=/dev/null --srcdir=. +configure: running /bin/sh ./configure --disable-option-checking '--prefix=/usr' '--build=aarch64-linux-gnu' '--includedir=${prefix}/include' '--mandir=${prefix}/share/man' '--infodir=${prefix}/share/info' '--sysconfdir=/etc' '--localstatedir=/var' '--disable-silent-rules' '--libdir=${prefix}/lib/aarch64-linux-gnu' '--runstatedir=/run' '--disable-maintainer-mode' '--disable-dependency-tracking' '--with-memhinfo=L2:4/64/512K,L1:8/64/24K' '--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=aarch64-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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard' 'BASH=/bin/sh' --cache-file=/dev/null --srcdir=. checking for a BSD-compatible install... /usr/bin/install -c checking whether build environment is sane... yes checking for a race-free mkdir -p... /usr/bin/mkdir -p @@ -1791,7 +1827,7 @@ checking for filesystem... yes checking for main in -lstdc++fs... yes configure: Assuming you are yet to build librsb.la. (set LIBS= -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la) -/bin/bash +/bin/sh checking that generated files are newer than configure... done configure: creating ./config.status config.status: creating Makefile @@ -1801,7 +1837,7 @@ config.status: executing libtool commands configure: Created a Makefile. === configuring in rsbtest (/build/reproducible-path/librsb-1.3.0.2+dfsg/rsbtest) -configure: running /bin/bash ./configure --disable-option-checking '--prefix=/usr' '--build=aarch64-linux-gnu' '--includedir=${prefix}/include' '--mandir=${prefix}/share/man' '--infodir=${prefix}/share/info' '--sysconfdir=/etc' '--localstatedir=/var' '--disable-silent-rules' '--libdir=${prefix}/lib/aarch64-linux-gnu' '--runstatedir=/run' '--disable-maintainer-mode' '--disable-dependency-tracking' '--with-memhinfo=L2:4/64/512K,L1:8/64/24K' '--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=aarch64-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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard' 'BASH=/bin/bash' --cache-file=/dev/null --srcdir=. +configure: running /bin/sh ./configure --disable-option-checking '--prefix=/usr' '--build=aarch64-linux-gnu' '--includedir=${prefix}/include' '--mandir=${prefix}/share/man' '--infodir=${prefix}/share/info' '--sysconfdir=/etc' '--localstatedir=/var' '--disable-silent-rules' '--libdir=${prefix}/lib/aarch64-linux-gnu' '--runstatedir=/run' '--disable-maintainer-mode' '--disable-dependency-tracking' '--with-memhinfo=L2:4/64/512K,L1:8/64/24K' '--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=aarch64-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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard' 'BASH=/bin/sh' --cache-file=/dev/null --srcdir=. checking for a BSD-compatible install... /usr/bin/install -c checking whether build environment is sane... yes checking for a race-free mkdir -p... /usr/bin/mkdir -p @@ -1912,7 +1948,7 @@ checking for filesystem... yes checking for rsb_lib_init... no checking for dd... yes -/bin/bash +/bin/sh /usr/bin/timeout checking that generated files are newer than configure... done configure: creating ./config.status @@ -1944,7 +1980,7 @@ ARFLAGS : cru M4 : m4 MAKE : gmake - BASH : /bin/bash + BASH : /bin/sh OCTAVE : false DOXYGEN : doxygen HELP2MAN : help2man @@ -2000,23 +2036,23 @@ 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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -DRSBPP_HAS_RSB_H=1 -Wl,-z -Wl,relro -o rsbpp rsbpp.o ./.libs/librsbpp.a -lpthread -lstdc++fs -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -DRSBPP_HAS_RSB_H=1 -Wl,-z -Wl,relro -o rsbct rsbct.o ./.libs/librsbpp.a -lpthread -lstdc++fs -fopenmp +libtool: link: g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -mbranch-protection=standard -DRSBPP_HAS_RSB_H=1 -Wl,-z -Wl,relro -o rsbtt rsbtt.o ./.libs/librsbpp.a -lpthread -lstdc++fs -fopenmp gmake all-am gmake[5]: Entering directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp' @@ -2035,89 +2071,83 @@ gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl.lo `test -f 'rsb_krnl.c' || echo './'`rsb_krnl.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 -mbranch-protection=standard -O3 -std=c99 -c rsb_stropts.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_stropts.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 -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 -mbranch-protection=standard -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl.lo `test -f 'rsb_krnl.c' || echo './'`rsb_krnl.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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c rsb_mergesort.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_mergesort.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 -mbranch-protection=standard -O3 -std=c99 -c -o librsb_nounroll_la-rsb_bench.lo `test -f 'rsb_bench.c' || echo './'`rsb_bench.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 -mbranch-protection=standard -O3 -std=c99 -c rsb_krnl_lb.c -o librsb_nounroll_la-rsb_krnl_lb.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 -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c -o librsb_nounroll_la-rsb_permute.lo `test -f 'rsb_permute.c' || echo './'`rsb_permute.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 -mbranch-protection=standard -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/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 -mbranch-protection=standard -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_bcss_u.lo `test -f 'rsb_krnl_bcss_u.c' || echo './'`rsb_krnl_bcss_u.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_bench.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_bench.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 -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 -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_bcss_u.lo `test -f 'rsb_krnl_bcss_u.c' || echo './'`rsb_krnl_bcss_u.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c rsb_mergesort.c -o librsb_nounroll_la-rsb_mergesort.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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c rsb_permute.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_permute.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 -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+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 -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c rsb_krnl_bcss_l.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_bcss_l.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 -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c rsb_krnl_bcss_u.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_bcss_u.o +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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/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 -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c rsb_krnl_bcss_spmv_u.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_bcss_spmv_u.o +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c -o librsb_nounroll_la-rsb_spmv.lo `test -f 'rsb_spmv.c' || echo './'`rsb_spmv.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 -mbranch-protection=standard -O3 -std=c99 -c rsb_krnl_bcss_misc_u.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_bcss_misc_u.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 -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 -mbranch-protection=standard -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_bcss.lo `test -f 'rsb_krnl_bcss.c' || echo './'`rsb_krnl_bcss.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_krnl_bcoo_spmv_u.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_bcoo_spmv_u.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 -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 -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c -o librsb_nounroll_la-rsb_merge.lo `test -f 'rsb_merge.c' || echo './'`rsb_merge.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_krnl_bcss.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_bcss.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 -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 -mbranch-protection=standard -O3 -std=c99 -c -o librsb_nounroll_la-rsb_merge.lo `test -f 'rsb_merge.c' || echo './'`rsb_merge.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c rsb_merge.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_merge.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 -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -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 -mbranch-protection=standard -O3 -std=c99 -c rsb_ompio.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_ompio.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -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 -mbranch-protection=standard -O3 -std=c99 -c rsb_permute.c -o librsb_nounroll_la-rsb_permute.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -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 -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c rsb_spmv.c -o librsb_nounroll_la-rsb_spmv.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -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 -mbranch-protection=standard -O3 -std=c99 -c rsb_ompio.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_ompio.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c -o librsb_nounroll_la-rsb_spgemm_csr.lo `test -f 'rsb_spgemm_csr.c' || echo './'`rsb_spgemm_csr.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c rsb_spgemm_csr.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_spgemm_csr.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 -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -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 -mbranch-protection=standard -O3 -std=c99 -c -o librsb_nounroll_la-rsb_spsum_misc.lo `test -f 'rsb_spsum_misc.c' || echo './'`rsb_spsum_misc.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_is.lo `test -f 'rsb_is.c' || echo './'`rsb_is.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -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 -mbranch-protection=standard -O3 -std=c99 -c rsb_spgemm_csr.c -o librsb_nounroll_la-rsb_spgemm_csr.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_is.lo `test -f 'rsb_is.c' || echo './'`rsb_is.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -mbranch-protection=standard -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 -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 -mbranch-protection=standard -O3 -std=c99 -c rsb_spsum_misc.c -o librsb_nounroll_la-rsb_spsum_misc.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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c rsb_is.c -o librsb_base_la-rsb_is.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c rsb_spsum_misc.c -o librsb_nounroll_la-rsb_spsum_misc.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_op.lo `test -f 'rsb_op.c' || echo './'`rsb_op.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 -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c rsb_op.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_op.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_bio.lo `test -f 'rsb_bio.c' || echo './'`rsb_bio.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 -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_get.lo `test -f 'rsb_get.c' || echo './'`rsb_get.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_bio.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_bio.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 -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_set.lo `test -f 'rsb_set.c' || echo './'`rsb_set.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_bio.c -o librsb_base_la-rsb_bio.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c rsb_set.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_set.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 -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_coo.lo `test -f 'rsb_coo.c' || echo './'`rsb_coo.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 -mbranch-protection=standard -O3 -std=c99 -c rsb_coo.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_coo.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_krnl_bcss_spsv_u.c -o librsb_nounroll_la-rsb_krnl_bcss_spsv_u.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_set.c -o librsb_base_la-rsb_set.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:"", @@ -2136,180 +2166,186 @@ | ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 32 | __va_arg_pack ()); | ~~~~~~~~~~~~~~~~~ +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_coo.lo `test -f 'rsb_coo.c' || echo './'`rsb_coo.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 -mbranch-protection=standard -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 -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c rsb_coo.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_coo.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_krnl_bcss_spsv_u.c -o librsb_nounroll_la-rsb_krnl_bcss_spsv_u.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c rsb_coo.c -o librsb_base_la-rsb_coo.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 -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_csr.lo `test -f 'rsb_csr.c' || echo './'`rsb_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 -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_csr.lo `test -f 'rsb_csr.c' || echo './'`rsb_csr.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c rsb_csr.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_csr.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c rsb_coo_check.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_coo_check.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c rsb_coo_symm.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_coo_symm.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 -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c rsb_coo_check.c -o librsb_base_la-rsb_coo_check.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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_srt.lo `test -f 'rsb_srt.c' || echo './'`rsb_srt.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c rsb_idx.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_idx.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_srtp.lo `test -f 'rsb_srtp.c' || echo './'`rsb_srtp.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_srtp.lo `test -f 'rsb_srtp.c' || echo './'`rsb_srtp.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c rsb_src.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_src.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_srt.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_srt.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 -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c rsb_srtp.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_srtp.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c rsb_src.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_src.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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c rsb_clone.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_clone.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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c rsb_idx.c -o librsb_base_la-rsb_idx.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c rsb_test_accuracy.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_test_accuracy.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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_test_accuracy.c -o librsb_base_la-rsb_test_accuracy.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c rsb_render.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_render.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 -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_eps.lo `test -f 'rsb_eps.c' || echo './'`rsb_eps.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_render.lo `test -f 'rsb_render.c' || echo './'`rsb_render.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 -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_eps.lo `test -f 'rsb_eps.c' || echo './'`rsb_eps.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_render.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_render.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 -mbranch-protection=standard -O3 -std=c99 -c rsb_eps.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_eps.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_msort_up.lo `test -f 'rsb_msort_up.c' || echo './'`rsb_msort_up.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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c rsb_rec.c -o librsb_base_la-rsb_rec.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 -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_blas_stuff.lo `test -f 'rsb_blas_stuff.c' || echo './'`rsb_blas_stuff.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_msort_up.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_msort_up.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 -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_sys.lo `test -f 'rsb_sys.c' || echo './'`rsb_sys.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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c rsb_sys.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_sys.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_blas_stuff.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_blas_stuff.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_perf.lo `test -f 'rsb_perf.c' || echo './'`rsb_perf.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c rsb_sys.c -o librsb_base_la-rsb_sys.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_tune.lo `test -f 'rsb_tune.c' || echo './'`rsb_tune.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_do.lo `test -f 'rsb_do.c' || echo './'`rsb_do.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_internals.lo `test -f 'rsb_internals.c' || echo './'`rsb_internals.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 -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_tune.lo `test -f 'rsb_tune.c' || echo './'`rsb_tune.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c rsb_perf.c -o librsb_base_la-rsb_perf.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c rsb_do.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_do.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 -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_internals.lo `test -f 'rsb_internals.c' || echo './'`rsb_internals.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 -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_mmio.lo `test -f 'rsb_mmio.c' || echo './'`rsb_mmio.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 -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c rsb_internals.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_internals.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_garbage.lo `test -f 'rsb_garbage.c' || echo './'`rsb_garbage.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 -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_mmio.lo `test -f 'rsb_mmio.c' || echo './'`rsb_mmio.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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c rsb_garbage.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_garbage.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 -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c rsb_partition.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_partition.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -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 -mbranch-protection=standard -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 -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_mbw.lo `test -f 'rsb_mbw.c' || echo './'`rsb_mbw.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 -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_limiter.lo `test -f 'rsb_limiter.c' || echo './'`rsb_limiter.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c rsb_internals.c -o librsb_base_la-rsb_internals.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 -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_mbw.lo `test -f 'rsb_mbw.c' || echo './'`rsb_mbw.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 -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_limiter.lo `test -f 'rsb_limiter.c' || echo './'`rsb_limiter.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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -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 -mbranch-protection=standard -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 -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c rsb_spgemm.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_spgemm.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c rsb_spgemm.c -o librsb_base_la-rsb_spgemm.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 -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_spsum.lo `test -f 'rsb_spsum.c' || echo './'`rsb_spsum.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_spgemm.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_spgemm.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -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 -mbranch-protection=standard -O3 -std=c99 -c rsb_krnl_bcss_misc_u.c -o librsb_nounroll_la-rsb_krnl_bcss_misc_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 -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_fpb.c -o librsb_base_la-rsb_fpb.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_spsum.lo `test -f 'rsb_spsum.c' || echo './'`rsb_spsum.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_mbw.c -o librsb_base_la-rsb_mbw.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c rsb_spsum.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_spsum.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 -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_spsv.lo `test -f 'rsb_spsv.c' || echo './'`rsb_spsv.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 -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_lock.lo `test -f 'rsb_lock.c' || echo './'`rsb_lock.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 -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c rsb_spsum.c -o librsb_base_la-rsb_spsum.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 -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c rsb_spsv.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_spsv.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_spsum.c -o librsb_base_la-rsb_spsum.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 -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_swt.lo `test -f 'rsb_swt.c' || echo './'`rsb_swt.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 -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c rsb_lock.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_lock.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 -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_dump.lo `test -f 'rsb_dump.c' || echo './'`rsb_dump.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 -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_cpmv.lo `test -f 'rsb_cpmv.c' || echo './'`rsb_cpmv.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c rsb_dump.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_dump.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_cpmv.lo `test -f 'rsb_cpmv.c' || echo './'`rsb_cpmv.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c rsb_cpmv.c -o librsb_base_la-rsb_cpmv.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c rsb_cpmv.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_cpmv.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 -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_asm.lo `test -f 'rsb_asm.c' || echo './'`rsb_asm.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 -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_asm.lo `test -f 'rsb_asm.c' || echo './'`rsb_asm.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 -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c rsb_swt.c -o librsb_base_la-rsb_swt.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:"", + | ^~ ~~~ +In function 'sprintf', + inlined from 'rsb__impcdstr' at rsb_test_matops.c:214:2, + inlined from 'rsb__main_block_partitioned_spsv_sxsx' at rsb_test_matops.c:6327:4: +/usr/include/aarch64-linux-gnu/bits/stdio2.h:30:10: note: '__builtin___sprintf_chk' output 19 or more bytes (assuming 2070) into a destination of size 1025 + 30 | return __builtin___sprintf_chk (__s, __USE_FORTIFY_LEVEL - 1, + | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + 31 | __glibc_objsize (__s), __fmt, + | ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + 32 | __va_arg_pack ()); + | ~~~~~~~~~~~~~~~~~ +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c rsb_dump.c -o librsb_base_la-rsb_dump.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 -mbranch-protection=standard -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 -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 -mbranch-protection=standard -O3 -std=c99 -c rsb_krnl_bcss_misc_u.c -o librsb_nounroll_la-rsb_krnl_bcss_misc_u.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 -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c rsb_cpmv.c -o librsb_base_la-rsb_cpmv.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_asm.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_asm.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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_rec2coo.lo `test -f 'rsb_rec2coo.c' || echo './'`rsb_rec2coo.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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c rsb_rec2coo.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_rec2coo.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 -mbranch-protection=standard -O3 -std=c99 -c rsb_rec2csr.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_rec2csr.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o librsb_base_la-rsb_csr2coo.lo `test -f 'rsb_csr2coo.c' || echo './'`rsb_csr2coo.c -/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 -mbranch-protection=standard -pipe -fopenmp -c -o rsb_blas_sparse.lo rsb_blas_sparse.F90 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -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 -mbranch-protection=standard -O3 -std=c99 -c rsb_krnl.c -o librsb_nounroll_la-rsb_krnl.o >/dev/null 2>&1 +/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 -mbranch-protection=standard -pipe -fopenmp -c -o rsb_blas_sparse.lo rsb_blas_sparse.F90 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c rsb_csr2coo.c -o librsb_base_la-rsb_csr2coo.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c rsb_rec2csr.c -o librsb_base_la-rsb_rec2csr.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o rsb_libspblas_handle.lo rsb_libspblas_handle.c 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 -mbranch-protection=standard -pipe -fopenmp -c rsb_blas_sparse.F90 -fPIC -o .libs/rsb_blas_sparse.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o rsb_libspblas_handle.lo rsb_libspblas_handle.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 -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c rsb_csr2coo.c -o librsb_base_la-rsb_csr2coo.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c -o rsb_libspblas.lo rsb_libspblas.c gfortran -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c rsb_libspblas_handle.c -fPIC -DPIC -o .libs/rsb_libspblas_handle.o +/bin/sh ./libtool --tag=CC --mode=link gcc -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -mbranch-protection=standard -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/aarch64-linux-gnu/13 -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/13/../../.. -lgfortran -lm libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+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 -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -c rsb_coo2rec.c -o librsb_base_la-rsb_coo2rec.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 -mbranch-protection=standard -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 -mbranch-protection=standard -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/aarch64-linux-gnu/13 -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/13/../../.. -lgfortran -lm 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 -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_libspblas_handle.c -o rsb_libspblas_handle.o >/dev/null 2>&1 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 -mbranch-protection=standard -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 -mbranch-protection=standard -O3 -std=c99 -Wl,-z -Wl,relro -o ch2icfb ch2icfb-ch2icfb.o -fopenmp -lhwloc -lz -L/usr/lib/gcc/aarch64-linux-gnu/13 -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/13/../../.. -lgfortran -lm -fopenmp if test -f ./rsb_types.h -a ! -f ./rsb_types.h ; then cp -pv ./rsb_types.h ./rsb_types.h ; fi # out-of-dir behaviour varies between installations -if test -f ch2icfb ; then if SED=/usr/bin/sed GREP=/usr/bin/grep /bin/bash ./scripts/rsb_h_to_rsb_fi.sh . /build/reproducible-path/librsb-1.3.0.2+dfsg > rsb.F90 ; then true; else rm "rsb.F90"; echo "Failure generating rsb.F90!" ; exit ; fi ; else echo "Warning: Your system did not build ch2icfb for some reason --- skipping rebuild of "rsb.F90 ;true ; fi -/bin/bash ./libtool --tag=FC --mode=compile gfortran -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -mbranch-protection=standard -pipe -fopenmp -c -o rsb.lo rsb.F90 -libtool: compile: gfortran -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -mbranch-protection=standard -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 -mbranch-protection=standard -pipe -fopenmp -c rsb.F90 -o rsb.o >/dev/null 2>&1 +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 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+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 -mbranch-protection=standard -O3 -std=c99 -c rsb_libspblas_handle.c -o rsb_libspblas_handle.o >/dev/null 2>&1 +/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 -mbranch-protection=standard -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 -mbranch-protection=standard -pipe -fopenmp -c -o rsb.o rsb.F90 libtool: compile: gfortran -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -mbranch-protection=standard -pipe -fopenmp -c rsb_blas_sparse.F90 -o rsb_blas_sparse.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 -mbranch-protection=standard -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 -mbranch-protection=standard -pipe -fopenmp -c rsb.F90 -o rsb.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 -c rsb_libspblas.c -o rsb_libspblas.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 -mbranch-protection=standard -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/aarch64-linux-gnu/13 -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/13/../../.. -lgfortran -lm -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:"", - | ^~ ~~~ -In function 'sprintf', - inlined from 'rsb__impcdstr' at rsb_test_matops.c:214:2, - inlined from 'rsb__main_block_partitioned_spsv_sxsx' at rsb_test_matops.c:6327:4: -/usr/include/aarch64-linux-gnu/bits/stdio2.h:30:10: note: '__builtin___sprintf_chk' output 19 or more bytes (assuming 2070) into a destination of size 1025 - 30 | return __builtin___sprintf_chk (__s, __USE_FORTIFY_LEVEL - 1, - | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - 31 | __glibc_objsize (__s), __fmt, - | ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - 32 | __va_arg_pack ()); - | ~~~~~~~~~~~~~~~~~ -/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 -mbranch-protection=standard -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/aarch64-linux-gnu/13 -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/13/../../.. -lgfortran -lm +/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 -mbranch-protection=standard -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/aarch64-linux-gnu/13 -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/13/../../.. -lgfortran -lm libtool: warning: '-version-info/-version-number' is ignored for convenience libraries +/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 -mbranch-protection=standard -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/aarch64-linux-gnu/13 -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/13/../../.. -lgfortran -lm +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: warning: '-version-info/-version-number' is ignored for convenience libraries libtool: link: ar cr .libs/librsb_spblas.a .libs/rsb_libspblas_handle.o .libs/rsb_libspblas.o libtool: link: ranlib .libs/librsb_spblas.a libtool: link: ( cd ".libs" && rm -f "librsb_spblas.la" && ln -s "../librsb_spblas.la" "librsb_spblas.la" ) -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+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 -mbranch-protection=standard -O3 -std=c99 -c rsb_krnl.c -o librsb_nounroll_la-rsb_krnl.o >/dev/null 2>&1 -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" ) 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:"", @@ -2326,12 +2362,12 @@ | ~~~~~~~~~~~~~~~~~ libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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/aarch64-linux-gnu/13 -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/13/../../.. -lgfortran -lm +/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 -mbranch-protection=standard -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/aarch64-linux-gnu/13 -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/13/../../.. -lgfortran -lm 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 -mbranch-protection=standard -O3 -std=c99 -no-undefined -version-info 0:0:0 -Wl,-z,relro -o librsb.la -rpath /usr/lib/aarch64-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/aarch64-linux-gnu/13 -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/13/../../.. -lgfortran -lm +/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 -mbranch-protection=standard -O3 -std=c99 -no-undefined -version-info 0:0:0 -Wl,-z,relro -o librsb.la -rpath /usr/lib/aarch64-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/aarch64-linux-gnu/13 -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/13/../../.. -lgfortran -lm 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/aarch64-linux-gnu/13 -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/13/../../.. -lpthread -lstdc++fs -lstdc++ -lhwloc -lz -lgfortran -lm -g -O2 -fstack-protector-strong -mbranch-protection=standard -O3 -Wl,-z -Wl,relro -fopenmp -fopenmp -Wl,-soname -Wl,librsb.so.0 -o .libs/librsb.so.0.0.0 libtool: link: (cd ".libs" && rm -f "librsb.so.0" && ln -s "librsb.so.0.0.0" "librsb.so.0") libtool: link: (cd ".libs" && rm -f "librsb.so" && ln -s "librsb.so.0.0.0" "librsb.so") @@ -2343,7 +2379,7 @@ libtool: link: ranlib .libs/librsb.a libtool: link: rm -fr .libs/librsb.lax libtool: link: ( cd ".libs" && rm -f "librsb.la" && ln -s "../librsb.la" "librsb.la" ) -/bin/bash ./libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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/aarch64-linux-gnu/13 -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/13/../../.. -lgfortran -lm +/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 -mbranch-protection=standard -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/aarch64-linux-gnu/13 -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/13/../../.. -lgfortran -lm 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 -mbranch-protection=standard -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/aarch64-linux-gnu/13 -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/13/../../.. -lgfortran -lm -fopenmp gmake[4]: Leaving directory '/build/reproducible-path/librsb-1.3.0.2+dfsg' @@ -2360,27 +2396,27 @@ gfortran -DHAVE_CONFIG_H -I. -I.. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -I.. -I.. -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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/aarch64-linux-gnu/13 -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/13/../../.. -lgfortran -lm -/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 -mbranch-protection=standard -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/aarch64-linux-gnu/13 -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/13/../../.. -lgfortran -lm -/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 -mbranch-protection=standard -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/aarch64-linux-gnu/13 -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/13/../../.. -lgfortran -lm -/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 -mbranch-protection=standard -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/aarch64-linux-gnu/13 -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/13/../../.. -lgfortran -lm -/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 -mbranch-protection=standard -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/aarch64-linux-gnu/13 -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/13/../../.. -lgfortran -lm -/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 -mbranch-protection=standard -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/aarch64-linux-gnu/13 -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/13/../../.. -lgfortran -lm -/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 -mbranch-protection=standard -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/aarch64-linux-gnu/13 -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/13/../../.. -lgfortran -lm -/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 -mbranch-protection=standard -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/aarch64-linux-gnu/13 -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/13/../../.. -lgfortran -lm -/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 -mbranch-protection=standard -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/aarch64-linux-gnu/13 -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/13/../../.. -lgfortran -lm -/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 -mbranch-protection=standard -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/aarch64-linux-gnu/13 -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/13/../../.. -lgfortran -lm +/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 -mbranch-protection=standard -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/aarch64-linux-gnu/13 -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/13/../../.. -lgfortran -lm +/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 -mbranch-protection=standard -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/aarch64-linux-gnu/13 -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/13/../../.. -lgfortran -lm +/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 -mbranch-protection=standard -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/aarch64-linux-gnu/13 -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/13/../../.. -lgfortran -lm +/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 -mbranch-protection=standard -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/aarch64-linux-gnu/13 -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/13/../../.. -lgfortran -lm +/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 -mbranch-protection=standard -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/aarch64-linux-gnu/13 -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/13/../../.. -lgfortran -lm +/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 -mbranch-protection=standard -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/aarch64-linux-gnu/13 -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/13/../../.. -lgfortran -lm +/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 -mbranch-protection=standard -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/aarch64-linux-gnu/13 -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/13/../../.. -lgfortran -lm +/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 -mbranch-protection=standard -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/aarch64-linux-gnu/13 -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/13/../../.. -lgfortran -lm 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 -mbranch-protection=standard -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/aarch64-linux-gnu/13 -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/13/../../.. -lgfortran -lm -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 -mbranch-protection=standard -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/aarch64-linux-gnu/13 -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/13/../../.. -lgfortran -lm -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 -mbranch-protection=standard -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/aarch64-linux-gnu/13 -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/13/../../.. -lgfortran -lm -fopenmp +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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/aarch64-linux-gnu/13 -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/13/../../.. -lgfortran -lm 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 -mbranch-protection=standard -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/aarch64-linux-gnu/13 -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/13/../../.. -lgfortran -lm -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 -mbranch-protection=standard -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/aarch64-linux-gnu/13 -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/13/../../.. -lgfortran -lm -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 -mbranch-protection=standard -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/aarch64-linux-gnu/13 -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/13/../../.. -lgfortran -lm -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 -mbranch-protection=standard -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/aarch64-linux-gnu/13 -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/13/../../.. -lgfortran -lm -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 -mbranch-protection=standard -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/aarch64-linux-gnu/13 -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/13/../../.. -lgfortran -lm -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 -mbranch-protection=standard -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/aarch64-linux-gnu/13 -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/13/../../.. -lgfortran -lm -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 -mbranch-protection=standard -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/aarch64-linux-gnu/13 -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/13/../../.. -lgfortran -lm -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 -mbranch-protection=standard -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/aarch64-linux-gnu/13 -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/13/../../.. -lgfortran -lm -fopenmp +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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/aarch64-linux-gnu/13 -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/13/../../.. -lgfortran -lm 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 -mbranch-protection=standard -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/aarch64-linux-gnu/13 -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/13/../../.. -lgfortran -lm -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 -mbranch-protection=standard -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/aarch64-linux-gnu/13 -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/13/../../.. -lgfortran -lm -fopenmp +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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/aarch64-linux-gnu/13 -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/13/../../.. -lgfortran -lm 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 -mbranch-protection=standard -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/aarch64-linux-gnu/13 -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/13/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/13/../../.. -lgfortran -lm -fopenmp gmake[4]: Leaving directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/examples' Making all in scripts @@ -2398,11 +2434,11 @@ Making all in doc gmake[4]: Entering directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/doc' /usr/bin/mkdir -p man -SOURCE_DATE_EPOCH=1704114061 \ -help2man --name="benchmark and test for librsb" --no-info ../rsbench | /usr/bin/sed 's/January //g' > man/rsbench.1 /usr/bin/mkdir -p man gmake makedox -SOURCE_DATE_EPOCH=1704114061 \ +SOURCE_DATE_EPOCH=1735642861 \ +help2man --name="benchmark and test for librsb" --no-info ../rsbench | /usr/bin/sed 's/January //g' > man/rsbench.1 +SOURCE_DATE_EPOCH=1735642861 \ 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[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 ?" @@ -3114,13 +3150,13 @@ g++ -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -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 -mbranch-protection=standard -Wl,-z,relro -o rgt_rv rgt_rv-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 -mbranch-protection=standard -Wl,-z,relro -o rgt_ne rgt_ne-rgt.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la +/bin/sh ./libtool --tag=CXX --mode=link g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -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 -mbranch-protection=standard -Wl,-z,relro -o rgt_ne rgt_ne-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 -mbranch-protection=standard -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++ -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 -mbranch-protection=standard -Wl,-z -Wl,relro -o .libs/rgt_ne rgt_ne-rgt.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp libtool: link: g++ -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -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 -mbranch-protection=standard -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 -mbranch-protection=standard -Wl,-z,relro -o rsb rsb.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la +/bin/sh ./libtool --tag=CXX --mode=link g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -mbranch-protection=standard -Wl,-z -Wl,relro -o .libs/rsb rsb.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp gmake[6]: Leaving directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib' Making all in examples @@ -3135,25 +3171,25 @@ g++ -DHAVE_CONFIG_H -I.. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -Wl,-z,relro -o example example.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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -Wl,-z,relro -o render render.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la +/bin/sh ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -Wl,-z -Wl,relro -o .libs/assemble assemble.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp libtool: link: g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -Wl,-z -Wl,relro -o .libs/render render.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp -libtool: link: g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -mbranch-protection=standard -Wl,-z -Wl,relro -o .libs/misc misc.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 -mbranch-protection=standard -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 -mbranch-protection=standard -Wl,-z -Wl,relro -o .libs/example example.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp -/bin/bash ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -Wl,-z,relro -o build build.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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -Wl,-z -Wl,relro -o .libs/misc misc.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 -mbranch-protection=standard -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 -mbranch-protection=standard -Wl,-z -Wl,relro -o .libs/build build.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 -mbranch-protection=standard -Wl,-z,relro -o twonnz twonnz.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 -mbranch-protection=standard -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 -mbranch-protection=standard -Wl,-z -Wl,relro -o .libs/twonnz twonnz.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 -mbranch-protection=standard -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 -mbranch-protection=standard -Wl,-z,relro -o autotune autotune.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 -mbranch-protection=standard -Wl,-z,relro -o bench bench.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 -mbranch-protection=standard -Wl,-z,relro -o autotune autotune.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 -mbranch-protection=standard -Wl,-z -Wl,relro -o .libs/autotune autotune.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 -mbranch-protection=standard -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 -mbranch-protection=standard -Wl,-z -Wl,relro -o .libs/bench bench.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp gmake[6]: Leaving directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib/examples' gmake[5]: Leaving directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib' @@ -3163,7 +3199,7 @@ gmake all-am gmake[5]: Entering directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/rsbtest' g++ -DHAVE_CONFIG_H -I. -I/build/reproducible-path/librsb-1.3.0.2+dfsg -Wdate-time -D_FORTIFY_SOURCE=2 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -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 -mbranch-protection=standard -Wl,-z -Wl,relro -o .libs/rsbtest rsbtest.o /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -lstdc++fs -fopenmp gmake[5]: Leaving directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/rsbtest' gmake[4]: Leaving directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/rsbtest' @@ -3239,7 +3275,7 @@ gmake[3]: Leaving directory '/build/reproducible-path/librsb-1.3.0.2+dfsg' gmake mtests -C . gmake[3]: Entering directory '/build/reproducible-path/librsb-1.3.0.2+dfsg' -srcdir="/build/reproducible-path/librsb-1.3.0.2+dfsg" /bin/bash -ex ./scripts/readme-tests.sh +srcdir="/build/reproducible-path/librsb-1.3.0.2+dfsg" /bin/sh -ex ./scripts/readme-tests.sh + test x/build/reproducible-path/librsb-1.3.0.2+dfsg = x + ./rsbench -oa -Ob --bench -f /build/reproducible-path/librsb-1.3.0.2+dfsg/A.mtx -qH -R -n1,4 -T z --verbose --nrhs 1,2 --by-rows # --bench option implies -qH -R --write-performance-record --want-mkl-autotune --mkl-benchmark --types : --split-experimental 6 --merge-experimental 6 --also-transpose --sort-filenames-list --want-memory-benchmark @@ -3249,15 +3285,15 @@ Adding matrix file: /build/reproducible-path/librsb-1.3.0.2+dfsg/A.mtx # Sorting matrices list (use --no-sort-filenames-list to prevent this) # Using matrices: A.mtx -# beginning run at 1715831657 +# beginning run at 1750243426 # /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 -mbranch-protection=standard -O3 -std=c99 -# average timer granularity: 2.93e-08 s -# Will write a final performance record to file rsbench_pr__1715831657_gcc-13.2-1,4th.rpr and periodic checkpoints to rsbench_pr__1715831657_gcc-13.2-1,4th.rpr.tmp +# average timer granularity: 7.6e-08 s +# Will write a final performance record to file rsbench_pr__1750243426_gcc-13.2-1,4th.rpr and periodic checkpoints to rsbench_pr__1750243426_gcc-13.2-1,4th.rpr.tmp # will NOT perform ancillary tests. # will flush cache memory: between each operation measurement series, and NOT between each operation. # will keep any zero encountered in the matrix. -# env: export PATH=/usr/sbin:/usr/bin:/sbin:/bin:/usr/games +# env: export PATH=/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/i/capture/the/path # env: export LD_LIBRARY_PATH=/build/reproducible-path/librsb-1.3.0.2+dfsg/.libs # env: HOSTNAME is not set # env: KMP_AFFINITY is not set @@ -3296,61 +3332,61 @@ # 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: codethink04-arm64 +# 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 4.981s +# Memory benchmark took 5.469s # 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 524288 bytes, per-thread 43690 bytes -# so far, program took 4.983s 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 . +# so far, program took 5.473s 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, 37063 nnz/s ) (1.14 MB/s ) -#pre-sorting (6 elements) took 0.0226159 s -#weeding duplicates (to 6 elements) took 3.09944e-06 s (and check, 9.53674e-07 s ) +# file input of A.mtx took 0.00 s (6 nnz, 34664 nnz/s ) (1.06 MB/s ) +#pre-sorting (6 elements) took 0.000608921 s +#weeding duplicates (to 6 elements) took 2.14577e-06 s (and check, 9.53674e-07 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 0.044s): (3 x 3)[0xaaaae032f540]{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 0.000s): (3 x 3)[0xaaaab0644540]{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 0.02378s; avg 0.007927s ( +/- 4.93/ 6.64 %); best 0.007537s; worst 0.008454s; std dev. 0.0003866 (taking best). -Reference operation time is 0.00753689 s (0.01274 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: 0.007537 Mflops: 0.013) -Merge (3 -> 1 leaves) took w.c.t. of 2.599e-05s, ~8.821e-06s of computing time (of which 0s sorting, 5.007e-06s analysis) -3 iterations (1 th.) took 0.0003159s; avg 0.0001053s ( +/- 99.97/200.00 %); best 2.935e-08s; worst 0.0003159s; std dev. 0.0001489 (taking best). -Reference operation time is 2.93493e-08 s (3271 Mflops) with 1 threads. -After merge step 1: tpop: 2.935e-08 s ~Mflops: 3270.944 nsubm:1 otn:1 -Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 256799.350x: 0.007537s -> 2.935e-08s, so taking this instance. +3 iterations (1 th.) took 0.000315s; avg 0.000105s ( +/- 96.14/192.28 %); best 4.053e-06s; worst 0.0003068s; std dev. 0.0001427 (taking best). +Reference operation time is 4.05312e-06 s (23.69 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: 4.053e-06 Mflops: 23.685) +Merge (3 -> 1 leaves) took w.c.t. of 1.097e-05s, ~5.007e-06s of computing time (of which 9.537e-07s sorting, 9.537e-07s analysis) +3 iterations (1 th.) took 0.0002668s; avg 8.893e-05s ( +/- 99.91/198.93 %); best 8.29e-08s; worst 0.0002658s; std dev. 0.0001251 (taking best). +Reference operation time is 8.28981e-08 s (1158 Mflops) with 1 threads. +After merge step 1: tpop: 8.29e-08 s ~Mflops: 1158.048 nsubm:1 otn:1 +Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 48.893x: 4.053e-06s -> 8.29e-08s, 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 0.02441s (of which 2.885e-05s partitioning, 0s I/O); computing times: 8.821e-06s in par. loops, 0s sorting, 5.007e-06s analyzing) -Total merge + benchmarking process took 0.02441s, equivalent to 831567.8/3.2 new/old ops (0.04799s for 2 clones -- as 1635239.6/6.4 ops, or 817619.8/3.2 ops per clone), SPEEDUP of 256799.350x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 256799.350x (0.007537s -> 2.935e-08s), will amortize in 3.2 ops by saving 0.007537s per op. -In 1 tuning rounds (tot. 0.072s, 0.048s for constructor, 2 clones) obtained a SPEEDUP of 25679835.0% (2.568e+05x) (from 0.01274 to 3271 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.000298s (of which 1.407e-05s partitioning, 0s I/O); computing times: 5.007e-06s in par. loops, 9.537e-07s sorting, 9.537e-07s analyzing) +Total merge + benchmarking process took 0.000298s, equivalent to 3595.1/73.5 new/old ops (2.48e-05s for 2 clones -- as 299.1/6.1 ops, or 149.6/3.1 ops per clone), SPEEDUP of 48.893x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 48.893x (4.053e-06s -> 8.29e-08s), will amortize in 75.1 ops by saving 3.97e-06s per op. +In 1 tuning rounds (tot. 0.00065s, 2.5e-05s for constructor, 2 clones) obtained a SPEEDUP of 4789.3% (48.89x) (from 23.69 to 1158 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 0.0723081 s (7.537e-03 s -> 2.935e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.000748158 s (4.053e-06 s -> 8.290e-08 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 0.399553 s and estimated a speedup of 1.000000 x (2.935e-08 s -> 2.935e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.000289917 s and estimated a speedup of 1.000000 x (8.290e-08 s -> 8.290e-08 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 0.011856 0.015766 0.027622 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 1 3 3 6 0.027622 -%:RSB_SUBDIVISION_TIME:A.mtx S N 1 3 3 6 0.011856 -%:RSB_SHUFFLE_TIME:A.mtx S N 1 3 3 6 0.015766 +%:CONSTRUCTOR_TIMES:A.mtx S N 1 3 3 6 0.000000 0.000139 0.000017 0.000156 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 1 3 3 6 0.000156 +%:RSB_SUBDIVISION_TIME:A.mtx S N 1 3 3 6 0.000139 +%:RSB_SHUFFLE_TIME:A.mtx S N 1 3 3 6 0.000017 %: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 0.027622 +%:SORTEDCOO2RSB_TIME:A.mtx S N 1 3 3 6 0.000156 %: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 @@ -3365,47 +3401,47 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 1 3 3 6 6 6 6 # # Using 4 threads -# Constructed matrix (took 0.055s): (3 x 3)[0xaaaae032f540]{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 0.001s): (3 x 3)[0xaaaab0644540]{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 0.02396s; avg 0.007987s ( +/- 0.20/ 0.11 %); best 0.007971s; worst 0.007995s; std dev. 1.108e-05 (taking best). -Reference operation time is 0.00797105 s (0.01204 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: 0.007971 Mflops: 0.012) -Merge (3 -> 1 leaves) took w.c.t. of 1.407e-05s, ~4.053e-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 ( +/- 97.69/200.00 %); best 2.935e-08s; worst 3.815e-06s; std dev. 1.798e-06 (taking best). -Reference operation time is 2.93493e-08 s (3271 Mflops) with 4 threads. -After merge step 1: tpop: 2.935e-08 s ~Mflops: 3270.944 nsubm:1 otn:1 -Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 271592.201x: 0.007971s -> 2.935e-08s, so taking this instance. +3 iterations (4 th.) took 0.0004818s; avg 0.0001606s ( +/- 95.70/191.39 %); best 6.914e-06s; worst 0.000468s; std dev. 0.0002174 (taking best). +Reference operation time is 6.91414e-06 s (13.88 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: 6.914e-06 Mflops: 13.885) +Merge (3 -> 1 leaves) took w.c.t. of 6.914e-06s, ~1.907e-06s of computing time (of which 0s sorting, 1.907e-06s analysis) +3 iterations (4 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 86.96/200.00 %); best 8.29e-08s; worst 1.907e-06s; std dev. 8.991e-07 (taking best). +Reference operation time is 8.28981e-08 s (1158 Mflops) with 4 threads. +After merge step 1: tpop: 8.29e-08 s ~Mflops: 1158.048 nsubm:1 otn:1 +Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 83.405x: 6.914e-06s -> 8.29e-08s, 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 0.02402s (of which 1.597e-05s partitioning, 0s I/O); computing times: 4.053e-06s in par. loops, 9.537e-07s sorting, 3.099e-06s analyzing) -Total merge + benchmarking process took 0.02402s, equivalent to 818586.5/3.0 new/old ops (0.04795s for 2 clones -- as 1633631.2/6.0 ops, or 816815.6/3.0 ops per clone), SPEEDUP of 271592.201x -Applying multi-merge (3 -> 1 leaves, 1 steps, 1 -> 1 th.sp.) yielded SPEEDUP of 271592.201x (0.007971s -> 2.935e-08s), will amortize in 3.0 ops by saving 0.007971s per op. -In 1 tuning rounds (tot. 0.072s, 0.048s for constructor, 2 clones) obtained a SPEEDUP of 27159120.1% (2.716e+05x) (from 0.01204 to 3271 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 2.694e-05s (of which 7.868e-06s partitioning, 0s I/O); computing times: 1.907e-06s in par. loops, 0s sorting, 1.907e-06s analyzing) +Total merge + benchmarking process took 2.694e-05s, equivalent to 325.0/3.9 new/old ops (2.217e-05s for 2 clones -- as 267.5/3.2 ops, or 133.7/1.6 ops per clone), SPEEDUP of 83.405x +Applying multi-merge (3 -> 1 leaves, 1 steps, 1 -> 1 th.sp.) yielded SPEEDUP of 83.405x (6.914e-06s -> 8.29e-08s), will amortize in 3.9 ops by saving 6.831e-06s per op. +In 1 tuning rounds (tot. 0.00054s, 2.2e-05s for constructor, 2 clones) obtained a SPEEDUP of 8240.5% (83.41x) (from 13.88 to 1158 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 0.0719972 s (7.971e-03 s -> 2.935e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.000546932 s (6.914e-06 s -> 8.290e-08 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 0.403969 s and estimated a speedup of 1.000000 x (2.935e-08 s -> 2.935e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.000437975 s and estimated a speedup of 1.000000 x (8.290e-08 s -> 8.290e-08 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 0.015506 0.019867 0.035373 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 4 3 3 6 0.035373 -%:RSB_SUBDIVISION_TIME:A.mtx S N 4 3 3 6 0.015506 -%:RSB_SHUFFLE_TIME:A.mtx S N 4 3 3 6 0.019867 +%:CONSTRUCTOR_TIMES:A.mtx S N 4 3 3 6 0.000000 0.000146 0.001000 0.001146 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 4 3 3 6 0.001146 +%:RSB_SUBDIVISION_TIME:A.mtx S N 4 3 3 6 0.000146 +%:RSB_SHUFFLE_TIME:A.mtx S N 4 3 3 6 0.001000 %: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 0.035373 +%:SORTEDCOO2RSB_TIME:A.mtx S N 4 3 3 6 0.001146 %: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 0.78 -%:SORTEDCOO2RSB_SCALING:A.mtx S N 4 3 3 6 0.78 -%:RSB_SUBDIVISION_SCALING:A.mtx S N 4 3 3 6 0.76 -%:RSB_SHUFFLE_SCALING:A.mtx S N 4 3 3 6 0.79 -%:CONSTRUCTOR_SCALING:A.mtx S N 4 3 3 6 nan 0.76 0.79 0.78 +%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 4 3 3 6 0.14 +%:SORTEDCOO2RSB_SCALING:A.mtx S N 4 3 3 6 0.14 +%:RSB_SUBDIVISION_SCALING:A.mtx S N 4 3 3 6 0.95 +%:RSB_SHUFFLE_SCALING:A.mtx S N 4 3 3 6 0.02 +%:CONSTRUCTOR_SCALING:A.mtx S N 4 3 3 6 nan 0.95 0.02 0.14 #%:SM_COUNTS: Tot HalfwordCsr FullwordCsr HalfwordCoo FullwordCoo %:SM_COUNTS:A.mtx S N 4 3 3 6 1 1 0 0 0 %:SM_IDXOCCUPATIONRSBVSCOOANDCSR:A.mtx S N 4 3 3 6 28 48 36 @@ -3414,50 +3450,50 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 4 3 3 6 6 6 6 # %operation:matrix CONSTRUCTOR[1] SPMV[1] SPMV[4] -%operation:A.mtx 0.0436299 1e+09 1e+09 +%operation:A.mtx 0.000175953 1e+09 1e+09 %constructor:matrix SORT[1] SCAN[1] SHUFFLE[1] INSERT[1] -%constructor:A.mtx 0 0.0118558 0 0.0157659 +%constructor:A.mtx 0 0.000138998 0 1.69277e-05 # 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 0.044s): (3 x 3)[0xaaaae032f540]{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 0.000s): (3 x 3)[0xaaaab0644540]{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 0.02423s; avg 0.008077s ( +/- 47.54/ 48.55 %); best 0.004237s; worst 0.012s; std dev. 0.003169 (taking best). -Reference operation time is 0.00423694 s (0.04532 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: 0.004237 Mflops: 0.045) -Merge (3 -> 1 leaves) took w.c.t. of 1.812e-05s, ~5.007e-06s of computing time (of which 9.537e-07s sorting, 4.053e-06s analysis) -3 iterations (1 th.) took 3.815e-06s; avg 1.272e-06s ( +/- 97.69/125.00 %); best 2.935e-08s; worst 2.861e-06s; std dev. 1.189e-06 (taking best). -Reference operation time is 2.93493e-08 s (6542 Mflops) with 1 threads. -After merge step 1: tpop: 2.935e-08 s ~Mflops: 6541.888 nsubm:1 otn:1 -Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 144362.307x: 0.004237s -> 2.935e-08s, so taking this instance. +3 iterations (1 th.) took 0.0001171s; avg 3.902e-05s ( +/- 89.61/179.23 %); best 4.053e-06s; worst 0.000109s; std dev. 4.945e-05 (taking best). +Reference operation time is 4.05312e-06 s (47.37 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: 4.053e-06 Mflops: 47.371) +Merge (3 -> 1 leaves) took w.c.t. of 4.053e-06s, ~2.146e-06s of computing time (of which 1.192e-06s sorting, 9.537e-07s analysis) +3 iterations (1 th.) took 3.099e-06s; avg 1.033e-06s ( +/- 91.98/200.00 %); best 8.29e-08s; worst 3.099e-06s; std dev. 1.461e-06 (taking best). +Reference operation time is 8.28981e-08 s (2316 Mflops) with 1 threads. +After merge step 1: tpop: 8.29e-08 s ~Mflops: 2316.095 nsubm:1 otn:1 +Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 48.893x: 4.053e-06s -> 8.29e-08s, 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 0.02776s (of which 2.098e-05s partitioning, 0s I/O); computing times: 5.007e-06s in par. loops, 9.537e-07s sorting, 4.053e-06s analyzing) -Total merge + benchmarking process took 0.02776s, equivalent to 945743.3/6.6 new/old ops (0.05565s for 2 clones -- as 1896190.1/13.1 ops, or 948095.0/6.6 ops per clone), SPEEDUP of 144362.307x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 144362.307x (0.004237s -> 2.935e-08s), will amortize in 6.6 ops by saving 0.004237s per op. -In 1 tuning rounds (tot. 0.08s, 0.056s for constructor, 2 clones) obtained a SPEEDUP of 14436130.7% (1.444e+05x) (from 0.04532 to 6542 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 2.503e-05s (of which 6.914e-06s partitioning, 0s I/O); computing times: 2.146e-06s in par. loops, 1.192e-06s sorting, 9.537e-07s analyzing) +Total merge + benchmarking process took 2.503e-05s, equivalent to 302.0/6.2 new/old ops (1.979e-05s for 2 clones -- as 238.7/4.9 ops, or 119.4/2.4 ops per clone), SPEEDUP of 48.893x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 48.893x (4.053e-06s -> 8.29e-08s), will amortize in 6.3 ops by saving 3.97e-06s per op. +In 1 tuning rounds (tot. 0.00017s, 2e-05s for constructor, 2 clones) obtained a SPEEDUP of 4789.3% (48.89x) (from 47.37 to 2316 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 0.079978 s (4.237e-03 s -> 2.935e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.000174999 s (4.053e-06 s -> 8.290e-08 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 0.416008 s and estimated a speedup of 1.000000 x (2.935e-08 s -> 2.935e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.000257015 s and estimated a speedup of 1.000000 x (8.290e-08 s -> 8.290e-08 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 0.011696 0.015988 0.027684 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 1 3 3 6 0.027684 -%:RSB_SUBDIVISION_TIME:A.mtx S N 1 3 3 6 0.011696 -%:RSB_SHUFFLE_TIME:A.mtx S N 1 3 3 6 0.015988 +%:CONSTRUCTOR_TIMES:A.mtx S N 1 3 3 6 0.000000 0.000026 0.000010 0.000036 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 1 3 3 6 0.000036 +%:RSB_SUBDIVISION_TIME:A.mtx S N 1 3 3 6 0.000026 +%:RSB_SHUFFLE_TIME:A.mtx S N 1 3 3 6 0.000010 %: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 0.027684 +%:SORTEDCOO2RSB_TIME:A.mtx S N 1 3 3 6 0.000036 %:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 1 3 3 6 0.000 %:UNSORTEDCOO2RSB_SCALING:A.mtx S N 1 3 3 6 1.00 %:SORTEDCOO2RSB_SCALING:A.mtx S N 1 3 3 6 1.00 @@ -3472,47 +3508,47 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 1 3 3 6 6 6 6 # # Using 4 threads -# Constructed matrix (took 0.056s): (3 x 3)[0xaaaae032f540]{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 0.001s): (3 x 3)[0xaaaab0644540]{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 0.02064s; avg 0.006881s ( +/- 28.71/ 16.08 %); best 0.004905s; worst 0.007987s; std dev. 0.0014 (taking best). -Reference operation time is 0.00490499 s (0.03914 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: 0.004905 Mflops: 0.039) -Merge (3 -> 1 leaves) took w.c.t. of 1.383e-05s, ~4.053e-06s of computing time (of which 1.192e-06s sorting, 3.815e-06s analysis) -3 iterations (4 th.) took 5.96e-06s; avg 1.987e-06s ( +/- 98.52/200.00 %); best 2.935e-08s; worst 5.96e-06s; std dev. 2.81e-06 (taking best). -Reference operation time is 2.93493e-08 s (6542 Mflops) with 4 threads. -After merge step 1: tpop: 2.935e-08 s ~Mflops: 6541.888 nsubm:1 otn:1 -Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 167124.289x: 0.004905s -> 2.935e-08s, so taking this instance. +3 iterations (4 th.) took 2.599e-05s; avg 8.663e-06s ( +/- 31.19/ 62.39 %); best 5.96e-06s; worst 1.407e-05s; std dev. 3.821e-06 (taking best). +Reference operation time is 5.96046e-06 s (32.21 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: 5.96e-06 Mflops: 32.212) +Merge (3 -> 1 leaves) took w.c.t. of 5.007e-06s, ~2.146e-06s of computing time (of which 1.192e-06s sorting, 9.537e-07s analysis) +3 iterations (4 th.) took 4.053e-06s; avg 1.351e-06s ( +/- 93.86/129.41 %); best 8.29e-08s; worst 3.099e-06s; std dev. 1.296e-06 (taking best). +Reference operation time is 8.28981e-08 s (2316 Mflops) with 4 threads. +After merge step 1: tpop: 8.29e-08 s ~Mflops: 2316.095 nsubm:1 otn:1 +Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 71.901x: 5.96e-06s -> 8.29e-08s, 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 0.02419s (of which 1.621e-05s partitioning, 0s I/O); computing times: 4.053e-06s in par. loops, 1.192e-06s sorting, 3.815e-06s analyzing) -Total merge + benchmarking process took 0.02419s, equivalent to 824281.1/4.9 new/old ops (0.04811s for 2 clones -- as 1639358.2/9.8 ops, or 819679.1/4.9 ops per clone), SPEEDUP of 167124.289x -Applying multi-merge (3 -> 1 leaves, 1 steps, 1 -> 1 th.sp.) yielded SPEEDUP of 167124.289x (0.004905s -> 2.935e-08s), will amortize in 4.9 ops by saving 0.004905s per op. -In 1 tuning rounds (tot. 0.069s, 0.048s for constructor, 2 clones) obtained a SPEEDUP of 16712328.9% (1.671e+05x) (from 0.03914 to 6542 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 2.599e-05s (of which 6.914e-06s partitioning, 0s I/O); computing times: 2.146e-06s in par. loops, 1.192e-06s sorting, 9.537e-07s analyzing) +Total merge + benchmarking process took 2.599e-05s, equivalent to 313.5/4.4 new/old ops (2.074e-05s for 2 clones -- as 250.2/3.5 ops, or 125.1/1.7 ops per clone), SPEEDUP of 71.901x +Applying multi-merge (3 -> 1 leaves, 1 steps, 1 -> 1 th.sp.) yielded SPEEDUP of 71.901x (5.96e-06s -> 8.29e-08s), will amortize in 4.4 ops by saving 5.878e-06s per op. +In 1 tuning rounds (tot. 8e-05s, 2.1e-05s for constructor, 2 clones) obtained a SPEEDUP of 7090.1% (71.9x) (from 32.21 to 2316 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 0.0688462 s (4.905e-03 s -> 2.935e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 8.79765e-05 s (5.960e-06 s -> 8.290e-08 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 0.399337 s and estimated a speedup of 1.000000 x (2.935e-08 s -> 2.935e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.00115609 s and estimated a speedup of 1.000000 x (8.290e-08 s -> 8.290e-08 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 0.015803 0.023959 0.039762 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 4 3 3 6 0.039762 -%:RSB_SUBDIVISION_TIME:A.mtx S N 4 3 3 6 0.015803 -%:RSB_SHUFFLE_TIME:A.mtx S N 4 3 3 6 0.023959 +%:CONSTRUCTOR_TIMES:A.mtx S N 4 3 3 6 0.000000 0.000020 0.000687 0.000707 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 4 3 3 6 0.000707 +%:RSB_SUBDIVISION_TIME:A.mtx S N 4 3 3 6 0.000020 +%:RSB_SHUFFLE_TIME:A.mtx S N 4 3 3 6 0.000687 %: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 0.039762 +%:SORTEDCOO2RSB_TIME:A.mtx S N 4 3 3 6 0.000707 %: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 0.70 -%:SORTEDCOO2RSB_SCALING:A.mtx S N 4 3 3 6 0.70 -%:RSB_SUBDIVISION_SCALING:A.mtx S N 4 3 3 6 0.74 -%:RSB_SHUFFLE_SCALING:A.mtx S N 4 3 3 6 0.67 -%:CONSTRUCTOR_SCALING:A.mtx S N 4 3 3 6 nan 0.74 0.67 0.70 +%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 4 3 3 6 0.05 +%:SORTEDCOO2RSB_SCALING:A.mtx S N 4 3 3 6 0.05 +%:RSB_SUBDIVISION_SCALING:A.mtx S N 4 3 3 6 1.31 +%:RSB_SHUFFLE_SCALING:A.mtx S N 4 3 3 6 0.01 +%:CONSTRUCTOR_SCALING:A.mtx S N 4 3 3 6 nan 1.31 0.01 0.05 #%:SM_COUNTS: Tot HalfwordCsr FullwordCsr HalfwordCoo FullwordCoo %:SM_COUNTS:A.mtx S N 4 3 3 6 1 1 0 0 0 %:SM_IDXOCCUPATIONRSBVSCOOANDCSR:A.mtx S N 4 3 3 6 28 48 36 @@ -3521,184 +3557,184 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 4 3 3 6 6 6 6 # %operation:matrix CONSTRUCTOR[1] SPMV[1] SPMV[4] -%operation:A.mtx 0.0437078 1e+09 1e+09 +%operation:A.mtx 4.91142e-05 1e+09 1e+09 %constructor:matrix SORT[1] SCAN[1] SHUFFLE[1] INSERT[1] -%constructor:A.mtx 0 0.0116959 0 0.0159879 +%constructor:A.mtx 0 2.59876e-05 0 1.00136e-05 # symmetric matrix --- skipping transposed benchmarking -# so far, program took 7.290s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 1.912s/0.000s . +# so far, program took 5.484s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.004s/0.000s . getrusage() stats: ru_maxrss: 6 (maximum resident set size -- MB) -ru_stime : 0.04853s (system CPU time used) -ru_utime : 5.639s (user CPU time used) +ru_stime : 0.05249s (system CPU time used) +ru_utime : 5.517s (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 3270.94 7.537e-03 0.000e+00 2.935e-08 0.000e+00 7.231e-02 9.13e+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 3270.94 7.971e-03 0.000e+00 2.935e-08 0.000e+00 7.200e-02 9.13e+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 1158.05 4.053e-06 0.000e+00 8.290e-08 0.000e+00 7.482e-04 3.23e+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 1158.05 6.914e-06 0.000e+00 8.290e-08 0.000e+00 5.469e-04 3.23e+00 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. 26419477.6 % faster, avg. sp. ratio 264195.776x, max sp. ratio 271592.201x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 2458407.8/2453111.3/2463704.3/4916815.6 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 9.3/ 9.0/ 9.6/ 18.6 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 9.3, min. 9.0, max. 9.6 ops) +#pr: (in succ. cases rsb autotuning gave avg. 6514.9 % faster, avg. sp. ratio 66.149x, max sp. ratio 83.405x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 7811.3/6597.6/9025.0/15622.7 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 131.8/ 79.1/184.6/263.7 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 134.3, min. 80.1, max. 188.4 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 32/ 32/ 32) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 96/ 96/ 96) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 7.496/ 7.496/ 7.496,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 18.263/ 9.131/ 9.131,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 2.654/ 2.654/ 2.654,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 6.466/ 3.233/ 3.233,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.: 0.07 s, min 0.07 s, max 0.07 s, tot 0.14 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.07 s, min 0.07 s, max 0.07 s, tot 0.14 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 3.271e+03, min 3.271e+03, max 3.271e+03 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 1.239e-02, min 1.204e-02, max 1.274e-02 (2 samples) -#pr: best tun. rsb operation time was: on avg. 2.935e-08s, min 2.935e-08s, max 2.935e-08s, tot 5.870e-08s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 7.754e-03s, min 7.537e-03s, max 7.971e-03s, tot 1.551e-02s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 5.929e+00 5.929e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 8.670e-01 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.00 s, min 0.00 s, max 0.00 s, tot 0.00 s (2 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.00 s, min 0.00 s, max 0.00 s, tot 0.00 s (2 samples) +#pr: best tun. rsb canon. mflops were: on avg. 1.158e+03, min 1.158e+03, max 1.158e+03 (2 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 1.879e+01, min 1.388e+01, max 2.369e+01 (2 samples) +#pr: best tun. rsb operation time was: on avg. 8.290e-08s, min 8.290e-08s, max 8.290e-08s, tot 1.658e-07s (2 samples) +#pr: ref. unt. rsb operation time was: on avg. 5.484e-06s, min 4.053e-06s, max 6.914e-06s, tot 1.097e-05s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.804e+01 1.804e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 9.985e-01 #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 6541.89 4.237e-03 0.000e+00 2.935e-08 0.000e+00 7.998e-02 1.40e+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 6541.89 4.905e-03 0.000e+00 2.935e-08 0.000e+00 6.885e-02 1.40e+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 2316.10 4.053e-06 0.000e+00 8.290e-08 0.000e+00 1.750e-04 4.97e+00 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 2316.10 5.960e-06 0.000e+00 8.290e-08 0.000e+00 8.798e-05 4.97e+00 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. 15574229.8 % faster, avg. sp. ratio 155743.298x, max sp. ratio 167124.289x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 2535394.0/2345751.4/2725036.6/5070788.0 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 16.5/ 14.0/ 18.9/ 32.9 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 16.5, min. 14.0, max. 18.9 ops) +#pr: (in succ. cases rsb autotuning gave avg. 5939.7 % faster, avg. sp. ratio 60.397x, max sp. ratio 71.901x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 1586.1/1061.3/2111.0/3172.3 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 29.0/ 14.8/ 43.2/ 57.9 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 29.5, min. 15.0, max. 44.1 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 32/ 32/ 32) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 96/ 96/ 96) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 10.767/ 10.767/ 10.767,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 28.076/ 14.038/ 14.038,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 3.812/ 3.812/ 3.812,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 9.940/ 4.970/ 4.970,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 0.07 s, max 0.08 s, tot 0.15 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.07 s, min 0.07 s, max 0.08 s, tot 0.15 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 6.542e+03, min 6.542e+03, max 6.542e+03 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 4.223e-02, min 3.914e-02, max 4.532e-02 (2 samples) -#pr: best tun. rsb operation time was: on avg. 2.935e-08s, min 2.935e-08s, max 2.935e-08s, tot 5.870e-08s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 4.571e-03s, min 4.237e-03s, max 4.905e-03s, tot 9.142e-03s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 4.128e+00 4.128e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 8.670e-01 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.00 s, min 0.00 s, max 0.00 s, tot 0.00 s (2 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.00 s, min 0.00 s, max 0.00 s, tot 0.00 s (2 samples) +#pr: best tun. rsb canon. mflops were: on avg. 2.316e+03, min 2.316e+03, max 2.316e+03 (2 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 3.979e+01, min 3.221e+01, max 4.737e+01 (2 samples) +#pr: best tun. rsb operation time was: on avg. 8.290e-08s, min 8.290e-08s, max 8.290e-08s, tot 1.658e-07s (2 samples) +#pr: ref. unt. rsb operation time was: on avg. 5.007e-06s, min 4.053e-06s, max 5.960e-06s, tot 1.001e-05s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.256e+01 1.256e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 9.985e-01 #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 3270.94 7.537e-03 0.000e+00 2.935e-08 0.000e+00 7.231e-02 9.13e+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 6541.89 4.237e-03 0.000e+00 2.935e-08 0.000e+00 7.998e-02 1.40e+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 3270.94 7.971e-03 0.000e+00 2.935e-08 0.000e+00 7.200e-02 9.13e+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 6541.89 4.905e-03 0.000e+00 2.935e-08 0.000e+00 6.885e-02 1.40e+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 1158.05 4.053e-06 0.000e+00 8.290e-08 0.000e+00 7.482e-04 3.23e+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 2316.10 4.053e-06 0.000e+00 8.290e-08 0.000e+00 1.750e-04 4.97e+00 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 1158.05 6.914e-06 0.000e+00 8.290e-08 0.000e+00 5.469e-04 3.23e+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 2316.10 5.960e-06 0.000e+00 8.290e-08 0.000e+00 8.798e-05 4.97e+00 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. 20996853.7 % faster, avg. sp. ratio 209969.537x, max sp. ratio 271592.201x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 2496900.9/2345751.4/2725036.6/9987603.6 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 12.9/ 9.0/ 18.9/ 51.5 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 12.9, min. 9.0, max. 18.9 ops) +#pr: (in succ. cases rsb autotuning gave avg. 6227.3 % faster, avg. sp. ratio 63.273x, max sp. ratio 83.405x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 4698.7/1061.3/9025.0/18794.9 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 80.4/ 14.8/184.6/321.6 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 81.9, min. 15.0, max. 188.4 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 32/ 32/ 32) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 96/ 96/ 96) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 9.131/ 7.496/ 10.767,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 46.338/ 9.131/ 14.038,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 3.233/ 2.654/ 3.812,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 16.406/ 3.233/ 4.970,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.: 0.07 s, min 0.07 s, max 0.08 s, tot 0.29 s (4 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.07 s, min 0.07 s, max 0.08 s, tot 0.29 s (4 samples) -#pr: best tun. rsb canon. mflops were: on avg. 4.906e+03, min 3.271e+03, max 6.542e+03 (4 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 2.731e-02, min 1.204e-02, max 4.532e-02 (4 samples) -#pr: best tun. rsb operation time was: on avg. 2.935e-08s, min 2.935e-08s, max 2.935e-08s, tot 1.174e-07s (4 samples) -#pr: ref. unt. rsb operation time was: on avg. 6.162e-03s, min 4.237e-03s, max 7.971e-03s, tot 2.465e-02s (4 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 4.128e+00 5.929e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 8.670e-01 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.00 s, min 0.00 s, max 0.00 s, tot 0.00 s (4 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.00 s, min 0.00 s, max 0.00 s, tot 0.00 s (4 samples) +#pr: best tun. rsb canon. mflops were: on avg. 1.737e+03, min 1.158e+03, max 2.316e+03 (4 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 2.929e+01, min 1.388e+01, max 4.737e+01 (4 samples) +#pr: best tun. rsb operation time was: on avg. 8.290e-08s, min 8.290e-08s, max 8.290e-08s, tot 3.316e-07s (4 samples) +#pr: ref. unt. rsb operation time was: on avg. 5.245e-06s, min 4.053e-06s, max 6.914e-06s, tot 2.098e-05s (4 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.256e+01 1.804e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 9.985e-01 #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 3270.94 7.537e-03 0.000e+00 2.935e-08 0.000e+00 7.231e-02 9.13e+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 3270.94 7.971e-03 0.000e+00 2.935e-08 0.000e+00 7.200e-02 9.13e+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 1158.05 4.053e-06 0.000e+00 8.290e-08 0.000e+00 7.482e-04 3.23e+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 1158.05 6.914e-06 0.000e+00 8.290e-08 0.000e+00 5.469e-04 3.23e+00 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. 26419477.6 % faster, avg. sp. ratio 264195.776x, max sp. ratio 271592.201x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 2458407.8/2453111.3/2463704.3/4916815.6 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 9.3/ 9.0/ 9.6/ 18.6 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 9.3, min. 9.0, max. 9.6 ops) +#pr: (in succ. cases rsb autotuning gave avg. 6514.9 % faster, avg. sp. ratio 66.149x, max sp. ratio 83.405x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 7811.3/6597.6/9025.0/15622.7 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 131.8/ 79.1/184.6/263.7 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 134.3, min. 80.1, max. 188.4 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 32/ 32/ 32) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 96/ 96/ 96) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 7.496/ 7.496/ 7.496,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 18.263/ 9.131/ 9.131,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 2.654/ 2.654/ 2.654,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 6.466/ 3.233/ 3.233,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.: 0.07 s, min 0.07 s, max 0.07 s, tot 0.14 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.07 s, min 0.07 s, max 0.07 s, tot 0.14 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 3.271e+03, min 3.271e+03, max 3.271e+03 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 1.239e-02, min 1.204e-02, max 1.274e-02 (2 samples) -#pr: best tun. rsb operation time was: on avg. 2.935e-08s, min 2.935e-08s, max 2.935e-08s, tot 5.870e-08s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 7.754e-03s, min 7.537e-03s, max 7.971e-03s, tot 1.551e-02s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 5.929e+00 5.929e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 8.670e-01 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.00 s, min 0.00 s, max 0.00 s, tot 0.00 s (2 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.00 s, min 0.00 s, max 0.00 s, tot 0.00 s (2 samples) +#pr: best tun. rsb canon. mflops were: on avg. 1.158e+03, min 1.158e+03, max 1.158e+03 (2 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 1.879e+01, min 1.388e+01, max 2.369e+01 (2 samples) +#pr: best tun. rsb operation time was: on avg. 8.290e-08s, min 8.290e-08s, max 8.290e-08s, tot 1.658e-07s (2 samples) +#pr: ref. unt. rsb operation time was: on avg. 5.484e-06s, min 4.053e-06s, max 6.914e-06s, tot 1.097e-05s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.804e+01 1.804e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 9.985e-01 #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 6541.89 4.237e-03 0.000e+00 2.935e-08 0.000e+00 7.998e-02 1.40e+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 6541.89 4.905e-03 0.000e+00 2.935e-08 0.000e+00 6.885e-02 1.40e+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 2316.10 4.053e-06 0.000e+00 8.290e-08 0.000e+00 1.750e-04 4.97e+00 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 2316.10 5.960e-06 0.000e+00 8.290e-08 0.000e+00 8.798e-05 4.97e+00 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. 15574229.8 % faster, avg. sp. ratio 155743.298x, max sp. ratio 167124.289x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 2535394.0/2345751.4/2725036.6/5070788.0 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 16.5/ 14.0/ 18.9/ 32.9 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 16.5, min. 14.0, max. 18.9 ops) +#pr: (in succ. cases rsb autotuning gave avg. 5939.7 % faster, avg. sp. ratio 60.397x, max sp. ratio 71.901x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 1586.1/1061.3/2111.0/3172.3 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 29.0/ 14.8/ 43.2/ 57.9 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 29.5, min. 15.0, max. 44.1 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 32/ 32/ 32) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 96/ 96/ 96) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 10.767/ 10.767/ 10.767,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 28.076/ 14.038/ 14.038,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 3.812/ 3.812/ 3.812,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 9.940/ 4.970/ 4.970,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 0.07 s, max 0.08 s, tot 0.15 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.07 s, min 0.07 s, max 0.08 s, tot 0.15 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 6.542e+03, min 6.542e+03, max 6.542e+03 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 4.223e-02, min 3.914e-02, max 4.532e-02 (2 samples) -#pr: best tun. rsb operation time was: on avg. 2.935e-08s, min 2.935e-08s, max 2.935e-08s, tot 5.870e-08s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 4.571e-03s, min 4.237e-03s, max 4.905e-03s, tot 9.142e-03s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 4.128e+00 4.128e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 8.670e-01 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.00 s, min 0.00 s, max 0.00 s, tot 0.00 s (2 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.00 s, min 0.00 s, max 0.00 s, tot 0.00 s (2 samples) +#pr: best tun. rsb canon. mflops were: on avg. 2.316e+03, min 2.316e+03, max 2.316e+03 (2 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 3.979e+01, min 3.221e+01, max 4.737e+01 (2 samples) +#pr: best tun. rsb operation time was: on avg. 8.290e-08s, min 8.290e-08s, max 8.290e-08s, tot 1.658e-07s (2 samples) +#pr: ref. unt. rsb operation time was: on avg. 5.007e-06s, min 4.053e-06s, max 5.960e-06s, tot 1.001e-05s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.256e+01 1.256e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 9.985e-01 #pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 2.000e+00 x, min 2.000e+00 x, max 2.000e+00 x (2 samples, the non-min-nrhs ones) #pr: ======== Limiting to transA=T: #pr: No sample (out of 4) matched the dump criteria -- skipping dump round. @@ -3709,44 +3745,44 @@ #pr: ======== All results (not limiting) #pr: Dump from a base of 4 samples (of max 8) ordered by (1,2,1,1,2,1,2) = (filename x cores x incX x incY x nrhs x typecode x transA). pr: BESTCODE MTX NR NC NNZ NRHS TYPE SYM TRANS NT AT-NT AT-MKL-NT BPNZ AT-BPNZ NSUBM AT-SUBM RSBBEST-MFLOPS OPTIME MKL-OPTIME AT-OPTIME AT-MKL-OPTIME AT-TIME RWminBW-GBps CB-bpf AT-MS CMFLOPS -pr: 1:R_R A 3 3 6 1 Z S N 1 1 0 4.0000 4.6667 3 1 3270.94 7.537e-03 0.000e+00 2.935e-08 0.000e+00 7.231e-02 9.13e+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 6541.89 4.237e-03 0.000e+00 2.935e-08 0.000e+00 7.998e-02 1.40e+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 3270.94 7.971e-03 0.000e+00 2.935e-08 0.000e+00 7.200e-02 9.13e+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 6541.89 4.905e-03 0.000e+00 2.935e-08 0.000e+00 6.885e-02 1.40e+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 1158.05 4.053e-06 0.000e+00 8.290e-08 0.000e+00 7.482e-04 3.23e+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 2316.10 4.053e-06 0.000e+00 8.290e-08 0.000e+00 1.750e-04 4.97e+00 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 1158.05 6.914e-06 0.000e+00 8.290e-08 0.000e+00 5.469e-04 3.23e+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 2316.10 5.960e-06 0.000e+00 8.290e-08 0.000e+00 8.798e-05 4.97e+00 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. 20996853.7 % faster, avg. sp. ratio 209969.537x, max sp. ratio 271592.201x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 2496900.9/2345751.4/2725036.6/9987603.6 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 12.9/ 9.0/ 18.9/ 51.5 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 12.9, min. 9.0, max. 18.9 ops) +#pr: (in succ. cases rsb autotuning gave avg. 6227.3 % faster, avg. sp. ratio 63.273x, max sp. ratio 83.405x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 4698.7/1061.3/9025.0/18794.9 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 80.4/ 14.8/184.6/321.6 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 81.9, min. 15.0, max. 188.4 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 32/ 32/ 32) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 96/ 96/ 96) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 9.131/ 7.496/ 10.767,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 46.338/ 9.131/ 14.038,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 3.233/ 2.654/ 3.812,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 16.406/ 3.233/ 4.970,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.: 0.07 s, min 0.07 s, max 0.08 s, tot 0.29 s (4 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.07 s, min 0.07 s, max 0.08 s, tot 0.29 s (4 samples) -#pr: best tun. rsb canon. mflops were: on avg. 4.906e+03, min 3.271e+03, max 6.542e+03 (4 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 2.731e-02, min 1.204e-02, max 4.532e-02 (4 samples) -#pr: best tun. rsb operation time was: on avg. 2.935e-08s, min 2.935e-08s, max 2.935e-08s, tot 1.174e-07s (4 samples) -#pr: ref. unt. rsb operation time was: on avg. 6.162e-03s, min 4.237e-03s, max 7.971e-03s, tot 2.465e-02s (4 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 4.128e+00 5.929e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 8.670e-01 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.00 s, min 0.00 s, max 0.00 s, tot 0.00 s (4 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.00 s, min 0.00 s, max 0.00 s, tot 0.00 s (4 samples) +#pr: best tun. rsb canon. mflops were: on avg. 1.737e+03, min 1.158e+03, max 2.316e+03 (4 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 2.929e+01, min 1.388e+01, max 4.737e+01 (4 samples) +#pr: best tun. rsb operation time was: on avg. 8.290e-08s, min 8.290e-08s, max 8.290e-08s, tot 3.316e-07s (4 samples) +#pr: ref. unt. rsb operation time was: on avg. 5.245e-06s, min 4.053e-06s, max 6.914e-06s, tot 2.098e-05s (4 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.256e+01 1.804e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 9.985e-01 #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 1.86 s. +#pr: Record collection took 0.01 s. #pr: Record comprises 40 memory benchmark samples (prepend RSB_PR_MBW=1 to dump this). -#pr: Record comprises 100 environment variables in 4341 bytes (prepend RSB_PR_ENV=1 to dump this). +#pr: Record comprises 100 environment variables in 4395 bytes (prepend RSB_PR_ENV=1 to dump this). # ====== END Total summary record. -#pr: ======== Saved a performance record of 8 samples to rsbench_pr__1715831657_gcc-13.2-1,4th.rpr -# Removing the temporary record file rsbench_pr__1715831657_gcc-13.2-1,4th.rpr.tmp. -# terminating run at 1715831664 (after 7.3s of w.c.t.) +#pr: ======== Saved a performance record of 8 samples to rsbench_pr__1750243426_gcc-13.2-1,4th.rpr +# Removing the temporary record file rsbench_pr__1750243426_gcc-13.2-1,4th.rpr.tmp. +# terminating run at 1750243432 (after 5.5s of w.c.t.) + ./rsbench -oa -Ob --help /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/rsbench is a swiss army knife for testing the library functionality and performance. You can use it to perform sparse matrix - unitary vector multiplication, specifying the blocking parameters, the times to perform multiplication. @@ -4018,10 +4054,10 @@ L1 size: 24576 L2 size: 524288 sysconf() : 4096 bytes per pagesize -sysconf() : 15402653 physical pages -sysconf() : 63089266688 bytes (60166 MB) of physical memory -sysconf() : 2603063 available (free) physical pages -sysconf() : 10662146048 available (free) physical memory +sysconf() : 15402650 physical pages +sysconf() : 63089254400 bytes (60166 MB) of physical memory +sysconf() : 13666326 available (free) physical pages +sysconf() : 55977271296 available (free) physical memory sysconf() , processors : 12 sysconf() , processors online : 12 sysconf() : no level 1 cache @@ -4046,30 +4082,30 @@ 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 : 3.06487e-08 s +timing granularity : 7.7796e-08 s CFLAGS : -g -O2 -Werror=implicit-function-declaration -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -O3 -std=c99 CXXFLAGS : -g -O2 -fstack-protector-strong -fstack-clash-protection -Wformat -Werror=format-security -mbranch-protection=standard -fopenmp CC : gcc memhinfo : L2:4/64/512K,L1:8/64/24K -detected free memory : 10662146048 -detected total memory : 63089266688 -for array sized 524288 elems, took 0.000350952 s for linear search and 0 s for binary search for element 524287, in 153 tries, for a total of 0.100100 s (ignore this:160431822) -for array sized 524288 elems, took 0.000174999 s for linear search and 0 s for binary search for element 262143, in 313 tries, for a total of 0.100032 s (ignore this:324533340) -for array sized 524288 elems, took 8.67844e-05 s for linear search and 0 s for binary search for element 131071, in 655 tries, for a total of 0.106069 s (ignore this:496236350) -for array sized 524288 elems, took 4.29153e-05 s for linear search and 0 s for binary search for element 65535, in 1263 tries, for a total of 0.100013 s (ignore this:661777760) -for array sized 524288 elems, took 2.09808e-05 s for linear search and 0 s for binary search for element 32767, in 2522 tries, for a total of 0.100013 s (ignore this:827054508) -for array sized 524288 elems, took 1.09673e-05 s for linear search and 0 s for binary search for element 16383, in 5288 tries, for a total of 0.107309 s (ignore this:1000321116) -for array sized 524288 elems, took 4.76837e-06 s for linear search and 0 s for binary search for element 8191, in 9814 tries, for a total of 0.103344 s (ignore this:1161094064) -for array sized 524288 elems, took 1.90735e-06 s for linear search and 0 s for binary search for element 4095, in 19091 tries, for a total of 0.102686 s (ignore this:1317449354) -for array sized 524288 elems, took 9.53674e-07 s for linear search and 0 s for binary search for element 2047, in 25738 tries, for a total of 0.102296 s (ignore this:1422820726) -for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 1023, in 46399 tries, for a total of 0.100980 s (ignore this:1517753080) -for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 511, in 101039 tries, for a total of 0.101105 s (ignore this:1621014938) -for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 255, in 196422 tries, for a total of 0.100001 s (ignore this:1721190158) -for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 127, in 336048 tries, for a total of 0.100000 s (ignore this:1806546350) -for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 63, in 395585 tries, for a total of 0.100001 s (ignore this:1856390060) -for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 31, in 867079 tries, for a total of 0.100001 s (ignore this:1910148958) -for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 15, in 943633 tries, for a total of 0.100000 s (ignore this:1938457948) -for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 7, in 909868 tries, for a total of 0.100001 s (ignore this:1951196100) +detected free memory : 55977271296 +detected total memory : 63089254400 +for array sized 524288 elems, took 0.000389814 s for linear search and 0 s for binary search for element 524287, in 151 tries, for a total of 0.100017 s (ignore this:158334674) +for array sized 524288 elems, took 0.000174999 s for linear search and 0 s for binary search for element 262143, in 558 tries, for a total of 0.100070 s (ignore this:450886262) +for array sized 524288 elems, took 8.67844e-05 s for linear search and 0 s for binary search for element 131071, in 1137 tries, for a total of 0.100041 s (ignore this:748941716) +for array sized 524288 elems, took 4.29153e-05 s for linear search and 0 s for binary search for element 65535, in 2277 tries, for a total of 0.100043 s (ignore this:1047388106) +for array sized 524288 elems, took 2.09808e-05 s for linear search and 0 s for binary search for element 32767, in 4542 tries, for a total of 0.100019 s (ignore this:1345043534) +for array sized 524288 elems, took 1.09673e-05 s for linear search and 0 s for binary search for element 16383, in 8988 tries, for a total of 0.100008 s (ignore this:1639544342) +for array sized 524288 elems, took 4.76837e-06 s for linear search and 0 s for binary search for element 8191, in 17946 tries, for a total of 0.100005 s (ignore this:1933535714) +for array sized 524288 elems, took 1.90735e-06 s for linear search and 0 s for binary search for element 4095, in 35371 tries, for a total of 0.100001 s (ignore this:-2071743092) +for array sized 524288 elems, took 9.53674e-07 s for linear search and 0 s for binary search for element 2047, in 68067 tries, for a total of 0.100002 s (ignore this:-1793076794) +for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 1023, in 127363 tries, for a total of 0.100000 s (ignore this:-1532492096) +for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 511, in 225917 tries, for a total of 0.100001 s (ignore this:-1301604922) +for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 255, in 378354 tries, for a total of 0.100000 s (ignore this:-1108644382) +for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 127, in 562268 tries, for a total of 0.100000 s (ignore this:-965828310) +for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 63, in 740471 tries, for a total of 0.100000 s (ignore this:-872528964) +for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 31, in 894809 tries, for a total of 0.100000 s (ignore this:-817050806) +for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 15, in 1148380 tries, for a total of 0.100000 s (ignore this:-782599406) +for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 7, in 1049318 tries, for a total of 0.100001 s (ignore this:-767908954) + ./rsbench -C /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/rsbench version: 1.3.0 format switches:br @@ -4116,17 +4152,17 @@ 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 1715831667 +# beginning run at 1750243434 # /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 -mbranch-protection=standard -O3 -std=c99 # User did not specify threads; assuming 1. Environment provides max 12 threads; this build supports max 128. # User did not specify threads; assuming 1. Environment provides max 12 threads; this build supports max 128. -# average timer granularity: 3.89e-08 s -# Will write a final performance record to file rsbench_pr__1715831667_gcc-13.2.rpr and periodic checkpoints to rsbench_pr__1715831667_gcc-13.2.rpr.tmp +# average timer granularity: 4.03e-08 s +# Will write a final performance record to file rsbench_pr__1750243434_gcc-13.2.rpr and periodic checkpoints to rsbench_pr__1750243434_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 @@ -4165,61 +4201,61 @@ # 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: codethink04-arm64 +# detected hostname: i-capture-the-hostname # user specified a verbosity level of 1 (each --verbose occurrence counts +1) # This test will measure times in scanning arrays sized and aligned to fit in caches. # 2 cache levels detected Will fill struct with 40 samples... -# Memory benchmark took 6.058s +# Memory benchmark took 5.221s # 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 524288 bytes, per-thread 43690 bytes -# so far, program took 6.060s 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 . +# so far, program took 5.223s 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, 70493 nnz/s ) (2.16 MB/s ) -#pre-sorting (6 elements) took 0.0227671 s -#weeding duplicates (to 6 elements) took 2.14577e-06 s (and check, 1.90735e-06 s ) +# file input of A.mtx took 0.00 s (6 nnz, 73156 nnz/s ) (2.24 MB/s ) +#pre-sorting (6 elements) took 0.00052309 s +#weeding duplicates (to 6 elements) took 1.90735e-06 s (and check, 9.53674e-07 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 12 threads -# Constructed matrix (took 0.059s): (3 x 3)[0xaaaac1560cd0]{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' +# Constructed matrix (took 0.000s): (3 x 3)[0xaaaaeb47ed10]{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 (12 th.) took 0.02358s; avg 0.007858s ( +/- 3.54/ 4.43 %); best 0.00758s; worst 0.008206s; std dev. 0.0002603 (taking best). -Reference operation time is 0.00758004 s (0.003166 Mflops) with 12 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: 0.00758 Mflops: 0.003) -Merge (3 -> 1 leaves) took w.c.t. of 2.384e-05s, ~8.106e-06s of computing time (of which 9.537e-07s sorting, 5.007e-06s analysis) -3 iterations (12 th.) took 2.599e-05s; avg 8.663e-06s ( +/- 99.58/188.99 %); best 3.6e-08s; worst 2.503e-05s; std dev. 1.158e-05 (taking best). -Reference operation time is 3.60012e-08 s (666.6 Mflops) with 12 threads. -After merge step 1: tpop: 3.6e-08 s ~Mflops: 666.644 nsubm:1 otn:12 -Applying merge (3 -> 1 leaves, 12 th.) yielded SPEEDUP of 210549.669x: 0.00758s -> 3.6e-08s, so taking this instance. +3 iterations (12 th.) took 5.198e-05s; avg 1.733e-05s ( +/- 65.60/ 50.00 %); best 5.96e-06s; worst 2.599e-05s; std dev. 8.396e-06 (taking best). +Reference operation time is 5.96046e-06 s (4.027 Mflops) with 12 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: 5.96e-06 Mflops: 4.027) +Merge (3 -> 1 leaves) took w.c.t. of 1.502e-05s, ~6.914e-06s of computing time (of which 9.537e-07s sorting, 2.146e-06s analysis) +3 iterations (12 th.) took 1.597e-05s; avg 5.325e-06s ( +/- 99.27/182.09 %); best 3.885e-08s; worst 1.502e-05s; std dev. 6.867e-06 (taking best). +Reference operation time is 3.88503e-08 s (617.8 Mflops) with 12 threads. +After merge step 1: tpop: 3.885e-08 s ~Mflops: 617.756 nsubm:1 otn:12 +Applying merge (3 -> 1 leaves, 12 th.) yielded SPEEDUP of 153.421x: 5.96e-06s -> 3.885e-08s, 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 0.02421s (of which 2.718e-05s partitioning, 0s I/O); computing times: 8.106e-06s in par. loops, 9.537e-07s sorting, 5.007e-06s analyzing) -Total merge + benchmarking process took 0.02421s, equivalent to 672397.4/3.2 new/old ops (0.04842s for 2 clones -- as 1345086.1/6.4 ops, or 672543.0/3.2 ops per clone), SPEEDUP of 210549.669x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 210549.669x (0.00758s -> 3.6e-08s), will amortize in 3.2 ops by saving 0.00758s per op. -In 1 tuning rounds (tot. 0.072s, 0.048s for constructor, 2 clones) obtained a SPEEDUP of 21054866.9% (2.105e+05x) (from 0.003166 to 666.6 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 5.007e-05s (of which 1.693e-05s partitioning, 0s I/O); computing times: 6.914e-06s in par. loops, 9.537e-07s sorting, 2.146e-06s analyzing) +Total merge + benchmarking process took 5.007e-05s, equivalent to 1288.7/8.4 new/old ops (2.408e-05s for 2 clones -- as 619.8/4.0 ops, or 309.9/2.0 ops per clone), SPEEDUP of 153.421x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 153.421x (5.96e-06s -> 3.885e-08s), will amortize in 8.5 ops by saving 5.922e-06s per op. +In 1 tuning rounds (tot. 0.00013s, 2.4e-05s for constructor, 2 clones) obtained a SPEEDUP of 15242.1% (153.4x) (from 4.027 to 617.8 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 0.0721452 s (7.580e-03 s -> 3.600e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.000159025 s (5.960e-06 s -> 3.885e-08 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 0.404198 s and estimated a speedup of 1.000000 x (3.600e-08 s -> 3.600e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.0324209 s and estimated a speedup of 1.000000 x (3.885e-08 s -> 3.885e-08 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 12 3 3 6 0.000000 0.019754 0.023557 0.043311 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.043311 -%:RSB_SUBDIVISION_TIME:A.mtx S N 12 3 3 6 0.019754 -%:RSB_SHUFFLE_TIME:A.mtx S N 12 3 3 6 0.023557 +%:CONSTRUCTOR_TIMES:A.mtx S N 12 3 3 6 0.000000 0.000113 0.000019 0.000132 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.000132 +%:RSB_SUBDIVISION_TIME:A.mtx S N 12 3 3 6 0.000113 +%:RSB_SHUFFLE_TIME:A.mtx S N 12 3 3 6 0.000019 %:ROW_MAJOR_SORT_TIME:A.mtx S N 12 3 3 6 0.000000 %:ROW_MAJOR_SORT_SCALING:A.mtx S N 12 3 3 6 nan -%:SORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.043311 +%:SORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.000132 %:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 12 3 3 6 0.000 %:UNSORTEDCOO2RSB_SCALING:A.mtx S N 12 3 3 6 1.00 %:SORTEDCOO2RSB_SCALING:A.mtx S N 12 3 3 6 1.00 @@ -4234,50 +4270,50 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 12 3 3 6 6 6 6 # %operation:matrix CONSTRUCTOR[12] SPMV[12] SPMV[12] -%operation:A.mtx 0.0593679 1e+09 1e+09 +%operation:A.mtx 0.000159979 1e+09 1e+09 %constructor:matrix SORT[12] SCAN[12] SHUFFLE[12] INSERT[12] -%constructor:A.mtx 0 0.0197539 0 0.0235569 +%constructor:A.mtx 0 0.00011301 0 1.90735e-05 # 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 12 threads -# Constructed matrix (took 0.055s): (3 x 3)[0xaaaac1560cd0]{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' +# Constructed matrix (took 0.000s): (3 x 3)[0xaaaaeb47ed10]{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 (12 th.) took 0.02358s; avg 0.007861s ( +/- 3.54/ 7.03 %); best 0.007583s; worst 0.008414s; std dev. 0.0003908 (taking best). -Reference operation time is 0.0075829 s (0.01266 Mflops) with 12 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: 0.007583 Mflops: 0.013) -Merge (3 -> 1 leaves) took w.c.t. of 1.597e-05s, ~3.815e-06s of computing time (of which 9.537e-07s sorting, 3.099e-06s analysis) -3 iterations (12 th.) took 5.007e-06s; avg 1.669e-06s ( +/- 97.84/142.86 %); best 3.6e-08s; worst 4.053e-06s; std dev. 1.73e-06 (taking best). -Reference operation time is 3.60012e-08 s (2667 Mflops) with 12 threads. -After merge step 1: tpop: 3.6e-08 s ~Mflops: 2666.577 nsubm:1 otn:12 -Applying merge (3 -> 1 leaves, 12 th.) yielded SPEEDUP of 210629.139x: 0.007583s -> 3.6e-08s, so taking this instance. +3 iterations (12 th.) took 0.008852s; avg 0.002951s ( +/- 99.43/198.41 %); best 1.693e-05s; worst 0.008805s; std dev. 0.00414 (taking best). +Reference operation time is 1.69277e-05 s (5.671 Mflops) with 12 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: 1.693e-05 Mflops: 5.671) +Merge (3 -> 1 leaves) took w.c.t. of 5.007e-06s, ~1.907e-06s of computing time (of which 9.537e-07s sorting, 9.537e-07s analysis) +3 iterations (12 th.) took 2.861e-06s; avg 9.537e-07s ( +/- 95.93/100.00 %); best 3.885e-08s; worst 1.907e-06s; std dev. 7.787e-07 (taking best). +Reference operation time is 3.88503e-08 s (2471 Mflops) with 12 threads. +After merge step 1: tpop: 3.885e-08 s ~Mflops: 2471.023 nsubm:1 otn:12 +Applying merge (3 -> 1 leaves, 12 th.) yielded SPEEDUP of 435.716x: 1.693e-05s -> 3.885e-08s, 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 0.02419s (of which 1.812e-05s partitioning, 0s I/O); computing times: 3.815e-06s in par. loops, 9.537e-07s sorting, 3.099e-06s analyzing) -Total merge + benchmarking process took 0.02419s, equivalent to 672033.1/3.2 new/old ops (0.04853s for 2 clones -- as 1348013.2/6.4 ops, or 674006.6/3.2 ops per clone), SPEEDUP of 210629.139x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 210629.139x (0.007583s -> 3.6e-08s), will amortize in 3.2 ops by saving 0.007583s per op. -In 1 tuning rounds (tot. 0.072s, 0.049s for constructor, 2 clones) obtained a SPEEDUP of 21062813.9% (2.106e+05x) (from 0.01266 to 2667 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 4.697e-05s (of which 7.153e-06s partitioning, 0s I/O); computing times: 1.907e-06s in par. loops, 9.537e-07s sorting, 9.537e-07s analyzing) +Total merge + benchmarking process took 4.697e-05s, equivalent to 1209.0/2.8 new/old ops (4.125e-05s for 2 clones -- as 1061.7/2.4 ops, or 530.8/1.2 ops per clone), SPEEDUP of 435.716x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 435.716x (1.693e-05s -> 3.885e-08s), will amortize in 2.8 ops by saving 1.689e-05s per op. +In 1 tuning rounds (tot. 0.0089s, 4.1e-05s for constructor, 2 clones) obtained a SPEEDUP of 43471.6% (435.7x) (from 5.671 to 2471 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 0.0722039 s (7.583e-03 s -> 3.600e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.00893307 s (1.693e-05 s -> 3.885e-08 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 0.407772 s and estimated a speedup of 1.000000 x (3.600e-08 s -> 3.600e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.00555706 s and estimated a speedup of 1.000000 x (3.885e-08 s -> 3.885e-08 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 12 3 3 6 0.000000 0.023095 0.016005 0.039100 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.039100 -%:RSB_SUBDIVISION_TIME:A.mtx S N 12 3 3 6 0.023095 -%:RSB_SHUFFLE_TIME:A.mtx S N 12 3 3 6 0.016005 +%:CONSTRUCTOR_TIMES:A.mtx S N 12 3 3 6 0.000000 0.000154 0.000010 0.000164 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.000164 +%:RSB_SUBDIVISION_TIME:A.mtx S N 12 3 3 6 0.000154 +%:RSB_SHUFFLE_TIME:A.mtx S N 12 3 3 6 0.000010 %:ROW_MAJOR_SORT_TIME:A.mtx S N 12 3 3 6 0.000000 %:ROW_MAJOR_SORT_SCALING:A.mtx S N 12 3 3 6 nan -%:SORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.039100 +%:SORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.000164 %:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 12 3 3 6 0.000 %:UNSORTEDCOO2RSB_SCALING:A.mtx S N 12 3 3 6 1.00 %:SORTEDCOO2RSB_SCALING:A.mtx S N 12 3 3 6 1.00 @@ -4292,59 +4328,59 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 12 3 3 6 6 6 6 # %operation:matrix CONSTRUCTOR[12] SPMV[12] SPMV[12] -%operation:A.mtx 0.0546899 1e+09 1e+09 +%operation:A.mtx 0.000175953 1e+09 1e+09 %constructor:matrix SORT[12] SCAN[12] SHUFFLE[12] INSERT[12] -%constructor:A.mtx 0 0.0230949 0 0.0160048 +%constructor:A.mtx 0 0.000154018 0 1.00136e-05 # symmetric matrix --- skipping transposed benchmarking -# so far, program took 7.234s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.956s/0.000s . +# so far, program took 5.273s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.047s/0.000s . getrusage() stats: -ru_maxrss: 6 (maximum resident set size -- MB) -ru_stime : 0.02816s (system CPU time used) -ru_utime : 3.731s (user CPU time used) +ru_maxrss: 8 (maximum resident set size -- MB) +ru_stime : 0.0362s (system CPU time used) +ru_utime : 5.384s (user CPU time used) # multi-type benchmarking (DSCZ) -- now using typecode S (last was D). # Cache block size total 524288 bytes, per-thread 43690 bytes -# so far, program took 7.234s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.956s/0.000s . +# so far, program took 5.273s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.047s/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 12 threads -# Constructed matrix (took 0.048s): (3 x 3)[0xaaaac1560cd0]{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' +# Constructed matrix (took 0.000s): (3 x 3)[0xaaaaeb47ed10]{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 (12 th.) took 0.024s; avg 0.007999s ( +/- 46.97/ 46.17 %); best 0.004242s; worst 0.01169s; std dev. 0.003042 (taking best). -Reference operation time is 0.00424194 s (0.005658 Mflops) with 12 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: 0.004242 Mflops: 0.006) -Merge (3 -> 1 leaves) took w.c.t. of 1.788e-05s, ~5.007e-06s of computing time (of which 9.537e-07s sorting, 3.099e-06s analysis) -3 iterations (12 th.) took 0.0001559s; avg 5.198e-05s ( +/- 99.93/198.17 %); best 3.6e-08s; worst 0.000155s; std dev. 7.283e-05 (taking best). -Reference operation time is 3.60012e-08 s (666.6 Mflops) with 12 threads. -After merge step 1: tpop: 3.6e-08 s ~Mflops: 666.644 nsubm:1 otn:12 -Applying merge (3 -> 1 leaves, 12 th.) yielded SPEEDUP of 117827.815x: 0.004242s -> 3.6e-08s, so taking this instance. +3 iterations (12 th.) took 0.0002701s; avg 9.004e-05s ( +/- 93.38/184.38 %); best 5.96e-06s; worst 0.0002561s; std dev. 0.0001174 (taking best). +Reference operation time is 5.96046e-06 s (4.027 Mflops) with 12 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: 5.96e-06 Mflops: 4.027) +Merge (3 -> 1 leaves) took w.c.t. of 5.96e-06s, ~3.099e-06s of computing time (of which 0s sorting, 0s analysis) +3 iterations (12 th.) took 0.000103s; avg 3.433e-05s ( +/- 99.89/197.22 %); best 3.885e-08s; worst 0.000102s; std dev. 4.788e-05 (taking best). +Reference operation time is 3.88503e-08 s (617.8 Mflops) with 12 threads. +After merge step 1: tpop: 3.885e-08 s ~Mflops: 617.756 nsubm:1 otn:12 +Applying merge (3 -> 1 leaves, 12 th.) yielded SPEEDUP of 153.421x: 5.96e-06s -> 3.885e-08s, 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 0.02399s (of which 2.003e-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 0.02399s, equivalent to 666476.8/5.7 new/old ops (0.05155s for 2 clones -- as 1431980.1/12.2 ops, or 715990.1/6.1 ops per clone), SPEEDUP of 117827.815x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 117827.815x (0.004242s -> 3.6e-08s), will amortize in 5.7 ops by saving 0.004242s per op. -In 1 tuning rounds (tot. 0.076s, 0.052s for constructor, 2 clones) obtained a SPEEDUP of 11782681.5% (1.178e+05x) (from 0.005658 to 666.6 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.0001249s (of which 6.914e-06s partitioning, 0s I/O); computing times: 3.099e-06s in par. loops, 0s sorting, 0s analyzing) +Total merge + benchmarking process took 0.0001249s, equivalent to 3215.7/21.0 new/old ops (2.098e-05s for 2 clones -- as 540.0/3.5 ops, or 270.0/1.8 ops per clone), SPEEDUP of 153.421x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 153.421x (5.96e-06s -> 3.885e-08s), will amortize in 21.1 ops by saving 5.922e-06s per op. +In 1 tuning rounds (tot. 0.00047s, 2.1e-05s for constructor, 2 clones) obtained a SPEEDUP of 15242.1% (153.4x) (from 4.027 to 617.8 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 0.0760028 s (4.242e-03 s -> 3.600e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.000478029 s (5.960e-06 s -> 3.885e-08 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 0.359983 s and estimated a speedup of 1.000000 x (3.600e-08 s -> 3.600e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.000403881 s and estimated a speedup of 1.000000 x (3.885e-08 s -> 3.885e-08 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 12 3 3 6 0.000000 0.019680 0.012204 0.031884 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.031884 -%:RSB_SUBDIVISION_TIME:A.mtx S N 12 3 3 6 0.019680 -%:RSB_SHUFFLE_TIME:A.mtx S N 12 3 3 6 0.012204 +%:CONSTRUCTOR_TIMES:A.mtx S N 12 3 3 6 0.000000 0.000123 0.000009 0.000132 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.000132 +%:RSB_SUBDIVISION_TIME:A.mtx S N 12 3 3 6 0.000123 +%:RSB_SHUFFLE_TIME:A.mtx S N 12 3 3 6 0.000009 %:ROW_MAJOR_SORT_TIME:A.mtx S N 12 3 3 6 0.000000 %:ROW_MAJOR_SORT_SCALING:A.mtx S N 12 3 3 6 nan -%:SORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.031884 +%:SORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.000132 %:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 12 3 3 6 0.000 %:UNSORTEDCOO2RSB_SCALING:A.mtx S N 12 3 3 6 1.00 %:SORTEDCOO2RSB_SCALING:A.mtx S N 12 3 3 6 1.00 @@ -4359,56 +4395,56 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 12 3 3 6 6 6 6 # %operation:matrix CONSTRUCTOR[12] SPMV[12] SPMV[12] -%operation:A.mtx 0.047895 1e+09 1e+09 +%operation:A.mtx 0.000145912 1e+09 1e+09 %constructor:matrix SORT[12] SCAN[12] SHUFFLE[12] INSERT[12] -%constructor:A.mtx 0 0.01968 0 0.0122039 +%constructor:A.mtx 0 0.000123024 0 9.05991e-06 # 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 12 threads -# Constructed matrix (took 0.052s): (3 x 3)[0xaaaac1560cd0]{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' +# Constructed matrix (took 0.000s): (3 x 3)[0xaaaaeb47f0a0]{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 (12 th.) took 0.02239s; avg 0.007462s ( +/- 36.00/ 50.24 %); best 0.004776s; worst 0.01121s; std dev. 0.002732 (taking best). -Reference operation time is 0.004776 s (0.0201 Mflops) with 12 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: 0.004776 Mflops: 0.020) -Merge (3 -> 1 leaves) took w.c.t. of 1.597e-05s, ~4.053e-06s of computing time (of which 9.537e-07s sorting, 3.815e-06s analysis) -3 iterations (12 th.) took 5.007e-06s; avg 1.669e-06s ( +/- 97.84/200.00 %); best 3.6e-08s; worst 5.007e-06s; std dev. 2.36e-06 (taking best). -Reference operation time is 3.60012e-08 s (2667 Mflops) with 12 threads. -After merge step 1: tpop: 3.6e-08 s ~Mflops: 2666.577 nsubm:1 otn:12 -Applying merge (3 -> 1 leaves, 12 th.) yielded SPEEDUP of 132662.252x: 0.004776s -> 3.6e-08s, so taking this instance. +3 iterations (12 th.) took 0.000555s; avg 0.000185s ( +/- 95.62/173.45 %); best 8.106e-06s; worst 0.0005059s; std dev. 0.0002273 (taking best). +Reference operation time is 8.10623e-06 s (11.84 Mflops) with 12 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: 8.106e-06 Mflops: 11.843) +Merge (3 -> 1 leaves) took w.c.t. of 5.007e-06s, ~2.146e-06s of computing time (of which 0s sorting, 9.537e-07s analysis) +3 iterations (12 th.) took 3.099e-06s; avg 1.033e-06s ( +/- 96.24/200.00 %); best 3.885e-08s; worst 3.099e-06s; std dev. 1.461e-06 (taking best). +Reference operation time is 3.88503e-08 s (2471 Mflops) with 12 threads. +After merge step 1: tpop: 3.885e-08 s ~Mflops: 2471.023 nsubm:1 otn:12 +Applying merge (3 -> 1 leaves, 12 th.) yielded SPEEDUP of 208.653x: 8.106e-06s -> 3.885e-08s, 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 0.02422s (of which 1.812e-05s partitioning, 0s I/O); computing times: 4.053e-06s in par. loops, 9.537e-07s sorting, 3.815e-06s analyzing) -Total merge + benchmarking process took 0.02422s, equivalent to 672649.0/5.1 new/old ops (0.05331s for 2 clones -- as 1480920.5/11.2 ops, or 740460.3/5.6 ops per clone), SPEEDUP of 132662.252x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 132662.252x (0.004776s -> 3.6e-08s), will amortize in 5.1 ops by saving 0.004776s per op. -In 1 tuning rounds (tot. 0.076s, 0.053s for constructor, 2 clones) obtained a SPEEDUP of 13266125.2% (1.327e+05x) (from 0.0201 to 2667 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.0001299s (of which 6.914e-06s partitioning, 0s I/O); computing times: 2.146e-06s in par. loops, 0s sorting, 9.537e-07s analyzing) +Total merge + benchmarking process took 0.0001299s, equivalent to 3344.6/16.0 new/old ops (2.098e-05s for 2 clones -- as 540.0/2.6 ops, or 270.0/1.3 ops per clone), SPEEDUP of 208.653x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 208.653x (8.106e-06s -> 3.885e-08s), will amortize in 16.1 ops by saving 8.067e-06s per op. +In 1 tuning rounds (tot. 0.00071s, 2.1e-05s for constructor, 2 clones) obtained a SPEEDUP of 20765.3% (208.7x) (from 11.84 to 2471 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 0.0760121 s (4.776e-03 s -> 3.600e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.000717878 s (8.106e-06 s -> 3.885e-08 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 0.347991 s and estimated a speedup of 1.000000 x (3.600e-08 s -> 3.600e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.00110412 s and estimated a speedup of 1.000000 x (3.885e-08 s -> 3.885e-08 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 12 3 3 6 0.000000 0.020055 0.015603 0.035658 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.035658 -%:RSB_SUBDIVISION_TIME:A.mtx S N 12 3 3 6 0.020055 -%:RSB_SHUFFLE_TIME:A.mtx S N 12 3 3 6 0.015603 -%:ROW_MAJOR_SORT_TIME:A.mtx S N 12 3 3 6 0.000000 -%:ROW_MAJOR_SORT_SCALING:A.mtx S N 12 3 3 6 nan -%:SORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.035658 +%:CONSTRUCTOR_TIMES:A.mtx S N 12 3 3 6 0.000001 0.000013 0.000010 0.000023 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.000024 +%:RSB_SUBDIVISION_TIME:A.mtx S N 12 3 3 6 0.000013 +%:RSB_SHUFFLE_TIME:A.mtx S N 12 3 3 6 0.000010 +%:ROW_MAJOR_SORT_TIME:A.mtx S N 12 3 3 6 0.000001 +%:ROW_MAJOR_SORT_SCALING:A.mtx S N 12 3 3 6 1.000 +%:SORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.000023 %:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 12 3 3 6 0.000 %:UNSORTEDCOO2RSB_SCALING:A.mtx S N 12 3 3 6 1.00 %:SORTEDCOO2RSB_SCALING:A.mtx S N 12 3 3 6 1.00 %:RSB_SUBDIVISION_SCALING:A.mtx S N 12 3 3 6 1.00 %:RSB_SHUFFLE_SCALING:A.mtx S N 12 3 3 6 1.00 -%:CONSTRUCTOR_SCALING:A.mtx S N 12 3 3 6 nan 1.00 1.00 1.00 +%:CONSTRUCTOR_SCALING:A.mtx S N 12 3 3 6 1.00 1.00 1.00 1.00 #%:SM_COUNTS: Tot HalfwordCsr FullwordCsr HalfwordCoo FullwordCoo %:SM_COUNTS:A.mtx S N 12 3 3 6 1 1 0 0 0 %:SM_IDXOCCUPATIONRSBVSCOOANDCSR:A.mtx S N 12 3 3 6 28 48 36 @@ -4417,59 +4453,59 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 12 3 3 6 6 6 6 # %operation:matrix CONSTRUCTOR[12] SPMV[12] SPMV[12] -%operation:A.mtx 0.0516529 1e+09 1e+09 +%operation:A.mtx 3.29018e-05 1e+09 1e+09 %constructor:matrix SORT[12] SCAN[12] SHUFFLE[12] INSERT[12] -%constructor:A.mtx 0 0.0200548 0 0.0156031 +%constructor:A.mtx 9.53674e-07 1.3113e-05 0 1.00136e-05 # symmetric matrix --- skipping transposed benchmarking -# so far, program took 8.271s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 1.816s/0.000s . +# so far, program took 5.278s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.050s/0.000s . getrusage() stats: -ru_maxrss: 6 (maximum resident set size -- MB) -ru_stime : 0.03249s (system CPU time used) -ru_utime : 4.305s (user CPU time used) +ru_maxrss: 8 (maximum resident set size -- MB) +ru_stime : 0.0362s (system CPU time used) +ru_utime : 5.419s (user CPU time used) # multi-type benchmarking (DSCZ) -- now using typecode C (last was S). # Cache block size total 524288 bytes, per-thread 43690 bytes -# so far, program took 8.271s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 1.816s/0.000s . +# so far, program took 5.278s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.050s/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 12 threads -# Constructed matrix (took 0.056s): (3 x 3)[0xaaaac15640c0]{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' +# Constructed matrix (took 0.000s): (3 x 3)[0xaaaaeb482100]{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 (12 th.) took 0.02421s; avg 0.008069s ( +/- 3.50/ 1.77 %); best 0.007787s; worst 0.008212s; std dev. 0.0001994 (taking best). -Reference operation time is 0.00778699 s (0.01233 Mflops) with 12 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: 0.007787 Mflops: 0.012) -Merge (3 -> 1 leaves) took w.c.t. of 1.597e-05s, ~5.007e-06s of computing time (of which 1.907e-06s sorting, 3.099e-06s analysis) -3 iterations (12 th.) took 0.000241s; avg 8.035e-05s ( +/- 99.96/198.52 %); best 3.6e-08s; worst 0.0002398s; std dev. 0.0001128 (taking best). -Reference operation time is 3.60012e-08 s (2667 Mflops) with 12 threads. -After merge step 1: tpop: 3.6e-08 s ~Mflops: 2666.577 nsubm:1 otn:12 -Applying merge (3 -> 1 leaves, 12 th.) yielded SPEEDUP of 216298.013x: 0.007787s -> 3.6e-08s, so taking this instance. +3 iterations (12 th.) took 0.000603s; avg 0.000201s ( +/- 96.56/191.10 %); best 6.914e-06s; worst 0.0005851s; std dev. 0.0002716 (taking best). +Reference operation time is 6.91414e-06 s (13.88 Mflops) with 12 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: 6.914e-06 Mflops: 13.885) +Merge (3 -> 1 leaves) took w.c.t. of 7.868e-06s, ~4.053e-06s of computing time (of which 9.537e-07s sorting, 9.537e-07s analysis) +3 iterations (12 th.) took 0.000185s; avg 6.167e-05s ( +/- 99.94/198.07 %); best 3.885e-08s; worst 0.0001838s; std dev. 8.637e-05 (taking best). +Reference operation time is 3.88503e-08 s (2471 Mflops) with 12 threads. +After merge step 1: tpop: 3.885e-08 s ~Mflops: 2471.023 nsubm:1 otn:12 +Applying merge (3 -> 1 leaves, 12 th.) yielded SPEEDUP of 177.969x: 6.914e-06s -> 3.885e-08s, 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 0.02379s (of which 1.788e-05s partitioning, 0s I/O); computing times: 5.007e-06s in par. loops, 1.907e-06s sorting, 3.099e-06s analyzing) -Total merge + benchmarking process took 0.02379s, equivalent to 660755.0/3.1 new/old ops (0.04706s for 2 clones -- as 1307231.8/6.0 ops, or 653615.9/3.0 ops per clone), SPEEDUP of 216298.013x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 216298.013x (0.007787s -> 3.6e-08s), will amortize in 3.1 ops by saving 0.007787s per op. -In 1 tuning rounds (tot. 0.072s, 0.047s for constructor, 2 clones) obtained a SPEEDUP of 21629701.3% (2.163e+05x) (from 0.01233 to 2667 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.00021s (of which 1.001e-05s partitioning, 0s I/O); computing times: 4.053e-06s in par. loops, 9.537e-07s sorting, 9.537e-07s analyzing) +Total merge + benchmarking process took 0.00021s, equivalent to 5406.6/30.4 new/old ops (8.512e-05s for 2 clones -- as 2190.9/12.3 ops, or 1095.4/6.2 ops per clone), SPEEDUP of 177.969x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 177.969x (6.914e-06s -> 3.885e-08s), will amortize in 30.6 ops by saving 6.875e-06s per op. +In 1 tuning rounds (tot. 0.00091s, 8.5e-05s for constructor, 2 clones) obtained a SPEEDUP of 17696.9% (178x) (from 13.88 to 2471 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 0.071599 s (7.787e-03 s -> 3.600e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.000914812 s (6.914e-06 s -> 3.885e-08 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 0.400864 s and estimated a speedup of 1.000000 x (3.600e-08 s -> 3.600e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.000416994 s and estimated a speedup of 1.000000 x (3.885e-08 s -> 3.885e-08 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 12 3 3 6 0.000000 0.023814 0.015788 0.039602 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.039602 -%:RSB_SUBDIVISION_TIME:A.mtx S N 12 3 3 6 0.023814 -%:RSB_SHUFFLE_TIME:A.mtx S N 12 3 3 6 0.015788 +%:CONSTRUCTOR_TIMES:A.mtx S N 12 3 3 6 0.000000 0.000015 0.000011 0.000026 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.000026 +%:RSB_SUBDIVISION_TIME:A.mtx S N 12 3 3 6 0.000015 +%:RSB_SHUFFLE_TIME:A.mtx S N 12 3 3 6 0.000011 %:ROW_MAJOR_SORT_TIME:A.mtx S N 12 3 3 6 0.000000 %:ROW_MAJOR_SORT_SCALING:A.mtx S N 12 3 3 6 nan -%:SORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.039602 +%:SORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.000026 %:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 12 3 3 6 0.000 %:UNSORTEDCOO2RSB_SCALING:A.mtx S N 12 3 3 6 1.00 %:SORTEDCOO2RSB_SCALING:A.mtx S N 12 3 3 6 1.00 @@ -4484,50 +4520,50 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 12 3 3 6 6 6 6 # %operation:matrix CONSTRUCTOR[12] SPMV[12] SPMV[12] -%operation:A.mtx 0.0556068 1e+09 1e+09 +%operation:A.mtx 3.69549e-05 1e+09 1e+09 %constructor:matrix SORT[12] SCAN[12] SHUFFLE[12] INSERT[12] -%constructor:A.mtx 0 0.023814 0 0.0157881 +%constructor:A.mtx 0 1.50204e-05 0 1.09673e-05 # 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 12 threads -# Constructed matrix (took 0.055s): (3 x 3)[0xaaaac15640c0]{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' +# Constructed matrix (took 0.001s): (3 x 3)[0xaaaaeb482100]{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 (12 th.) took 0.02775s; avg 0.00925s ( +/- 15.88/ 18.29 %); best 0.007781s; worst 0.01094s; std dev. 0.0013 (taking best). -Reference operation time is 0.00778103 s (0.04935 Mflops) with 12 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: 0.007781 Mflops: 0.049) -Merge (3 -> 1 leaves) took w.c.t. of 1.597e-05s, ~5.007e-06s of computing time (of which 0s sorting, 4.053e-06s analysis) -3 iterations (12 th.) took 4.768e-06s; avg 1.589e-06s ( +/- 97.73/140.00 %); best 3.6e-08s; worst 3.815e-06s; std dev. 1.621e-06 (taking best). -Reference operation time is 3.60012e-08 s (1.067e+04 Mflops) with 12 threads. -After merge step 1: tpop: 3.6e-08 s ~Mflops: 10666.310 nsubm:1 otn:12 -Applying merge (3 -> 1 leaves, 12 th.) yielded SPEEDUP of 216132.450x: 0.007781s -> 3.6e-08s, so taking this instance. +3 iterations (12 th.) took 0.0005579s; avg 0.000186s ( +/- 91.41/172.56 %); best 1.597e-05s; worst 0.0005069s; std dev. 0.0002271 (taking best). +Reference operation time is 1.5974e-05 s (24.04 Mflops) with 12 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: 1.597e-05 Mflops: 24.039) +Merge (3 -> 1 leaves) took w.c.t. of 5.007e-06s, ~1.907e-06s of computing time (of which 0s sorting, 1.192e-06s analysis) +3 iterations (12 th.) took 2.861e-06s; avg 9.537e-07s ( +/- 95.93/200.00 %); best 3.885e-08s; worst 2.861e-06s; std dev. 1.349e-06 (taking best). +Reference operation time is 3.88503e-08 s (9884 Mflops) with 12 threads. +After merge step 1: tpop: 3.885e-08 s ~Mflops: 9884.092 nsubm:1 otn:12 +Applying merge (3 -> 1 leaves, 12 th.) yielded SPEEDUP of 411.169x: 1.597e-05s -> 3.885e-08s, 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 0.02041s (of which 1.788e-05s partitioning, 0s I/O); computing times: 5.007e-06s in par. loops, 0s sorting, 4.053e-06s analyzing) -Total merge + benchmarking process took 0.02041s, equivalent to 567006.6/2.6 new/old ops (0.04017s for 2 clones -- as 1115708.6/5.2 ops, or 557854.3/2.6 ops per clone), SPEEDUP of 216132.450x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 216132.450x (0.007781s -> 3.6e-08s), will amortize in 2.6 ops by saving 0.007781s per op. -In 1 tuning rounds (tot. 0.068s, 0.04s for constructor, 2 clones) obtained a SPEEDUP of 21613145.0% (2.161e+05x) (from 0.04935 to 1.067e+04 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 2.503e-05s (of which 6.199e-06s partitioning, 0s I/O); computing times: 1.907e-06s in par. loops, 0s sorting, 1.192e-06s analyzing) +Total merge + benchmarking process took 2.503e-05s, equivalent to 644.4/1.6 new/old ops (2.193e-05s for 2 clones -- as 564.6/1.4 ops, or 282.3/0.7 ops per clone), SPEEDUP of 411.169x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 411.169x (1.597e-05s -> 3.885e-08s), will amortize in 1.6 ops by saving 1.594e-05s per op. +In 1 tuning rounds (tot. 0.00061s, 2.2e-05s for constructor, 2 clones) obtained a SPEEDUP of 41016.9% (411.2x) (from 24.04 to 9884 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 0.068006 s (7.781e-03 s -> 3.600e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.000617981 s (1.597e-05 s -> 3.885e-08 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 0.404007 s and estimated a speedup of 1.000000 x (3.600e-08 s -> 3.600e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.000346899 s and estimated a speedup of 1.000000 x (3.885e-08 s -> 3.885e-08 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 12 3 3 6 0.000000 0.019412 0.016410 0.035822 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.035822 -%:RSB_SUBDIVISION_TIME:A.mtx S N 12 3 3 6 0.019412 -%:RSB_SHUFFLE_TIME:A.mtx S N 12 3 3 6 0.016410 +%:CONSTRUCTOR_TIMES:A.mtx S N 12 3 3 6 0.000000 0.000615 0.000010 0.000625 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.000625 +%:RSB_SUBDIVISION_TIME:A.mtx S N 12 3 3 6 0.000615 +%:RSB_SHUFFLE_TIME:A.mtx S N 12 3 3 6 0.000010 %:ROW_MAJOR_SORT_TIME:A.mtx S N 12 3 3 6 0.000000 %:ROW_MAJOR_SORT_SCALING:A.mtx S N 12 3 3 6 nan -%:SORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.035822 +%:SORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.000625 %:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 12 3 3 6 0.000 %:UNSORTEDCOO2RSB_SCALING:A.mtx S N 12 3 3 6 1.00 %:SORTEDCOO2RSB_SCALING:A.mtx S N 12 3 3 6 1.00 @@ -4542,59 +4578,59 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 12 3 3 6 6 6 6 # %operation:matrix CONSTRUCTOR[12] SPMV[12] SPMV[12] -%operation:A.mtx 0.0551789 1e+09 1e+09 +%operation:A.mtx 0.000636101 1e+09 1e+09 %constructor:matrix SORT[12] SCAN[12] SHUFFLE[12] INSERT[12] -%constructor:A.mtx 0 0.019412 0 0.0164101 +%constructor:A.mtx 0 0.000614882 0 1.00136e-05 # symmetric matrix --- skipping transposed benchmarking -# so far, program took 9.407s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 2.761s/0.000s . +# so far, program took 5.282s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.052s/0.000s . getrusage() stats: -ru_maxrss: 6 (maximum resident set size -- MB) -ru_stime : 0.03717s (system CPU time used) -ru_utime : 4.931s (user CPU time used) +ru_maxrss: 8 (maximum resident set size -- MB) +ru_stime : 0.0362s (system CPU time used) +ru_utime : 5.47s (user CPU time used) # multi-type benchmarking (DSCZ) -- now using typecode Z (last was C). # Cache block size total 524288 bytes, per-thread 43690 bytes -# so far, program took 9.407s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 2.761s/0.000s . +# so far, program took 5.282s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.052s/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 12 threads -# Constructed matrix (took 0.052s): (3 x 3)[0xaaaac15640c0]{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 0.000s): (3 x 3)[0xaaaaeb482100]{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 (12 th.) took 0.02815s; avg 0.009383s ( +/- 21.06/ 31.64 %); best 0.007407s; worst 0.01235s; std dev. 0.002137 (taking best). -Reference operation time is 0.00740695 s (0.01296 Mflops) with 12 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: 0.007407 Mflops: 0.013) -Merge (3 -> 1 leaves) took w.c.t. of 1.407e-05s, ~5.007e-06s of computing time (of which 9.537e-07s sorting, 3.099e-06s analysis) -3 iterations (12 th.) took 1.907e-05s; avg 6.358e-06s ( +/- 99.43/181.25 %); best 3.6e-08s; worst 1.788e-05s; std dev. 8.163e-06 (taking best). -Reference operation time is 3.60012e-08 s (2667 Mflops) with 12 threads. -After merge step 1: tpop: 3.6e-08 s ~Mflops: 2666.577 nsubm:1 otn:12 -Applying merge (3 -> 1 leaves, 12 th.) yielded SPEEDUP of 205741.722x: 0.007407s -> 3.6e-08s, so taking this instance. +3 iterations (12 th.) took 0.0005381s; avg 0.0001794s ( +/- 90.56/180.46 %); best 1.693e-05s; worst 0.0005031s; std dev. 0.0002289 (taking best). +Reference operation time is 1.69277e-05 s (5.671 Mflops) with 12 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: 1.693e-05 Mflops: 5.671) +Merge (3 -> 1 leaves) took w.c.t. of 5.007e-06s, ~2.146e-06s of computing time (of which 9.537e-07s sorting, 9.537e-07s analysis) +3 iterations (12 th.) took 1.597e-05s; avg 5.325e-06s ( +/- 99.27/200.00 %); best 3.885e-08s; worst 1.597e-05s; std dev. 7.53e-06 (taking best). +Reference operation time is 3.88503e-08 s (2471 Mflops) with 12 threads. +After merge step 1: tpop: 3.885e-08 s ~Mflops: 2471.023 nsubm:1 otn:12 +Applying merge (3 -> 1 leaves, 12 th.) yielded SPEEDUP of 435.716x: 1.693e-05s -> 3.885e-08s, 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 0.027s (of which 1.693e-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 0.027s, equivalent to 749894.0/3.6 new/old ops (0.05111s for 2 clones -- as 1419682.1/6.9 ops, or 709841.1/3.5 ops per clone), SPEEDUP of 205741.722x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 205741.722x (0.007407s -> 3.6e-08s), will amortize in 3.6 ops by saving 0.007407s per op. -In 1 tuning rounds (tot. 0.079s, 0.051s for constructor, 2 clones) obtained a SPEEDUP of 20574072.2% (2.057e+05x) (from 0.01296 to 2667 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 3.791e-05s (of which 6.914e-06s partitioning, 0s I/O); computing times: 2.146e-06s in par. loops, 9.537e-07s sorting, 9.537e-07s analyzing) +Total merge + benchmarking process took 3.791e-05s, equivalent to 975.8/2.2 new/old ops (2.098e-05s for 2 clones -- as 540.0/1.2 ops, or 270.0/0.6 ops per clone), SPEEDUP of 435.716x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 435.716x (1.693e-05s -> 3.885e-08s), will amortize in 2.2 ops by saving 1.689e-05s per op. +In 1 tuning rounds (tot. 0.0006s, 2.1e-05s for constructor, 2 clones) obtained a SPEEDUP of 43471.6% (435.7x) (from 5.671 to 2471 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 0.079365 s (7.407e-03 s -> 3.600e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.00060606 s (1.693e-05 s -> 3.885e-08 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 0.404774 s and estimated a speedup of 1.000000 x (3.600e-08 s -> 3.600e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.000394106 s and estimated a speedup of 1.000000 x (3.885e-08 s -> 3.885e-08 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 12 3 3 6 0.000000 0.020358 0.018980 0.039338 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.039338 -%:RSB_SUBDIVISION_TIME:A.mtx S N 12 3 3 6 0.020358 -%:RSB_SHUFFLE_TIME:A.mtx S N 12 3 3 6 0.018980 +%:CONSTRUCTOR_TIMES:A.mtx S N 12 3 3 6 0.000000 0.000045 0.000010 0.000055 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.000055 +%:RSB_SUBDIVISION_TIME:A.mtx S N 12 3 3 6 0.000045 +%:RSB_SHUFFLE_TIME:A.mtx S N 12 3 3 6 0.000010 %:ROW_MAJOR_SORT_TIME:A.mtx S N 12 3 3 6 0.000000 %:ROW_MAJOR_SORT_SCALING:A.mtx S N 12 3 3 6 nan -%:SORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.039338 +%:SORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.000055 %:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 12 3 3 6 0.000 %:UNSORTEDCOO2RSB_SCALING:A.mtx S N 12 3 3 6 1.00 %:SORTEDCOO2RSB_SCALING:A.mtx S N 12 3 3 6 1.00 @@ -4609,50 +4645,50 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 12 3 3 6 6 6 6 # %operation:matrix CONSTRUCTOR[12] SPMV[12] SPMV[12] -%operation:A.mtx 0.051959 1e+09 1e+09 +%operation:A.mtx 6.69956e-05 1e+09 1e+09 %constructor:matrix SORT[12] SCAN[12] SHUFFLE[12] INSERT[12] -%constructor:A.mtx 0 0.0203581 0 0.01898 +%constructor:A.mtx 0 4.50611e-05 0 9.77516e-06 # 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 12 threads -# Constructed matrix (took 0.055s): (3 x 3)[0xaaaac15640c0]{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 0.000s): (3 x 3)[0xaaaaeb482100]{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 (12 th.) took 0.02339s; avg 0.007798s ( +/- 5.31/ 2.67 %); best 0.007384s; worst 0.008006s; std dev. 0.0002927 (taking best). -Reference operation time is 0.00738406 s (0.052 Mflops) with 12 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: 0.007384 Mflops: 0.052) -Merge (3 -> 1 leaves) took w.c.t. of 1.597e-05s, ~3.815e-06s of computing time (of which 9.537e-07s sorting, 5.007e-06s analysis) -3 iterations (12 th.) took 6.199e-06s; avg 2.066e-06s ( +/- 98.26/142.31 %); best 3.6e-08s; worst 5.007e-06s; std dev. 2.135e-06 (taking best). -Reference operation time is 3.60012e-08 s (1.067e+04 Mflops) with 12 threads. -After merge step 1: tpop: 3.6e-08 s ~Mflops: 10666.310 nsubm:1 otn:12 -Applying merge (3 -> 1 leaves, 12 th.) yielded SPEEDUP of 205105.960x: 0.007384s -> 3.6e-08s, so taking this instance. +3 iterations (12 th.) took 0.000102s; avg 3.401e-05s ( +/- 78.97/ 43.69 %); best 7.153e-06s; worst 4.888e-05s; std dev. 1.903e-05 (taking best). +Reference operation time is 7.15256e-06 s (53.69 Mflops) with 12 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: 7.153e-06 Mflops: 53.687) +Merge (3 -> 1 leaves) took w.c.t. of 6.199e-06s, ~2.861e-06s of computing time (of which 9.537e-07s sorting, 1.192e-06s analysis) +3 iterations (12 th.) took 4.053e-06s; avg 1.351e-06s ( +/- 97.12/111.76 %); best 3.885e-08s; worst 2.861e-06s; std dev. 1.173e-06 (taking best). +Reference operation time is 3.88503e-08 s (9884 Mflops) with 12 threads. +After merge step 1: tpop: 3.885e-08 s ~Mflops: 9884.092 nsubm:1 otn:12 +Applying merge (3 -> 1 leaves, 12 th.) yielded SPEEDUP of 184.106x: 7.153e-06s -> 3.885e-08s, 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 0.02462s (of which 1.788e-05s partitioning, 0s I/O); computing times: 3.815e-06s in par. loops, 9.537e-07s sorting, 5.007e-06s analyzing) -Total merge + benchmarking process took 0.02462s, equivalent to 683973.5/3.3 new/old ops (0.04937s for 2 clones -- as 1371423.8/6.7 ops, or 685711.9/3.3 ops per clone), SPEEDUP of 205105.960x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 205105.960x (0.007384s -> 3.6e-08s), will amortize in 3.3 ops by saving 0.007384s per op. -In 1 tuning rounds (tot. 0.073s, 0.049s for constructor, 2 clones) obtained a SPEEDUP of 20510496.0% (2.051e+05x) (from 0.052 to 1.067e+04 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 2.694e-05s (of which 7.153e-06s partitioning, 0s I/O); computing times: 2.861e-06s in par. loops, 9.537e-07s sorting, 1.192e-06s analyzing) +Total merge + benchmarking process took 2.694e-05s, equivalent to 693.5/3.8 new/old ops (2.098e-05s for 2 clones -- as 540.0/2.9 ops, or 270.0/1.5 ops per clone), SPEEDUP of 184.106x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 184.106x (7.153e-06s -> 3.885e-08s), will amortize in 3.8 ops by saving 7.114e-06s per op. +In 1 tuning rounds (tot. 0.00015s, 2.1e-05s for constructor, 2 clones) obtained a SPEEDUP of 18310.6% (184.1x) (from 53.69 to 9884 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 0.0730541 s (7.384e-03 s -> 3.600e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.000237942 s (7.153e-06 s -> 3.885e-08 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 0.406699 s and estimated a speedup of 1.000000 x (3.600e-08 s -> 3.600e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.000668049 s and estimated a speedup of 1.000000 x (3.885e-08 s -> 3.885e-08 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 12 3 3 6 0.000000 0.019627 0.015990 0.035617 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.035617 -%:RSB_SUBDIVISION_TIME:A.mtx S N 12 3 3 6 0.019627 -%:RSB_SHUFFLE_TIME:A.mtx S N 12 3 3 6 0.015990 +%:CONSTRUCTOR_TIMES:A.mtx S N 12 3 3 6 0.000000 0.000263 0.000010 0.000273 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.000273 +%:RSB_SUBDIVISION_TIME:A.mtx S N 12 3 3 6 0.000263 +%:RSB_SHUFFLE_TIME:A.mtx S N 12 3 3 6 0.000010 %:ROW_MAJOR_SORT_TIME:A.mtx S N 12 3 3 6 0.000000 %:ROW_MAJOR_SORT_SCALING:A.mtx S N 12 3 3 6 nan -%:SORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.035617 +%:SORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.000273 %:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 12 3 3 6 0.000 %:UNSORTEDCOO2RSB_SCALING:A.mtx S N 12 3 3 6 1.00 %:SORTEDCOO2RSB_SCALING:A.mtx S N 12 3 3 6 1.00 @@ -4667,332 +4703,332 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 12 3 3 6 6 6 6 # %operation:matrix CONSTRUCTOR[12] SPMV[12] SPMV[12] -%operation:A.mtx 0.0553861 1e+09 1e+09 +%operation:A.mtx 0.00028491 1e+09 1e+09 %constructor:matrix SORT[12] SCAN[12] SHUFFLE[12] INSERT[12] -%constructor:A.mtx 0 0.0196269 0 0.01599 +%constructor:A.mtx 0 0.000262976 0 1.00136e-05 # symmetric matrix --- skipping transposed benchmarking -# so far, program took 10.558s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 3.725s/0.000s . +# so far, program took 5.286s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.054s/0.000s . getrusage() stats: -ru_maxrss: 6 (maximum resident set size -- MB) -ru_stime : 0.04188s (system CPU time used) -ru_utime : 5.577s (user CPU time used) +ru_maxrss: 8 (maximum resident set size -- MB) +ru_stime : 0.04783s (system CPU time used) +ru_utime : 5.504s (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 12 12 0 4.0000 4.6667 3 1 666.64 7.580e-03 0.000e+00 3.600e-08 0.000e+00 7.215e-02 4.11e+00 5.17e+00 1 2.40e-05 -pr: 9:R_R A 3 3 6 4 D S N 12 12 0 4.0000 4.6667 3 1 2666.58 7.583e-03 0.000e+00 3.600e-08 0.000e+00 7.220e-02 1.01e+01 2.79e+00 1 9.60e-05 +pr: 1:R_R A 3 3 6 1 D S N 12 12 0 4.0000 4.6667 3 1 617.76 5.960e-06 0.000e+00 3.885e-08 0.000e+00 1.590e-04 3.81e+00 5.17e+00 1 2.40e-05 +pr: 9:R_R A 3 3 6 4 D S N 12 12 0 4.0000 4.6667 3 1 2471.02 1.693e-05 0.000e+00 3.885e-08 0.000e+00 8.933e-03 9.37e+00 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. 21058840.4 % faster, avg. sp. ratio 210589.404x, max sp. ratio 210629.139x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 2004781.5/2003966.9/2005596.0/4009562.9 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 9.5/ 9.5/ 9.5/ 19.0 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 9.5, min. 9.5, max. 9.5 ops) +#pr: (in succ. cases rsb autotuning gave avg. 29356.9 % faster, avg. sp. ratio 294.569x, max sp. ratio 435.716x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 117014.4/4093.3/229935.6/234028.8 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 277.2/ 26.7/527.7/554.4 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 277.9, min. 26.9, max. 528.9 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 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 5.444/ 3.444/ 7.444,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 14.222/ 4.111/ 10.111,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 5.045/ 3.192/ 6.898,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 13.179/ 3.809/ 9.369,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 0.07 s, max 0.07 s, tot 0.14 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.07 s, min 0.07 s, max 0.07 s, tot 0.14 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 1.667e+03, min 6.666e+02, max 2.667e+03 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 7.913e-03, min 3.166e-03, max 1.266e-02 (2 samples) -#pr: best tun. rsb operation time was: on avg. 3.600e-08s, min 3.600e-08s, max 3.600e-08s, tot 7.200e-08s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 7.581e-03s, min 7.580e-03s, max 7.583e-03s, tot 1.516e-02s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 3.281e+00 7.092e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.057e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.00 s, min 0.00 s, max 0.01 s, tot 0.01 s (2 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.00 s, min 0.00 s, max 0.01 s, tot 0.01 s (2 samples) +#pr: best tun. rsb canon. mflops were: on avg. 1.544e+03, min 6.178e+02, max 2.471e+03 (2 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 4.849e+00, min 4.027e+00, max 5.671e+00 (2 samples) +#pr: best tun. rsb operation time was: on avg. 3.885e-08s, min 3.885e-08s, max 3.885e-08s, tot 7.770e-08s (2 samples) +#pr: ref. unt. rsb operation time was: on avg. 1.144e-05s, min 5.960e-06s, max 1.693e-05s, tot 2.289e-05s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 6.933e+00 1.498e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 9.995e-01 #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 12 12 0 4.0000 4.6667 3 1 666.64 4.242e-03 0.000e+00 3.600e-08 0.000e+00 7.600e-02 2.44e+00 3.17e+00 1 2.40e-05 -pr: 11:R_R A 3 3 6 4 S S N 12 12 0 4.0000 4.6667 3 1 2666.58 4.776e-03 0.000e+00 3.600e-08 0.000e+00 7.601e-02 5.44e+00 1.54e+00 1 9.60e-05 +pr: 3:R_R A 3 3 6 1 S S N 12 12 0 4.0000 4.6667 3 1 617.76 5.960e-06 0.000e+00 3.885e-08 0.000e+00 4.780e-04 2.27e+00 3.17e+00 1 2.40e-05 +pr: 11:R_R A 3 3 6 4 S S N 12 12 0 4.0000 4.6667 3 1 2471.02 8.106e-06 0.000e+00 3.885e-08 0.000e+00 7.179e-04 5.05e+00 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. 12524403.3 % faster, avg. sp. ratio 125245.033x, max sp. ratio 132662.252x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 2111248.3/2111119.2/2111377.5/4222496.7 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 16.9/ 15.9/ 17.9/ 33.8 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 16.9, min. 15.9, max. 17.9 ops) +#pr: (in succ. cases rsb autotuning gave avg. 18003.7 % faster, avg. sp. ratio 181.037x, max sp. ratio 208.653x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 15391.2/12304.4/18478.1/30782.4 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 84.4/ 80.2/ 88.6/168.8 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 84.9, min. 80.7, max. 89.0 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 3.111/ 2.111/ 4.111,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 7.889/ 2.444/ 5.444,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 2.883/ 1.956/ 3.809,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 7.310/ 2.265/ 5.045,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.: 0.08 s, min 0.08 s, max 0.08 s, tot 0.15 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.08 s, min 0.08 s, max 0.08 s, tot 0.15 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 1.667e+03, min 6.666e+02, max 2.667e+03 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 1.288e-02, min 5.658e-03, max 2.010e-02 (2 samples) -#pr: best tun. rsb operation time was: on avg. 3.600e-08s, min 3.600e-08s, max 3.600e-08s, tot 7.200e-08s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 4.509e-03s, min 4.242e-03s, max 4.776e-03s, tot 9.018e-03s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 5.942e+00 1.157e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.057e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.00 s, min 0.00 s, max 0.00 s, tot 0.00 s (2 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.00 s, min 0.00 s, max 0.00 s, tot 0.00 s (2 samples) +#pr: best tun. rsb canon. mflops were: on avg. 1.544e+03, min 6.178e+02, max 2.471e+03 (2 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 7.935e+00, min 4.027e+00, max 1.184e+01 (2 samples) +#pr: best tun. rsb operation time was: on avg. 3.885e-08s, min 3.885e-08s, max 3.885e-08s, tot 7.770e-08s (2 samples) +#pr: ref. unt. rsb operation time was: on avg. 7.033e-06s, min 5.960e-06s, max 8.106e-06s, tot 1.407e-05s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.255e+01 2.445e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 9.995e-01 #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 12 12 0 4.0000 4.6667 3 1 2666.58 7.787e-03 0.000e+00 3.600e-08 0.000e+00 7.160e-02 4.11e+00 1.29e+00 1 9.60e-05 -pr: 13:R_R A 3 3 6 4 C S N 12 12 0 4.0000 4.6667 3 1 10666.31 7.781e-03 0.000e+00 3.600e-08 0.000e+00 6.801e-02 1.01e+01 6.98e-01 1 3.84e-04 +pr: 5:R_R A 3 3 6 1 C S N 12 12 0 4.0000 4.6667 3 1 2471.02 6.914e-06 0.000e+00 3.885e-08 0.000e+00 9.148e-04 3.81e+00 1.29e+00 1 9.60e-05 +pr: 13:R_R A 3 3 6 4 C S N 12 12 0 4.0000 4.6667 3 1 9884.09 1.597e-05 0.000e+00 3.885e-08 0.000e+00 6.180e-04 9.37e+00 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. 21621423.2 % faster, avg. sp. ratio 216215.232x, max sp. ratio 216298.013x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 1938894.0/1888993.4/1988794.7/3877788.1 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 9.0/ 8.7/ 9.2/ 17.9 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 9.0, min. 8.7, max. 9.2 ops) +#pr: (in succ. cases rsb autotuning gave avg. 29356.9 % faster, avg. sp. ratio 294.569x, max sp. ratio 411.169x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 19726.9/15906.7/23547.1/39453.8 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 85.5/ 38.7/132.3/171.0 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 85.9, min. 38.8, max. 133.1 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 5.444/ 3.444/ 7.444,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 14.222/ 4.111/ 10.111,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 5.045/ 3.192/ 6.898,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 13.179/ 3.809/ 9.369,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.: 0.07 s, min 0.07 s, max 0.07 s, tot 0.14 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.07 s, min 0.07 s, max 0.07 s, tot 0.14 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 6.666e+03, min 2.667e+03, max 1.067e+04 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 3.084e-02, min 1.233e-02, max 4.935e-02 (2 samples) -#pr: best tun. rsb operation time was: on avg. 3.600e-08s, min 3.600e-08s, max 3.600e-08s, tot 7.200e-08s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 7.784e-03s, min 7.781e-03s, max 7.787e-03s, tot 1.557e-02s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 3.281e+00 7.092e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.057e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.00 s, min 0.00 s, max 0.00 s, tot 0.00 s (2 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.00 s, min 0.00 s, max 0.00 s, tot 0.00 s (2 samples) +#pr: best tun. rsb canon. mflops were: on avg. 6.178e+03, min 2.471e+03, max 9.884e+03 (2 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 1.896e+01, min 1.388e+01, max 2.404e+01 (2 samples) +#pr: best tun. rsb operation time was: on avg. 3.885e-08s, min 3.885e-08s, max 3.885e-08s, tot 7.770e-08s (2 samples) +#pr: ref. unt. rsb operation time was: on avg. 1.144e-05s, min 6.914e-06s, max 1.597e-05s, tot 2.289e-05s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 6.933e+00 1.498e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 9.995e-01 #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 12 12 0 4.0000 4.6667 3 1 2666.58 7.407e-03 0.000e+00 3.600e-08 0.000e+00 7.937e-02 7.44e+00 2.29e+00 1 9.60e-05 -pr: 15:R_R A 3 3 6 4 Z S N 12 12 0 4.0000 4.6667 3 1 10666.31 7.384e-03 0.000e+00 3.600e-08 0.000e+00 7.305e-02 1.94e+01 1.32e+00 1 3.84e-04 +pr: 7:R_R A 3 3 6 1 Z S N 12 12 0 4.0000 4.6667 3 1 2471.02 1.693e-05 0.000e+00 3.885e-08 0.000e+00 6.061e-04 6.90e+00 2.29e+00 1 9.60e-05 +pr: 15:R_R A 3 3 6 4 Z S N 12 12 0 4.0000 4.6667 3 1 9884.09 7.153e-06 0.000e+00 3.885e-08 0.000e+00 2.379e-04 1.80e+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. 20542284.1 % faster, avg. sp. ratio 205423.841x, max sp. ratio 205741.722x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 2116860.9/2029211.9/2204509.9/4233721.9 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 10.3/ 9.9/ 10.7/ 20.6 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 10.3, min. 9.9, max. 10.7 ops) +#pr: (in succ. cases rsb autotuning gave avg. 30891.1 % faster, avg. sp. ratio 309.911x, max sp. ratio 435.716x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 10862.2/6124.6/15599.9/21724.5 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 34.5/ 33.3/ 35.8/ 69.1 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 34.7, min. 33.4, max. 35.9 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 10.111/ 6.111/ 14.111,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 26.888/ 7.444/ 19.444,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 9.369/ 5.663/ 13.076,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 24.916/ 6.898/ 18.018,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.: 0.08 s, min 0.07 s, max 0.08 s, tot 0.15 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.08 s, min 0.07 s, max 0.08 s, tot 0.15 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 6.666e+03, min 2.667e+03, max 1.067e+04 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 3.248e-02, min 1.296e-02, max 5.200e-02 (2 samples) -#pr: best tun. rsb operation time was: on avg. 3.600e-08s, min 3.600e-08s, max 3.600e-08s, tot 7.200e-08s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 7.396e-03s, min 7.384e-03s, max 7.407e-03s, tot 1.479e-02s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.731e+00 3.997e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.057e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.00 s, min 0.00 s, max 0.00 s, tot 0.00 s (2 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.00 s, min 0.00 s, max 0.00 s, tot 0.00 s (2 samples) +#pr: best tun. rsb canon. mflops were: on avg. 6.178e+03, min 2.471e+03, max 9.884e+03 (2 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 2.968e+01, min 5.671e+00, max 5.369e+01 (2 samples) +#pr: best tun. rsb operation time was: on avg. 3.885e-08s, min 3.885e-08s, max 3.885e-08s, tot 7.770e-08s (2 samples) +#pr: ref. unt. rsb operation time was: on avg. 1.204e-05s, min 7.153e-06s, max 1.693e-05s, tot 2.408e-05s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 3.657e+00 8.445e+00 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 9.995e-01 #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 12 12 0 4.0000 4.6667 3 1 666.64 7.580e-03 0.000e+00 3.600e-08 0.000e+00 7.215e-02 4.11e+00 5.17e+00 1 2.40e-05 -pr: 3:R_R A 3 3 6 1 S S N 12 12 0 4.0000 4.6667 3 1 666.64 4.242e-03 0.000e+00 3.600e-08 0.000e+00 7.600e-02 2.44e+00 3.17e+00 1 2.40e-05 -pr: 5:R_R A 3 3 6 1 C S N 12 12 0 4.0000 4.6667 3 1 2666.58 7.787e-03 0.000e+00 3.600e-08 0.000e+00 7.160e-02 4.11e+00 1.29e+00 1 9.60e-05 -pr: 7:R_R A 3 3 6 1 Z S N 12 12 0 4.0000 4.6667 3 1 2666.58 7.407e-03 0.000e+00 3.600e-08 0.000e+00 7.937e-02 7.44e+00 2.29e+00 1 9.60e-05 +pr: 1:R_R A 3 3 6 1 D S N 12 12 0 4.0000 4.6667 3 1 617.76 5.960e-06 0.000e+00 3.885e-08 0.000e+00 1.590e-04 3.81e+00 5.17e+00 1 2.40e-05 +pr: 3:R_R A 3 3 6 1 S S N 12 12 0 4.0000 4.6667 3 1 617.76 5.960e-06 0.000e+00 3.885e-08 0.000e+00 4.780e-04 2.27e+00 3.17e+00 1 2.40e-05 +pr: 5:R_R A 3 3 6 1 C S N 12 12 0 4.0000 4.6667 3 1 2471.02 6.914e-06 0.000e+00 3.885e-08 0.000e+00 9.148e-04 3.81e+00 1.29e+00 1 9.60e-05 +pr: 7:R_R A 3 3 6 1 Z S N 12 12 0 4.0000 4.6667 3 1 2471.02 1.693e-05 0.000e+00 3.885e-08 0.000e+00 6.061e-04 6.90e+00 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. 18760330.5 % faster, avg. sp. ratio 187604.305x, max sp. ratio 216298.013x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 2077097.7/1988794.7/2204509.9/8308390.7 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 11.8/ 9.2/ 17.9/ 47.3 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 11.8, min. 9.2, max. 17.9 ops) +#pr: (in succ. cases rsb autotuning gave avg. 22913.2 % faster, avg. sp. ratio 230.132x, max sp. ratio 435.716x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 13886.2/4093.3/23547.1/55544.6 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 68.7/ 26.7/132.3/275.0 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 69.1, min. 26.9, max. 133.1 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 3.778/ 2.111/ 6.111,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 18.111/ 2.444/ 7.444,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 3.501/ 1.956/ 5.663,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 16.782/ 2.265/ 6.898,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 0.07 s, max 0.08 s, tot 0.30 s (4 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.07 s, min 0.07 s, max 0.08 s, tot 0.30 s (4 samples) -#pr: best tun. rsb canon. mflops were: on avg. 1.667e+03, min 6.666e+02, max 2.667e+03 (4 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 8.528e-03, min 3.166e-03, max 1.296e-02 (4 samples) -#pr: best tun. rsb operation time was: on avg. 3.600e-08s, min 3.600e-08s, max 3.600e-08s, tot 1.440e-07s (4 samples) -#pr: ref. unt. rsb operation time was: on avg. 6.754e-03s, min 4.242e-03s, max 7.787e-03s, tot 2.702e-02s (4 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 3.997e+00 1.157e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.057e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.00 s, min 0.00 s, max 0.00 s, tot 0.00 s (4 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.00 s, min 0.00 s, max 0.00 s, tot 0.00 s (4 samples) +#pr: best tun. rsb canon. mflops were: on avg. 1.544e+03, min 6.178e+02, max 2.471e+03 (4 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 6.902e+00, min 4.027e+00, max 1.388e+01 (4 samples) +#pr: best tun. rsb operation time was: on avg. 3.885e-08s, min 3.885e-08s, max 3.885e-08s, tot 1.554e-07s (4 samples) +#pr: ref. unt. rsb operation time was: on avg. 8.941e-06s, min 5.960e-06s, max 1.693e-05s, tot 3.576e-05s (4 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 8.445e+00 2.445e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 9.995e-01 #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 12 12 0 4.0000 4.6667 3 1 2666.58 7.583e-03 0.000e+00 3.600e-08 0.000e+00 7.220e-02 1.01e+01 2.79e+00 1 9.60e-05 -pr: 11:R_R A 3 3 6 4 S S N 12 12 0 4.0000 4.6667 3 1 2666.58 4.776e-03 0.000e+00 3.600e-08 0.000e+00 7.601e-02 5.44e+00 1.54e+00 1 9.60e-05 -pr: 13:R_R A 3 3 6 4 C S N 12 12 0 4.0000 4.6667 3 1 10666.31 7.781e-03 0.000e+00 3.600e-08 0.000e+00 6.801e-02 1.01e+01 6.98e-01 1 3.84e-04 -pr: 15:R_R A 3 3 6 4 Z S N 12 12 0 4.0000 4.6667 3 1 10666.31 7.384e-03 0.000e+00 3.600e-08 0.000e+00 7.305e-02 1.94e+01 1.32e+00 1 3.84e-04 +pr: 9:R_R A 3 3 6 4 D S N 12 12 0 4.0000 4.6667 3 1 2471.02 1.693e-05 0.000e+00 3.885e-08 0.000e+00 8.933e-03 9.37e+00 2.79e+00 1 9.60e-05 +pr: 11:R_R A 3 3 6 4 S S N 12 12 0 4.0000 4.6667 3 1 2471.02 8.106e-06 0.000e+00 3.885e-08 0.000e+00 7.179e-04 5.05e+00 1.54e+00 1 9.60e-05 +pr: 13:R_R A 3 3 6 4 C S N 12 12 0 4.0000 4.6667 3 1 9884.09 1.597e-05 0.000e+00 3.885e-08 0.000e+00 6.180e-04 9.37e+00 6.98e-01 1 3.84e-04 +pr: 15:R_R A 3 3 6 4 Z S N 12 12 0 4.0000 4.6667 3 1 9884.09 7.153e-06 0.000e+00 3.885e-08 0.000e+00 2.379e-04 1.80e+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. 19113145.0 % faster, avg. sp. ratio 191132.450x, max sp. ratio 216132.450x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 2008794.7/1888993.4/2111377.5/8035178.8 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 11.0/ 8.7/ 15.9/ 44.1 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 11.0, min. 8.7, max. 15.9 ops) +#pr: (in succ. cases rsb autotuning gave avg. 30891.1 % faster, avg. sp. ratio 309.911x, max sp. ratio 435.716x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 67611.2/6124.6/229935.6/270444.9 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 172.1/ 33.3/527.7/688.2 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 172.5, min. 33.4, max. 528.9 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 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 8.278/ 4.111/ 14.111,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 45.110/ 5.444/ 19.444,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 7.670/ 3.809/ 13.076,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 41.801/ 5.045/ 18.018,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.: 0.07 s, min 0.07 s, max 0.08 s, tot 0.29 s (4 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.07 s, min 0.07 s, max 0.08 s, tot 0.29 s (4 samples) -#pr: best tun. rsb canon. mflops were: on avg. 6.666e+03, min 2.667e+03, max 1.067e+04 (4 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 3.353e-02, min 1.266e-02, max 5.200e-02 (4 samples) -#pr: best tun. rsb operation time was: on avg. 3.600e-08s, min 3.600e-08s, max 3.600e-08s, tot 1.440e-07s (4 samples) -#pr: ref. unt. rsb operation time was: on avg. 6.881e-03s, min 4.776e-03s, max 7.781e-03s, tot 2.752e-02s (4 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.731e+00 5.942e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.057e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.00 s, min 0.00 s, max 0.01 s, tot 0.01 s (4 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.00 s, min 0.00 s, max 0.01 s, tot 0.01 s (4 samples) +#pr: best tun. rsb canon. mflops were: on avg. 6.178e+03, min 2.471e+03, max 9.884e+03 (4 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 2.381e+01, min 5.671e+00, max 5.369e+01 (4 samples) +#pr: best tun. rsb operation time was: on avg. 3.885e-08s, min 3.885e-08s, max 3.885e-08s, tot 1.554e-07s (4 samples) +#pr: ref. unt. rsb operation time was: on avg. 1.204e-05s, min 7.153e-06s, max 1.693e-05s, tot 4.816e-05s (4 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 3.657e+00 1.255e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 9.995e-01 #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 12 12 0 4.0000 4.6667 3 1 666.64 7.580e-03 0.000e+00 3.600e-08 0.000e+00 7.215e-02 4.11e+00 5.17e+00 1 2.40e-05 -pr: 3:R_R A 3 3 6 1 S S N 12 12 0 4.0000 4.6667 3 1 666.64 4.242e-03 0.000e+00 3.600e-08 0.000e+00 7.600e-02 2.44e+00 3.17e+00 1 2.40e-05 -pr: 5:R_R A 3 3 6 1 C S N 12 12 0 4.0000 4.6667 3 1 2666.58 7.787e-03 0.000e+00 3.600e-08 0.000e+00 7.160e-02 4.11e+00 1.29e+00 1 9.60e-05 -pr: 7:R_R A 3 3 6 1 Z S N 12 12 0 4.0000 4.6667 3 1 2666.58 7.407e-03 0.000e+00 3.600e-08 0.000e+00 7.937e-02 7.44e+00 2.29e+00 1 9.60e-05 -pr: 9:R_R A 3 3 6 4 D S N 12 12 0 4.0000 4.6667 3 1 2666.58 7.583e-03 0.000e+00 3.600e-08 0.000e+00 7.220e-02 1.01e+01 2.79e+00 1 9.60e-05 -pr: 11:R_R A 3 3 6 4 S S N 12 12 0 4.0000 4.6667 3 1 2666.58 4.776e-03 0.000e+00 3.600e-08 0.000e+00 7.601e-02 5.44e+00 1.54e+00 1 9.60e-05 -pr: 13:R_R A 3 3 6 4 C S N 12 12 0 4.0000 4.6667 3 1 10666.31 7.781e-03 0.000e+00 3.600e-08 0.000e+00 6.801e-02 1.01e+01 6.98e-01 1 3.84e-04 -pr: 15:R_R A 3 3 6 4 Z S N 12 12 0 4.0000 4.6667 3 1 10666.31 7.384e-03 0.000e+00 3.600e-08 0.000e+00 7.305e-02 1.94e+01 1.32e+00 1 3.84e-04 +pr: 1:R_R A 3 3 6 1 D S N 12 12 0 4.0000 4.6667 3 1 617.76 5.960e-06 0.000e+00 3.885e-08 0.000e+00 1.590e-04 3.81e+00 5.17e+00 1 2.40e-05 +pr: 3:R_R A 3 3 6 1 S S N 12 12 0 4.0000 4.6667 3 1 617.76 5.960e-06 0.000e+00 3.885e-08 0.000e+00 4.780e-04 2.27e+00 3.17e+00 1 2.40e-05 +pr: 5:R_R A 3 3 6 1 C S N 12 12 0 4.0000 4.6667 3 1 2471.02 6.914e-06 0.000e+00 3.885e-08 0.000e+00 9.148e-04 3.81e+00 1.29e+00 1 9.60e-05 +pr: 7:R_R A 3 3 6 1 Z S N 12 12 0 4.0000 4.6667 3 1 2471.02 1.693e-05 0.000e+00 3.885e-08 0.000e+00 6.061e-04 6.90e+00 2.29e+00 1 9.60e-05 +pr: 9:R_R A 3 3 6 4 D S N 12 12 0 4.0000 4.6667 3 1 2471.02 1.693e-05 0.000e+00 3.885e-08 0.000e+00 8.933e-03 9.37e+00 2.79e+00 1 9.60e-05 +pr: 11:R_R A 3 3 6 4 S S N 12 12 0 4.0000 4.6667 3 1 2471.02 8.106e-06 0.000e+00 3.885e-08 0.000e+00 7.179e-04 5.05e+00 1.54e+00 1 9.60e-05 +pr: 13:R_R A 3 3 6 4 C S N 12 12 0 4.0000 4.6667 3 1 9884.09 1.597e-05 0.000e+00 3.885e-08 0.000e+00 6.180e-04 9.37e+00 6.98e-01 1 3.84e-04 +pr: 15:R_R A 3 3 6 4 Z S N 12 12 0 4.0000 4.6667 3 1 9884.09 7.153e-06 0.000e+00 3.885e-08 0.000e+00 2.379e-04 1.80e+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. 18936737.7 % faster, avg. sp. ratio 189368.377x, max sp. ratio 216298.013x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 2042946.2/1888993.4/2204509.9/16343569.5 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 11.4/ 8.7/ 17.9/ 91.4 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 11.4, min. 8.7, max. 17.9 ops) +#pr: (in succ. cases rsb autotuning gave avg. 26902.1 % faster, avg. sp. ratio 270.021x, max sp. ratio 435.716x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 40748.7/4093.3/229935.6/325989.6 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 120.4/ 26.7/527.7/963.2 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 120.8, min. 26.9, max. 528.9 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 18/ 8/ 32) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 54/ 24/ 96) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 6.028/ 2.111/ 14.111,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 63.220/ 2.444/ 19.444,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 5.586/ 1.956/ 13.076,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 58.584/ 2.265/ 18.018,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.: 0.07 s, min 0.07 s, max 0.08 s, tot 0.59 s (8 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.07 s, min 0.07 s, max 0.08 s, tot 0.59 s (8 samples) -#pr: best tun. rsb canon. mflops were: on avg. 4.167e+03, min 6.666e+02, max 1.067e+04 (8 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 2.103e-02, min 3.166e-03, max 5.200e-02 (8 samples) -#pr: best tun. rsb operation time was: on avg. 3.600e-08s, min 3.600e-08s, max 3.600e-08s, tot 2.880e-07s (8 samples) -#pr: ref. unt. rsb operation time was: on avg. 6.817e-03s, min 4.242e-03s, max 7.787e-03s, tot 5.454e-02s (8 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.731e+00 1.157e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.057e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.00 s, min 0.00 s, max 0.01 s, tot 0.01 s (8 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.00 s, min 0.00 s, max 0.01 s, tot 0.01 s (8 samples) +#pr: best tun. rsb canon. mflops were: on avg. 3.861e+03, min 6.178e+02, max 9.884e+03 (8 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 1.536e+01, min 4.027e+00, max 5.369e+01 (8 samples) +#pr: best tun. rsb operation time was: on avg. 3.885e-08s, min 3.885e-08s, max 3.885e-08s, tot 3.108e-07s (8 samples) +#pr: ref. unt. rsb operation time was: on avg. 1.049e-05s, min 5.960e-06s, max 1.693e-05s, tot 8.392e-05s (8 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 3.657e+00 2.445e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 9.995e-01 #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 12 12 0 4.0000 4.6667 3 1 666.64 7.580e-03 0.000e+00 3.600e-08 0.000e+00 7.215e-02 4.11e+00 5.17e+00 1 2.40e-05 -pr: 3:R_R A 3 3 6 1 S S N 12 12 0 4.0000 4.6667 3 1 666.64 4.242e-03 0.000e+00 3.600e-08 0.000e+00 7.600e-02 2.44e+00 3.17e+00 1 2.40e-05 -pr: 5:R_R A 3 3 6 1 C S N 12 12 0 4.0000 4.6667 3 1 2666.58 7.787e-03 0.000e+00 3.600e-08 0.000e+00 7.160e-02 4.11e+00 1.29e+00 1 9.60e-05 -pr: 7:R_R A 3 3 6 1 Z S N 12 12 0 4.0000 4.6667 3 1 2666.58 7.407e-03 0.000e+00 3.600e-08 0.000e+00 7.937e-02 7.44e+00 2.29e+00 1 9.60e-05 +pr: 1:R_R A 3 3 6 1 D S N 12 12 0 4.0000 4.6667 3 1 617.76 5.960e-06 0.000e+00 3.885e-08 0.000e+00 1.590e-04 3.81e+00 5.17e+00 1 2.40e-05 +pr: 3:R_R A 3 3 6 1 S S N 12 12 0 4.0000 4.6667 3 1 617.76 5.960e-06 0.000e+00 3.885e-08 0.000e+00 4.780e-04 2.27e+00 3.17e+00 1 2.40e-05 +pr: 5:R_R A 3 3 6 1 C S N 12 12 0 4.0000 4.6667 3 1 2471.02 6.914e-06 0.000e+00 3.885e-08 0.000e+00 9.148e-04 3.81e+00 1.29e+00 1 9.60e-05 +pr: 7:R_R A 3 3 6 1 Z S N 12 12 0 4.0000 4.6667 3 1 2471.02 1.693e-05 0.000e+00 3.885e-08 0.000e+00 6.061e-04 6.90e+00 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. 18760330.5 % faster, avg. sp. ratio 187604.305x, max sp. ratio 216298.013x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 2077097.7/1988794.7/2204509.9/8308390.7 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 11.8/ 9.2/ 17.9/ 47.3 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 11.8, min. 9.2, max. 17.9 ops) +#pr: (in succ. cases rsb autotuning gave avg. 22913.2 % faster, avg. sp. ratio 230.132x, max sp. ratio 435.716x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 13886.2/4093.3/23547.1/55544.6 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 68.7/ 26.7/132.3/275.0 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 69.1, min. 26.9, max. 133.1 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 3.778/ 2.111/ 6.111,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 18.111/ 2.444/ 7.444,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 3.501/ 1.956/ 5.663,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 16.782/ 2.265/ 6.898,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 0.07 s, max 0.08 s, tot 0.30 s (4 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.07 s, min 0.07 s, max 0.08 s, tot 0.30 s (4 samples) -#pr: best tun. rsb canon. mflops were: on avg. 1.667e+03, min 6.666e+02, max 2.667e+03 (4 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 8.528e-03, min 3.166e-03, max 1.296e-02 (4 samples) -#pr: best tun. rsb operation time was: on avg. 3.600e-08s, min 3.600e-08s, max 3.600e-08s, tot 1.440e-07s (4 samples) -#pr: ref. unt. rsb operation time was: on avg. 6.754e-03s, min 4.242e-03s, max 7.787e-03s, tot 2.702e-02s (4 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 3.997e+00 1.157e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.057e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.00 s, min 0.00 s, max 0.00 s, tot 0.00 s (4 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.00 s, min 0.00 s, max 0.00 s, tot 0.00 s (4 samples) +#pr: best tun. rsb canon. mflops were: on avg. 1.544e+03, min 6.178e+02, max 2.471e+03 (4 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 6.902e+00, min 4.027e+00, max 1.388e+01 (4 samples) +#pr: best tun. rsb operation time was: on avg. 3.885e-08s, min 3.885e-08s, max 3.885e-08s, tot 1.554e-07s (4 samples) +#pr: ref. unt. rsb operation time was: on avg. 8.941e-06s, min 5.960e-06s, max 1.693e-05s, tot 3.576e-05s (4 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 8.445e+00 2.445e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 9.995e-01 #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 12 12 0 4.0000 4.6667 3 1 2666.58 7.583e-03 0.000e+00 3.600e-08 0.000e+00 7.220e-02 1.01e+01 2.79e+00 1 9.60e-05 -pr: 11:R_R A 3 3 6 4 S S N 12 12 0 4.0000 4.6667 3 1 2666.58 4.776e-03 0.000e+00 3.600e-08 0.000e+00 7.601e-02 5.44e+00 1.54e+00 1 9.60e-05 -pr: 13:R_R A 3 3 6 4 C S N 12 12 0 4.0000 4.6667 3 1 10666.31 7.781e-03 0.000e+00 3.600e-08 0.000e+00 6.801e-02 1.01e+01 6.98e-01 1 3.84e-04 -pr: 15:R_R A 3 3 6 4 Z S N 12 12 0 4.0000 4.6667 3 1 10666.31 7.384e-03 0.000e+00 3.600e-08 0.000e+00 7.305e-02 1.94e+01 1.32e+00 1 3.84e-04 +pr: 9:R_R A 3 3 6 4 D S N 12 12 0 4.0000 4.6667 3 1 2471.02 1.693e-05 0.000e+00 3.885e-08 0.000e+00 8.933e-03 9.37e+00 2.79e+00 1 9.60e-05 +pr: 11:R_R A 3 3 6 4 S S N 12 12 0 4.0000 4.6667 3 1 2471.02 8.106e-06 0.000e+00 3.885e-08 0.000e+00 7.179e-04 5.05e+00 1.54e+00 1 9.60e-05 +pr: 13:R_R A 3 3 6 4 C S N 12 12 0 4.0000 4.6667 3 1 9884.09 1.597e-05 0.000e+00 3.885e-08 0.000e+00 6.180e-04 9.37e+00 6.98e-01 1 3.84e-04 +pr: 15:R_R A 3 3 6 4 Z S N 12 12 0 4.0000 4.6667 3 1 9884.09 7.153e-06 0.000e+00 3.885e-08 0.000e+00 2.379e-04 1.80e+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. 19113145.0 % faster, avg. sp. ratio 191132.450x, max sp. ratio 216132.450x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 2008794.7/1888993.4/2111377.5/8035178.8 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 11.0/ 8.7/ 15.9/ 44.1 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 11.0, min. 8.7, max. 15.9 ops) +#pr: (in succ. cases rsb autotuning gave avg. 30891.1 % faster, avg. sp. ratio 309.911x, max sp. ratio 435.716x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 67611.2/6124.6/229935.6/270444.9 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 172.1/ 33.3/527.7/688.2 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 172.5, min. 33.4, max. 528.9 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 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 8.278/ 4.111/ 14.111,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 45.110/ 5.444/ 19.444,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 7.670/ 3.809/ 13.076,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 41.801/ 5.045/ 18.018,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.: 0.07 s, min 0.07 s, max 0.08 s, tot 0.29 s (4 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.07 s, min 0.07 s, max 0.08 s, tot 0.29 s (4 samples) -#pr: best tun. rsb canon. mflops were: on avg. 6.666e+03, min 2.667e+03, max 1.067e+04 (4 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 3.353e-02, min 1.266e-02, max 5.200e-02 (4 samples) -#pr: best tun. rsb operation time was: on avg. 3.600e-08s, min 3.600e-08s, max 3.600e-08s, tot 1.440e-07s (4 samples) -#pr: ref. unt. rsb operation time was: on avg. 6.881e-03s, min 4.776e-03s, max 7.781e-03s, tot 2.752e-02s (4 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.731e+00 5.942e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.057e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.00 s, min 0.00 s, max 0.01 s, tot 0.01 s (4 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.00 s, min 0.00 s, max 0.01 s, tot 0.01 s (4 samples) +#pr: best tun. rsb canon. mflops were: on avg. 6.178e+03, min 2.471e+03, max 9.884e+03 (4 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 2.381e+01, min 5.671e+00, max 5.369e+01 (4 samples) +#pr: best tun. rsb operation time was: on avg. 3.885e-08s, min 3.885e-08s, max 3.885e-08s, tot 1.554e-07s (4 samples) +#pr: ref. unt. rsb operation time was: on avg. 1.204e-05s, min 7.153e-06s, max 1.693e-05s, tot 4.816e-05s (4 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 3.657e+00 1.255e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 9.995e-01 #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. @@ -5003,65 +5039,65 @@ #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 12 12 0 4.0000 4.6667 3 1 666.64 7.580e-03 0.000e+00 3.600e-08 0.000e+00 7.215e-02 4.11e+00 5.17e+00 1 2.40e-05 -pr: 3:R_R A 3 3 6 1 S S N 12 12 0 4.0000 4.6667 3 1 666.64 4.242e-03 0.000e+00 3.600e-08 0.000e+00 7.600e-02 2.44e+00 3.17e+00 1 2.40e-05 -pr: 5:R_R A 3 3 6 1 C S N 12 12 0 4.0000 4.6667 3 1 2666.58 7.787e-03 0.000e+00 3.600e-08 0.000e+00 7.160e-02 4.11e+00 1.29e+00 1 9.60e-05 -pr: 7:R_R A 3 3 6 1 Z S N 12 12 0 4.0000 4.6667 3 1 2666.58 7.407e-03 0.000e+00 3.600e-08 0.000e+00 7.937e-02 7.44e+00 2.29e+00 1 9.60e-05 -pr: 9:R_R A 3 3 6 4 D S N 12 12 0 4.0000 4.6667 3 1 2666.58 7.583e-03 0.000e+00 3.600e-08 0.000e+00 7.220e-02 1.01e+01 2.79e+00 1 9.60e-05 -pr: 11:R_R A 3 3 6 4 S S N 12 12 0 4.0000 4.6667 3 1 2666.58 4.776e-03 0.000e+00 3.600e-08 0.000e+00 7.601e-02 5.44e+00 1.54e+00 1 9.60e-05 -pr: 13:R_R A 3 3 6 4 C S N 12 12 0 4.0000 4.6667 3 1 10666.31 7.781e-03 0.000e+00 3.600e-08 0.000e+00 6.801e-02 1.01e+01 6.98e-01 1 3.84e-04 -pr: 15:R_R A 3 3 6 4 Z S N 12 12 0 4.0000 4.6667 3 1 10666.31 7.384e-03 0.000e+00 3.600e-08 0.000e+00 7.305e-02 1.94e+01 1.32e+00 1 3.84e-04 +pr: 1:R_R A 3 3 6 1 D S N 12 12 0 4.0000 4.6667 3 1 617.76 5.960e-06 0.000e+00 3.885e-08 0.000e+00 1.590e-04 3.81e+00 5.17e+00 1 2.40e-05 +pr: 3:R_R A 3 3 6 1 S S N 12 12 0 4.0000 4.6667 3 1 617.76 5.960e-06 0.000e+00 3.885e-08 0.000e+00 4.780e-04 2.27e+00 3.17e+00 1 2.40e-05 +pr: 5:R_R A 3 3 6 1 C S N 12 12 0 4.0000 4.6667 3 1 2471.02 6.914e-06 0.000e+00 3.885e-08 0.000e+00 9.148e-04 3.81e+00 1.29e+00 1 9.60e-05 +pr: 7:R_R A 3 3 6 1 Z S N 12 12 0 4.0000 4.6667 3 1 2471.02 1.693e-05 0.000e+00 3.885e-08 0.000e+00 6.061e-04 6.90e+00 2.29e+00 1 9.60e-05 +pr: 9:R_R A 3 3 6 4 D S N 12 12 0 4.0000 4.6667 3 1 2471.02 1.693e-05 0.000e+00 3.885e-08 0.000e+00 8.933e-03 9.37e+00 2.79e+00 1 9.60e-05 +pr: 11:R_R A 3 3 6 4 S S N 12 12 0 4.0000 4.6667 3 1 2471.02 8.106e-06 0.000e+00 3.885e-08 0.000e+00 7.179e-04 5.05e+00 1.54e+00 1 9.60e-05 +pr: 13:R_R A 3 3 6 4 C S N 12 12 0 4.0000 4.6667 3 1 9884.09 1.597e-05 0.000e+00 3.885e-08 0.000e+00 6.180e-04 9.37e+00 6.98e-01 1 3.84e-04 +pr: 15:R_R A 3 3 6 4 Z S N 12 12 0 4.0000 4.6667 3 1 9884.09 7.153e-06 0.000e+00 3.885e-08 0.000e+00 2.379e-04 1.80e+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. 18936737.7 % faster, avg. sp. ratio 189368.377x, max sp. ratio 216298.013x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 2042946.2/1888993.4/2204509.9/16343569.5 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 11.4/ 8.7/ 17.9/ 91.4 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 11.4, min. 8.7, max. 17.9 ops) +#pr: (in succ. cases rsb autotuning gave avg. 26902.1 % faster, avg. sp. ratio 270.021x, max sp. ratio 435.716x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 40748.7/4093.3/229935.6/325989.6 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 120.4/ 26.7/527.7/963.2 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 120.8, min. 26.9, max. 528.9 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 18/ 8/ 32) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 54/ 24/ 96) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 6.028/ 2.111/ 14.111,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 63.220/ 2.444/ 19.444,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 5.586/ 1.956/ 13.076,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 58.584/ 2.265/ 18.018,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.: 0.07 s, min 0.07 s, max 0.08 s, tot 0.59 s (8 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.07 s, min 0.07 s, max 0.08 s, tot 0.59 s (8 samples) -#pr: best tun. rsb canon. mflops were: on avg. 4.167e+03, min 6.666e+02, max 1.067e+04 (8 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 2.103e-02, min 3.166e-03, max 5.200e-02 (8 samples) -#pr: best tun. rsb operation time was: on avg. 3.600e-08s, min 3.600e-08s, max 3.600e-08s, tot 2.880e-07s (8 samples) -#pr: ref. unt. rsb operation time was: on avg. 6.817e-03s, min 4.242e-03s, max 7.787e-03s, tot 5.454e-02s (8 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.731e+00 1.157e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.057e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.00 s, min 0.00 s, max 0.01 s, tot 0.01 s (8 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.00 s, min 0.00 s, max 0.01 s, tot 0.01 s (8 samples) +#pr: best tun. rsb canon. mflops were: on avg. 3.861e+03, min 6.178e+02, max 9.884e+03 (8 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 1.536e+01, min 4.027e+00, max 5.369e+01 (8 samples) +#pr: best tun. rsb operation time was: on avg. 3.885e-08s, min 3.885e-08s, max 3.885e-08s, tot 3.108e-07s (8 samples) +#pr: ref. unt. rsb operation time was: on avg. 1.049e-05s, min 5.960e-06s, max 1.693e-05s, tot 8.392e-05s (8 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 3.657e+00 2.445e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 9.995e-01 #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 4.05 s. +#pr: Record collection took 0.06 s. #pr: Record comprises 40 memory benchmark samples (prepend RSB_PR_MBW=1 to dump this). -#pr: Record comprises 100 environment variables in 4341 bytes (prepend RSB_PR_ENV=1 to dump this). +#pr: Record comprises 100 environment variables in 4395 bytes (prepend RSB_PR_ENV=1 to dump this). # ====== END Total summary record. -#pr: ======== Saved a performance record of 16 samples to rsbench_pr__1715831667_gcc-13.2.rpr -# Removing the temporary record file rsbench_pr__1715831667_gcc-13.2.rpr.tmp. -# terminating run at 1715831678 (after 10.6s 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__1750243434_gcc-13.2.rpr +# Removing the temporary record file rsbench_pr__1750243434_gcc-13.2.rpr.tmp. +# terminating run at 1750243439 (after 5.3s 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,\}' + true -++ wc -l ++ /build/reproducible-path/librsb-1.3.0.2+dfsg/rsbench -h +++ wc -l + test 63 -ge 61 -++ wc -c ++ /build/reproducible-path/librsb-1.3.0.2+dfsg/rsbench -h +++ wc -c + test 2014 -ge 1966 -++ wc -l ++ /build/reproducible-path/librsb-1.3.0.2+dfsg/rsbench -oa -Ob -h +++ wc -l + test 182 -ge 157 ++ /build/reproducible-path/librsb-1.3.0.2+dfsg/rsbench -oa -Ob -h ++ wc -c @@ -5099,7 +5135,7 @@ 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 @@ -5109,15 +5145,15 @@ 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 1715831679 +# beginning run at 1750243439 # /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 -mbranch-protection=standard -O3 -std=c99 -# average timer granularity: 2.93e-08 s +# average timer granularity: 1.07e-07 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 @@ -5156,7 +5192,7 @@ # 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: codethink04-arm64 +# 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 524288 bytes, per-thread 43690 bytes @@ -5176,29 +5212,29 @@ # This test will measure times in scanning arrays sized and aligned to fit in caches. # 2 cache levels detected Will fill struct with 40 samples... -# Memory benchmark took 5.863s +# Memory benchmark took 5.494s # 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 524288 bytes, per-thread 43690 bytes -# so far, program took 5.865s 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 . +# so far, program took 5.498s 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 7.276e-02 s (100.00 %) - analyzed arrays in 2.519e-02 s (34.62 %) - cleaned-up arrays in 1.001e-05 s (0.01 %) - deduplicated arrays in 7.868e-06 s (0.01 %) + converted COO to RSB in 6.411e-04 s (100.00 %) + analyzed arrays in 5.281e-04 s (82.37 %) + cleaned-up arrays in 1.001e-05 s (1.56 %) + deduplicated arrays in 8.106e-06 s (1.26 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 3.532e-02 s (48.55 %) - memory allocations took 1.907e-05 s (0.03 %) - leafs setup took 6.914e-06 s (0.01 %) - halfword conversion took 1.220e-02 s (16.77 %) -Built (100 x 100)[0xaaaaf2ae4500]{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 0.073s): (100 x 100)[0xaaaaf2ae4500]{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' + shuffled partitions in 6.390e-05 s (9.97 %) + memory allocations took 9.060e-06 s (1.41 %) + leafs setup took 3.099e-06 s (0.48 %) + halfword conversion took 1.693e-05 s (2.64 %) +Built (100 x 100)[0xaaaaeb3fc540]{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 0.001s): (100 x 100)[0xaaaaeb3fc540]{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. @@ -5249,10 +5285,10 @@ # 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 0.02418s; avg 0.008062s ( +/- 3.51/ 6.73 %); best 0.007779s; worst 0.008604s; std dev. 0.0003837 (taking best). -Reference operation time is 0.00777888 s (2.597 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: 0.007779 Mflops: 2.597) -Merge (3 -> 1 leaves) took w.c.t. of 4.888e-05s, ~3.505e-05s of computing time (of which 1.407e-05s sorting, 5.007e-06s analysis) +3 iterations (1 th.) took 6.604e-05s; avg 2.201e-05s ( +/- 41.52/ 81.95 %); best 1.287e-05s; worst 4.005e-05s; std dev. 1.276e-05 (taking best). +Reference operation time is 1.28746e-05 s (1569 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: 1.287e-05 Mflops: 1568.980) +Merge (3 -> 1 leaves) took w.c.t. of 4.482e-05s, ~3.815e-05s of computing time (of which 1.717e-05s sorting, 1.907e-06s analysis) # 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 @@ -5283,7 +5319,7 @@ # 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 2.098e-05s; avg 6.994e-06s ( +/- 28.41/ 43.18 %); best 5.007e-06s; worst 1.001e-05s; std dev. 2.171e-06 (taking best). +3 iterations (1 th.) took 2.003e-05s; avg 6.676e-06s ( +/- 25.00/ 35.71 %); best 5.007e-06s; worst 9.06e-06s; std dev. 1.73e-06 (taking best). Reference operation time is 5.00679e-06 s (4035 Mflops) with 1 threads. # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes @@ -5301,15 +5337,15 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success After merge step 1: tpop: 5.007e-06 s ~Mflops: 4034.521 nsubm:1 otn:1 -Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 1553.667x: 0.007779s -> 5.007e-06s, so taking this instance. +Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 2.571x: 1.287e-05s -> 5.007e-06s, 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 0.07185s (of which 5.198e-05s partitioning, 0.04848s I/O); computing times: 3.505e-05s in par. loops, 1.407e-05s sorting, 5.007e-06s analyzing) -Total merge + benchmarking process took 0.07185s, equivalent to 14351.1/9.2 new/old ops (0.04748s for 2 clones -- as 9484.0/6.1 ops, or 4742.0/3.1 ops per clone), SPEEDUP of 1553.667x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 1553.667x (0.007779s -> 5.007e-06s), will amortize in 9.2 ops by saving 0.007774s per op. -In 1 tuning rounds (tot. 0.12s, 0.047s for constructor, 2 clones) obtained a SPEEDUP of 155266.7% (1554x) (from 2.597 to 4035 Mflops). Employed 0.051s for I/O of matrix plots. +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.002045s (of which 4.721e-05s partitioning, 0.001766s I/O); computing times: 3.815e-05s in par. loops, 1.717e-05s sorting, 1.907e-06s analyzing) +Total merge + benchmarking process took 0.002045s, equivalent to 408.5/158.9 new/old ops (3.672e-05s for 2 clones -- as 7.3/2.9 ops, or 3.7/1.4 ops per clone), SPEEDUP of 2.571x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 2.571x (1.287e-05s -> 5.007e-06s), will amortize in 259.9 ops by saving 7.868e-06s per op. +In 1 tuning rounds (tot. 0.0022s, 3.7e-05s for constructor, 2 clones) obtained a SPEEDUP of 157.1% (2.571x) (from 1569 to 4035 Mflops). Employed 0.0018s 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 0.171938 s (7.779e-03 s -> 5.007e-06 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.00405383 s (1.287e-05 s -> 5.007e-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 D, 5050 nnz, 50 nnz/r, 1 subms, 1 lsubms, 2.0800 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:10 @@ -5375,20 +5411,20 @@ # 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 2.289e-05s; avg 7.629e-06s ( +/- 34.38/ 56.25 %); best 5.007e-06s; worst 1.192e-05s; std dev. 3.059e-06 (taking best). +3 iterations (1 th.) took 2.313e-05s; avg 7.709e-06s ( +/- 35.05/ 57.73 %); best 5.007e-06s; worst 1.216e-05s; std dev. 3.171e-06 (taking best). Reference operation time is 5.00679e-06 s (4035 Mflops) with 1 threads. Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 2.443e-02 s (100.00 %) - analyzed arrays in 8.401e-03 s (34.39 %) - cleaned-up arrays in 1.001e-05 s (0.04 %) - deduplicated arrays in 8.106e-06 s (0.03 %) + converted COO to RSB in 4.482e-05 s (100.00 %) + analyzed arrays in 1.097e-05 s (24.47 %) + cleaned-up arrays in 9.060e-06 s (20.21 %) + deduplicated arrays in 6.914e-06 s (15.43 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.600e-02 s (65.48 %) - memory allocations took 4.053e-06 s (0.02 %) - leafs setup took 2.861e-06 s (0.01 %) - halfword conversion took 6.199e-06 s (0.03 %) -Built (100 x 100)[0xaaaaf2aeecd0]{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' + shuffled partitions in 1.001e-05 s (22.34 %) + memory allocations took 3.815e-06 s (8.51 %) + leafs setup took 9.537e-07 s (2.13 %) + halfword conversion took 1.907e-06 s (4.26 %) +Built (100 x 100)[0xaaaaeb406d10]{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 = 12). # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes @@ -5422,16 +5458,16 @@ # 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 4.689e-02 s (100.00 %) - analyzed arrays in 1.491e-02 s (31.79 %) - cleaned-up arrays in 1.001e-05 s (0.02 %) - deduplicated arrays in 7.153e-06 s (0.02 %) + converted COO to RSB in 8.106e-05 s (100.00 %) + analyzed arrays in 1.907e-05 s (23.53 %) + cleaned-up arrays in 8.106e-06 s (10.00 %) + deduplicated arrays in 6.914e-06 s (8.53 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.597e-02 s (34.06 %) - memory allocations took 5.007e-06 s (0.01 %) - leafs setup took 2.861e-06 s (0.01 %) - halfword conversion took 1.599e-02 s (34.10 %) -Built (100 x 100)[0xaaaaf2ae4850]{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' + shuffled partitions in 3.409e-05 s (42.06 %) + memory allocations took 2.861e-06 s (3.53 %) + leafs setup took 0.000e+00 s (0.00 %) + halfword conversion took 1.001e-05 s (12.35 %) +Built (100 x 100)[0xaaaaeb3fc890]{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 @@ -5477,9 +5513,9 @@ # 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 0.02434s; avg 0.008113s ( +/- 6.67/ 3.70 %); best 0.007572s; worst 0.008413s; std dev. 0.0003833 (taking best). -Reference operation time is 0.00757194 s (2.668 Mflops) with 1 threads. -Challenging best inner round reference (5.00679e-06 s/1 threads) with: subdivision 0.25, 3 leaves, 2.121 bytes/nz, 0.00757194 s/0 threads (speedup 0.00066123 x), same?n. +3 iterations (1 th.) took 4.601e-05s; avg 1.534e-05s ( +/- 16.06/ 30.57 %); best 1.287e-05s; worst 2.003e-05s; std dev. 3.317e-06 (taking best). +Reference operation time is 1.28746e-05 s (1569 Mflops) with 1 threads. +Challenging best inner round reference (5.00679e-06 s/1 threads) with: subdivision 0.25, 3 leaves, 2.121 bytes/nz, 1.28746e-05 s/0 threads (speedup 0.388889 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 524288 bytes, per-thread 524288 bytes @@ -5513,16 +5549,16 @@ # 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 5.152e-02 s (100.00 %) - analyzed arrays in 1.595e-02 s (30.96 %) - cleaned-up arrays in 8.821e-06 s (0.02 %) - deduplicated arrays in 8.106e-06 s (0.02 %) + converted COO to RSB in 9.799e-05 s (100.00 %) + analyzed arrays in 4.005e-05 s (40.88 %) + cleaned-up arrays in 9.060e-06 s (9.25 %) + deduplicated arrays in 6.914e-06 s (7.06 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.601e-02 s (31.07 %) - memory allocations took 6.199e-06 s (0.01 %) - leafs setup took 5.960e-06 s (0.01 %) - halfword conversion took 1.954e-02 s (37.92 %) -Built (100 x 100)[0xaaaaf2ae5240]{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' + shuffled partitions in 3.099e-05 s (31.63 %) + memory allocations took 9.537e-07 s (0.97 %) + leafs setup took 9.537e-07 s (0.97 %) + halfword conversion took 9.060e-06 s (9.25 %) +Built (100 x 100)[0xaaaaeb3fd280]{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 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -5568,9 +5604,9 @@ # 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 0.02081s; avg 0.006936s ( +/- 30.18/ 24.53 %); best 0.004843s; worst 0.008637s; std dev. 0.001574 (taking best). -Reference operation time is 0.004843 s (4.171 Mflops) with 1 threads. -Challenging best inner round reference (5.00679e-06 s/1 threads) with: subdivision 0.5, 10 leaves, 2.206 bytes/nz, 0.004843 s/0 threads (speedup 0.00103382 x), same?n. +3 iterations (1 th.) took 5.412e-05s; avg 1.804e-05s ( +/- 11.45/ 22.91 %); best 1.597e-05s; worst 2.217e-05s; std dev. 2.922e-06 (taking best). +Reference operation time is 1.5974e-05 s (1265 Mflops) with 1 threads. +Challenging best inner round reference (5.00679e-06 s/1 threads) with: subdivision 0.5, 10 leaves, 2.206 bytes/nz, 1.5974e-05 s/0 threads (speedup 0.313433 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 # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes @@ -5604,16 +5640,16 @@ # 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 5.488e-02 s (100.00 %) - analyzed arrays in 1.870e-02 s (34.07 %) - cleaned-up arrays in 9.060e-06 s (0.02 %) - deduplicated arrays in 7.868e-06 s (0.01 %) + converted COO to RSB in 1.509e-04 s (100.00 %) + analyzed arrays in 6.914e-05 s (45.81 %) + cleaned-up arrays in 8.106e-06 s (5.37 %) + deduplicated arrays in 6.914e-06 s (4.58 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.659e-02 s (30.24 %) - memory allocations took 7.153e-06 s (0.01 %) - leafs setup took 3.099e-06 s (0.01 %) - halfword conversion took 1.956e-02 s (35.64 %) -Built (100 x 100)[0xaaaaf2aeedf0]{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: 25, symflags:'LS' + shuffled partitions in 5.198e-05 s (34.44 %) + memory allocations took 3.815e-06 s (2.53 %) + leafs setup took 1.907e-06 s (1.26 %) + halfword conversion took 9.060e-06 s (6.00 %) +Built (100 x 100)[0xaaaaeb406e30]{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: 24, 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 @@ -5659,10 +5695,10 @@ # 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 0.02347s; avg 0.007822s ( +/- 40.73/ 47.91 %); best 0.004636s; worst 0.01157s; std dev. 0.002858 (taking best). -Reference operation time is 0.00463605 s (4.357 Mflops) with 1 threads. -Challenging best inner round reference (5.00679e-06 s/1 threads) with: subdivision 1, 25 leaves, 2.317 bytes/nz, 0.00463605 s/0 threads (speedup 0.00107997 x), same?n. -New candidate clone performs slowly; discarding it: 100 x 100, type D, 5050 nnz, 50 nnz/r, 34 subms, 25 lsubms, 2.3168 bpnz +3 iterations (1 th.) took 6.199e-05s; avg 2.066e-05s ( +/- 12.31/ 21.15 %); best 1.812e-05s; worst 2.503e-05s; std dev. 3.105e-06 (taking best). +Reference operation time is 1.81198e-05 s (1115 Mflops) with 1 threads. +Challenging best inner round reference (5.00679e-06 s/1 threads) with: subdivision 1, 24 leaves, 2.295 bytes/nz, 1.81198e-05 s/0 threads (speedup 0.276316 x), same?n. +New candidate clone performs slowly; discarding it: 100 x 100, type D, 5050 nnz, 50 nnz/r, 34 subms, 24 lsubms, 2.2947 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 @@ -5695,16 +5731,16 @@ # 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 4.858e-02 s (100.00 %) - analyzed arrays in 1.656e-02 s (34.08 %) - cleaned-up arrays in 9.060e-06 s (0.02 %) - deduplicated arrays in 7.868e-06 s (0.02 %) + converted COO to RSB in 1.991e-04 s (100.00 %) + analyzed arrays in 9.394e-05 s (47.19 %) + cleaned-up arrays in 7.868e-06 s (3.95 %) + deduplicated arrays in 8.106e-06 s (4.07 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.621e-02 s (33.38 %) - memory allocations took 5.960e-06 s (0.01 %) - leafs setup took 7.153e-06 s (0.01 %) - halfword conversion took 1.578e-02 s (32.48 %) -Built (100 x 100)[0xaaaaf2b15a60]{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: 36, symflags:'LS' + shuffled partitions in 7.415e-05 s (37.25 %) + memory allocations took 3.099e-06 s (1.56 %) + leafs setup took 1.907e-06 s (0.96 %) + halfword conversion took 1.001e-05 s (5.03 %) +Built (100 x 100)[0xaaaaeb42daa0]{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: 36, 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 @@ -5750,9 +5786,9 @@ # 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 0.02368s; avg 0.007895s ( +/- 43.92/ 37.29 %); best 0.004427s; worst 0.01084s; std dev. 0.002644 (taking best). -Reference operation time is 0.00442696 s (4.563 Mflops) with 1 threads. -Challenging best inner round reference (5.00679e-06 s/1 threads) with: subdivision 2, 36 leaves, 2.383 bytes/nz, 0.00442696 s/0 threads (speedup 0.00113098 x), same?n. +3 iterations (1 th.) took 6.509e-05s; avg 2.17e-05s ( +/- 12.09/ 19.78 %); best 1.907e-05s; worst 2.599e-05s; std dev. 3.059e-06 (taking best). +Reference operation time is 1.90735e-05 s (1059 Mflops) with 1 threads. +Challenging best inner round reference (5.00679e-06 s/1 threads) with: subdivision 2, 36 leaves, 2.383 bytes/nz, 1.90735e-05 s/0 threads (speedup 0.2625 x), same?n. New candidate clone performs slowly; discarding it: 100 x 100, type D, 5050 nnz, 50 nnz/r, 50 subms, 36 lsubms, 2.3834 bpnz # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes @@ -5786,16 +5822,16 @@ # 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 5.174e-02 s (100.00 %) - analyzed arrays in 1.931e-02 s (37.32 %) - cleaned-up arrays in 8.821e-06 s (0.02 %) - deduplicated arrays in 8.106e-06 s (0.02 %) + converted COO to RSB in 1.969e-04 s (100.00 %) + analyzed arrays in 9.298e-05 s (47.22 %) + cleaned-up arrays in 9.060e-06 s (4.60 %) + deduplicated arrays in 6.914e-06 s (3.51 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.977e-02 s (38.21 %) - memory allocations took 7.153e-06 s (0.01 %) - leafs setup took 7.153e-06 s (0.01 %) - halfword conversion took 1.263e-02 s (24.41 %) -Built (100 x 100)[0xaaaaf2b15a60]{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: 36, symflags:'LS' + shuffled partitions in 7.319e-05 s (37.17 %) + memory allocations took 2.861e-06 s (1.45 %) + leafs setup took 1.907e-06 s (0.97 %) + halfword conversion took 1.001e-05 s (5.08 %) +Built (100 x 100)[0xaaaaeb42daa0]{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: 36, 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 @@ -5841,9 +5877,9 @@ # 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 0.0237s; avg 0.007901s ( +/- 43.88/ 37.06 %); best 0.004434s; worst 0.01083s; std dev. 0.002638 (taking best). -Reference operation time is 0.00443411 s (4.556 Mflops) with 1 threads. -Challenging best inner round reference (5.00679e-06 s/1 threads) with: subdivision 4, 36 leaves, 2.383 bytes/nz, 0.00443411 s/0 threads (speedup 0.00112915 x), same?n. +3 iterations (1 th.) took 6.318e-05s; avg 2.106e-05s ( +/- 9.43/ 18.87 %); best 1.907e-05s; worst 2.503e-05s; std dev. 2.81e-06 (taking best). +Reference operation time is 1.90735e-05 s (1059 Mflops) with 1 threads. +Challenging best inner round reference (5.00679e-06 s/1 threads) with: subdivision 4, 36 leaves, 2.383 bytes/nz, 1.90735e-05 s/0 threads (speedup 0.2625 x), same?n. New candidate clone performs slowly; discarding it: 100 x 100, type D, 5050 nnz, 50 nnz/r, 50 subms, 36 lsubms, 2.3834 bpnz Best sparse multiply performance with subdivision multiplier of 1: 4034.52 Mflops. # librsb version 1.3.0.2 - 202212201855: Initializing @@ -5861,23 +5897,23 @@ # 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 0.396576 s (eq. to 8e+04/ 8e+04 old/new op.times), gained local/global speedup 1 x (5.00679e-06 : 5.00679e-06) / 1 x (5.00679e-06 : 5.00679e-06). This is not amortizable ! +Last tuner inner round (1 of 1) took 0.00193501 s (eq. to 4e+02/ 4e+02 old/new op.times), gained local/global speedup 1 x (5.00679e-06 : 5.00679e-06) / 1 x (5.00679e-06 : 5.00679e-06). This is not amortizable ! Auto tuning inner round 1 did not find a configuration better than the original. -In 1 tuning rounds (tot. 0.4s, 0.28s for constructor, 0 clones) obtained NO speedup (best stays 4035 Mflops). -Second run of RSB Autotuner took 0.396602 s and estimated a speedup of 1.000000 x (5.007e-06 s -> 5.007e-06 s per op) in same matrix (1 -> 1 lsubm) +In 1 tuning rounds (tot. 0.0019s, 0.0013s for constructor, 0 clones) obtained NO speedup (best stays 4035 Mflops). +Second run of RSB Autotuner took 0.00195694 s and estimated a speedup of 1.000000 x (5.007e-06 s -> 5.007e-06 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 0.025189 0.035324 0.060513 -%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.060513 -%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.025189 -%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.035324 +%:CONSTRUCTOR_TIMES:lower-100x100-5050nz S N 1 100 100 5050 0.000000 0.000528 0.000064 0.000592 +%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.000592 +%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.000528 +%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.000064 %: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 0.060513 +%:SORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.000592 %: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 @@ -5892,34 +5928,34 @@ %: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 0.0727611 1e+09 1e+09 +%operation:lower-100x100-5050nz 0.000641108 1e+09 1e+09 %constructor:matrix SORT[1] SCAN[1] SHUFFLE[1] INSERT[1] -%constructor:lower-100x100-5050nz 0 0.0251892 0 0.0353241 -# so far, program took 6.547s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.569s/0.000s . +%constructor:lower-100x100-5050nz 0 0.000528097 0 6.38962e-05 +# so far, program took 5.506s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.006s/0.000s . getrusage() stats: -ru_maxrss: 6 (maximum resident set size -- MB) -ru_stime : 0.0257s (system CPU time used) -ru_utime : 3.843s (user CPU time used) +ru_maxrss: 8 (maximum resident set size -- MB) +ru_stime : 0.0675s (system CPU time used) +ru_utime : 5.496s (user CPU time used) # multi-type benchmarking (DSCZ) -- now using typecode S (last was D). # Cache block size total 524288 bytes, per-thread 524288 bytes -# so far, program took 6.547s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.569s/0.000s . +# so far, program took 5.506s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.006s/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 6.313e-02 s (100.00 %) - analyzed arrays in 1.169e-02 s (18.52 %) - cleaned-up arrays in 1.001e-05 s (0.02 %) - deduplicated arrays in 8.106e-06 s (0.01 %) + converted COO to RSB in 8.607e-05 s (100.00 %) + analyzed arrays in 1.597e-05 s (18.56 %) + cleaned-up arrays in 1.097e-05 s (12.74 %) + deduplicated arrays in 8.106e-06 s (9.42 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 3.514e-02 s (55.66 %) - memory allocations took 3.815e-06 s (0.01 %) - leafs setup took 4.053e-06 s (0.01 %) - halfword conversion took 1.627e-02 s (25.77 %) -Built (100 x 100)[0xaaaaf2aeedf0]{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 0.063s): (100 x 100)[0xaaaaf2aeedf0]{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' + shuffled partitions in 3.695e-05 s (42.94 %) + memory allocations took 1.907e-06 s (2.22 %) + leafs setup took 1.192e-06 s (1.39 %) + halfword conversion took 1.001e-05 s (11.63 %) +Built (100 x 100)[0xaaaaeb406e30]{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 0.000s): (100 x 100)[0xaaaaeb406e30]{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. @@ -5970,10 +6006,10 @@ # 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 0.02419s; avg 0.008063s ( +/- 10.98/ 9.52 %); best 0.007178s; worst 0.008831s; std dev. 0.0006799 (taking best). -Reference operation time is 0.00717807 s (2.814 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: 0.007178 Mflops: 2.814) -Merge (3 -> 1 leaves) took w.c.t. of 4.101e-05s, ~3.314e-05s of computing time (of which 1.311e-05s sorting, 3.099e-06s analysis) +3 iterations (1 th.) took 6.294e-05s; avg 2.098e-05s ( +/- 38.64/ 71.59 %); best 1.287e-05s; worst 3.6e-05s; std dev. 1.063e-05 (taking best). +Reference operation time is 1.28746e-05 s (1569 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: 1.287e-05 Mflops: 1568.980) +Merge (3 -> 1 leaves) took w.c.t. of 3.695e-05s, ~3.314e-05s of computing time (of which 1.216e-05s sorting, 9.537e-07s analysis) # 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 @@ -6004,7 +6040,7 @@ # 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 2.098e-05s; avg 6.994e-06s ( +/- 28.41/ 43.18 %); best 5.007e-06s; worst 1.001e-05s; std dev. 2.171e-06 (taking best). +3 iterations (1 th.) took 1.693e-05s; avg 5.643e-06s ( +/- 11.27/ 5.63 %); best 5.007e-06s; worst 5.96e-06s; std dev. 4.496e-07 (taking best). Reference operation time is 5.00679e-06 s (4035 Mflops) with 1 threads. # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes @@ -6022,15 +6058,15 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success After merge step 1: tpop: 5.007e-06 s ~Mflops: 4034.521 nsubm:1 otn:1 -Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 1433.667x: 0.007178s -> 5.007e-06s, so taking this instance. +Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 2.571x: 1.287e-05s -> 5.007e-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 0.07233s (of which 4.387e-05s partitioning, 0.0477s I/O); computing times: 3.314e-05s in par. loops, 1.311e-05s sorting, 3.099e-06s analyzing) -Total merge + benchmarking process took 0.07233s, equivalent to 14445.6/10.1 new/old ops (0.04417s for 2 clones -- as 8822.4/6.2 ops, or 4411.2/3.1 ops per clone), SPEEDUP of 1433.667x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 1433.667x (0.007178s -> 5.007e-06s), will amortize in 10.1 ops by saving 0.007173s per op. -In 1 tuning rounds (tot. 0.12s, 0.044s for constructor, 2 clones) obtained a SPEEDUP of 143266.7% (1434x) (from 2.814 to 4035 Mflops). Employed 0.048s for I/O of matrix plots. +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.001885s (of which 3.886e-05s partitioning, 0.001735s I/O); computing times: 3.314e-05s in par. loops, 1.216e-05s sorting, 9.537e-07s analyzing) +Total merge + benchmarking process took 0.001885s, equivalent to 376.5/146.4 new/old ops (3.314e-05s for 2 clones -- as 6.6/2.6 ops, or 3.3/1.3 ops per clone), SPEEDUP of 2.571x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 2.571x (1.287e-05s -> 5.007e-06s), will amortize in 239.6 ops by saving 7.868e-06s per op. +In 1 tuning rounds (tot. 0.002s, 3.3e-05s for constructor, 2 clones) obtained a SPEEDUP of 157.1% (2.571x) (from 1569 to 4035 Mflops). Employed 0.0018s 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 0.164892 s (7.178e-03 s -> 5.007e-06 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.00390291 s (1.287e-05 s -> 5.007e-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 @@ -6096,20 +6132,20 @@ # 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 2.289e-05s; avg 7.629e-06s ( +/- 34.38/ 56.25 %); best 5.007e-06s; worst 1.192e-05s; std dev. 3.059e-06 (taking best). +3 iterations (1 th.) took 2.098e-05s; avg 6.994e-06s ( +/- 28.41/ 43.18 %); best 5.007e-06s; worst 1.001e-05s; std dev. 2.171e-06 (taking best). Reference operation time is 5.00679e-06 s (4035 Mflops) with 1 threads. Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 2.722e-02 s (100.00 %) - analyzed arrays in 1.456e-02 s (53.47 %) - cleaned-up arrays in 9.060e-06 s (0.03 %) - deduplicated arrays in 1.118e-04 s (0.41 %) + converted COO to RSB in 1.700e-04 s (100.00 %) + analyzed arrays in 1.001e-05 s (5.89 %) + cleaned-up arrays in 1.001e-05 s (5.89 %) + deduplicated arrays in 6.914e-06 s (4.07 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.253e-02 s (46.04 %) - memory allocations took 6.199e-06 s (0.02 %) - leafs setup took 3.099e-06 s (0.01 %) - halfword conversion took 2.861e-06 s (0.01 %) -Built (100 x 100)[0xaaaaf2aeecd0]{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' + shuffled partitions in 1.097e-05 s (6.45 %) + memory allocations took 1.302e-04 s (76.58 %) + leafs setup took 0.000e+00 s (0.00 %) + halfword conversion took 1.907e-06 s (1.12 %) +Built (100 x 100)[0xaaaaeb406d10]{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 = 12). # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes @@ -6143,16 +6179,16 @@ # 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 1.935e-02 s (100.00 %) - analyzed arrays in 1.318e-02 s (68.09 %) - cleaned-up arrays in 9.060e-06 s (0.05 %) - deduplicated arrays in 8.106e-06 s (0.04 %) + converted COO to RSB in 3.409e-05 s (100.00 %) + analyzed arrays in 9.775e-06 s (28.67 %) + cleaned-up arrays in 9.060e-06 s (26.57 %) + deduplicated arrays in 7.153e-06 s (20.98 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 6.145e-03 s (31.76 %) - memory allocations took 5.722e-06 s (0.03 %) - leafs setup took 3.099e-06 s (0.02 %) - halfword conversion took 2.861e-06 s (0.01 %) -Built (100 x 100)[0xaaaaf2ae5240]{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' + shuffled partitions in 5.007e-06 s (14.69 %) + memory allocations took 9.537e-07 s (2.80 %) + leafs setup took 0.000e+00 s (0.00 %) + halfword conversion took 2.146e-06 s (6.29 %) +Built (100 x 100)[0xaaaaeb3fd280]{S} @ (0(0..100),0(0..100)) (5050 nnz, 50 nnz/r) flags 0x42644096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 1, symflags:'LS' # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -6198,7 +6234,7 @@ # 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 2.408e-05s; avg 8.027e-06s ( +/- 37.62/ 63.37 %); best 5.007e-06s; worst 1.311e-05s; std dev. 3.618e-06 (taking best). +3 iterations (1 th.) took 2.003e-05s; avg 6.676e-06s ( +/- 25.00/ 35.71 %); best 5.007e-06s; worst 9.06e-06s; std dev. 1.73e-06 (taking best). Reference operation time is 5.00679e-06 s (4035 Mflops) with 1 threads. Challenging best inner round reference (5.00679e-06 s/1 threads) with: subdivision 0.25, 1 leaves, 2.08 bytes/nz, 5.00679e-06 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 @@ -6234,16 +6270,16 @@ # 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 5.505e-02 s (100.00 %) - analyzed arrays in 1.924e-02 s (34.95 %) - cleaned-up arrays in 9.060e-06 s (0.02 %) - deduplicated arrays in 8.106e-06 s (0.01 %) + converted COO to RSB in 9.418e-05 s (100.00 %) + analyzed arrays in 3.886e-05 s (41.27 %) + cleaned-up arrays in 8.821e-06 s (9.37 %) + deduplicated arrays in 7.153e-06 s (7.59 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 2.339e-02 s (42.48 %) - memory allocations took 6.914e-06 s (0.01 %) - leafs setup took 5.007e-06 s (0.01 %) - halfword conversion took 1.240e-02 s (22.52 %) -Built (100 x 100)[0xaaaaf2ae5240]{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' + shuffled partitions in 2.813e-05 s (29.87 %) + memory allocations took 1.192e-06 s (1.27 %) + leafs setup took 9.537e-07 s (1.01 %) + halfword conversion took 9.060e-06 s (9.62 %) +Built (100 x 100)[0xaaaaeb3fd280]{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 @@ -6289,9 +6325,9 @@ # 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 0.02774s; avg 0.009247s ( +/- 9.69/ 18.73 %); best 0.008351s; worst 0.01098s; std dev. 0.001225 (taking best). -Reference operation time is 0.00835085 s (2.419 Mflops) with 1 threads. -Challenging best inner round reference (5.00679e-06 s/1 threads) with: subdivision 0.5, 8 leaves, 2.185 bytes/nz, 0.00835085 s/0 threads (speedup 0.000599555 x), same?n. +3 iterations (1 th.) took 5.007e-05s; avg 1.669e-05s ( +/- 15.71/ 31.43 %); best 1.407e-05s; worst 2.193e-05s; std dev. 3.709e-06 (taking best). +Reference operation time is 1.40667e-05 s (1436 Mflops) with 1 threads. +Challenging best inner round reference (5.00679e-06 s/1 threads) with: subdivision 0.5, 8 leaves, 2.185 bytes/nz, 1.40667e-05 s/0 threads (speedup 0.355932 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 524288 bytes, per-thread 524288 bytes @@ -6325,16 +6361,16 @@ # 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 5.183e-02 s (100.00 %) - analyzed arrays in 1.989e-02 s (38.38 %) - cleaned-up arrays in 9.060e-06 s (0.02 %) - deduplicated arrays in 8.106e-06 s (0.02 %) + converted COO to RSB in 1.309e-04 s (100.00 %) + analyzed arrays in 6.104e-05 s (46.63 %) + cleaned-up arrays in 9.060e-06 s (6.92 %) + deduplicated arrays in 6.914e-06 s (5.28 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.223e-02 s (23.59 %) - memory allocations took 4.768e-06 s (0.01 %) - leafs setup took 3.099e-06 s (0.01 %) - halfword conversion took 1.968e-02 s (37.98 %) -Built (100 x 100)[0xaaaaf2aeedf0]{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' + shuffled partitions in 4.292e-05 s (32.79 %) + memory allocations took 9.537e-07 s (0.73 %) + leafs setup took 1.192e-06 s (0.91 %) + halfword conversion took 8.821e-06 s (6.74 %) +Built (100 x 100)[0xaaaaeb406e30]{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 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -6380,9 +6416,9 @@ # 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 0.02365s; avg 0.007883s ( +/- 44.59/ 41.26 %); best 0.004368s; worst 0.01114s; std dev. 0.002769 (taking best). -Reference operation time is 0.00436783 s (4.625 Mflops) with 1 threads. -Challenging best inner round reference (5.00679e-06 s/1 threads) with: subdivision 1, 19 leaves, 2.272 bytes/nz, 0.00436783 s/0 threads (speedup 0.00114629 x), same?n. +3 iterations (1 th.) took 5.603e-05s; avg 1.868e-05s ( +/- 9.36/ 17.45 %); best 1.693e-05s; worst 2.193e-05s; std dev. 2.306e-06 (taking best). +Reference operation time is 1.69277e-05 s (1193 Mflops) with 1 threads. +Challenging best inner round reference (5.00679e-06 s/1 threads) with: subdivision 1, 19 leaves, 2.272 bytes/nz, 1.69277e-05 s/0 threads (speedup 0.295775 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 524288 bytes, per-thread 524288 bytes @@ -6416,16 +6452,16 @@ # 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 5.320e-02 s (100.00 %) - analyzed arrays in 2.096e-02 s (39.39 %) - cleaned-up arrays in 1.001e-05 s (0.02 %) - deduplicated arrays in 8.106e-06 s (0.02 %) + converted COO to RSB in 2.010e-04 s (100.00 %) + analyzed arrays in 9.608e-05 s (47.81 %) + cleaned-up arrays in 9.060e-06 s (4.51 %) + deduplicated arrays in 6.914e-06 s (3.44 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.624e-02 s (30.52 %) - memory allocations took 5.960e-06 s (0.01 %) - leafs setup took 5.960e-06 s (0.01 %) - halfword conversion took 1.597e-02 s (30.03 %) -Built (100 x 100)[0xaaaaf2aeedf0]{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: 36, symflags:'LS' + shuffled partitions in 7.606e-05 s (37.84 %) + memory allocations took 1.907e-06 s (0.95 %) + leafs setup took 1.907e-06 s (0.95 %) + halfword conversion took 9.060e-06 s (4.51 %) +Built (100 x 100)[0xaaaaeb406e30]{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: 36, 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 @@ -6471,9 +6507,9 @@ # 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 0.02345s; avg 0.007816s ( +/- 38.93/ 45.73 %); best 0.004773s; worst 0.01139s; std dev. 0.002727 (taking best). -Reference operation time is 0.00477314 s (4.232 Mflops) with 1 threads. -Challenging best inner round reference (5.00679e-06 s/1 threads) with: subdivision 2, 36 leaves, 2.383 bytes/nz, 0.00477314 s/0 threads (speedup 0.00104895 x), same?n. +3 iterations (1 th.) took 6.39e-05s; avg 2.13e-05s ( +/- 11.57/ 22.01 %); best 1.884e-05s; worst 2.599e-05s; std dev. 3.317e-06 (taking best). +Reference operation time is 1.88351e-05 s (1072 Mflops) with 1 threads. +Challenging best inner round reference (5.00679e-06 s/1 threads) with: subdivision 2, 36 leaves, 2.383 bytes/nz, 1.88351e-05 s/0 threads (speedup 0.265823 x), same?n. New candidate clone performs slowly; discarding it: 100 x 100, type S, 5050 nnz, 50 nnz/r, 50 subms, 36 lsubms, 2.3834 bpnz # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes @@ -6507,16 +6543,16 @@ # 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 5.256e-02 s (100.00 %) - analyzed arrays in 2.308e-02 s (43.92 %) - cleaned-up arrays in 1.001e-05 s (0.02 %) - deduplicated arrays in 8.106e-06 s (0.02 %) - sorted arrays in 9.537e-07 s (0.00 %) - shuffled partitions in 1.346e-02 s (25.61 %) - memory allocations took 7.868e-06 s (0.01 %) - leafs setup took 7.153e-06 s (0.01 %) - halfword conversion took 1.598e-02 s (30.40 %) -Built (100 x 100)[0xaaaaf2b01ea0]{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: 36, symflags:'LS' + converted COO to RSB in 1.879e-04 s (100.00 %) + analyzed arrays in 8.798e-05 s (46.83 %) + cleaned-up arrays in 9.060e-06 s (4.82 %) + deduplicated arrays in 6.914e-06 s (3.68 %) + sorted arrays in 0.000e+00 s (0.00 %) + shuffled partitions in 6.890e-05 s (36.68 %) + memory allocations took 2.861e-06 s (1.52 %) + leafs setup took 2.146e-06 s (1.14 %) + halfword conversion took 8.821e-06 s (4.70 %) +Built (100 x 100)[0xaaaaeb419ee0]{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: 36, 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 @@ -6562,9 +6598,9 @@ # 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 0.03033s; avg 0.01011s ( +/- 30.67/ 18.82 %); best 0.007009s; worst 0.01201s; std dev. 0.002211 (taking best). -Reference operation time is 0.00700879 s (2.882 Mflops) with 1 threads. -Challenging best inner round reference (5.00679e-06 s/1 threads) with: subdivision 4, 36 leaves, 2.383 bytes/nz, 0.00700879 s/0 threads (speedup 0.000714359 x), same?n. +3 iterations (1 th.) took 6.294e-05s; avg 2.098e-05s ( +/- 10.23/ 19.32 %); best 1.884e-05s; worst 2.503e-05s; std dev. 2.868e-06 (taking best). +Reference operation time is 1.88351e-05 s (1072 Mflops) with 1 threads. +Challenging best inner round reference (5.00679e-06 s/1 threads) with: subdivision 4, 36 leaves, 2.383 bytes/nz, 1.88351e-05 s/0 threads (speedup 0.265823 x), same?n. New candidate clone performs slowly; discarding it: 100 x 100, type S, 5050 nnz, 50 nnz/r, 50 subms, 36 lsubms, 2.3834 bpnz Best sparse multiply performance with subdivision multiplier of 1: 4034.52 Mflops. # librsb version 1.3.0.2 - 202212201855: Initializing @@ -6582,23 +6618,23 @@ # 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 0.366798 s (eq. to 7e+04/ 7e+04 old/new op.times), gained local/global speedup 1 x (5.00679e-06 : 5.00679e-06) / 1 x (5.00679e-06 : 5.00679e-06). This is not amortizable ! +Last tuner inner round (1 of 1) took 0.00170708 s (eq. to 3e+02/ 3e+02 old/new op.times), gained local/global speedup 1 x (5.00679e-06 : 5.00679e-06) / 1 x (5.00679e-06 : 5.00679e-06). This is not amortizable ! Auto tuning inner round 1 did not find a configuration better than the original. -In 1 tuning rounds (tot. 0.37s, 0.26s for constructor, 0 clones) obtained NO speedup (best stays 4035 Mflops). -Second run of RSB Autotuner took 0.366824 s and estimated a speedup of 1.000000 x (5.007e-06 s -> 5.007e-06 s per op) in same matrix (1 -> 1 lsubm) +In 1 tuning rounds (tot. 0.0017s, 0.00097s for constructor, 0 clones) obtained NO speedup (best stays 4035 Mflops). +Second run of RSB Autotuner took 0.0017271 s and estimated a speedup of 1.000000 x (5.007e-06 s -> 5.007e-06 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 0.011693 0.035141 0.046834 -%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.046834 -%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.011693 -%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.035141 +%:CONSTRUCTOR_TIMES:lower-100x100-5050nz S N 1 100 100 5050 0.000000 0.000016 0.000037 0.000053 +%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.000053 +%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.000016 +%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.000037 %: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 0.046834 +%:SORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.000053 %: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 @@ -6613,34 +6649,34 @@ %: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 0.063133 1e+09 1e+09 +%operation:lower-100x100-5050nz 8.60691e-05 1e+09 1e+09 %constructor:matrix SORT[1] SCAN[1] SHUFFLE[1] INSERT[1] -%constructor:lower-100x100-5050nz 0 0.011693 0 0.035141 -# so far, program took 7.179s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 1.100s/0.000s . +%constructor:lower-100x100-5050nz 0 1.5974e-05 0 3.69549e-05 +# so far, program took 5.513s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.012s/0.000s . getrusage() stats: -ru_maxrss: 6 (maximum resident set size -- MB) -ru_stime : 0.02817s (system CPU time used) -ru_utime : 4.217s (user CPU time used) +ru_maxrss: 8 (maximum resident set size -- MB) +ru_stime : 0.0675s (system CPU time used) +ru_utime : 5.539s (user CPU time used) # multi-type benchmarking (DSCZ) -- now using typecode C (last was D). # Cache block size total 524288 bytes, per-thread 524288 bytes -# so far, program took 7.179s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 1.100s/0.000s . +# so far, program took 5.513s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.012s/0.000s . # 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 6.281e-02 s (100.00 %) - analyzed arrays in 1.145e-02 s (18.22 %) - cleaned-up arrays in 7.868e-06 s (0.01 %) - deduplicated arrays in 8.106e-06 s (0.01 %) + converted COO to RSB in 1.011e-04 s (100.00 %) + analyzed arrays in 1.407e-05 s (13.92 %) + cleaned-up arrays in 9.060e-06 s (8.96 %) + deduplicated arrays in 6.914e-06 s (6.84 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 3.534e-02 s (56.26 %) - memory allocations took 5.007e-06 s (0.01 %) - leafs setup took 2.861e-06 s (0.00 %) - halfword conversion took 1.600e-02 s (25.47 %) -Built (100 x 100)[0xaaaaf2aeedf0]{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 0.063s): (100 x 100)[0xaaaaf2aeedf0]{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 3.910e-05 s (38.68 %) + memory allocations took 2.193e-05 s (21.70 %) + leafs setup took 9.537e-07 s (0.94 %) + halfword conversion took 9.060e-06 s (8.96 %) +Built (100 x 100)[0xaaaaeb406e30]{C} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x2446196 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LS' +# Constructed matrix (took 0.000s): (100 x 100)[0xaaaaeb406e30]{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. @@ -6691,10 +6727,10 @@ # 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 0.02737s; avg 0.009122s ( +/- 16.29/ 22.12 %); best 0.007636s; worst 0.01114s; std dev. 0.001479 (taking best). -Reference operation time is 0.00763607 s (10.58 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: 0.007636 Mflops: 10.581) -Merge (3 -> 1 leaves) took w.c.t. of 4.601e-05s, ~3.6e-05s of computing time (of which 1.502e-05s sorting, 3.099e-06s analysis) +3 iterations (1 th.) took 0.0001111s; avg 3.703e-05s ( +/- 21.46/ 40.34 %); best 2.909e-05s; worst 5.198e-05s; std dev. 1.057e-05 (taking best). +Reference operation time is 2.90871e-05 s (2778 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: 2.909e-05 Mflops: 2777.867) +Merge (3 -> 1 leaves) took w.c.t. of 3.695e-05s, ~3.314e-05s of computing time (of which 1.311e-05s sorting, 1.907e-06s analysis) # 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 @@ -6725,8 +6761,8 @@ # 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 6.294e-05s; avg 2.098e-05s ( +/- 10.23/ 19.32 %); best 1.884e-05s; worst 2.503e-05s; std dev. 2.868e-06 (taking best). -Reference operation time is 1.88351e-05 s (4290 Mflops) with 1 threads. +3 iterations (1 th.) took 6.104e-05s; avg 2.035e-05s ( +/- 6.25/ 7.81 %); best 1.907e-05s; worst 2.193e-05s; std dev. 1.189e-06 (taking best). +Reference operation time is 1.90735e-05 s (4236 Mflops) with 1 threads. # 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 @@ -6742,16 +6778,16 @@ # 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: 1.884e-05 s ~Mflops: 4289.870 nsubm:1 otn:1 -Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 405.418x: 0.007636s -> 1.884e-05s, so taking this instance. +After merge step 1: tpop: 1.907e-05 s ~Mflops: 4236.247 nsubm:1 otn:1 +Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 1.525x: 2.909e-05s -> 1.907e-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 0.06873s (of which 4.816e-05s partitioning, 0.04812s I/O); computing times: 3.6e-05s in par. loops, 1.502e-05s sorting, 3.099e-06s analyzing) -Total merge + benchmarking process took 0.06873s, equivalent to 3649.1/9.0 new/old ops (0.04437s for 2 clones -- as 2355.8/5.8 ops, or 1177.9/2.9 ops per clone), SPEEDUP of 405.418x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 405.418x (0.007636s -> 1.884e-05s), will amortize in 9.0 ops by saving 0.007617s per op. -In 1 tuning rounds (tot. 0.12s, 0.044s for constructor, 2 clones) obtained a SPEEDUP of 40441.8% (405.4x) (from 10.58 to 4290 Mflops). Employed 0.044s for I/O of matrix plots. +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.002145s (of which 3.791e-05s partitioning, 0.001864s I/O); computing times: 3.314e-05s in par. loops, 1.311e-05s sorting, 1.907e-06s analyzing) +Total merge + benchmarking process took 0.002145s, equivalent to 112.5/73.7 new/old ops (3.505e-05s for 2 clones -- as 1.8/1.2 ops, or 0.9/0.6 ops per clone), SPEEDUP of 1.525x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 1.525x (2.909e-05s -> 1.907e-05s), will amortize in 214.2 ops by saving 1.001e-05s per op. +In 1 tuning rounds (tot. 0.0023s, 3.5e-05s for constructor, 2 clones) obtained a SPEEDUP of 52.5% (1.525x) (from 2778 to 4236 Mflops). Employed 0.0019s 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 0.164738 s (7.636e-03 s -> 1.884e-05 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.00421691 s (2.909e-05 s -> 1.907e-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 @@ -6817,20 +6853,20 @@ # 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 6.509e-05s; avg 2.17e-05s ( +/- 12.09/ 19.78 %); best 1.907e-05s; worst 2.599e-05s; std dev. 3.059e-06 (taking best). -Reference operation time is 1.90735e-05 s (4236 Mflops) with 1 threads. +3 iterations (1 th.) took 6.294e-05s; avg 2.098e-05s ( +/- 10.23/ 19.32 %); best 1.884e-05s; worst 2.503e-05s; std dev. 2.868e-06 (taking best). +Reference operation time is 1.88351e-05 s (4290 Mflops) with 1 threads. Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 2.806e-02 s (100.00 %) - analyzed arrays in 1.441e-02 s (51.37 %) - cleaned-up arrays in 9.060e-06 s (0.03 %) - deduplicated arrays in 7.868e-06 s (0.03 %) + converted COO to RSB in 4.005e-05 s (100.00 %) + analyzed arrays in 1.001e-05 s (25.00 %) + cleaned-up arrays in 8.821e-06 s (22.02 %) + deduplicated arrays in 7.153e-06 s (17.86 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.362e-02 s (48.53 %) - memory allocations took 2.861e-06 s (0.01 %) - leafs setup took 4.053e-06 s (0.01 %) - halfword conversion took 2.861e-06 s (0.01 %) -Built (100 x 100)[0xaaaaf2aeecd0]{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' + shuffled partitions in 1.001e-05 s (25.00 %) + memory allocations took 1.192e-06 s (2.98 %) + leafs setup took 0.000e+00 s (0.00 %) + halfword conversion took 1.907e-06 s (4.76 %) +Built (100 x 100)[0xaaaaeb406d10]{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 = 12). # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes @@ -6864,16 +6900,16 @@ # 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 4.315e-02 s (100.00 %) - analyzed arrays in 1.430e-02 s (33.15 %) - cleaned-up arrays in 9.060e-06 s (0.02 %) - deduplicated arrays in 7.868e-06 s (0.02 %) + converted COO to RSB in 7.510e-05 s (100.00 %) + analyzed arrays in 1.597e-05 s (21.27 %) + cleaned-up arrays in 9.060e-06 s (12.06 %) + deduplicated arrays in 7.153e-06 s (9.52 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.598e-02 s (37.04 %) - memory allocations took 5.007e-06 s (0.01 %) - leafs setup took 5.007e-06 s (0.01 %) - halfword conversion took 1.283e-02 s (29.75 %) -Built (100 x 100)[0xaaaaf2ae5610]{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' + shuffled partitions in 3.195e-05 s (42.54 %) + memory allocations took 9.537e-07 s (1.27 %) + leafs setup took 0.000e+00 s (0.00 %) + halfword conversion took 1.001e-05 s (13.33 %) +Built (100 x 100)[0xaaaaeb3fd650]{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 @@ -6919,9 +6955,9 @@ # 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 0.0233s; avg 0.007767s ( +/- 5.98/ 8.61 %); best 0.007303s; worst 0.008436s; std dev. 0.0004846 (taking best). -Reference operation time is 0.007303 s (11.06 Mflops) with 1 threads. -Challenging best inner round reference (1.90735e-05 s/1 threads) with: subdivision 0.25, 3 leaves, 2.121 bytes/nz, 0.007303 s/0 threads (speedup 0.00261173 x), same?n. +3 iterations (1 th.) took 9.394e-05s; avg 3.131e-05s ( +/- 7.87/ 11.93 %); best 2.885e-05s; worst 3.505e-05s; std dev. 2.686e-06 (taking best). +Reference operation time is 2.88486e-05 s (2801 Mflops) with 1 threads. +Challenging best inner round reference (1.88351e-05 s/1 threads) with: subdivision 0.25, 3 leaves, 2.121 bytes/nz, 2.88486e-05 s/0 threads (speedup 0.652893 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 524288 bytes, per-thread 524288 bytes @@ -6955,16 +6991,16 @@ # 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 5.193e-02 s (100.00 %) - analyzed arrays in 2.327e-02 s (44.81 %) - cleaned-up arrays in 9.060e-06 s (0.02 %) - deduplicated arrays in 7.868e-06 s (0.02 %) + converted COO to RSB in 9.704e-05 s (100.00 %) + analyzed arrays in 4.005e-05 s (41.28 %) + cleaned-up arrays in 8.106e-06 s (8.35 %) + deduplicated arrays in 6.914e-06 s (7.13 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.600e-02 s (30.81 %) - memory allocations took 5.960e-06 s (0.01 %) - leafs setup took 3.815e-06 s (0.01 %) - halfword conversion took 1.263e-02 s (24.32 %) -Built (100 x 100)[0xaaaaf2aeedf0]{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' + shuffled partitions in 3.004e-05 s (30.96 %) + memory allocations took 2.861e-06 s (2.95 %) + leafs setup took 0.000e+00 s (0.00 %) + halfword conversion took 9.060e-06 s (9.34 %) +Built (100 x 100)[0xaaaaeb406e30]{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 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -7010,9 +7046,9 @@ # 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 0.02339s; avg 0.007798s ( +/- 5.13/ 7.72 %); best 0.007398s; worst 0.0084s; std dev. 0.0004333 (taking best). -Reference operation time is 0.00739789 s (10.92 Mflops) with 1 threads. -Challenging best inner round reference (1.90735e-05 s/1 threads) with: subdivision 0.5, 10 leaves, 2.206 bytes/nz, 0.00739789 s/0 threads (speedup 0.00257823 x), same?n. +3 iterations (1 th.) took 0.000102s; avg 3.401e-05s ( +/- 6.07/ 11.45 %); best 3.195e-05s; worst 3.791e-05s; std dev. 2.755e-06 (taking best). +Reference operation time is 3.19481e-05 s (2529 Mflops) with 1 threads. +Challenging best inner round reference (1.88351e-05 s/1 threads) with: subdivision 0.5, 10 leaves, 2.206 bytes/nz, 3.19481e-05 s/0 threads (speedup 0.589552 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 # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes @@ -7046,16 +7082,16 @@ # 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 5.210e-02 s (100.00 %) - analyzed arrays in 2.344e-02 s (44.98 %) - cleaned-up arrays in 9.060e-06 s (0.02 %) - deduplicated arrays in 7.868e-06 s (0.02 %) + converted COO to RSB in 1.569e-04 s (100.00 %) + analyzed arrays in 7.010e-05 s (44.68 %) + cleaned-up arrays in 8.106e-06 s (5.17 %) + deduplicated arrays in 6.914e-06 s (4.41 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.266e-02 s (24.29 %) - memory allocations took 6.914e-06 s (0.01 %) - leafs setup took 3.815e-06 s (0.01 %) - halfword conversion took 1.598e-02 s (30.67 %) -Built (100 x 100)[0xaaaaf2aeedf0]{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: 25, symflags:'LS' + shuffled partitions in 5.794e-05 s (36.93 %) + memory allocations took 2.861e-06 s (1.82 %) + leafs setup took 9.537e-07 s (0.61 %) + halfword conversion took 1.001e-05 s (6.38 %) +Built (100 x 100)[0xaaaaeb406e30]{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: 25, 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 @@ -7101,9 +7137,9 @@ # 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 0.02333s; avg 0.007777s ( +/- 5.73/ 8.09 %); best 0.007332s; worst 0.008406s; std dev. 0.0004574 (taking best). -Reference operation time is 0.00733185 s (11.02 Mflops) with 1 threads. -Challenging best inner round reference (1.90735e-05 s/1 threads) with: subdivision 1, 25 leaves, 2.317 bytes/nz, 0.00733185 s/0 threads (speedup 0.00260146 x), same?n. +3 iterations (1 th.) took 0.0001068s; avg 3.56e-05s ( +/- 7.59/ 11.83 %); best 3.29e-05s; worst 3.982e-05s; std dev. 3.018e-06 (taking best). +Reference operation time is 3.29018e-05 s (2456 Mflops) with 1 threads. +Challenging best inner round reference (1.88351e-05 s/1 threads) with: subdivision 1, 25 leaves, 2.317 bytes/nz, 3.29018e-05 s/0 threads (speedup 0.572464 x), same?n. New candidate clone performs slowly; discarding it: 100 x 100, type C, 5050 nnz, 50 nnz/r, 34 subms, 25 lsubms, 2.3168 bpnz # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes @@ -7137,16 +7173,16 @@ # 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 5.543e-02 s (100.00 %) - analyzed arrays in 2.028e-02 s (36.59 %) - cleaned-up arrays in 9.060e-06 s (0.02 %) - deduplicated arrays in 7.868e-06 s (0.01 %) + converted COO to RSB in 1.979e-04 s (100.00 %) + analyzed arrays in 9.298e-05 s (46.99 %) + cleaned-up arrays in 8.106e-06 s (4.10 %) + deduplicated arrays in 6.914e-06 s (3.49 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.914e-02 s (34.52 %) - memory allocations took 7.153e-06 s (0.01 %) - leafs setup took 6.914e-06 s (0.01 %) - halfword conversion took 1.598e-02 s (28.83 %) -Built (100 x 100)[0xaaaaf2b15a60]{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: 36, symflags:'LS' + shuffled partitions in 7.510e-05 s (37.95 %) + memory allocations took 3.815e-06 s (1.93 %) + leafs setup took 9.537e-07 s (0.48 %) + halfword conversion took 1.001e-05 s (5.06 %) +Built (100 x 100)[0xaaaaeb42daa0]{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: 36, 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 @@ -7192,9 +7228,9 @@ # 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 0.02367s; avg 0.007891s ( +/- 2.70/ 1.41 %); best 0.007678s; worst 0.008002s; std dev. 0.0001507 (taking best). -Reference operation time is 0.00767803 s (10.52 Mflops) with 1 threads. -Challenging best inner round reference (1.90735e-05 s/1 threads) with: subdivision 2, 36 leaves, 2.383 bytes/nz, 0.00767803 s/0 threads (speedup 0.00248416 x), same?n. +3 iterations (1 th.) took 0.0001161s; avg 3.87e-05s ( +/- 6.98/ 10.88 %); best 3.6e-05s; worst 4.292e-05s; std dev. 3.018e-06 (taking best). +Reference operation time is 3.60012e-05 s (2244 Mflops) with 1 threads. +Challenging best inner round reference (1.88351e-05 s/1 threads) with: subdivision 2, 36 leaves, 2.383 bytes/nz, 3.60012e-05 s/0 threads (speedup 0.523179 x), same?n. New candidate clone performs slowly; discarding it: 100 x 100, type C, 5050 nnz, 50 nnz/r, 50 subms, 36 lsubms, 2.3834 bpnz # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes @@ -7228,16 +7264,16 @@ # 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 5.195e-02 s (100.00 %) - analyzed arrays in 1.993e-02 s (38.35 %) - cleaned-up arrays in 8.821e-06 s (0.02 %) - deduplicated arrays in 8.106e-06 s (0.02 %) + converted COO to RSB in 1.919e-04 s (100.00 %) + analyzed arrays in 8.917e-05 s (46.46 %) + cleaned-up arrays in 9.060e-06 s (4.72 %) + deduplicated arrays in 6.914e-06 s (3.60 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.601e-02 s (30.81 %) - memory allocations took 8.106e-06 s (0.02 %) - leafs setup took 7.153e-06 s (0.01 %) - halfword conversion took 1.599e-02 s (30.77 %) -Built (100 x 100)[0xaaaaf2b15a60]{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: 36, symflags:'LS' + shuffled partitions in 7.391e-05 s (38.51 %) + memory allocations took 1.907e-06 s (0.99 %) + leafs setup took 9.537e-07 s (0.50 %) + halfword conversion took 1.001e-05 s (5.22 %) +Built (100 x 100)[0xaaaaeb42daa0]{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: 36, 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 @@ -7283,11 +7319,11 @@ # 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 0.02365s; avg 0.007884s ( +/- 3.33/ 1.89 %); best 0.007622s; worst 0.008033s; std dev. 0.0001861 (taking best). -Reference operation time is 0.007622 s (10.6 Mflops) with 1 threads. -Challenging best inner round reference (1.90735e-05 s/1 threads) with: subdivision 4, 36 leaves, 2.383 bytes/nz, 0.007622 s/0 threads (speedup 0.00250242 x), same?n. +3 iterations (1 th.) took 0.0001149s; avg 3.831e-05s ( +/- 6.02/ 9.54 %); best 3.6e-05s; worst 4.196e-05s; std dev. 2.614e-06 (taking best). +Reference operation time is 3.60012e-05 s (2244 Mflops) with 1 threads. +Challenging best inner round reference (1.88351e-05 s/1 threads) with: subdivision 4, 36 leaves, 2.383 bytes/nz, 3.60012e-05 s/0 threads (speedup 0.523179 x), same?n. New candidate clone performs slowly; discarding it: 100 x 100, type C, 5050 nnz, 50 nnz/r, 50 subms, 36 lsubms, 2.3834 bpnz -Best sparse multiply performance with subdivision multiplier of 1: 4236.25 Mflops. +Best sparse multiply performance with subdivision multiplier of 1: 4289.87 Mflops. # 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 @@ -7303,23 +7339,23 @@ # 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 0.403029 s (eq. to 2e+04/ 2e+04 old/new op.times), gained local/global speedup 1 x (1.90735e-05 : 1.90735e-05) / 1 x (1.90735e-05 : 1.90735e-05). This is not amortizable ! +Last tuner inner round (1 of 1) took 0.00222397 s (eq. to 1e+02/ 1e+02 old/new op.times), gained local/global speedup 1 x (1.88351e-05 : 1.88351e-05) / 1 x (1.88351e-05 : 1.88351e-05). This is not amortizable ! Auto tuning inner round 1 did not find a configuration better than the original. -In 1 tuning rounds (tot. 0.4s, 0.28s for constructor, 0 clones) obtained NO speedup (best stays 4236 Mflops). -Second run of RSB Autotuner took 0.403053 s and estimated a speedup of 1.000000 x (1.907e-05 s -> 1.907e-05 s per op) in same matrix (1 -> 1 lsubm) +In 1 tuning rounds (tot. 0.0022s, 0.0014s for constructor, 0 clones) obtained NO speedup (best stays 4290 Mflops). +Second run of RSB Autotuner took 0.00224614 s and estimated a speedup of 1.000000 x (1.884e-05 s -> 1.884e-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 0.011445 0.035338 0.046783 -%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.046783 -%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.011445 -%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.035338 +%:CONSTRUCTOR_TIMES:lower-100x100-5050nz S N 1 100 100 5050 0.000000 0.000014 0.000039 0.000053 +%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.000053 +%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.000014 +%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.000039 %: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 0.046783 +%:SORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.000053 %: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 @@ -7334,34 +7370,34 @@ %: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 0.0628071 1e+09 1e+09 +%operation:lower-100x100-5050nz 0.000101089 1e+09 1e+09 %constructor:matrix SORT[1] SCAN[1] SHUFFLE[1] INSERT[1] -%constructor:lower-100x100-5050nz 0 0.011445 0 0.0353382 -# so far, program took 7.850s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 1.668s/0.000s . +%constructor:lower-100x100-5050nz 0 1.40667e-05 0 3.91006e-05 +# so far, program took 5.520s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.018s/0.000s . getrusage() stats: -ru_maxrss: 6 (maximum resident set size -- MB) -ru_stime : 0.03073s (system CPU time used) -ru_utime : 4.599s (user CPU time used) +ru_maxrss: 8 (maximum resident set size -- MB) +ru_stime : 0.06753s (system CPU time used) +ru_utime : 5.598s (user CPU time used) # multi-type benchmarking (DSCZ) -- now using typecode Z (last was D). # Cache block size total 524288 bytes, per-thread 524288 bytes -# so far, program took 7.850s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 1.668s/0.000s . +# so far, program took 5.520s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.018s/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 5.957e-02 s (100.00 %) - analyzed arrays in 1.160e-02 s (19.47 %) - cleaned-up arrays in 8.106e-06 s (0.01 %) - deduplicated arrays in 6.914e-06 s (0.01 %) - sorted arrays in 9.537e-07 s (0.00 %) - shuffled partitions in 3.195e-02 s (53.63 %) - memory allocations took 5.007e-06 s (0.01 %) - leafs setup took 2.861e-06 s (0.00 %) - halfword conversion took 1.600e-02 s (26.85 %) -Built (100 x 100)[0xaaaaf2aeedf0]{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 0.060s): (100 x 100)[0xaaaaf2aeedf0]{Z} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x2446196 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LS' + converted COO to RSB in 9.203e-05 s (100.00 %) + analyzed arrays in 1.502e-05 s (16.32 %) + cleaned-up arrays in 7.868e-06 s (8.55 %) + deduplicated arrays in 7.153e-06 s (7.77 %) + sorted arrays in 0.000e+00 s (0.00 %) + shuffled partitions in 4.792e-05 s (52.07 %) + memory allocations took 3.099e-06 s (3.37 %) + leafs setup took 9.537e-07 s (1.04 %) + halfword conversion took 1.001e-05 s (10.88 %) +Built (100 x 100)[0xaaaaeb406e30]{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 0.000s): (100 x 100)[0xaaaaeb406e30]{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. @@ -7412,10 +7448,10 @@ # 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 0.02398s; avg 0.007994s ( +/- 0.19/ 0.10 %); best 0.007979s; worst 0.008002s; std dev. 1.073e-05 (taking best). -Reference operation time is 0.00797915 s (10.13 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: 0.007979 Mflops: 10.126) -Merge (3 -> 1 leaves) took w.c.t. of 5.388e-05s, ~4.196e-05s of computing time (of which 2.098e-05s sorting, 3.099e-06s analysis) +3 iterations (1 th.) took 0.0001149s; avg 3.831e-05s ( +/- 19.09/ 38.17 %); best 3.099e-05s; worst 5.293e-05s; std dev. 1.034e-05 (taking best). +Reference operation time is 3.09944e-05 s (2607 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: 3.099e-05 Mflops: 2606.921) +Merge (3 -> 1 leaves) took w.c.t. of 4.387e-05s, ~3.815e-05s of computing time (of which 1.812e-05s sorting, 1.907e-06s analysis) # 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 @@ -7446,7 +7482,7 @@ # 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 6.294e-05s; avg 2.098e-05s ( +/- 9.09/ 13.64 %); best 1.907e-05s; worst 2.384e-05s; std dev. 2.06e-06 (taking best). +3 iterations (1 th.) took 5.794e-05s; avg 1.931e-05s ( +/- 1.23/ 2.47 %); best 1.907e-05s; worst 1.979e-05s; std dev. 3.372e-07 (taking best). Reference operation time is 1.90735e-05 s (4236 Mflops) with 1 threads. # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes @@ -7464,15 +7500,15 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success After merge step 1: tpop: 1.907e-05 s ~Mflops: 4236.247 nsubm:1 otn:1 -Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 418.337x: 0.007979s -> 1.907e-05s, so taking this instance. +Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 1.625x: 3.099e-05s -> 1.907e-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 0.07199s (of which 5.603e-05s partitioning, 0.04773s I/O); computing times: 4.196e-05s in par. loops, 2.098e-05s sorting, 3.099e-06s analyzing) -Total merge + benchmarking process took 0.07199s, equivalent to 3774.4/9.0 new/old ops (0.04747s for 2 clones -- as 2488.8/5.9 ops, or 1244.4/3.0 ops per clone), SPEEDUP of 418.337x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 418.337x (0.007979s -> 1.907e-05s), will amortize in 9.0 ops by saving 0.00796s per op. -In 1 tuning rounds (tot. 0.12s, 0.047s for constructor, 2 clones) obtained a SPEEDUP of 41733.8% (418.3x) (from 10.13 to 4236 Mflops). Employed 0.048s for I/O of matrix plots. +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.002057s (of which 4.601e-05s partitioning, 0.001836s I/O); computing times: 3.815e-05s in par. loops, 1.812e-05s sorting, 1.907e-06s analyzing) +Total merge + benchmarking process took 0.002057s, equivalent to 107.8/66.4 new/old ops (4.196e-05s for 2 clones -- as 2.2/1.4 ops, or 1.1/0.7 ops per clone), SPEEDUP of 1.625x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 1.625x (3.099e-05s -> 1.907e-05s), will amortize in 172.5 ops by saving 1.192e-05s per op. +In 1 tuning rounds (tot. 0.0022s, 4.2e-05s for constructor, 2 clones) obtained a SPEEDUP of 62.5% (1.625x) (from 2607 to 4236 Mflops). Employed 0.0019s 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 0.168015 s (7.979e-03 s -> 1.907e-05 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.00429988 s (3.099e-05 s -> 1.907e-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 @@ -7538,20 +7574,20 @@ # 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 6.604e-05s; avg 2.201e-05s ( +/- 13.36/ 22.38 %); best 1.907e-05s; worst 2.694e-05s; std dev. 3.506e-06 (taking best). +3 iterations (1 th.) took 6.318e-05s; avg 2.106e-05s ( +/- 9.43/ 14.34 %); best 1.907e-05s; worst 2.408e-05s; std dev. 2.171e-06 (taking best). Reference operation time is 1.90735e-05 s (4236 Mflops) with 1 threads. Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 2.784e-02 s (100.00 %) - analyzed arrays in 1.130e-02 s (40.61 %) - cleaned-up arrays in 1.001e-05 s (0.04 %) - deduplicated arrays in 6.914e-06 s (0.02 %) + converted COO to RSB in 7.701e-05 s (100.00 %) + analyzed arrays in 4.697e-05 s (60.99 %) + cleaned-up arrays in 8.821e-06 s (11.46 %) + deduplicated arrays in 7.153e-06 s (9.29 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.602e-02 s (57.54 %) - memory allocations took 4.892e-04 s (1.76 %) - leafs setup took 2.861e-06 s (0.01 %) - halfword conversion took 5.007e-06 s (0.02 %) -Built (100 x 100)[0xaaaaf2aeecd0]{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' + shuffled partitions in 1.001e-05 s (13.00 %) + memory allocations took 1.192e-06 s (1.55 %) + leafs setup took 9.537e-07 s (1.24 %) + halfword conversion took 9.537e-07 s (1.24 %) +Built (100 x 100)[0xaaaaeb406d10]{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 = 12). # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes @@ -7585,16 +7621,16 @@ # 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 5.189e-02 s (100.00 %) - analyzed arrays in 1.987e-02 s (38.29 %) - cleaned-up arrays in 8.821e-06 s (0.02 %) - deduplicated arrays in 8.106e-06 s (0.02 %) + converted COO to RSB in 9.799e-05 s (100.00 %) + analyzed arrays in 3.099e-05 s (31.63 %) + cleaned-up arrays in 8.821e-06 s (9.00 %) + deduplicated arrays in 7.153e-06 s (7.30 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.600e-02 s (30.83 %) - memory allocations took 6.199e-06 s (0.01 %) - leafs setup took 5.007e-06 s (0.01 %) - halfword conversion took 1.599e-02 s (30.82 %) -Built (100 x 100)[0xaaaaf2aeedf0]{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' + shuffled partitions in 4.101e-05 s (41.85 %) + memory allocations took 9.537e-07 s (0.97 %) + leafs setup took 0.000e+00 s (0.00 %) + halfword conversion took 9.060e-06 s (9.25 %) +Built (100 x 100)[0xaaaaeb406e30]{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 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -7640,9 +7676,9 @@ # 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 0.02369s; avg 0.007896s ( +/- 46.46/ 49.16 %); best 0.004228s; worst 0.01178s; std dev. 0.003086 (taking best). -Reference operation time is 0.00422788 s (19.11 Mflops) with 1 threads. -Challenging best inner round reference (1.90735e-05 s/1 threads) with: subdivision 0.25, 6 leaves, 2.163 bytes/nz, 0.00422788 s/0 threads (speedup 0.00451136 x), same?n. +3 iterations (1 th.) took 9.918e-05s; avg 3.306e-05s ( +/- 9.13/ 18.27 %); best 3.004e-05s; worst 3.91e-05s; std dev. 4.271e-06 (taking best). +Reference operation time is 3.00407e-05 s (2690 Mflops) with 1 threads. +Challenging best inner round reference (1.90735e-05 s/1 threads) with: subdivision 0.25, 6 leaves, 2.163 bytes/nz, 3.00407e-05 s/0 threads (speedup 0.634921 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 524288 bytes, per-thread 524288 bytes @@ -7676,16 +7712,16 @@ # 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 5.193e-02 s (100.00 %) - analyzed arrays in 1.993e-02 s (38.38 %) - cleaned-up arrays in 9.060e-06 s (0.02 %) - deduplicated arrays in 7.153e-06 s (0.01 %) + converted COO to RSB in 1.249e-04 s (100.00 %) + analyzed arrays in 5.507e-05 s (44.08 %) + cleaned-up arrays in 9.060e-06 s (7.25 %) + deduplicated arrays in 6.914e-06 s (5.53 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.599e-02 s (30.78 %) - memory allocations took 6.914e-06 s (0.01 %) - leafs setup took 5.960e-06 s (0.01 %) - halfword conversion took 1.598e-02 s (30.78 %) -Built (100 x 100)[0xaaaaf2aeedf0]{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' + shuffled partitions in 4.196e-05 s (33.59 %) + memory allocations took 9.537e-07 s (0.76 %) + leafs setup took 2.146e-06 s (1.72 %) + halfword conversion took 7.868e-06 s (6.30 %) +Built (100 x 100)[0xaaaaeb406e30]{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 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -7731,9 +7767,9 @@ # 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 0.0199s; avg 0.006634s ( +/- 36.78/ 20.66 %); best 0.004194s; worst 0.008005s; std dev. 0.00173 (taking best). -Reference operation time is 0.00419402 s (19.27 Mflops) with 1 threads. -Challenging best inner round reference (1.90735e-05 s/1 threads) with: subdivision 0.5, 16 leaves, 2.25 bytes/nz, 0.00419402 s/0 threads (speedup 0.00454778 x), same?n. +3 iterations (1 th.) took 0.0001302s; avg 4.339e-05s ( +/- 19.23/ 22.53 %); best 3.505e-05s; worst 5.317e-05s; std dev. 7.466e-06 (taking best). +Reference operation time is 3.50475e-05 s (2305 Mflops) with 1 threads. +Challenging best inner round reference (1.90735e-05 s/1 threads) with: subdivision 0.5, 16 leaves, 2.25 bytes/nz, 3.50475e-05 s/0 threads (speedup 0.544218 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 # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes @@ -7767,16 +7803,16 @@ # 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 5.569e-02 s (100.00 %) - analyzed arrays in 2.367e-02 s (42.50 %) - cleaned-up arrays in 8.821e-06 s (0.02 %) - deduplicated arrays in 8.106e-06 s (0.01 %) + converted COO to RSB in 2.139e-04 s (100.00 %) + analyzed arrays in 9.418e-05 s (44.04 %) + cleaned-up arrays in 9.060e-06 s (4.24 %) + deduplicated arrays in 6.914e-06 s (3.23 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.600e-02 s (28.73 %) - memory allocations took 7.153e-06 s (0.01 %) - leafs setup took 6.199e-06 s (0.01 %) - halfword conversion took 1.599e-02 s (28.71 %) -Built (100 x 100)[0xaaaaf2b3d1b0]{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' + shuffled partitions in 8.893e-05 s (41.58 %) + memory allocations took 1.907e-06 s (0.89 %) + leafs setup took 1.907e-06 s (0.89 %) + halfword conversion took 1.001e-05 s (4.68 %) +Built (100 x 100)[0xaaaaeb4551f0]{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' # 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 @@ -7822,9 +7858,9 @@ # 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 0.02367s; avg 0.00789s ( +/- 12.47/ 15.20 %); best 0.006906s; worst 0.009089s; std dev. 0.0009041 (taking best). -Reference operation time is 0.00690603 s (11.7 Mflops) with 1 threads. -Challenging best inner round reference (1.90735e-05 s/1 threads) with: subdivision 1, 36 leaves, 2.383 bytes/nz, 0.00690603 s/0 threads (speedup 0.00276186 x), same?n. +3 iterations (1 th.) took 0.0001218s; avg 4.061e-05s ( +/- 6.65/ 10.37 %); best 3.791e-05s; worst 4.482e-05s; std dev. 3.018e-06 (taking best). +Reference operation time is 3.79086e-05 s (2131 Mflops) with 1 threads. +Challenging best inner round reference (1.90735e-05 s/1 threads) with: subdivision 1, 36 leaves, 2.383 bytes/nz, 3.79086e-05 s/0 threads (speedup 0.503145 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 # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes @@ -7858,16 +7894,16 @@ # 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 5.592e-02 s (100.00 %) - analyzed arrays in 2.391e-02 s (42.77 %) - cleaned-up arrays in 8.821e-06 s (0.02 %) - deduplicated arrays in 7.868e-06 s (0.01 %) - sorted arrays in 1.192e-06 s (0.00 %) - shuffled partitions in 1.598e-02 s (28.57 %) - memory allocations took 7.153e-06 s (0.01 %) - leafs setup took 6.199e-06 s (0.01 %) - halfword conversion took 1.599e-02 s (28.60 %) -Built (100 x 100)[0xaaaaf2b3d1b0]{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 2.050e-04 s (100.00 %) + analyzed arrays in 9.489e-05 s (46.28 %) + cleaned-up arrays in 8.821e-06 s (4.30 %) + deduplicated arrays in 7.153e-06 s (3.49 %) + sorted arrays in 0.000e+00 s (0.00 %) + shuffled partitions in 8.106e-05 s (39.53 %) + memory allocations took 2.146e-06 s (1.05 %) + leafs setup took 9.537e-07 s (0.47 %) + halfword conversion took 1.001e-05 s (4.88 %) +Built (100 x 100)[0xaaaaeb4551f0]{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' # 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 @@ -7913,9 +7949,9 @@ # 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 0.02368s; avg 0.007892s ( +/- 2.68/ 1.39 %); best 0.007681s; worst 0.008002s; std dev. 0.0001495 (taking best). -Reference operation time is 0.00768089 s (10.52 Mflops) with 1 threads. -Challenging best inner round reference (1.90735e-05 s/1 threads) with: subdivision 2, 36 leaves, 2.383 bytes/nz, 0.00768089 s/0 threads (speedup 0.00248324 x), same?n. +3 iterations (1 th.) took 0.0001221s; avg 4.069e-05s ( +/- 6.84/ 13.09 %); best 3.791e-05s; worst 4.601e-05s; std dev. 3.766e-06 (taking best). +Reference operation time is 3.79086e-05 s (2131 Mflops) with 1 threads. +Challenging best inner round reference (1.90735e-05 s/1 threads) with: subdivision 2, 36 leaves, 2.383 bytes/nz, 3.79086e-05 s/0 threads (speedup 0.503145 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 # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes @@ -7949,16 +7985,16 @@ # 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 1.992e-02 s (38.35 %) - cleaned-up arrays in 9.060e-06 s (0.02 %) - deduplicated arrays in 7.868e-06 s (0.02 %) + converted COO to RSB in 1.979e-04 s (100.00 %) + analyzed arrays in 9.108e-05 s (46.02 %) + cleaned-up arrays in 9.060e-06 s (4.58 %) + deduplicated arrays in 6.914e-06 s (3.49 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.598e-02 s (30.77 %) - memory allocations took 9.060e-06 s (0.02 %) - leafs setup took 7.153e-06 s (0.01 %) - halfword conversion took 1.601e-02 s (30.82 %) -Built (100 x 100)[0xaaaaf2b3d1b0]{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' + shuffled partitions in 7.701e-05 s (38.92 %) + memory allocations took 1.907e-06 s (0.96 %) + leafs setup took 2.861e-06 s (1.45 %) + halfword conversion took 9.060e-06 s (4.58 %) +Built (100 x 100)[0xaaaaeb4551f0]{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' # 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 @@ -8004,9 +8040,9 @@ # 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 0.02368s; avg 0.007894s ( +/- 2.68/ 1.37 %); best 0.007682s; worst 0.008002s; std dev. 0.0001498 (taking best). -Reference operation time is 0.00768209 s (10.52 Mflops) with 1 threads. -Challenging best inner round reference (1.90735e-05 s/1 threads) with: subdivision 4, 36 leaves, 2.383 bytes/nz, 0.00768209 s/0 threads (speedup 0.00248285 x), same?n. +3 iterations (1 th.) took 0.0001221s; avg 4.069e-05s ( +/- 6.25/ 10.74 %); best 3.815e-05s; worst 4.506e-05s; std dev. 3.105e-06 (taking best). +Reference operation time is 3.8147e-05 s (2118 Mflops) with 1 threads. +Challenging best inner round reference (1.90735e-05 s/1 threads) with: subdivision 4, 36 leaves, 2.383 bytes/nz, 3.8147e-05 s/0 threads (speedup 0.5 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 Best sparse multiply performance with subdivision multiplier of 1: 4236.25 Mflops. # librsb version 1.3.0.2 - 202212201855: Initializing @@ -8024,29 +8060,29 @@ # 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 0.411977 s (eq. to 2e+04/ 2e+04 old/new op.times), gained local/global speedup 1 x (1.90735e-05 : 1.90735e-05) / 1 x (1.90735e-05 : 1.90735e-05). This is not amortizable ! +Last tuner inner round (1 of 1) took 0.00264788 s (eq. to 1e+02/ 1e+02 old/new op.times), gained local/global speedup 1 x (1.90735e-05 : 1.90735e-05) / 1 x (1.90735e-05 : 1.90735e-05). This is not amortizable ! Auto tuning inner round 1 did not find a configuration better than the original. -In 1 tuning rounds (tot. 0.41s, 0.3s for constructor, 0 clones) obtained NO speedup (best stays 4236 Mflops). -Second run of RSB Autotuner took 0.412002 s and estimated a speedup of 1.000000 x (1.907e-05 s -> 1.907e-05 s per op) in same matrix (1 -> 1 lsubm) +In 1 tuning rounds (tot. 0.0026s, 0.0012s for constructor, 0 clones) obtained NO speedup (best stays 4236 Mflops). +Second run of RSB Autotuner took 0.00267005 s and estimated a speedup of 1.000000 x (1.907e-05 s -> 1.907e-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 0.000001 0.011600 0.031952 0.043552 -%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.043553 -%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.011600 -%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.031952 -%: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 0.043552 +%:CONSTRUCTOR_TIMES:lower-100x100-5050nz S N 1 100 100 5050 0.000000 0.000015 0.000048 0.000063 +%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.000063 +%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.000015 +%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.000048 +%: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 0.000063 %: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 1.00 1.00 1.00 1.00 +%:CONSTRUCTOR_SCALING:lower-100x100-5050nz S N 1 100 100 5050 nan 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 @@ -8055,68 +8091,68 @@ %:SM_MINMAXAVGNNZ:lower-100x100-5050nz S N 1 100 100 5050 5050 5050 5050 # %operation:matrix CONSTRUCTOR[1] SPMV[1] SPMV[1] -%operation:lower-100x100-5050nz 0.0595739 1e+09 1e+09 +%operation:lower-100x100-5050nz 9.20296e-05 1e+09 1e+09 %constructor:matrix SORT[1] SCAN[1] SHUFFLE[1] INSERT[1] -%constructor:lower-100x100-5050nz 9.53674e-07 0.0116 0 0.0319521 -# so far, program took 8.530s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 2.248s/0.000s . +%constructor:lower-100x100-5050nz 0 1.50204e-05 0 4.79221e-05 +# so far, program took 5.528s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.025s/0.000s . getrusage() stats: -ru_maxrss: 6 (maximum resident set size -- MB) -ru_stime : 0.0332s (system CPU time used) -ru_utime : 4.98s (user CPU time used) +ru_maxrss: 8 (maximum resident set size -- MB) +ru_stime : 0.06753s (system CPU time used) +ru_utime : 5.667s (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 4034.52 7.779e-03 0.000e+00 5.007e-06 0.000e+00 1.719e-01 1.06e+01 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 4034.52 7.178e-03 0.000e+00 5.007e-06 0.000e+00 1.649e-01 6.37e+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 4289.87 7.636e-03 0.000e+00 1.884e-05 0.000e+00 1.647e-01 2.83e+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 4236.25 7.979e-03 0.000e+00 1.907e-05 0.000e+00 1.680e-01 5.04e+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 4034.52 1.287e-05 0.000e+00 5.007e-06 0.000e+00 4.054e-03 1.06e+01 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 4034.52 1.287e-05 0.000e+00 5.007e-06 0.000e+00 3.903e-03 6.37e+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 4236.25 2.909e-05 0.000e+00 1.907e-05 0.000e+00 4.217e-03 2.79e+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 4236.25 3.099e-05 0.000e+00 1.907e-05 0.000e+00 4.300e-03 5.04e+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. 95177.2 % faster, avg. sp. ratio 952.772x, max sp. ratio 1553.667x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 21207.5/8746.3/34341.0/84829.8 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 21.9/ 21.1/ 23.0/ 87.7 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 22.0, min. 21.1, max. 23.0 ops) +#pr: (in succ. cases rsb autotuning gave avg. 107.3 % faster, avg. sp. ratio 2.073x, max sp. ratio 2.571x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 508.9/221.1/809.7/2035.7 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 225.4/138.7/314.9/901.7 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 448.3, min. 360.7, max. 515.2 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 6.130/ 2.788/ 10.487,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 24.887/ 2.830/ 10.646,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 6.122/ 2.753/ 10.487,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 24.852/ 2.795/ 10.646,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.: 0.17 s, min 0.16 s, max 0.17 s, tot 0.67 s (4 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.17 s, min 0.16 s, max 0.17 s, tot 0.67 s (4 samples) -#pr: best tun. rsb canon. mflops were: on avg. 4.149e+03, min 4.035e+03, max 4.290e+03 (4 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 6.530e+00, min 2.597e+00, max 1.058e+01 (4 samples) -#pr: best tun. rsb operation time was: on avg. 1.198e-05s, min 5.007e-06s, max 1.907e-05s, tot 4.792e-05s (4 samples) -#pr: ref. unt. rsb operation time was: on avg. 7.643e-03s, min 7.178e-03s, max 7.979e-03s, tot 3.057e-02s (4 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 2.038e+00 7.668e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.322e+00 -#pr: Record collection took 2.21 s. +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.00 s, min 0.00 s, max 0.00 s, tot 0.02 s (4 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.00 s, min 0.00 s, max 0.00 s, tot 0.02 s (4 samples) +#pr: best tun. rsb canon. mflops were: on avg. 4.135e+03, min 4.035e+03, max 4.236e+03 (4 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 2.131e+03, min 1.569e+03, max 2.778e+03 (4 samples) +#pr: best tun. rsb operation time was: on avg. 1.204e-05s, min 5.007e-06s, max 1.907e-05s, tot 4.816e-05s (4 samples) +#pr: ref. unt. rsb operation time was: on avg. 2.146e-05s, min 1.287e-05s, max 3.099e-05s, tot 8.583e-05s (4 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 4.568e+00 1.740e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 9.977e-01 +#pr: Record collection took 0.03 s. #pr: Record comprises 40 memory benchmark samples (prepend RSB_PR_MBW=1 to dump this). -#pr: Record comprises 99 environment variables in 4387 bytes (prepend RSB_PR_ENV=1 to dump this). +#pr: Record comprises 99 environment variables in 4441 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 1715831688 (after 8.5s of w.c.t.) +# terminating run at 1750243445 (after 5.5s 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 85638 May 15 15:54 test-tuning-lower-100x100-5050nz--D-N-1--base.eps --rw-r--r-- 1 pbuilder1 pbuilder1 84560 May 15 15:54 test-tuning-lower-100x100-5050nz--D-N-1--mv-tuned_merge1_1x1th.eps --rw-r--r-- 1 pbuilder1 pbuilder1 85638 May 15 15:54 test-tuning-lower-100x100-5050nz--S-N-1--base.eps --rw-r--r-- 1 pbuilder1 pbuilder1 84560 May 15 15:54 test-tuning-lower-100x100-5050nz--S-N-1--mv-tuned_merge1_1x1th.eps --rw-r--r-- 1 pbuilder1 pbuilder1 85637 May 15 15:54 test-tuning-lower-100x100-5050nz--C-N-1--base.eps --rw-r--r-- 1 pbuilder1 pbuilder1 84558 May 15 15:54 test-tuning-lower-100x100-5050nz--C-N-1--mv-tuned_merge1_1x1th.eps --rw-r--r-- 1 pbuilder1 pbuilder1 85638 May 15 15:54 test-tuning-lower-100x100-5050nz--Z-N-1--base.eps --rw-r--r-- 1 pbuilder1 pbuilder1 84560 May 15 15:54 test-tuning-lower-100x100-5050nz--Z-N-1--mv-tuned_merge1_1x1th.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 85644 Jun 19 00:44 test-tuning-lower-100x100-5050nz--D-N-1--base.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 84566 Jun 19 00:44 test-tuning-lower-100x100-5050nz--D-N-1--mv-tuned_merge1_1x1th.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 85644 Jun 19 00:44 test-tuning-lower-100x100-5050nz--S-N-1--base.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 84566 Jun 19 00:44 test-tuning-lower-100x100-5050nz--S-N-1--mv-tuned_merge1_1x1th.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 85643 Jun 19 00:44 test-tuning-lower-100x100-5050nz--C-N-1--base.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 84566 Jun 19 00:44 test-tuning-lower-100x100-5050nz--C-N-1--mv-tuned_merge1_1x1th.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 84566 Jun 19 00:44 test-tuning-lower-100x100-5050nz--Z-N-1--mv-tuned_merge1_1x1th.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 85643 Jun 19 00:44 test-tuning-lower-100x100-5050nz--Z-N-1--base.eps + rsbench --read-performance-record test.rpr + ls -ltr test.txt --rw-r--r-- 1 pbuilder1 pbuilder1 4099 May 15 15:54 test.txt +-rw-r--r-- 1 pbuilder2 pbuilder2 4086 Jun 19 00:44 test.txt + RSB_PR_WLTC=2 + RSB_PR_SR=0 + rsbench --read-performance-record test.rpr @@ -8126,29 +8162,29 @@ /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 @@ -8163,7 +8199,7 @@ This error may be safely ignored. Correctly allocated a matrix. Summary information of the matrix: -(3 x 3)[0xaaab04cac4a0]{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)[0xaaab0325f4a0]{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. @@ -8178,7 +8214,7 @@ This error may be safely ignored. Correctly allocated a matrix. Summary information of the matrix: -(3 x 3)[0xaaaae7cf54a0]{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)[0xaaab00e0f4a0]{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. @@ -8242,51 +8278,51 @@ Done. Building a matrix with 5 nnz, 5 x 5 Duplicates check: 5 - 0 = 5 - converted COO to RSB in 5.973e-02 s (100.00 %) - analyzed arrays in 1.964e-02 s (32.88 %) - cleaned-up arrays in 9.537e-07 s (0.00 %) - deduplicated arrays in 9.537e-07 s (0.00 %) - sorted arrays in 7.944e-03 s (13.30 %) - shuffled partitions in 1.612e-02 s (26.99 %) - memory allocations took 7.868e-06 s (0.01 %) - leafs setup took 3.099e-06 s (0.01 %) - halfword conversion took 1.601e-02 s (26.81 %) -Built (5 x 5)[0xaaaae7cf7820]{D} @ (0(0..0),0(0..0)) (5 nnz, 1 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 2, symflags:'' + converted COO to RSB in 1.321e-04 s (100.00 %) + analyzed arrays in 1.884e-05 s (14.26 %) + cleaned-up arrays in 9.537e-07 s (0.72 %) + deduplicated arrays in 9.537e-07 s (0.72 %) + sorted arrays in 8.297e-05 s (62.82 %) + shuffled partitions in 1.121e-05 s (8.48 %) + memory allocations took 6.199e-06 s (4.69 %) + leafs setup took 9.537e-07 s (0.72 %) + halfword conversion took 1.001e-05 s (7.58 %) +Built (5 x 5)[0xaaab00e11820]{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)[0xaaaae7cf7820]{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)[0xaaab00e11820]{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 0.815739s. +Before auto-tuning, 100 multiplications took 0.003145s. 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.=2.93612e-08), 12 suggested as starting thread count(default). -3 iterations (12 th.) took 0.02435s; avg 0.008116s ( +/- 8.85/ 6.00 %); best 0.007398s; worst 0.008603s; std dev. 0.0005184 (taking best). -Reference operation time is 0.00739789 s (0.002703 Mflops) with 12 threads. -3 iterations (12 th.) took 0.02339s; avg 0.007796s ( +/- 5.24/ 10.31 %); best 0.007388s; worst 0.0086s; std dev. 0.0005683 (taking best). -Reference operation time is 0.00738788 s (0.002707 Mflops) with 12 threads. -After 0.047785s, autotuning routine did not find a better threads count configuration. -(5 x 5)[0xaaaae7cf7820]{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 0.815363s -- effective speedup of 1.00046 x +Sampling (15 x 0.1 s stages, transA=N, nrhs=2, timer gran.=7.9e-08), 12 suggested as starting thread count(default). +3 iterations (12 th.) took 2.098e-05s; avg 6.994e-06s ( +/- 14.77/ 15.91 %); best 5.96e-06s; worst 8.106e-06s; std dev. 8.778e-07 (taking best). +Reference operation time is 5.96046e-06 s (3.355 Mflops) with 12 threads. +3 iterations (12 th.) took 2.885e-05s; avg 9.616e-06s ( +/- 38.02/ 66.12 %); best 5.96e-06s; worst 1.597e-05s; std dev. 4.512e-06 (taking best). +Reference operation time is 5.96046e-06 s (3.355 Mflops) with 12 threads. +After 0.000111s, autotuning routine did not find a better threads count configuration. +(5 x 5)[0xaaab00e11820]{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 0.002832s -- effective speedup of 1.11054 x Matrix autotuning (may take more than 1.500000s; using 12 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.=2.93612e-08), 12 suggested as starting thread count. -3 iterations (12 th.) took 0.02397s; avg 0.007989s ( +/- 0.21/ 0.14 %); best 0.007972s; worst 0.008s; std dev. 1.207e-05 (taking best). -Reference operation time is 0.007972 s (0.002509 Mflops) with 12 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: 0.007972 Mflops: 0.003) -Merge (2 -> 1 leaves) took w.c.t. of 1.597e-05s, ~3.099e-06s of computing time (of which 0s sorting, 3.099e-06s analysis) -3 iterations (12 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 95.38/200.00 %); best 2.936e-08s; worst 1.907e-06s; std dev. 8.991e-07 (taking best). -Reference operation time is 2.93612e-08 s (681.2 Mflops) with 12 threads. -After merge step 1: tpop: 2.936e-08 s ~Mflops: 681.170 nsubm:1 otn:12 -Applying merge (2 -> 1 leaves, 12 th.) yielded SPEEDUP of 271514.413x: 0.007972s -> 2.936e-08s, so taking this instance. +Starting autotuning (15 x 0.1 s stages, transA=N, nrhs=2, timer gran.=7.9e-08), 12 suggested as starting thread count. +3 iterations (12 th.) took 4.506e-05s; avg 1.502e-05s ( +/- 52.38/ 58.73 %); best 7.153e-06s; worst 2.384e-05s; std dev. 6.847e-06 (taking best). +Reference operation time is 7.15256e-06 s (2.796 Mflops) with 12 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: 7.153e-06 Mflops: 2.796) +Merge (2 -> 1 leaves) took w.c.t. of 1.287e-05s, ~3.099e-06s of computing time (of which 9.537e-07s sorting, 1.907e-06s analysis) +3 iterations (12 th.) took 4.053e-06s; avg 1.351e-06s ( +/- 94.15/111.76 %); best 7.9e-08s; worst 2.861e-06s; std dev. 1.173e-06 (taking best). +Reference operation time is 7.9e-08 s (253.2 Mflops) with 12 threads. +After merge step 1: tpop: 7.9e-08 s ~Mflops: 253.165 nsubm:1 otn:12 +Applying merge (2 -> 1 leaves, 12 th.) yielded SPEEDUP of 90.539x: 7.153e-06s -> 7.9e-08s, 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 0.024s (of which 0.000221s partitioning, 0s I/O); computing times: 3.099e-06s in par. loops, 0s sorting, 3.099e-06s analyzing) -Total merge + benchmarking process took 0.024s, equivalent to 817369.1/3.0 new/old ops (0.04775s for 2 clones -- as 1626228.2/6.0 ops, or 813114.1/3.0 ops per clone), SPEEDUP of 271514.413x -Applying multi-merge (2 -> 1 leaves, 1 steps, 12 -> 12 th.sp.) yielded SPEEDUP of 271514.413x (0.007972s -> 2.936e-08s), will amortize in 3.0 ops by saving 0.007972s per op. -In 1 tuning rounds (tot. 0.072s, 0.048s for constructor, 2 clones) obtained a SPEEDUP of 27151341.3% (2.715e+05x) (from 0.002509 to 681.2 Mflops). -After 0.072012s, autotuning routine declared speedup of 271514 x, when using threads count of 12. -(5 x 5)[0xaaaae7cfade0]{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 0.000016s -- further speedup of 51043 x +A total of 1 merge steps (of max 6) (2 -> 1 subms) took 0.0003722s (of which 0.000329s partitioning, 0s I/O); computing times: 3.099e-06s in par. loops, 9.537e-07s sorting, 1.907e-06s analyzing) +Total merge + benchmarking process took 0.0003722s, equivalent to 4711.0/52.0 new/old ops (3.719e-05s for 2 clones -- as 470.8/5.2 ops, or 235.4/2.6 ops per clone), SPEEDUP of 90.539x +Applying multi-merge (2 -> 1 leaves, 1 steps, 12 -> 12 th.sp.) yielded SPEEDUP of 90.539x (7.153e-06s -> 7.9e-08s), will amortize in 52.6 ops by saving 7.074e-06s per op. +In 1 tuning rounds (tot. 0.00047s, 3.7e-05s for constructor, 2 clones) obtained a SPEEDUP of 8953.9% (90.54x) (from 2.796 to 253.2 Mflops). +After 0.000487s, autotuning routine declared speedup of 90.5387 x, when using threads count of 12. +(5 x 5)[0xaaab00e14de0]{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 0.000027s -- further speedup of 105.115 x 0/2 0 0 -> 0 1/2 1 0 -> 5 0/2 0 3 -> 0 @@ -8297,7 +8333,7 @@ Correctly initialized the library. Correctly allocated a matrix with 7 nonzeroes. Summary information of the matrix: -(6 x 6)[0xaaaae7cf7820]{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)[0xaaab00e11820]{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 @@ -8448,56 +8484,62 @@ 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 1.209e-01 s (100.00 %) - analyzed arrays in 1.968e-02 s (16.28 %) - cleaned-up arrays in 1.068e-04 s (0.09 %) - deduplicated arrays in 8.702e-05 s (0.07 %) - sorted arrays in 5.699e-02 s (47.13 %) - shuffled partitions in 2.841e-02 s (23.50 %) - memory allocations took 4.411e-05 s (0.04 %) - leafs setup took 6.914e-06 s (0.01 %) - halfword conversion took 1.558e-02 s (12.89 %) -Built (500 x 500)[0xaaaaf389f2d0]{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: 55, symflags:'' + converted COO to RSB in 4.403e-03 s (100.00 %) + analyzed arrays in 3.102e-04 s (7.04 %) + cleaned-up arrays in 3.071e-04 s (6.97 %) + deduplicated arrays in 2.460e-04 s (5.59 %) + sorted arrays in 3.251e-03 s (73.83 %) + shuffled partitions in 1.969e-04 s (4.47 %) + memory allocations took 4.196e-05 s (0.95 %) + leafs setup took 9.060e-06 s (0.21 %) + halfword conversion took 3.481e-05 s (0.79 %) +Built (500 x 500)[0xaaaaf5bdc2d0]{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: 55, symflags:'' Allocated matrix of 62500 nonzeroes: -(500 x 500)[0xaaaaf389f2d0]{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: 55, symflags:'' +(500 x 500)[0xaaaaf5bdc2d0]{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: 55, symflags:'' -Before auto-tuning, 100 multiplications took 0.820205s. +Before auto-tuning, 100 multiplications took 0.135335s. 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, 75 subms, 55 lsubms, 2.1196 bpnz. +Will use autotuning routine to sample matrix: 500 x 500, type D, 62500 nnz, 1.2e+02 nnz/r, 75 subms, 55 lsubms, 2.1195 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.=3.02553e-08), 12 suggested as starting thread count(default). -3 iterations (12 th.) took 0.02001s; avg 0.006671s ( +/- 36.80/ 35.12 %); best 0.004216s; worst 0.009014s; std dev. 0.00196 (taking best). -Reference operation time is 0.00421596 s (59.3 Mflops) with 12 threads. -3 iterations (12 th.) took 0.02791s; avg 0.009303s ( +/- 5.34/ 6.43 %); best 0.008807s; worst 0.009902s; std dev. 0.0004529 (taking best). -Reference operation time is 0.00880694 s (28.39 Mflops) with 12 threads. -After 0.048004s, autotuning routine did not find a better threads count configuration. -(500 x 500)[0xaaaaf389f2d0]{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: 55, symflags:'' -After threads auto-tuning, 100 multiplications took 0.659616s -- effective speedup of 1.24346 x +Sampling (15 x 0.1 s stages, transA=N, nrhs=2, timer gran.=8.29458e-08), 12 suggested as starting thread count(default). +3 iterations (12 th.) took 0.002257s; avg 0.0007524s ( +/- 12.13/ 13.64 %); best 0.0006611s; worst 0.000855s; std dev. 7.954e-05 (taking best). +Reference operation time is 0.000661135 s (378.1 Mflops) with 12 threads. +3 iterations (12 th.) took 0.002348s; avg 0.0007826s ( +/- 8.03/ 8.11 %); best 0.0007198s; worst 0.0008461s; std dev. 5.159e-05 (taking best). +Reference operation time is 0.000719786 s (347.3 Mflops) with 12 threads. +After 0.004661s, autotuning routine did not find a better threads count configuration. +(500 x 500)[0xaaaaf5bdc2d0]{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: 55, symflags:'' +After threads auto-tuning, 100 multiplications took 0.078351s -- effective speedup of 1.72729 x Matrix autotuning (may take more than 1.500000s; using 12 threads )... -Will autotune matrix: 500 x 500, type D, 62500 nnz, 1.2e+02 nnz/r, 75 subms, 55 lsubms, 2.1196 bpnz. +Will autotune matrix: 500 x 500, type D, 62500 nnz, 1.2e+02 nnz/r, 75 subms, 55 lsubms, 2.1195 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.=3.02553e-08), 12 suggested as starting thread count. -3 iterations (12 th.) took 0.01511s; avg 0.005037s ( +/- 3.04/ 5.96 %); best 0.004884s; worst 0.005337s; std dev. 0.0002122 (taking best). -Reference operation time is 0.004884 s (51.19 Mflops) with 12 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, 75 subms, 55 lsubms, 2.1196 bpnz (tpop: 0.004884 Mflops: 51.188) -Merge (55 -> 37 leaves) took w.c.t. of 0.003416s, ~0.0003431s of computing time (of which 0.0001307s sorting, 1.407e-05s analysis) -3 iterations (12 th.) took 0.03227s; avg 0.01076s ( +/- 60.58/ 92.32 %); best 0.00424s; worst 0.02069s; std dev. 0.007135 (taking best). -Reference operation time is 0.00424004 s (58.96 Mflops) with 12 threads. -After merge step 1: tpop: 0.00424 s ~Mflops: 58.962 nsubm:37 otn:12 -Applying merge (55 -> 37 leaves, 12 th.) yielded SPEEDUP of 1.152x: 0.004884s -> 0.00424s, so taking this instance. -Merge (37 -> 28 leaves) took w.c.t. of 0.00759s, ~0.0001168s of computing time (of which 4.792e-05s sorting, 7.868e-06s analysis) -3 iterations (12 th.) took 0.03259s; avg 0.01086s ( +/- 31.84/ 54.86 %); best 0.007404s; worst 0.01682s; std dev. 0.004232 (taking best). -Reference operation time is 0.00740409 s (33.77 Mflops) with 12 threads. -After merge step 2: tpop: 0.007404 s ~Mflops: 33.765 nsubm:28 otn:12 -Applying merge (37 -> 28 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.746x: 0.00424s -> 0.007404s. +Starting autotuning (15 x 0.1 s stages, transA=N, nrhs=2, timer gran.=8.29458e-08), 12 suggested as starting thread count. +3 iterations (12 th.) took 0.002512s; avg 0.0008373s ( +/- 72.41/ 94.68 %); best 0.000231s; worst 0.00163s; std dev. 0.0005862 (taking best). +Reference operation time is 0.000231028 s (1082 Mflops) with 12 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, 75 subms, 55 lsubms, 2.1195 bpnz (tpop: 0.000231 Mflops: 1082.122) +Merge (55 -> 37 leaves) took w.c.t. of 0.0007892s, ~0.002706s of computing time (of which 0.0002298s sorting, 7.868e-06s analysis) +3 iterations (12 th.) took 0.003595s; avg 0.001198s ( +/- 39.32/ 61.38 %); best 0.0007272s; worst 0.001934s; std dev. 0.0005269 (taking best). +Reference operation time is 0.000727177 s (343.8 Mflops) with 12 threads. +After merge step 1: tpop: 0.0007272 s ~Mflops: 343.795 nsubm:37 otn:12 +Applying merge (55 -> 37 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 3.148x: 0.000231s -> 0.0007272s. 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) (55 -> 28 subms) took 0.1037s (of which 0.01103s partitioning, 0s I/O); computing times: 0.0004599s in par. loops, 0.0001786s sorting, 2.193e-05s analyzing) -Total merge + benchmarking process took 0.1037s, equivalent to 24.5/21.2 new/old ops (0.04112s for 2 clones -- as 9.7/8.4 ops, or 4.8/4.2 ops per clone), SPEEDUP of 1.152x -Applying multi-merge (55 -> 37 leaves, 1 steps, 12 -> 12 th.sp.) yielded SPEEDUP of 1.152x (0.004884s -> 0.00424s), will amortize in 161.0 ops by saving 0.000644s per op. -In 1 tuning rounds (tot. 0.13s, 0.041s for constructor, 2 clones) obtained a SPEEDUP of 15.2% (1.152x) (from 51.19 to 58.96 Mflops). -After 0.132501s, autotuning routine declared speedup of 1.15188 x, when using threads count of 12. -(500 x 500)[0xaaaaf38a79f0]{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 0.803477s -- further speedup of 0.820952 x +A total of 1 merge steps (of max 6) (55 -> 37 subms) took 0.004407s (of which 0.0007939s partitioning, 0s I/O); computing times: 0.002706s in par. loops, 0.0002298s sorting, 7.868e-06s analyzing) +Total merge + benchmarking process took 0.004407s, equivalent to 19.1/19.1 new/old ops (0.0006459s for 1 clones -- as 2.8/2.8 ops, or 2.8/2.8 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) +Merging based autotuning FAILED (=NO SPEEDUP); let's try splitting then... +3 iterations (12 th.) took 0.00293s; avg 0.0009766s ( +/- 42.05/ 67.61 %); best 0.000566s; worst 0.001637s; std dev. 0.0004715 (taking best). +Reference operation time is 0.000566006 s (441.7 Mflops) with 12 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, 75 subms, 55 lsubms, 2.1195 bpnz (tpop: 0.000566 Mflops: 441.692) +Split (55 -> 136 leaves, 75 -> 183 subms) took 0.0008662s (of which: 5.96e-06s analysis, -4.726e+10s mem.mgmt); compute time: 0.00274s overall, 0.0001538s searches, 0.002586s shuffle, 0.001407s switch, 0.0002389s quadrants. +3 iterations (12 th.) took 0.007643s; avg 0.002548s ( +/- 46.93/ 86.17 %); best 0.001352s; worst 0.004743s; std dev. 0.001554 (taking best). +Reference operation time is 0.00135207 s (184.9 Mflops) with 12 threads. +After split step 1: tpop: 0.001352 s ~Mflops: 184.901 nsubm:136 otn:12 +Applying split (55 -> 136 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 2.389x: 0.000566s -> 0.001352s. +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) (55 -> 136 subms) took 0.008659s (of which 0.001003s partitioning, 0s I/O); computing times: 0.00274s in par. loops, 0.0001538s sorting, 5.96e-06s analyzing) +Total split + benchmarking process took 0.008659s, equivalent to 15.3/15.3 new/old ops (0.001262s for 1 clones -- as 2.2/2.2 ops, or 2.2/2.2 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) +In 1 tuning rounds (tot. 0.021s, 0.0019s for constructor, 2 clones) obtained NO speedup (best stays 441.7 Mflops). +After 0.020968s, autotuning routine declared speedup of 1 x, when using threads count of 12. +(500 x 500)[0xaaaaf5bdc2d0]{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: 55, symflags:'' +After threads auto-tuning, 100 multiplications took 0.084138s -- further speedup of 0.931219 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! @@ -8505,19 +8547,19 @@ Correctly initialized the library. Building a matrix with 7 nnz, 6 x 6 Duplicates check: 1 - 0 = 1 - converted COO to RSB in 4.517e-02 s (100.00 %) - analyzed arrays in 3.754e-02 s (83.10 %) - cleaned-up arrays in 3.815e-06 s (0.01 %) + converted COO to RSB in 1.316e-03 s (100.00 %) + analyzed arrays in 1.276e-03 s (96.96 %) + cleaned-up arrays in 5.007e-06 s (0.38 %) deduplicated arrays in 0.000e+00 s (0.00 %) - sorted arrays in 2.146e-06 s (0.00 %) - shuffled partitions in 7.600e-03 s (16.83 %) - memory allocations took 1.287e-05 s (0.03 %) - leafs setup took 5.960e-06 s (0.01 %) - halfword conversion took 6.914e-06 s (0.02 %) -Built (6 x 6)[0xaaab2034b4d0]{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' + sorted arrays in 2.146e-06 s (0.16 %) + shuffled partitions in 1.192e-05 s (0.91 %) + memory allocations took 9.060e-06 s (0.69 %) + leafs setup took 2.146e-06 s (0.16 %) + halfword conversion took 7.868e-06 s (0.60 %) +Built (6 x 6)[0xaaaae92284d0]{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)[0xaaab2034b4d0]{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)[0xaaaae92284d0]{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 @@ -8543,55 +8585,55 @@ 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:2.96e-08 -3 iterations (12 th.) took 3.91e-05s; avg 1.303e-05s ( +/- 99.77/192.68 %); best 2.96e-08s; worst 3.815e-05s; std dev. 1.776e-05 (taking best). -Reference operation time is 2.95997e-08 s (67.57 Mflops) with 12 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: 2.96e-08 Mflops: 67.568) +Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:2.935e-08 +3 iterations (12 th.) took 1.812e-05s; avg 6.04e-06s ( +/- 99.51/200.00 %); best 2.935e-08s; worst 1.812e-05s; std dev. 8.542e-06 (taking best). +Reference operation time is 2.93493e-08 s (68.14 Mflops) with 12 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: 2.935e-08 Mflops: 68.145) Merge (1 -> 1 leaves) took w.c.t. of 0s, ~0s of computing time (of which 0s sorting, 0s analysis) -3 iterations (12 th.) took 1.192e-06s; avg 3.974e-07s ( +/- 92.55/200.00 %); best 2.96e-08s; worst 1.192e-06s; std dev. 5.62e-07 (taking best). -Reference operation time is 2.95997e-08 s (67.57 Mflops) with 12 threads. -After merge step 1: tpop: 2.96e-08 s ~Mflops: 67.568 nsubm:1 otn:12 -Applying merge (1 -> 1 leaves, 12 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=1.00000x): 2.96e-08s -> 2.96e-08s, so IGNORING this instance. +3 iterations (12 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 90.77/200.00 %); best 2.935e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). +Reference operation time is 2.93493e-08 s (68.14 Mflops) with 12 threads. +After merge step 1: tpop: 2.935e-08 s ~Mflops: 68.145 nsubm:1 otn:12 +Applying merge (1 -> 1 leaves, 12 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=1.00000x): 2.935e-08s -> 2.935e-08s, 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 9.06e-06s (of which 1.907e-06s partitioning, 0s I/O); computing times: 0s in par. loops, 0s sorting, 0s analyzing) -Total merge + benchmarking process took 9.06e-06s, equivalent to 306.1/306.1 new/old ops (0.02426s for 1 clones -- as 819605.3/819605.3 ops, or 819605.3/819605.3 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) +A total of 1 merge steps (of max 6) (1 -> 1 subms) took 8.106e-06s (of which 2.146e-06s partitioning, 0s I/O); computing times: 0s in par. loops, 0s sorting, 0s analyzing) +Total merge + benchmarking process took 8.106e-06s, equivalent to 276.2/276.2 new/old ops (1.287e-05s for 1 clones -- as 438.7/438.7 ops, or 438.7/438.7 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) Merging based autotuning FAILED (=NO SPEEDUP); let's try splitting then... -3 iterations (12 th.) took 8.106e-06s; avg 2.702e-06s ( +/- 98.90/164.71 %); best 2.96e-08s; worst 7.153e-06s; std dev. 3.171e-06 (taking best). -Reference operation time is 2.95997e-08 s (67.57 Mflops) with 12 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: 2.96e-08 Mflops: 67.568) -Split (1 -> 1 leaves, 1 -> 1 subms) took 1.812e-05s (of which: 4.053e-06s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. -3 iterations (12 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 90.69/200.00 %); best 2.96e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). -Reference operation time is 2.95997e-08 s (67.57 Mflops) with 12 threads. -After split step 1: tpop: 2.96e-08 s ~Mflops: 67.568 nsubm:1 otn:12 -Applying split (1 -> 1 leaves, 12 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=1.00000x): 2.96e-08s -> 2.96e-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 (12 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 90.69/200.00 %); best 2.96e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). -Reference operation time is 2.95997e-08 s (67.57 Mflops) with 12 threads. -After split step 2: tpop: 2.96e-08 s ~Mflops: 67.568 nsubm:1 otn:12 -Applying split (1 -> 1 leaves, 12 th.) yielded NEGLIGIBLE change (2th in a row) (old/new=1.00000x): 2.96e-08s -> 2.96e-08s, so IGNORING this instance. -Split (1 -> 1 leaves, 1 -> 1 subms) took 5.007e-06s (of which: 0s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. -3 iterations (12 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 95.34/ 50.00 %); best 2.96e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). -Reference operation time is 2.95997e-08 s (67.57 Mflops) with 12 threads. -After split step 3: tpop: 2.96e-08 s ~Mflops: 67.568 nsubm:1 otn:12 -Applying split (1 -> 1 leaves, 12 th.) yielded NEGLIGIBLE change (3th in a row) (old/new=1.00000x): 2.96e-08s -> 2.96e-08s, so IGNORING this instance. +3 iterations (12 th.) took 0s; avg 0s ( +/- -inf/ nan %); best 2.935e-08s; worst 0s; std dev. 0 (taking best). +Reference operation time is 2.93493e-08 s (68.14 Mflops) with 12 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: 2.935e-08 Mflops: 68.145) +Split (1 -> 1 leaves, 1 -> 1 subms) took 1.001e-05s (of which: 9.537e-07s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. +3 iterations (12 th.) took 0s; avg 0s ( +/- -inf/ nan %); best 2.935e-08s; worst 0s; std dev. 0 (taking best). +Reference operation time is 2.93493e-08 s (68.14 Mflops) with 12 threads. +After split step 1: tpop: 2.935e-08 s ~Mflops: 68.145 nsubm:1 otn:12 +Applying split (1 -> 1 leaves, 12 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=1.00000x): 2.935e-08s -> 2.935e-08s, so IGNORING this instance. Split (1 -> 1 leaves, 1 -> 1 subms) took 9.537e-07s (of which: 0s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. -3 iterations (12 th.) took 0s; avg 0s ( +/- -inf/ nan %); best 2.96e-08s; worst 0s; std dev. 0 (taking best). -Reference operation time is 2.95997e-08 s (67.57 Mflops) with 12 threads. -After split step 4: tpop: 2.96e-08 s ~Mflops: 67.568 nsubm:1 otn:12 -Applying split (1 -> 1 leaves, 12 th.) yielded NEGLIGIBLE change (4th in a row) (old/new=1.00000x): 2.96e-08s -> 2.96e-08s, so IGNORING this instance. -Split (1 -> 1 leaves, 1 -> 1 subms) took 1.192e-06s (of which: 0s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. -3 iterations (12 th.) took 0s; avg 0s ( +/- -inf/ nan %); best 2.96e-08s; worst 0s; std dev. 0 (taking best). -Reference operation time is 2.95997e-08 s (67.57 Mflops) with 12 threads. -After split step 5: tpop: 2.96e-08 s ~Mflops: 67.568 nsubm:1 otn:12 -Applying split (1 -> 1 leaves, 12 th.) yielded NEGLIGIBLE change (5th in a row) (old/new=1.00000x): 2.96e-08s -> 2.96e-08s, so IGNORING this instance. +3 iterations (12 th.) took 0s; avg 0s ( +/- -inf/ nan %); best 2.935e-08s; worst 0s; std dev. 0 (taking best). +Reference operation time is 2.93493e-08 s (68.14 Mflops) with 12 threads. +After split step 2: tpop: 2.935e-08 s ~Mflops: 68.145 nsubm:1 otn:12 +Applying split (1 -> 1 leaves, 12 th.) yielded NEGLIGIBLE change (2th in a row) (old/new=1.00000x): 2.935e-08s -> 2.935e-08s, 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 (12 th.) took 2.146e-06s; avg 7.153e-07s ( +/- 95.90/ 66.67 %); best 2.935e-08s; worst 1.192e-06s; std dev. 5.15e-07 (taking best). +Reference operation time is 2.93493e-08 s (68.14 Mflops) with 12 threads. +After split step 3: tpop: 2.935e-08 s ~Mflops: 68.145 nsubm:1 otn:12 +Applying split (1 -> 1 leaves, 12 th.) yielded NEGLIGIBLE change (3th in a row) (old/new=1.00000x): 2.935e-08s -> 2.935e-08s, so IGNORING this instance. Split (1 -> 1 leaves, 1 -> 1 subms) took 9.537e-07s (of which: 0s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. -3 iterations (12 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 90.69/200.00 %); best 2.96e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). -Reference operation time is 2.95997e-08 s (67.57 Mflops) with 12 threads. -After split step 6: tpop: 2.96e-08 s ~Mflops: 67.568 nsubm:1 otn:12 -Applying split (1 -> 1 leaves, 12 th.) yielded NEGLIGIBLE change (6th in a row) (old/new=1.00000x): 2.96e-08s -> 2.96e-08s, so IGNORING this instance. -A total of 6 split steps (of max 6) (1 -> 1 subms) took 0.0002711s (of which 4.816e-05s partitioning, 0s I/O); computing times: 0s in par. loops, 0s sorting, 4.053e-06s analyzing) -Total split + benchmarking process took 0.0002711s, equivalent to 9158.3/9158.3 new/old ops (0.01974s for 1 clones -- as 666999.6/666999.6 ops, or 666999.6/666999.6 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) -In 1 tuning rounds (tot. 0.044s, 0.044s for constructor, 2 clones) obtained NO speedup (best stays 67.57 Mflops). +3 iterations (12 th.) took 0s; avg 0s ( +/- -inf/ nan %); best 2.935e-08s; worst 0s; std dev. 0 (taking best). +Reference operation time is 2.93493e-08 s (68.14 Mflops) with 12 threads. +After split step 4: tpop: 2.935e-08 s ~Mflops: 68.145 nsubm:1 otn:12 +Applying split (1 -> 1 leaves, 12 th.) yielded NEGLIGIBLE change (4th in a row) (old/new=1.00000x): 2.935e-08s -> 2.935e-08s, so IGNORING this instance. +Split (1 -> 1 leaves, 1 -> 1 subms) took 9.537e-07s (of which: 0s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. +3 iterations (12 th.) took 1.192e-06s; avg 3.974e-07s ( +/- 92.61/200.00 %); best 2.935e-08s; worst 1.192e-06s; std dev. 5.62e-07 (taking best). +Reference operation time is 2.93493e-08 s (68.14 Mflops) with 12 threads. +After split step 5: tpop: 2.935e-08 s ~Mflops: 68.145 nsubm:1 otn:12 +Applying split (1 -> 1 leaves, 12 th.) yielded NEGLIGIBLE change (5th in a row) (old/new=1.00000x): 2.935e-08s -> 2.935e-08s, so IGNORING this instance. +Split (1 -> 1 leaves, 1 -> 1 subms) took 9.537e-07s (of which: 0s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. +3 iterations (12 th.) took 0s; avg 0s ( +/- -inf/ nan %); best 2.935e-08s; worst 0s; std dev. 0 (taking best). +Reference operation time is 2.93493e-08 s (68.14 Mflops) with 12 threads. +After split step 6: tpop: 2.935e-08 s ~Mflops: 68.145 nsubm:1 otn:12 +Applying split (1 -> 1 leaves, 12 th.) yielded NEGLIGIBLE change (6th in a row) (old/new=1.00000x): 2.935e-08s -> 2.935e-08s, so IGNORING this instance. +A total of 6 split steps (of max 6) (1 -> 1 subms) took 0.0002658s (of which 3.457e-05s partitioning, 0s I/O); computing times: 0s in par. loops, 0s sorting, 1.907e-06s analyzing) +Total split + benchmarking process took 0.0002658s, equivalent to 9057.7/9057.7 new/old ops (9.06e-06s for 1 clones -- as 308.7/308.7 ops, or 308.7/308.7 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) +In 1 tuning rounds (tot. 0.00034s, 2.2e-05s for constructor, 2 clones) obtained NO speedup (best stays 68.14 Mflops). Backsolving we should get a unitary vector: %%MatrixMarket matrix array real general @@ -8626,182 +8668,121 @@ /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 6.964e-02 s (100.00 %) - analyzed arrays in 1.955e-02 s (28.08 %) - cleaned-up arrays in 9.537e-07 s (0.00 %) - deduplicated arrays in 2.146e-06 s (0.00 %) - sorted arrays in 1.759e-02 s (25.25 %) - shuffled partitions in 1.933e-02 s (27.76 %) - memory allocations took 3.004e-05 s (0.04 %) - leafs setup took 8.106e-06 s (0.01 %) - halfword conversion took 1.311e-02 s (18.83 %) -Built (20 x 20)[0xaaab0010d9f0]{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' + converted COO to RSB in 1.292e-03 s (100.00 %) + analyzed arrays in 9.298e-05 s (7.20 %) + cleaned-up arrays in 3.099e-06 s (0.24 %) + deduplicated arrays in 2.861e-06 s (0.22 %) + sorted arrays in 1.053e-03 s (81.51 %) + shuffled partitions in 5.507e-05 s (4.26 %) + memory allocations took 3.791e-05 s (2.93 %) + leafs setup took 5.007e-06 s (0.39 %) + halfword conversion took 2.694e-05 s (2.09 %) +Built (20 x 20)[0xaaab061479f0]{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:3.8e-08 -Starting autotuning (16 x 3.80039e-08 s stages, transA=N, nrhs=1, timer gran.=3.80039e-08), 12 suggested as starting thread count(default). -3 iterations (12 th.) took 0.02462s; avg 0.008205s ( +/- 7.57/ 5.11 %); best 0.007584s; worst 0.008624s; std dev. 0.0004481 (taking best). -Reference operation time is 0.00758386 s (0.1108 Mflops) with 12 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: 0.007584 Mflops: 0.111) -Merge (22 -> 16 leaves) took w.c.t. of 0.001189s, ~6.008e-05s of computing time (of which 2.384e-06s sorting, 8.106e-06s analysis) -3 iterations (12 th.) took 0.04257s; avg 0.01419s ( +/- 42.17/ 63.54 %); best 0.008206s; worst 0.02321s; std dev. 0.006488 (taking best). -Reference operation time is 0.00820613 s (0.1024 Mflops) with 12 threads. -After merge step 1: tpop: 0.008206 s ~Mflops: 0.102 nsubm:16 otn:12 -Applying merge (22 -> 16 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.082x: 0.007584s -> 0.008206s. -Merge (16 -> 10 leaves) took w.c.t. of 0.006504s, ~1.502e-05s of computing time (of which 1.907e-06s sorting, 6.914e-06s analysis) -3 iterations (12 th.) took 0.0341s; avg 0.01137s ( +/- 34.93/ 59.22 %); best 0.007396s; worst 0.0181s; std dev. 0.004785 (taking best). -Reference operation time is 0.00739622 s (0.1136 Mflops) with 12 threads. -After merge step 2: tpop: 0.007396 s ~Mflops: 0.114 nsubm:10 otn:12 -Applying merge (16 -> 10 leaves, 12 th.) yielded SPEEDUP of 1.025x: 0.007584s -> 0.007396s, so taking this instance. -Merge (10 -> 8 leaves) took w.c.t. of 1.907e-05s, ~6.914e-06s of computing time (of which 1.907e-06s sorting, 5.96e-06s analysis) -3 iterations (12 th.) took 0.02416s; avg 0.008054s ( +/- 8.38/ 4.28 %); best 0.007379s; worst 0.008399s; std dev. 0.0004775 (taking best). -Reference operation time is 0.00737906 s (0.1138 Mflops) with 12 threads. -After merge step 3: tpop: 0.007379 s ~Mflops: 0.114 nsubm:8 otn:12 -Applying merge (10 -> 8 leaves, 12 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=1.00233x): 0.007396s -> 0.007379s, so IGNORING this instance. -Merge (8 -> 6 leaves) took w.c.t. of 1.693e-05s, ~5.007e-06s of computing time (of which 1.192e-06s sorting, 4.053e-06s analysis) -3 iterations (12 th.) took 0.02753s; avg 0.009178s ( +/- 17.33/ 25.66 %); best 0.007588s; worst 0.01153s; std dev. 0.001699 (taking best). -Reference operation time is 0.00758791 s (0.1107 Mflops) with 12 threads. -After merge step 4: tpop: 0.007588 s ~Mflops: 0.111 nsubm:6 otn:12 -Applying merge (8 -> 6 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.026x: 0.007396s -> 0.007588s. -Merge (6 -> 3 leaves) took w.c.t. of 3.91e-05s, ~2.599e-05s of computing time (of which 1.907e-06s sorting, 5.007e-06s analysis) -3 iterations (12 th.) took 0.01976s; avg 0.006585s ( +/- 31.24/ 16.99 %); best 0.004528s; worst 0.007704s; std dev. 0.001457 (taking best). -Reference operation time is 0.00452805 s (0.1855 Mflops) with 12 threads. -After merge step 5: tpop: 0.004528 s ~Mflops: 0.186 nsubm:3 otn:12 -Applying merge (6 -> 3 leaves, 12 th.) yielded SPEEDUP of 1.633x: 0.007396s -> 0.004528s, so taking this instance. -Merge (3 -> 1 leaves) took w.c.t. of 1.979e-05s, ~9.06e-06s of computing time (of which 2.146e-06s sorting, 5.007e-06s analysis) -3 iterations (12 th.) took 5.96e-06s; avg 1.987e-06s ( +/- 98.09/140.00 %); best 3.8e-08s; worst 4.768e-06s; std dev. 2.026e-06 (taking best). -Reference operation time is 3.80039e-08 s (2.21e+04 Mflops) with 12 threads. -After merge step 6: tpop: 3.8e-08 s ~Mflops: 22102.982 nsubm:1 otn:12 -Applying merge (3 -> 1 leaves, 12 th.) yielded SPEEDUP of 119146.801x: 0.004528s -> 3.8e-08s, so taking this instance. -Merged all the matrix leaves: no reason to continue merging. -A total of 6 merge steps (of max 6) (22 -> 1 subms) took 0.2284s (of which 0.007835s partitioning, 0s I/O); computing times: 0.0001221s in par. loops, 1.144e-05s sorting, 3.505e-05s analyzing) -Total merge + benchmarking process took 0.2284s, equivalent to 6010351.3/30.1 new/old ops (0.09915s for 4 clones -- as 2609021.3/13.1 ops, or 652255.3/3.3 ops per clone), SPEEDUP of 199554.580x -Applying multi-merge (22 -> 1 leaves, 6 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 199554.580x (0.007584s -> 3.8e-08s), will amortize in 30.1 ops by saving 0.007584s per op. -In 1 tuning rounds (tot. 0.28s, 0.099s for constructor, 4 clones) obtained a SPEEDUP of 19955358.0% (1.996e+05x) (from 0.1108 to 2.21e+04 Mflops). +Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:8.46e-08 +Starting autotuning (16 x 8.46028e-08 s stages, transA=N, nrhs=1, timer gran.=8.46028e-08), 12 suggested as starting thread count(default). +3 iterations (12 th.) took 0.004997s; avg 0.001666s ( +/- 30.59/ 32.37 %); best 0.001156s; worst 0.002205s; std dev. 0.0004287 (taking best). +Reference operation time is 0.00115609 s (0.7266 Mflops) with 12 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: 0.001156 Mflops: 0.727) +Merge (22 -> 16 leaves) took w.c.t. of 0.001628s, ~0.001586s of computing time (of which 2.861e-06s sorting, 6.199e-06s analysis) +3 iterations (12 th.) took 0.004514s; avg 0.001505s ( +/- 33.35/ 64.70 %); best 0.001003s; worst 0.002478s; std dev. 0.0006885 (taking best). +Reference operation time is 0.00100279 s (0.8377 Mflops) with 12 threads. +After merge step 1: tpop: 0.001003 s ~Mflops: 0.838 nsubm:16 otn:12 +Applying merge (22 -> 16 leaves, 12 th.) yielded SPEEDUP of 1.153x: 0.001156s -> 0.001003s, so taking this instance. +Merge (16 -> 13 leaves) took w.c.t. of 2.193e-05s, ~6.914e-06s of computing time (of which 1.907e-06s sorting, 6.914e-06s analysis) +3 iterations (12 th.) took 0.005134s; avg 0.001711s ( +/- 19.24/ 10.03 %); best 0.001382s; worst 0.001883s; std dev. 0.0002329 (taking best). +Reference operation time is 0.00138211 s (0.6078 Mflops) with 12 threads. +After merge step 2: tpop: 0.001382 s ~Mflops: 0.608 nsubm:13 otn:12 +Applying merge (16 -> 13 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.378x: 0.001003s -> 0.001382s. +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 -> 13 subms) took 0.0114s (of which 0.001663s partitioning, 0s I/O); computing times: 0.001593s in par. loops, 4.768e-06s sorting, 1.311e-05s analyzing) +Total merge + benchmarking process took 0.0114s, equivalent to 11.4/9.9 new/old ops (7.319e-05s for 2 clones -- as 0.1/0.1 ops, or 0.0/0.0 ops per clone), SPEEDUP of 1.153x +Applying multi-merge (22 -> 16 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 1.153x (0.001156s -> 0.001003s), will amortize in 74.4 ops by saving 0.0001533s per op. +In 1 tuning rounds (tot. 0.017s, 7.3e-05s for constructor, 2 clones) obtained a SPEEDUP of 15.3% (1.153x) (from 0.7266 to 0.8377 Mflops). autotuner chose 12 threads -Will autotune matrix: 20 x 20, type D, 210 nnz, 10 nnz/r, 1 subms, 1 lsubms, 2.4000 bpnz. -Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:3.8e-08 -Starting autotuning (16 x 3.80039e-08 s stages, transA=N, nrhs=1, timer gran.=3.80039e-08), 12 suggested as starting thread count(default). -3 iterations (12 th.) took 8.106e-06s; avg 2.702e-06s ( +/- 98.59/164.71 %); best 3.8e-08s; worst 7.153e-06s; std dev. 3.171e-06 (taking best). -~ 12 threads: 3.8e-08s (2.2e+04 Mflops) (0/2 degradations so far) - -3 iterations (11 th.) took 2.146e-06s; avg 7.153e-07s ( +/- 94.69/ 66.67 %); best 3.8e-08s; worst 1.192e-06s; std dev. 5.15e-07 (taking best). - 11 threads: 3.8e-08s (2.2e+04 Mflops) (0/2 degradations so far) - -3 iterations (10 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 94.02/ 50.00 %); best 3.8e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). - 10 threads: 3.8e-08s (2.2e+04 Mflops) (0/2 degradations so far) - -3 iterations (9 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 94.02/ 50.00 %); best 3.8e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). - 9 threads: 3.8e-08s (2.2e+04 Mflops) (0/2 degradations so far) - -3 iterations (8 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 88.05/200.00 %); best 3.8e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). - 8 threads: 3.8e-08s (2.2e+04 Mflops) (0/2 degradations so far) - -3 iterations (7 th.) took 1.192e-06s; avg 3.974e-07s ( +/- 90.44/200.00 %); best 3.8e-08s; worst 1.192e-06s; std dev. 5.62e-07 (taking best). - 7 threads: 3.8e-08s (2.2e+04 Mflops) (0/2 degradations so far) - -3 iterations (6 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 88.05/200.00 %); best 3.8e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). - 6 threads: 3.8e-08s (2.2e+04 Mflops) (0/2 degradations so far) - -3 iterations (5 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 88.05/200.00 %); best 3.8e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). - 5 threads: 3.8e-08s (2.2e+04 Mflops) (0/2 degradations so far) - -3 iterations (4 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 88.05/200.00 %); best 3.8e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). - 4 threads: 3.8e-08s (2.2e+04 Mflops) (0/2 degradations so far) - -3 iterations (3 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 88.05/200.00 %); best 3.8e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). - 3 threads: 3.8e-08s (2.2e+04 Mflops) (0/2 degradations so far) - -3 iterations (2 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 88.05/200.00 %); best 3.8e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). - 2 threads: 3.8e-08s (2.2e+04 Mflops) (0/2 degradations so far) - -3 iterations (1 th.) took 1.192e-06s; avg 3.974e-07s ( +/- 90.44/200.00 %); best 3.8e-08s; worst 1.192e-06s; std dev. 5.62e-07 (taking best). - 1 threads: 3.8e-08s (2.2e+04 Mflops) (0/2 degradations so far) - -Best threads choice is 12; starting threads were 12; max speed gap is 1x; search took 6.2e-05s. -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, 1 subms, 1 lsubms, 2.4000 bpnz (tpop: 3.8e-08 Mflops: 22102.982) -Merge (1 -> 1 leaves) took w.c.t. of 0s, ~0s of computing time (of which 0s sorting, 0s analysis) -3 iterations (12 th.) took 2.146e-06s; avg 7.153e-07s ( +/- 94.69/ 66.67 %); best 3.8e-08s; worst 1.192e-06s; std dev. 5.15e-07 (taking best). -~ 12 threads: 3.8e-08s (2.2e+04 Mflops) (0/2 degradations so far) - -3 iterations (11 th.) took 1.192e-06s; avg 3.974e-07s ( +/- 90.44/200.00 %); best 3.8e-08s; worst 1.192e-06s; std dev. 5.62e-07 (taking best). - 11 threads: 3.8e-08s (2.2e+04 Mflops) (0/2 degradations so far) - -3 iterations (10 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 88.05/200.00 %); best 3.8e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). - 10 threads: 3.8e-08s (2.2e+04 Mflops) (0/2 degradations so far) - -3 iterations (9 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 88.05/200.00 %); best 3.8e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). - 9 threads: 3.8e-08s (2.2e+04 Mflops) (0/2 degradations so far) - -3 iterations (8 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 88.05/200.00 %); best 3.8e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). - 8 threads: 3.8e-08s (2.2e+04 Mflops) (0/2 degradations so far) - -3 iterations (7 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 88.05/200.00 %); best 3.8e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). - 7 threads: 3.8e-08s (2.2e+04 Mflops) (0/2 degradations so far) - -3 iterations (6 th.) took 1.192e-06s; avg 3.974e-07s ( +/- 90.44/200.00 %); best 3.8e-08s; worst 1.192e-06s; std dev. 5.62e-07 (taking best). - 6 threads: 3.8e-08s (2.2e+04 Mflops) (0/2 degradations so far) - -3 iterations (5 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 88.05/200.00 %); best 3.8e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). - 5 threads: 3.8e-08s (2.2e+04 Mflops) (0/2 degradations so far) - -3 iterations (4 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 88.05/200.00 %); best 3.8e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). - 4 threads: 3.8e-08s (2.2e+04 Mflops) (0/2 degradations so far) - -3 iterations (3 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 88.05/200.00 %); best 3.8e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). - 3 threads: 3.8e-08s (2.2e+04 Mflops) (0/2 degradations so far) - -3 iterations (2 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 88.05/200.00 %); best 3.8e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). - 2 threads: 3.8e-08s (2.2e+04 Mflops) (0/2 degradations so far) - -3 iterations (1 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 88.05/200.00 %); best 3.8e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). - 1 threads: 3.8e-08s (2.2e+04 Mflops) (0/2 degradations so far) - -Best threads choice is 12; starting threads were 12; max speed gap is 1x; search took 6.7e-05s. -After merge step 1: tpop: 3.8e-08 s ~Mflops: 22102.982 nsubm:1 otn:12 -Applying merge (1 -> 1 leaves, 12 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=1.00000x): 3.8e-08s -> 3.8e-08s, 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 7.296e-05s (of which 9.537e-07s partitioning, 0s I/O); computing times: 0s in par. loops, 0s sorting, 0s analyzing) -Total merge + benchmarking process took 7.296e-05s, equivalent to 1919.7/1919.7 new/old ops (0.02374s for 1 clones -- as 624667.5/624667.5 ops, or 624667.5/624667.5 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) -Merging based autotuning FAILED (=NO SPEEDUP); let's try splitting then... -3 iterations (12 th.) took 7.868e-06s; avg 2.623e-06s ( +/- 98.55/163.64 %); best 3.8e-08s; worst 6.914e-06s; std dev. 3.059e-06 (taking best). -~ 12 threads: 3.8e-08s (2.2e+04 Mflops) (0/2 degradations so far) - -3 iterations (11 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 94.02/ 50.00 %); best 3.8e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). - 11 threads: 3.8e-08s (2.2e+04 Mflops) (0/2 degradations so far) - -3 iterations (10 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 88.05/200.00 %); best 3.8e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). - 10 threads: 3.8e-08s (2.2e+04 Mflops) (0/2 degradations so far) - -3 iterations (9 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 88.05/200.00 %); best 3.8e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). - 9 threads: 3.8e-08s (2.2e+04 Mflops) (0/2 degradations so far) - -3 iterations (8 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 88.05/200.00 %); best 3.8e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). - 8 threads: 3.8e-08s (2.2e+04 Mflops) (0/2 degradations so far) - -3 iterations (7 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 88.05/200.00 %); best 3.8e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). - 7 threads: 3.8e-08s (2.2e+04 Mflops) (0/2 degradations so far) - -3 iterations (6 th.) took 2.146e-06s; avg 7.153e-07s ( +/- 94.69/ 66.67 %); best 3.8e-08s; worst 1.192e-06s; std dev. 5.15e-07 (taking best). - 6 threads: 3.8e-08s (2.2e+04 Mflops) (0/2 degradations so far) - -3 iterations (5 th.) took 1.192e-06s; avg 3.974e-07s ( +/- 90.44/200.00 %); best 3.8e-08s; worst 1.192e-06s; std dev. 5.62e-07 (taking best). - 5 threads: 3.8e-08s (2.2e+04 Mflops) (0/2 degradations so far) - -3 iterations (4 th.) took 2.146e-06s; avg 7.153e-07s ( +/- 94.69/ 66.67 %); best 3.8e-08s; worst 1.192e-06s; std dev. 5.15e-07 (taking best). - 4 threads: 3.8e-08s (2.2e+04 Mflops) (0/2 degradations so far) - -3 iterations (3 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 88.05/200.00 %); best 3.8e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). - 3 threads: 3.8e-08s (2.2e+04 Mflops) (0/2 degradations so far) - -3 iterations (2 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 94.02/ 50.00 %); best 3.8e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). - 2 threads: 3.8e-08s (2.2e+04 Mflops) (0/2 degradations so far) - -3 iterations (1 th.) took 1.192e-06s; avg 3.974e-07s ( +/- 90.44/200.00 %); best 3.8e-08s; worst 1.192e-06s; std dev. 5.62e-07 (taking best). - 1 threads: 3.8e-08s (2.2e+04 Mflops) (0/2 degradations so far) - -Best threads choice is 12; starting threads were 12; max speed gap is 1x; search took 8.5e-05s. -Starting split (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, 1 subms, 1 lsubms, 2.4000 bpnz (tpop: 3.8e-08 Mflops: 22102.982) -Split (1 -> 3 leaves, 1 -> 4 subms) took 2.909e-05s (of which: 3.099e-06s analysis, -1.716e+09s mem.mgmt); compute time: 1.097e-05s overall, 2.146e-06s searches, 8.821e-06s shuffle, 2.861e-06s switch, 0s quadrants. -3 iterations (12 th.) took 0.02326s; avg 0.007752s ( +/- 3.80/ 5.57 %); best 0.007457s; worst 0.008184s; std dev. 0.0003122 (taking best). -~ 12 threads: 0.007457s (0.11 Mflops) (0/2 degradations so far) - -3 iterations (11 th.) took 0.02419s; avg 0.008063s ( +/- 0.94/ 1.72 %); best 0.007987s; worst 0.008202s; std dev. 9.848e-05 (taking best). - 11 threads: 0.007987s (0.11 Mflops) (1/2 degradations so far) - -3 iterations (10 th.) took 0.02379s; avg 0.007929s ( +/- 1.87/ 3.48 %); best 0.00778s; worst 0.008205s; std dev. 0.0001955 (taking best). - 10 threads: 0.00778s (0.11 Mflops) (2/2 degradations so far) - -Best threads choice is 12; starting threads were 12; max speed gap is 1.1x; search took 0.071s. -After split step 1: tpop: 0.007457 s ~Mflops: 0.113 nsubm:3 otn:12 -Applying split (1 -> 3 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 196217.064x: 3.8e-08s -> 0.007457s. -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) (1 -> 3 subms) took 0.07132s (of which 3.91e-05s partitioning, 0s I/O); computing times: 1.097e-05s in par. loops, 2.146e-06s sorting, 3.099e-06s analyzing) -Total split + benchmarking process took 0.07132s, equivalent to 1876624.8/1876624.8 new/old ops (0.02446s for 1 clones -- as 643538.3/643538.3 ops, or 643538.3/643538.3 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) -In 1 tuning rounds (tot. 0.12s, 0.048s for constructor, 2 clones) obtained NO speedup (best stays 2.21e+04 Mflops). +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:8.46e-08 +Starting autotuning (16 x 8.46028e-08 s stages, transA=N, nrhs=1, timer gran.=8.46028e-08), 12 suggested as starting thread count(default). +3 iterations (12 th.) took 0.005065s; avg 0.001688s ( +/- 38.18/ 74.02 %); best 0.001044s; worst 0.002938s; std dev. 0.0008838 (taking best). +~ 12 threads: 0.001044s (0.8 Mflops) (0/2 degradations so far) - +3 iterations (11 th.) took 0.005801s; avg 0.001934s ( +/- 36.18/ 22.98 %); best 0.001234s; worst 0.002378s; std dev. 0.0005007 (taking best). + 11 threads: 0.001234s (0.68 Mflops) (1/2 degradations so far) - +3 iterations (10 th.) took 0.004069s; avg 0.001356s ( +/- 18.69/ 27.26 %); best 0.001103s; worst 0.001726s; std dev. 0.0002674 (taking best). + 10 threads: 0.001103s (0.76 Mflops) (2/2 degradations so far) - +Best threads choice is 12; starting threads were 12; max speed gap is 1.2x; search took 0.015s. +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: 0.001044 Mflops: 0.805) +Merge (16 -> 13 leaves) took w.c.t. of 2.003e-05s, ~5.007e-06s of computing time (of which 9.537e-07s sorting, 5.96e-06s analysis) +3 iterations (12 th.) took 0.002808s; avg 0.000936s ( +/- 25.85/ 19.55 %); best 0.000694s; worst 0.001119s; std dev. 0.0001784 (taking best). +~ 12 threads: 0.000694s (1.2 Mflops) (0/2 degradations so far) - +3 iterations (11 th.) took 0.003586s; avg 0.001195s ( +/- 2.37/ 4.65 %); best 0.001167s; worst 0.001251s; std dev. 3.934e-05 (taking best). + 11 threads: 0.001167s (0.72 Mflops) (1/2 degradations so far) - +3 iterations (10 th.) took 0.003531s; avg 0.001177s ( +/- 4.17/ 5.35 %); best 0.001128s; worst 0.00124s; std dev. 4.68e-05 (taking best). + 10 threads: 0.001128s (0.74 Mflops) (2/2 degradations so far) - +Best threads choice is 12; starting threads were 12; max speed gap is 1.7x; search took 0.0099s. +After merge step 1: tpop: 0.000694 s ~Mflops: 1.210 nsubm:13 otn:12 +Applying merge (16 -> 13 leaves, 12 th.) yielded SPEEDUP of 1.504x: 0.001044s -> 0.000694s, so taking this instance. +Merge (13 -> 10 leaves) took w.c.t. of 1.287e-05s, ~4.053e-06s of computing time (of which 9.537e-07s sorting, 2.861e-06s analysis) +3 iterations (12 th.) took 0.002808s; avg 0.000936s ( +/- 35.15/ 40.60 %); best 0.000607s; worst 0.001316s; std dev. 0.0002917 (taking best). +~ 12 threads: 0.000607s (1.4 Mflops) (0/2 degradations so far) - +3 iterations (11 th.) took 0.002307s; avg 0.000769s ( +/- 31.60/ 36.67 %); best 0.000526s; worst 0.001051s; std dev. 0.0002161 (taking best). + 11 threads: 0.000526s (1.6 Mflops) (0/2 degradations so far) - +3 iterations (10 th.) took 0.00169s; avg 0.0005634s ( +/- 55.27/ 34.19 %); best 0.000252s; worst 0.000756s; std dev. 0.0002222 (taking best). + 10 threads: 0.000252s (3.3 Mflops) (0/2 degradations so far) - +3 iterations (9 th.) took 0.003081s; avg 0.001027s ( +/- 39.43/ 43.62 %); best 0.000622s; worst 0.001475s; std dev. 0.0003495 (taking best). + 9 threads: 0.000622s (1.4 Mflops) (1/2 degradations so far) - +3 iterations (8 th.) took 0.003039s; avg 0.001013s ( +/- 35.84/ 66.75 %); best 0.0006499s; worst 0.001689s; std dev. 0.0004786 (taking best). + 8 threads: 0.0006499s (1.3 Mflops) (2/2 degradations so far) - +Best threads choice is 10; starting threads were 12; max speed gap is 2.6x; search took 0.013s. +After merge step 2: tpop: 0.000252 s ~Mflops: 3.333 nsubm:10 otn:10 +Applying merge (13 -> 10 leaves, 10 th.) yielded SPEEDUP of 2.754x: 0.000694s -> 0.000252s, so taking this instance. +Merge (10 -> 8 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 (12 th.) took 0.001531s; avg 0.0005104s ( +/- 92.71/ 91.81 %); best 3.719e-05s; worst 0.0009789s; std dev. 0.0003845 (taking best). +~ 12 threads: 3.719e-05s (23 Mflops) (0/2 degradations so far) - +3 iterations (11 th.) took 0.00212s; avg 0.0007067s ( +/- 28.81/ 21.26 %); best 0.0005031s; worst 0.0008569s; std dev. 0.0001493 (taking best). + 11 threads: 0.0005031s (1.7 Mflops) (1/2 degradations so far) - +3 iterations (10 th.) took 0.003374s; avg 0.001125s ( +/- 3.88/ 3.41 %); best 0.001081s; worst 0.001163s; std dev. 3.369e-05 (taking best). + 10 threads: 0.001081s (0.78 Mflops) (2/2 degradations so far) - +Best threads choice is 12; starting threads were 12; max speed gap is 29x; search took 0.0076s. +After merge step 3: tpop: 3.719e-05 s ~Mflops: 22.585 nsubm:8 otn:12 +Applying merge (10 -> 8 leaves, 12 th.) yielded SPEEDUP of 6.776x: 0.000252s -> 3.719e-05s, so taking this instance. +Merge (8 -> 6 leaves) took w.c.t. of 1.597e-05s, ~5.96e-06s of computing time (of which 2.146e-06s sorting, 5.007e-06s analysis) +3 iterations (12 th.) took 0.004146s; avg 0.001382s ( +/- 43.55/ 66.99 %); best 0.0007801s; worst 0.002308s; std dev. 0.0006644 (taking best). +~ 12 threads: 0.0007801s (1.1 Mflops) (0/2 degradations so far) - +3 iterations (11 th.) took 0.004706s; avg 0.001569s ( +/- 37.71/ 75.37 %); best 0.000977s; worst 0.002751s; std dev. 0.000836 (taking best). + 11 threads: 0.000977s (0.86 Mflops) (1/2 degradations so far) - +3 iterations (10 th.) took 0.003064s; avg 0.001021s ( +/- 22.75/ 29.45 %); best 0.0007889s; worst 0.001322s; std dev. 0.0002229 (taking best). + 10 threads: 0.0007889s (1.1 Mflops) (2/2 degradations so far) - +Best threads choice is 12; starting threads were 12; max speed gap is 1.3x; search took 0.012s. +After merge step 4: tpop: 0.0007801 s ~Mflops: 1.077 nsubm:6 otn:12 +Applying merge (8 -> 6 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 20.974x: 3.719e-05s -> 0.0007801s. +Skipping further merge based tests after 1 definite performance degradations in a row (and last exceeding limit). +A total of 4 merge steps (of max 6) (16 -> 6 subms) took 0.04284s (of which 7.391e-05s partitioning, 0s I/O); computing times: 2.003e-05s in par. loops, 5.007e-06s sorting, 1.574e-05s analyzing) +Total merge + benchmarking process took 0.04284s, equivalent to 1151.9/41.0 new/old ops (0.0003037s for 4 clones -- as 8.2/0.3 ops, or 2.0/0.1 ops per clone), SPEEDUP of 28.064x +Applying multi-merge (16 -> 8 leaves, 3 steps, 12 -> 12 th.sp.) yielded SPEEDUP of 28.064x (0.001044s -> 3.719e-05s), will amortize in 42.6 ops by saving 0.001007s per op. +In 1 tuning rounds (tot. 0.058s, 0.0003s for constructor, 4 clones) obtained a SPEEDUP of 2706.4% (28.06x) (from 0.8048 to 22.58 Mflops). check results are ok Building a matrix with 36 nnz, 6 x 6 Duplicates check: 36 - 0 = 36 - converted COO to RSB in 3.136e-02 s (100.00 %) - analyzed arrays in 1.496e-02 s (47.69 %) - cleaned-up arrays in 0.000e+00 s (0.00 %) - deduplicated arrays in 0.000e+00 s (0.00 %) - sorted arrays in 7.981e-03 s (25.45 %) - shuffled partitions in 8.409e-03 s (26.81 %) - memory allocations took 7.868e-06 s (0.03 %) - leafs setup took 2.861e-06 s (0.01 %) - halfword conversion took 1.192e-06 s (0.00 %) -Built (6 x 6)[0xaaab00118ca0]{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 2.192e-03 s (100.00 %) + analyzed arrays in 1.083e-03 s (49.41 %) + cleaned-up arrays in 9.537e-07 s (0.04 %) + deduplicated arrays in 9.537e-07 s (0.04 %) + sorted arrays in 3.741e-04 s (17.07 %) + shuffled partitions in 7.241e-04 s (33.03 %) + memory allocations took 5.960e-06 s (0.27 %) + leafs setup took 9.537e-07 s (0.04 %) + halfword conversion took 1.907e-06 s (0.09 %) +Built (6 x 6)[0xaaab061467e0]{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 0.1099E-03 s -A single USMM took 0.1330E-03 s -USMM-to-USMV speed ratio is is 0.8262 x +A single USMM took 0.1559E-03 s +USMM-to-USMV speed ratio is is 0.7049 x Call auto-tuning routine.. Repeat measurement. -Tuned USMM took 0.2146E-05 s -Tuned-to-untuned speed ratio is is 62.00 x +Tuned USMM took 0.5007E-05 s +Tuned-to-untuned speed ratio is is 31.14 x FAILED: 0 PASSED: 2 /build/reproducible-path/librsb-1.3.0.2+dfsg/examples/fortran_rsb_fi @@ -8850,218 +8831,234 @@ 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 7.723e-02 s (100.00 %) - analyzed arrays in 1.681e-02 s (21.77 %) - cleaned-up arrays in 5.007e-06 s (0.01 %) - deduplicated arrays in 2.146e-06 s (0.00 %) - sorted arrays in 2.523e-02 s (32.67 %) - shuffled partitions in 1.936e-02 s (25.07 %) - memory allocations took 1.597e-05 s (0.02 %) - leafs setup took 7.153e-06 s (0.01 %) - halfword conversion took 1.578e-02 s (20.43 %) -Built (6 x 6)[0xaaaacd71aa20]{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 1.179e-03 s (100.00 %) + analyzed arrays in 9.608e-05 s (8.15 %) + cleaned-up arrays in 1.097e-05 s (0.93 %) + deduplicated arrays in 1.907e-06 s (0.16 %) + sorted arrays in 9.501e-04 s (80.59 %) + shuffled partitions in 6.008e-05 s (5.10 %) + memory allocations took 1.502e-05 s (1.27 %) + leafs setup took 5.007e-06 s (0.42 %) + halfword conversion took 2.193e-05 s (1.86 %) +Built (6 x 6)[0xaaaaf8855a20]{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)[0xaaaacd71eaa0]{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)[0xaaaaf8859aa0]{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 (12 th.) took 0.02415s; avg 0.008052s ( +/- 47.48/ 45.51 %); best 0.004229s; worst 0.01172s; std dev. 0.003059 (taking best). -Reference operation time is 0.00422907 s (0.03405 Mflops) with 12 threads. -After 0.024216s, autotuning routine did not find a better threads count configuration. +3 iterations (12 th.) took 0.004917s; avg 0.001639s ( +/- 32.83/ 24.78 %); best 0.001101s; worst 0.002045s; std dev. 0.0003966 (taking best). +Reference operation time is 0.00110102 s (0.1308 Mflops) with 12 threads. +After 0.004979s, 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 (12 th.) took 0.02355s; avg 0.007849s ( +/- 3.27/ 1.97 %); best 0.007592s; worst 0.008004s; std dev. 0.000183 (taking best). -Reference operation time is 0.00759196 s (0.01897 Mflops) with 12 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: 0.007592 Mflops: 0.019) -Merge (22 -> 16 leaves) took w.c.t. of 0.007548s, ~6.318e-05s of computing time (of which 2.146e-06s sorting, 5.96e-06s analysis) -3 iterations (12 th.) took 0.06321s; avg 0.02107s ( +/- 65.59/127.63 %); best 0.00725s; worst 0.04796s; std dev. 0.01902 (taking best). -Reference operation time is 0.00724983 s (0.01986 Mflops) with 12 threads. -After merge step 1: tpop: 0.00725 s ~Mflops: 0.020 nsubm:16 otn:12 -Applying merge (22 -> 16 leaves, 12 th.) yielded SPEEDUP of 1.047x: 0.007592s -> 0.00725s, so taking this instance. -Merge (16 -> 10 leaves) took w.c.t. of 0.008185s, ~1.502e-05s of computing time (of which 1.192e-06s sorting, 7.153e-06s analysis) -3 iterations (12 th.) took 0.0604s; avg 0.02013s ( +/- 77.98/123.54 %); best 0.004434s; worst 0.04501s; std dev. 0.01779 (taking best). -Reference operation time is 0.00443411 s (0.03248 Mflops) with 12 threads. -After merge step 2: tpop: 0.004434 s ~Mflops: 0.032 nsubm:10 otn:12 -Applying merge (16 -> 10 leaves, 12 th.) yielded SPEEDUP of 1.635x: 0.00725s -> 0.004434s, so taking this instance. -Merge (10 -> 7 leaves) took w.c.t. of 1.812e-05s, ~6.199e-06s of computing time (of which 0s sorting, 5.96e-06s analysis) -3 iterations (12 th.) took 0.02417s; avg 0.008057s ( +/- 8.35/ 6.94 %); best 0.007384s; worst 0.008616s; std dev. 0.0005093 (taking best). -Reference operation time is 0.00738406 s (0.0195 Mflops) with 12 threads. -After merge step 3: tpop: 0.007384 s ~Mflops: 0.020 nsubm:7 otn:12 -Applying merge (10 -> 7 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.665x: 0.004434s -> 0.007384s. +3 iterations (12 th.) took 0.003268s; avg 0.001089s ( +/- 2.23/ 2.17 %); best 0.001065s; worst 0.001113s; std dev. 1.957e-05 (taking best). +Reference operation time is 0.00106502 s (0.1352 Mflops) with 12 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: 0.001065 Mflops: 0.135) +Merge (22 -> 16 leaves) took w.c.t. of 0.001207s, ~0.001166s of computing time (of which 1.907e-06s sorting, 6.914e-06s analysis) +3 iterations (12 th.) took 0.004369s; avg 0.001456s ( +/- 25.90/ 43.17 %); best 0.001079s; worst 0.002085s; std dev. 0.0004475 (taking best). +Reference operation time is 0.00107908 s (0.1334 Mflops) with 12 threads. +After merge step 1: tpop: 0.001079 s ~Mflops: 0.133 nsubm:16 otn:12 +Applying merge (22 -> 16 leaves, 12 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=0.98696x): 0.001065s -> 0.001079s, so IGNORING this instance. +Merge (16 -> 10 leaves) took w.c.t. of 4.506e-05s, ~3.719e-05s of computing time (of which 8.106e-06s sorting, 5.007e-06s analysis) +3 iterations (12 th.) took 0.005127s; avg 0.001709s ( +/- 83.55/ 72.21 %); best 0.0002811s; worst 0.002943s; std dev. 0.001095 (taking best). +Reference operation time is 0.000281096 s (0.5123 Mflops) with 12 threads. +After merge step 2: tpop: 0.0002811 s ~Mflops: 0.512 nsubm:10 otn:12 +Applying merge (16 -> 10 leaves, 12 th.) yielded SPEEDUP of 3.789x: 0.001065s -> 0.0002811s, so taking this instance. +Merge (10 -> 7 leaves) took w.c.t. of 1.597e-05s, ~5.96e-06s of computing time (of which 9.537e-07s sorting, 4.053e-06s analysis) +3 iterations (12 th.) took 0.005667s; avg 0.001889s ( +/- 62.41/ 61.83 %); best 0.00071s; worst 0.003057s; std dev. 0.0009582 (taking best). +Reference operation time is 0.000710011 s (0.2028 Mflops) with 12 threads. +After merge step 3: tpop: 0.00071 s ~Mflops: 0.203 nsubm:7 otn:12 +Applying merge (10 -> 7 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 2.526x: 0.0002811s -> 0.00071s. Skipping further merge based tests after 1 definite performance degradations in a row (and last exceeding limit). -A total of 3 merge steps (of max 6) (22 -> 7 subms) took 0.2122s (of which 0.01578s partitioning, 0s I/O); computing times: 8.44e-05s in par. loops, 3.338e-06s sorting, 1.907e-05s analyzing) -Total merge + benchmarking process took 0.2122s, equivalent to 47.8/27.9 new/old ops (0.07273s for 3 clones -- as 16.4/9.6 ops, or 5.5/3.2 ops per clone), SPEEDUP of 1.712x -Applying multi-merge (22 -> 10 leaves, 2 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 1.712x (0.007592s -> 0.004434s), will amortize in 67.2 ops by saving 0.003158s per op. -In 1 tuning rounds (tot. 0.26s, 0.073s for constructor, 3 clones) obtained a SPEEDUP of 71.2% (1.712x) (from 0.01897 to 0.03248 Mflops). -After 0.260186s, global autotuning declared speedup of 1.71217 x, when using threads count of 12 and a new matrix: -(6 x 6)[0xaaaacd724ab0]{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: 10, symflags:'' +A total of 3 merge steps (of max 6) (22 -> 7 subms) took 0.01655s (of which 0.001286s partitioning, 0s I/O); computing times: 0.001209s in par. loops, 1.097e-05s sorting, 1.597e-05s analyzing) +Total merge + benchmarking process took 0.01655s, equivalent to 58.9/15.5 new/old ops (6.39e-05s for 2 clones -- as 0.2/0.1 ops, or 0.1/0.0 ops per clone), SPEEDUP of 3.789x +Applying multi-merge (22 -> 10 leaves, 2 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 3.789x (0.001065s -> 0.0002811s), will amortize in 21.1 ops by saving 0.0007839s per op. +In 1 tuning rounds (tot. 0.02s, 6.4e-05s for constructor, 2 clones) obtained a SPEEDUP of 278.9% (3.789x) (from 0.1352 to 0.5123 Mflops). +After 0.020321s, global autotuning declared speedup of 3.7888 x, when using threads count of 12 and a new matrix: +(6 x 6)[0xaaaaf885be70]{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: 10, symflags:'' Considering S clone. Building a matrix with 36 nnz, 6 x 6 Duplicates check: 36 - 0 = 36 - converted COO to RSB in 4.776e-02 s (100.00 %) - analyzed arrays in 1.575e-02 s (32.98 %) - cleaned-up arrays in 9.537e-07 s (0.00 %) - deduplicated arrays in 0.000e+00 s (0.00 %) + converted COO to RSB in 7.365e-03 s (100.00 %) + analyzed arrays in 2.515e-03 s (34.15 %) + cleaned-up arrays in 1.192e-06 s (0.02 %) + deduplicated arrays in 9.537e-07 s (0.01 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.600e-02 s (33.51 %) - memory allocations took 5.960e-06 s (0.01 %) - leafs setup took 3.815e-06 s (0.01 %) - halfword conversion took 1.599e-02 s (33.49 %) -Built (6 x 6)[0xaaaacd71eaa0]{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:'' + shuffled partitions in 2.408e-03 s (32.70 %) + memory allocations took 6.676e-06 s (0.09 %) + leafs setup took 3.099e-06 s (0.04 %) + halfword conversion took 2.429e-03 s (32.98 %) +Built (6 x 6)[0xaaaaf885be70]{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)[0xaaaacd71eaa0]{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)[0xaaaaf885be70]{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 (12 th.) took 0.02457s; avg 0.008189s ( +/- 9.71/ 5.11 %); best 0.007394s; worst 0.008607s; std dev. 0.0005623 (taking best). -Reference operation time is 0.00739384 s (0.01948 Mflops) with 12 threads. -After 0.024595s, autotuning routine did not find a better threads count configuration. +3 iterations (12 th.) took 0.005104s; avg 0.001701s ( +/- 28.77/ 20.85 %); best 0.001212s; worst 0.002056s; std dev. 0.0003576 (taking best). +Reference operation time is 0.00121188 s (0.1188 Mflops) with 12 threads. +After 0.005143s, 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 (12 th.) took 0.0246s; avg 0.0082s ( +/- 9.78/ 4.92 %); best 0.007398s; worst 0.008603s; std dev. 0.0005672 (taking best). -Reference operation time is 0.00739789 s (0.01947 Mflops) with 12 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: 0.007398 Mflops: 0.019) -Merge (16 -> 10 leaves) took w.c.t. of 0.01479s, ~1.669e-05s of computing time (of which 1.907e-06s sorting, 4.053e-06s analysis) -3 iterations (12 th.) took 0.05615s; avg 0.01872s ( +/- 59.41/ 96.53 %); best 0.007596s; worst 0.03678s; std dev. 0.01289 (taking best). -Reference operation time is 0.00759602 s (0.01896 Mflops) with 12 threads. -After merge step 1: tpop: 0.007596 s ~Mflops: 0.019 nsubm:10 otn:12 -Applying merge (16 -> 10 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.027x: 0.007398s -> 0.007596s. -Merge (10 -> 7 leaves) took w.c.t. of 1.717e-05s, ~5.96e-06s of computing time (of which 9.537e-07s sorting, 5.007e-06s analysis) -3 iterations (12 th.) took 0.02396s; avg 0.007987s ( +/- 47.06/ 46.86 %); best 0.004228s; worst 0.01173s; std dev. 0.003063 (taking best). -Reference operation time is 0.00422812 s (0.03406 Mflops) with 12 threads. -After merge step 2: tpop: 0.004228 s ~Mflops: 0.034 nsubm:7 otn:12 -Applying merge (10 -> 7 leaves, 12 th.) yielded SPEEDUP of 1.750x: 0.007398s -> 0.004228s, so taking this instance. -Merge (7 -> 4 leaves) took w.c.t. of 1.693e-05s, ~5.007e-06s of computing time (of which 9.537e-07s sorting, 5.007e-06s analysis) -3 iterations (12 th.) took 0.02416s; avg 0.008055s ( +/- 0.78/ 1.49 %); best 0.007992s; worst 0.008175s; std dev. 8.483e-05 (taking best). -Reference operation time is 0.00799203 s (0.01802 Mflops) with 12 threads. -After merge step 3: tpop: 0.007992 s ~Mflops: 0.018 nsubm:4 otn:12 -Applying merge (7 -> 4 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.890x: 0.004228s -> 0.007992s. -Skipping further merge based tests after 1 definite performance degradations in a row (and last exceeding limit). -A total of 3 merge steps (of max 6) (16 -> 4 subms) took 0.1394s (of which 0.01484s partitioning, 0s I/O); computing times: 2.766e-05s in par. loops, 3.815e-06s sorting, 1.407e-05s analyzing) -Total merge + benchmarking process took 0.1394s, equivalent to 33.0/18.8 new/old ops (0.04353s for 2 clones -- as 10.3/5.9 ops, or 5.1/2.9 ops per clone), SPEEDUP of 1.750x -Applying multi-merge (16 -> 7 leaves, 2 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 1.750x (0.007398s -> 0.004228s), will amortize in 44.0 ops by saving 0.00317s per op. -In 1 tuning rounds (tot. 0.19s, 0.044s for constructor, 2 clones) obtained a SPEEDUP of 75.0% (1.75x) (from 0.01947 to 0.03406 Mflops). -After 0.187369s, global autotuning declared speedup of 1.74969 x, when using threads count of 12 and a new matrix: -(6 x 6)[0xaaaacd720e70]{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: 7, symflags:'' +3 iterations (12 th.) took 0.004288s; avg 0.001429s ( +/- 12.96/ 17.25 %); best 0.001244s; worst 0.001676s; std dev. 0.0001815 (taking best). +Reference operation time is 0.00124407 s (0.1157 Mflops) with 12 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: 0.001244 Mflops: 0.116) +Merge (16 -> 10 leaves) took w.c.t. of 3.6e-05s, ~1.693e-05s of computing time (of which 4.053e-06s sorting, 4.053e-06s analysis) +3 iterations (12 th.) took 0.004224s; avg 0.001408s ( +/- 33.59/ 61.35 %); best 0.0009351s; worst 0.002272s; std dev. 0.0006118 (taking best). +Reference operation time is 0.000935078 s (0.154 Mflops) with 12 threads. +After merge step 1: tpop: 0.0009351 s ~Mflops: 0.154 nsubm:10 otn:12 +Applying merge (16 -> 10 leaves, 12 th.) yielded SPEEDUP of 1.330x: 0.001244s -> 0.0009351s, so taking this instance. +Merge (10 -> 7 leaves) took w.c.t. of 1.597e-05s, ~5.007e-06s of computing time (of which 9.537e-07s sorting, 4.053e-06s analysis) +3 iterations (12 th.) took 0.003175s; avg 0.001058s ( +/- 8.72/ 5.54 %); best 0.0009661s; worst 0.001117s; std dev. 6.604e-05 (taking best). +Reference operation time is 0.000966072 s (0.1491 Mflops) with 12 threads. +After merge step 2: tpop: 0.0009661 s ~Mflops: 0.149 nsubm:7 otn:12 +Applying merge (10 -> 7 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.033x: 0.0009351s -> 0.0009661s. +Merge (7 -> 4 leaves) took w.c.t. of 9.06e-06s, ~3.099e-06s of computing time (of which 0s sorting, 2.146e-06s analysis) +3 iterations (12 th.) took 0.001888s; avg 0.0006293s ( +/- 74.28/ 54.60 %); best 0.0001619s; worst 0.000973s; std dev. 0.0003425 (taking best). +Reference operation time is 0.000161886 s (0.8895 Mflops) with 12 threads. +After merge step 3: tpop: 0.0001619 s ~Mflops: 0.890 nsubm:4 otn:12 +Applying merge (7 -> 4 leaves, 12 th.) yielded SPEEDUP of 5.776x: 0.0009351s -> 0.0001619s, so taking this instance. +Merge (4 -> 1 leaves) took w.c.t. of 1.121e-05s, ~5.007e-06s of computing time (of which 9.537e-07s sorting, 2.146e-06s analysis) +3 iterations (12 th.) took 5.007e-06s; avg 1.669e-06s ( +/- 95.36/142.86 %); best 7.735e-08s; worst 4.053e-06s; std dev. 1.73e-06 (taking best). +Reference operation time is 7.73549e-08 s (1862 Mflops) with 12 threads. +After merge step 4: tpop: 7.735e-08 s ~Mflops: 1861.550 nsubm:1 otn:12 +Applying merge (4 -> 1 leaves, 12 th.) yielded SPEEDUP of 2092.772x: 0.0001619s -> 7.735e-08s, so taking this instance. +Merged all the matrix leaves: no reason to continue merging. +A total of 4 merge steps (of max 6) (16 -> 1 subms) took 0.009949s (of which 0.0002232s partitioning, 0s I/O); computing times: 3.004e-05s in par. loops, 5.96e-06s sorting, 1.24e-05s analyzing) +Total merge + benchmarking process took 0.009949s, equivalent to 128614.6/8.0 new/old ops (0.001603s for 4 clones -- as 20724.3/1.3 ops, or 5181.1/0.3 ops per clone), SPEEDUP of 16082.601x +Applying multi-merge (16 -> 1 leaves, 4 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 16082.601x (0.001244s -> 7.735e-08s), will amortize in 8.0 ops by saving 0.001244s per op. +In 1 tuning rounds (tot. 0.016s, 0.0016s for constructor, 4 clones) obtained a SPEEDUP of 1608160.1% (1.608e+04x) (from 0.1157 to 1862 Mflops). +After 0.015559s, global autotuning declared speedup of 16082.6 x, when using threads count of 12 and a new matrix: +(6 x 6)[0xaaaaf8858670]{S} @ (0(0..6),0(0..6)) (36 nnz, 6 nnz/r) flags 0x2244086 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 1, symflags:'' Considering C clone. Building a matrix with 36 nnz, 6 x 6 Duplicates check: 36 - 0 = 36 - converted COO to RSB in 5.179e-02 s (100.00 %) - analyzed arrays in 1.998e-02 s (38.58 %) - cleaned-up arrays in 9.537e-07 s (0.00 %) + converted COO to RSB in 1.619e-04 s (100.00 %) + analyzed arrays in 6.604e-05 s (40.80 %) + cleaned-up arrays in 9.537e-07 s (0.59 %) deduplicated arrays in 0.000e+00 s (0.00 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.601e-02 s (30.91 %) - memory allocations took 3.815e-06 s (0.01 %) - leafs setup took 3.099e-06 s (0.01 %) - halfword conversion took 1.579e-02 s (30.50 %) -Built (6 x 6)[0xaaaacd724ab0]{C} @ (0(0..0),0(0..0)) (36 nnz, 6 nnz/r) flags 0x42046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 22, symflags:'' + shuffled partitions in 5.102e-05 s (31.52 %) + memory allocations took 2.885e-05 s (17.82 %) + leafs setup took 1.907e-06 s (1.18 %) + halfword conversion took 1.192e-05 s (7.36 %) +Built (6 x 6)[0xaaaaf885fab0]{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)[0xaaaacd724ab0]{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)[0xaaaaf885fab0]{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, 4.2778 bpnz. +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 (12 th.) took 0.02457s; avg 0.008189s ( +/- 7.23/ 5.16 %); best 0.007597s; worst 0.008611s; std dev. 0.0004309 (taking best). -Reference operation time is 0.00759697 s (0.07582 Mflops) with 12 threads. -After 0.024593s, autotuning routine did not find a better threads count configuration. +3 iterations (12 th.) took 0.004158s; avg 0.001386s ( +/- 22.30/ 18.04 %); best 0.001077s; worst 0.001636s; std dev. 0.000232 (taking best). +Reference operation time is 0.00107694 s (0.5349 Mflops) with 12 threads. +After 0.004183s, 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, 4.2778 bpnz. +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 (12 th.) took 0.0238s; avg 0.007932s ( +/- 4.30/ 6.02 %); best 0.007591s; worst 0.00841s; std dev. 0.000348 (taking best). -Reference operation time is 0.00759101 s (0.07588 Mflops) with 12 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, 4.2778 bpnz (tpop: 0.007591 Mflops: 0.076) -Merge (22 -> 19 leaves) took w.c.t. of 1.693e-05s, ~4.053e-06s of computing time (of which 1.192e-06s sorting, 3.815e-06s analysis) -3 iterations (12 th.) took 0.02042s; avg 0.006807s ( +/- 34.94/ 20.80 %); best 0.004429s; worst 0.008223s; std dev. 0.001692 (taking best). -Reference operation time is 0.00442886 s (0.1301 Mflops) with 12 threads. -After merge step 1: tpop: 0.004429 s ~Mflops: 0.130 nsubm:19 otn:12 -Applying merge (22 -> 19 leaves, 12 th.) yielded SPEEDUP of 1.714x: 0.007591s -> 0.004429s, so taking this instance. -Merge (19 -> 16 leaves) took w.c.t. of 2.098e-05s, ~4.768e-06s of computing time (of which 9.537e-07s sorting, 8.106e-06s analysis) -3 iterations (12 th.) took 0.02395s; avg 0.007984s ( +/- 46.63/ 49.74 %); best 0.004261s; worst 0.01196s; std dev. 0.003146 (taking best). -Reference operation time is 0.00426102 s (0.1352 Mflops) with 12 threads. -After merge step 2: tpop: 0.004261 s ~Mflops: 0.135 nsubm:16 otn:12 -Applying merge (19 -> 16 leaves, 12 th.) yielded SPEEDUP of 1.039x: 0.004429s -> 0.004261s, so taking this instance. -Merge (16 -> 13 leaves) took w.c.t. of 2.003e-05s, ~5.007e-06s of computing time (of which 1.192e-06s sorting, 5.96e-06s analysis) -3 iterations (12 th.) took 0.02393s; avg 0.007976s ( +/- 1.88/ 2.40 %); best 0.007826s; worst 0.008168s; std dev. 0.0001426 (taking best). -Reference operation time is 0.00782609 s (0.0736 Mflops) with 12 threads. -After merge step 3: tpop: 0.007826 s ~Mflops: 0.074 nsubm:13 otn:12 -Applying merge (16 -> 13 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.837x: 0.004261s -> 0.007826s. +3 iterations (12 th.) took 0.006267s; avg 0.002089s ( +/- 37.39/ 43.32 %); best 0.001308s; worst 0.002994s; std dev. 0.0006939 (taking best). +Reference operation time is 0.00130796 s (0.4404 Mflops) with 12 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: 0.001308 Mflops: 0.440) +Merge (22 -> 16 leaves) took w.c.t. of 0.0005009s, ~1.502e-05s of computing time (of which 1.907e-06s sorting, 4.053e-06s analysis) +3 iterations (12 th.) took 0.007251s; avg 0.002417s ( +/- 31.81/ 20.97 %); best 0.001648s; worst 0.002924s; std dev. 0.0005528 (taking best). +Reference operation time is 0.00164819 s (0.3495 Mflops) with 12 threads. +After merge step 1: tpop: 0.001648 s ~Mflops: 0.349 nsubm:16 otn:12 +Applying merge (22 -> 16 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.260x: 0.001308s -> 0.001648s. Skipping further merge based tests after 1 definite performance degradations in a row (and last exceeding limit). -A total of 3 merge steps (of max 6) (22 -> 13 subms) took 0.1164s (of which 6.58e-05s partitioning, 0s I/O); computing times: 1.383e-05s in par. loops, 3.338e-06s sorting, 1.788e-05s analyzing) -Total merge + benchmarking process took 0.1164s, equivalent to 27.3/15.3 new/old ops (0.07508s for 3 clones -- as 17.6/9.9 ops, or 5.9/3.3 ops per clone), SPEEDUP of 1.782x -Applying multi-merge (22 -> 16 leaves, 2 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 1.782x (0.007591s -> 0.004261s), will amortize in 35.0 ops by saving 0.00333s per op. -In 1 tuning rounds (tot. 0.17s, 0.075s for constructor, 3 clones) obtained a SPEEDUP of 78.2% (1.782x) (from 0.07588 to 0.1352 Mflops). -After 0.167393s, global autotuning declared speedup of 1.7815 x, when using threads count of 12 and a new matrix: -(6 x 6)[0xaaaacd728fe0]{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:'' +A total of 1 merge steps (of max 6) (22 -> 16 subms) took 0.007789s (of which 0.0005078s partitioning, 0s I/O); computing times: 1.502e-05s in par. loops, 1.907e-06s sorting, 4.053e-06s analyzing) +Total merge + benchmarking process took 0.007789s, equivalent to 6.0/6.0 new/old ops (2.503e-05s for 1 clones -- as 0.0/0.0 ops, or 0.0/0.0 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) +Merging based autotuning FAILED (=NO SPEEDUP); let's try splitting then... +3 iterations (12 th.) took 0.002937s; avg 0.000979s ( +/- 1.01/ 1.43 %); best 0.0009692s; worst 0.000993s; std dev. 1.016e-05 (taking best). +Reference operation time is 0.000969172 s (0.5943 Mflops) with 12 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: 0.0009692 Mflops: 0.594) +Split (22 -> 28 leaves, 29 -> 37 subms) took 0.000123s (of which: 5.007e-06s analysis, -3.5e+09s mem.mgmt); compute time: 0.00017s overall, 2.861e-06s searches, 0.0001671s shuffle, 8.202e-05s switch, 2.146e-06s quadrants. +3 iterations (12 th.) took 0.00746s; avg 0.002487s ( +/- 41.29/ 52.70 %); best 0.00146s; worst 0.003797s; std dev. 0.000975 (taking best). +Reference operation time is 0.00145984 s (0.3946 Mflops) with 12 threads. +After split step 1: tpop: 0.00146 s ~Mflops: 0.395 nsubm:28 otn:12 +Applying split (22 -> 28 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.506x: 0.0009692s -> 0.00146s. +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 0.007654s (of which 0.0001731s partitioning, 0s I/O); computing times: 0.00017s in par. loops, 2.861e-06s sorting, 5.007e-06s analyzing) +Total split + benchmarking process took 0.007654s, equivalent to 7.9/7.9 new/old ops (8.202e-05s for 1 clones -- as 0.1/0.1 ops, or 0.1/0.1 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) +In 1 tuning rounds (tot. 0.025s, 0.00011s for constructor, 2 clones) obtained NO speedup (best stays 0.5943 Mflops). +After 0.025113s, global autotuning found old matrix optimal, with declared speedup 1 x when using 12 threads Considering Z clone. Building a matrix with 36 nnz, 6 x 6 Duplicates check: 36 - 0 = 36 - converted COO to RSB in 5.572e-02 s (100.00 %) - analyzed arrays in 2.371e-02 s (42.54 %) - cleaned-up arrays in 9.537e-07 s (0.00 %) - deduplicated arrays in 9.537e-07 s (0.00 %) + converted COO to RSB in 1.540e-04 s (100.00 %) + analyzed arrays in 7.606e-05 s (49.38 %) + cleaned-up arrays in 9.537e-07 s (0.62 %) + deduplicated arrays in 1.192e-06 s (0.77 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.600e-02 s (28.72 %) - memory allocations took 7.153e-06 s (0.01 %) - leafs setup took 5.960e-06 s (0.01 %) - halfword conversion took 1.600e-02 s (28.71 %) -Built (6 x 6)[0xaaaacd724ab0]{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:'' + shuffled partitions in 5.984e-05 s (38.85 %) + memory allocations took 3.815e-06 s (2.48 %) + leafs setup took 2.146e-06 s (1.39 %) + halfword conversion took 1.001e-05 s (6.50 %) +Built (6 x 6)[0xaaaaf885ea80]{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)[0xaaaacd724ab0]{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)[0xaaaaf885ea80]{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 (12 th.) took 0.02373s; avg 0.007909s ( +/- 2.24/ 3.97 %); best 0.007732s; worst 0.008223s; std dev. 0.0002225 (taking best). -Reference operation time is 0.00773191 s (0.0745 Mflops) with 12 threads. -After 0.023759s, autotuning routine did not find a better threads count configuration. +3 iterations (12 th.) took 0.004717s; avg 0.001572s ( +/- 36.59/ 64.40 %); best 0.0009971s; worst 0.002585s; std dev. 0.0007182 (taking best). +Reference operation time is 0.000997066 s (0.5777 Mflops) with 12 threads. +After 0.004738s, 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 (12 th.) took 0.02379s; avg 0.007929s ( +/- 1.81/ 3.57 %); best 0.007785s; worst 0.008212s; std dev. 0.0002002 (taking best). -Reference operation time is 0.00778508 s (0.07399 Mflops) with 12 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: 0.007785 Mflops: 0.074) -Merge (28 -> 22 leaves) took w.c.t. of 0.007981s, ~1.192e-05s of computing time (of which 9.537e-07s sorting, 5.007e-06s analysis) -3 iterations (12 th.) took 0.04798s; avg 0.01599s ( +/- 50.06/ 75.23 %); best 0.007986s; worst 0.02802s; std dev. 0.008661 (taking best). -Reference operation time is 0.00798607 s (0.07213 Mflops) with 12 threads. -After merge step 1: tpop: 0.007986 s ~Mflops: 0.072 nsubm:22 otn:12 -Applying merge (28 -> 22 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.026x: 0.007785s -> 0.007986s. -Merge (22 -> 16 leaves) took w.c.t. of 0.004035s, ~1.574e-05s of computing time (of which 2.861e-06s sorting, 5.96e-06s analysis) -3 iterations (12 th.) took 0.04793s; avg 0.01598s ( +/- 49.94/ 99.89 %); best 0.007998s; worst 0.03194s; std dev. 0.01129 (taking best). -Reference operation time is 0.00799799 s (0.07202 Mflops) with 12 threads. -After merge step 2: tpop: 0.007998 s ~Mflops: 0.072 nsubm:16 otn:12 -Applying merge (22 -> 16 leaves, 12 th.) yielded SLOWDOWN (2th of 3 tolerable) of 1.027x: 0.007785s -> 0.007998s. -Merge (16 -> 10 leaves) took w.c.t. of 0.007779s, ~1.502e-05s of computing time (of which 9.537e-07s sorting, 5.007e-06s analysis) -3 iterations (12 th.) took 0.06s; avg 0.02s ( +/- 60.07/119.89 %); best 0.007985s; worst 0.04398s; std dev. 0.01695 (taking best). -Reference operation time is 0.00798512 s (0.07213 Mflops) with 12 threads. -After merge step 3: tpop: 0.007985 s ~Mflops: 0.072 nsubm:10 otn:12 -Applying merge (16 -> 10 leaves, 12 th.) yielded SLOWDOWN (3th of 3 tolerable) of 1.026x: 0.007785s -> 0.007985s. -Merge (10 -> 7 leaves) took w.c.t. of 2.003e-05s, ~5.007e-06s of computing time (of which 1.192e-06s sorting, 5.007e-06s analysis) -3 iterations (12 th.) took 0.02394s; avg 0.007979s ( +/- 0.62/ 0.33 %); best 0.007929s; worst 0.008005s; std dev. 3.509e-05 (taking best). -Reference operation time is 0.00792909 s (0.07264 Mflops) with 12 threads. -After merge step 4: tpop: 0.007929 s ~Mflops: 0.073 nsubm:7 otn:12 -Applying merge (10 -> 7 leaves, 12 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=0.98184x): 0.007785s -> 0.007929s, so IGNORING this instance. -Merge (7 -> 4 leaves) took w.c.t. of 1.812e-05s, ~5.007e-06s of computing time (of which 9.537e-07s sorting, 4.053e-06s analysis) -3 iterations (12 th.) took 0.02319s; avg 0.00773s ( +/- 6.76/ 3.79 %); best 0.007208s; worst 0.008023s; std dev. 0.0003702 (taking best). -Reference operation time is 0.00720811 s (0.07991 Mflops) with 12 threads. -After merge step 5: tpop: 0.007208 s ~Mflops: 0.080 nsubm:4 otn:12 -Applying merge (7 -> 4 leaves, 12 th.) yielded SPEEDUP of 1.080x: 0.007785s -> 0.007208s, so taking this instance. -Merge (4 -> 1 leaves) took w.c.t. of 1.907e-05s, ~5.96e-06s of computing time (of which 1.192e-06s sorting, 4.053e-06s analysis) -3 iterations (12 th.) took 7.153e-06s; avg 2.384e-06s ( +/- 98.75/160.00 %); best 2.99e-08s; worst 6.199e-06s; std dev. 2.725e-06 (taking best). -Reference operation time is 2.98977e-08 s (1.927e+04 Mflops) with 12 threads. -After merge step 6: tpop: 2.99e-08 s ~Mflops: 19265.703 nsubm:1 otn:12 -Applying merge (4 -> 1 leaves, 12 th.) yielded SPEEDUP of 241092.504x: 0.007208s -> 2.99e-08s, so taking this instance. -Merged all the matrix leaves: no reason to continue merging. -A total of 6 merge steps (of max 6) (28 -> 1 subms) took 0.276s (of which 0.01989s partitioning, 0s I/O); computing times: 5.865e-05s in par. loops, 8.106e-06s sorting, 2.909e-05s analyzing) -Total merge + benchmarking process took 0.276s, equivalent to 9231586.9/35.5 new/old ops (0.07691s for 3 clones -- as 2572400.3/9.9 ops, or 857466.8/3.3 ops per clone), SPEEDUP of 260390.750x -Applying multi-merge (28 -> 1 leaves, 6 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 260390.750x (0.007785s -> 2.99e-08s), will amortize in 35.5 ops by saving 0.007785s per op. -In 1 tuning rounds (tot. 0.32s, 0.077s for constructor, 3 clones) obtained a SPEEDUP of 26038975.0% (2.604e+05x) (from 0.07399 to 1.927e+04 Mflops). -After 0.324031s, global autotuning declared speedup of 260391 x, when using threads count of 12 and a new matrix: -(6 x 6)[0xaaaacd7214c0]{Z} @ (0(0..6),0(0..6)) (36 nnz, 6 nnz/r) flags 0x2244086 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 1, symflags:'' +3 iterations (12 th.) took 0.003129s; avg 0.001043s ( +/- 13.62/ 10.07 %); best 0.000901s; worst 0.001148s; std dev. 0.0001042 (taking best). +Reference operation time is 0.000900984 s (0.6393 Mflops) with 12 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: 0.000901 Mflops: 0.639) +Merge (28 -> 22 leaves) took w.c.t. of 3.195e-05s, ~1.478e-05s of computing time (of which 2.861e-06s sorting, 5.007e-06s analysis) +3 iterations (12 th.) took 0.00569s; avg 0.001897s ( +/- 39.74/ 73.94 %); best 0.001143s; worst 0.003299s; std dev. 0.0009926 (taking best). +Reference operation time is 0.00114298 s (0.5039 Mflops) with 12 threads. +After merge step 1: tpop: 0.001143 s ~Mflops: 0.504 nsubm:22 otn:12 +Applying merge (28 -> 22 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.269x: 0.000901s -> 0.001143s. +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 0.005753s (of which 3.886e-05s partitioning, 0s I/O); computing times: 1.478e-05s in par. loops, 2.861e-06s sorting, 5.007e-06s analyzing) +Total merge + benchmarking process took 0.005753s, equivalent to 6.4/6.4 new/old ops (2.384e-05s for 1 clones -- as 0.0/0.0 ops, or 0.0/0.0 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) +Merging based autotuning FAILED (=NO SPEEDUP); let's try splitting then... +3 iterations (12 th.) took 0.004434s; avg 0.001478s ( +/- 27.20/ 15.43 %); best 0.001076s; worst 0.001706s; std dev. 0.0002852 (taking best). +Reference operation time is 0.00107598 s (0.5353 Mflops) with 12 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: 0.001076 Mflops: 0.535) +Split (28 -> 28 leaves, 37 -> 37 subms) took 2.789e-05s (of which: 5.007e-06s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. +3 iterations (12 th.) took 0.003589s; avg 0.001196s ( +/- 18.09/ 13.94 %); best 0.0009799s; worst 0.001363s; std dev. 0.0001603 (taking best). +Reference operation time is 0.0009799 s (0.5878 Mflops) with 12 threads. +After split step 1: tpop: 0.0009799 s ~Mflops: 0.588 nsubm:28 otn:12 +Applying split (28 -> 28 leaves, 12 th.) yielded SPEEDUP of 1.098x: 0.001076s -> 0.0009799s, so taking this instance. +Split (28 -> 28 leaves, 37 -> 37 subms) took 2.217e-05s (of which: 2.146e-06s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. +3 iterations (12 th.) took 0.003471s; avg 0.001157s ( +/- 24.54/ 33.89 %); best 0.0008731s; worst 0.001549s; std dev. 0.0002863 (taking best). +Reference operation time is 0.000873089 s (0.6597 Mflops) with 12 threads. +After split step 2: tpop: 0.0008731 s ~Mflops: 0.660 nsubm:28 otn:12 +Applying split (28 -> 28 leaves, 12 th.) yielded SPEEDUP of 1.122x: 0.0009799s -> 0.0008731s, so taking this instance. +Split (28 -> 28 leaves, 37 -> 37 subms) took 2.193e-05s (of which: 1.907e-06s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. +3 iterations (12 th.) took 0.003915s; avg 0.001305s ( +/- 34.03/ 22.77 %); best 0.0008609s; worst 0.001602s; std dev. 0.00032 (taking best). +Reference operation time is 0.000860929 s (0.669 Mflops) with 12 threads. +After split step 3: tpop: 0.0008609 s ~Mflops: 0.669 nsubm:28 otn:12 +Applying split (28 -> 28 leaves, 12 th.) yielded SPEEDUP of 1.014x: 0.0008731s -> 0.0008609s, so taking this instance. +Split (28 -> 28 leaves, 37 -> 37 subms) took 2.098e-05s (of which: 2.861e-06s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. +3 iterations (12 th.) took 0.002621s; avg 0.0008737s ( +/- 43.68/ 50.98 %); best 0.0004921s; worst 0.001319s; std dev. 0.0003407 (taking best). +Reference operation time is 0.000492096 s (1.171 Mflops) with 12 threads. +After split step 4: tpop: 0.0004921 s ~Mflops: 1.171 nsubm:28 otn:12 +Applying split (28 -> 28 leaves, 12 th.) yielded SPEEDUP of 1.750x: 0.0008609s -> 0.0004921s, so taking this instance. +Split (28 -> 28 leaves, 37 -> 37 subms) took 2.003e-05s (of which: 9.537e-07s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. +3 iterations (12 th.) took 0.002343s; avg 0.000781s ( +/- 34.30/ 41.74 %); best 0.0005131s; worst 0.001107s; std dev. 0.0002459 (taking best). +Reference operation time is 0.000513077 s (1.123 Mflops) with 12 threads. +After split step 5: tpop: 0.0005131 s ~Mflops: 1.123 nsubm:28 otn:12 +Applying split (28 -> 28 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.043x: 0.0004921s -> 0.0005131s. +Split (28 -> 28 leaves, 37 -> 37 subms) took 2.313e-05s (of which: 4.053e-06s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. +3 iterations (12 th.) took 0.001974s; avg 0.000658s ( +/- 60.18/ 77.79 %); best 0.000262s; worst 0.00117s; std dev. 0.0003796 (taking best). +Reference operation time is 0.000262022 s (2.198 Mflops) with 12 threads. +After split step 6: tpop: 0.000262 s ~Mflops: 2.198 nsubm:28 otn:12 +Applying split (28 -> 28 leaves, 12 th.) yielded SPEEDUP of 1.878x: 0.0004921s -> 0.000262s, so taking this instance. +A total of 6 split steps (of max 6) (28 -> 28 subms) took 0.01926s (of which 0.0004258s partitioning, 0s I/O); computing times: 0s in par. loops, 0s sorting, 1.693e-05s analyzing) +Total split + benchmarking process took 0.01926s, equivalent to 73.5/17.9 new/old ops (0.0008819s for 6 clones -- as 3.4/0.8 ops, or 0.6/0.1 ops per clone), SPEEDUP of 4.106x +Applying multi-split (28 -> 28 leaves, 6 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 4.106x (0.001076s -> 0.000262s), will amortize in 23.7 ops by saving 0.000814s per op. +In 1 tuning rounds (tot. 0.033s, 0.00091s for constructor, 7 clones) obtained a SPEEDUP of 310.6% (4.106x) (from 0.5353 to 2.198 Mflops). +After 0.032922s, global autotuning declared speedup of 4.10646 x, when using threads count of 12 and a new matrix: +(6 x 6)[0xaaaaf88621d0]{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' @@ -9192,10 +9189,10 @@ 4 0 DIFF PRINT TEST END Beginning large binary search test. -Detected 63089266688 bytes of memory, comprehensive of 8924008448 of free memory. +Detected 63089254400 bytes of memory, comprehensive of 55955607552 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 (6382 MB) than on the maximal coordinate indices array (6693006336) allows. -(c)allocated 1673251584 nnz (6693006336 bytes) +Will perform the test using less memory (7254 MB) than on the maximal coordinate indices array (7606967296) allows. +(c)allocated 1901741824 nnz (7606967296 bytes) Succeeded retrieving array last element. Successfully performed large binary search test. BASIC SPARSE BLAS TEST: BEGIN @@ -9204,7 +9201,7 @@ got RSB_IO_WANT_IS_INITIALIZED_MARKER: 1 INIT INTERFACE TEST: END (SUCCESS) DEVEL PRINT TEST: BEGIN -(4 x 4)[0xaaaab28ac3a0]{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)[0xaaaadb1643a0]{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 | @@ -9213,8 +9210,8 @@ RSB_FLAG_ASSEMBLED_IN_COO_ARRAYS | RSB_FLAG_OWN_PARTITIONING_ARRAYS | RSB_FLAG_SORT_INPUT -(2 x 2)[0xaaaab28ac4b0]{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)[0xaaaab28ac5c0]{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)[0xaaaadb1644b0]{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)[0xaaaadb1645c0]{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%) @@ -9222,9 +9219,9 @@ ( 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)[0xaaaab28ac4b0]{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)[0xaaaab28ac5c0]{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)[0xaaaab28ac3a0]{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)[0xaaaadb1644b0]{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)[0xaaaadb1645c0]{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)[0xaaaadb1643a0]{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 | @@ -9242,8 +9239,8 @@ 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 30.005490 s, max allowed was 30.000000. - PASSED:2560 +Terminating testing earlier due to user timeout request: test took 30.002557 s, max allowed was 30.000000. + PASSED:21392 FAILED:0 ADVANCED SPARSE BLAS TEST: END (SUCCESS) gmake qtests -C librsbpp @@ -9252,30 +9249,30 @@ 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 +if ! test -f G.mtx ; then cp -p /build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp/G.mtx . ; fi ; /bin/sh /build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp/test.sh ++ grep Z-sort -++ wc -l ++ ./rsbpp Td,s G.mtx +++ wc -l + test 54 = 54 ++ grep Z-sort ++ wc -l ++ ./rsbpp Td G.mtx + test 27 = 27 -++ wc -l -++ ./rsbpp Td,z G.mtx ++ grep Z-sort +++ ./rsbpp Td,z G.mtx +++ wc -l + test 54 = 54 ++ ./rsbpp vTd,z G.mtx ++ grep Z-sort ++ wc -l + test 54 = 54 +++ ./rsbpp vTd,z G.mtx ++ grep Z-sort ++ wc -l -++ ./rsbpp vTd,z G.mtx + test 54 = 54 ++ ./rsbpp vvvTd,z G.mtx -++ wc -l ++ grep Zorted +++ wc -l + test 8 = 8 ++ ./rsbpp vvTd,z G.mtx ++ grep Z-sort @@ -9286,41 +9283,41 @@ ++ wc -l + test 0 = 0 ++ ./rsbpp vvvTd,z G.mtx -++ wc -l ++ grep Range +++ wc -l + test 258 -gt 0 ++ grep Range -++ wc -l ++ ./rsbpp vvvTd,z S.mtx +++ wc -l + test 0 -eq 0 ++ ./rsbpp vvvTd,z G.mtx ++ grep Range ++ wc -l + test 258 = 258 -++ grep spmm- -++ wc -l ++ OMP_NUM_THREADS=1 ++ ./rsbpp m10M10I1r1,4,8sFv -+ test 9 = 9 ++ wc -l ++ grep spmm- ++ test 9 = 9 +++ grep spmm- +++ wc -l ++ OMP_NUM_THREADS=1 ++ ./rsbpp C1000m100M100I1r1,4,8sFv + test 9 = 9 -++ wc -l -++ grep spmm- ++ OMP_NUM_THREADS=1 ++ ./rsbpp C1000m100M100I1r1sFvtN,T -+ test 3 = 3 ++ grep spmm- -++ OMP_NUM_THREADS=1 ++ wc -l ++ test 3 = 3 +++ OMP_NUM_THREADS=1 ++ ./rsbpp C1000m100M100I1r1vtN,TsF -+ test 2 = 2 ++ grep spmm- ++ wc -l ++ test 2 = 2 ++ OMP_NUM_THREADS=1 ++ ./rsbpp C1000m100M100I1r0vtN,TsF +++ grep spmm- +++ wc -l + test 0 = 0 ++ OMP_NUM_THREADS=1 ++ RSB_NUM_THREADS=1 @@ -9331,19 +9328,19 @@ ++ OMP_NUM_THREADS=2 ++ RSB_NUM_THREADS=2 ++ ./rsbpp vvvC1000m100M100I1r1vtN,TorsF -++ wc -l ++ grep Recursing -+ test 4 = 4 ++ wc -l ++ test 4 = 4 ++ OMP_NUM_THREADS=1 ++ RSB_NUM_THREADS=1 ++ ./rsbpp vvvC1000m100M100I1r1vtN,ToRsF ++ grep Recursing +++ wc -l + test 208 = 208 ++ OMP_NUM_THREADS=2 -++ grep Recursing ++ RSB_NUM_THREADS=2 ++ ./rsbpp vvvC1000m100M100I1r1vtN,ToRsF +++ grep Recursing ++ wc -l + test 410 = 410 echo "Skipping tests based on Google Test (not detected at configure time)" @@ -9391,7 +9388,7 @@ 0 0 0 0 before tuning for SPMV: -(3 x 3)[0xaaaac458f4c0]{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)[0xaaaafc499120]{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 @@ -9480,18 +9477,18 @@ BEGIN Rsb_Matrix_test_multimatrix_ms_mnrhs BEGIN -(3 x 3)[0xaaaac459c3d0]{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)[0xaaaac459c3d0]{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)[0xaaaac45bd920]{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 1.00086: -(3 x 3)[0xaaaac45c3480]{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)[0xaaaac459c3d0]{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)[0xaaaac459c3d0]{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)[0xaaaac45bd920]{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)[0xaaaac45bd920]{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)[0xaaaafc4b06b0]{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 4.52: +(3 x 3)[0xaaaafc4cf660]{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)[0xaaaafc4b06b0]{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 1.06923: +(3 x 3)[0xaaaafc4cf660]{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)[0xaaaafc4b06b0]{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 2.75862: +(3 x 3)[0xaaaafc4c4b00]{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)[0xaaaafc4c54a0]{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 1.08163: +(3 x 3)[0xaaaafc4d1cb0]{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 ! @@ -9508,10 +9505,10 @@ ./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 codethink04-arm64 +running on i-capture-the-hostname Built without the MKL. ( ! ./rsbtest --unrecognized-option-triggers-abort ) -running on codethink04-arm64 +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 ) @@ -9520,7 +9517,7 @@ ( ! ./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 codethink04-arm64 +running on i-capture-the-hostname Will not invoke autotuning routine. Benchmark will sample for at most 0.01 s Built without render support! @@ -9572,7 +9569,7 @@ 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/aarch64-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/aarch64-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/aarch64-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/aarch64-linux-gnu/librsb.so.0.0.0 libtool: install: (cd /build/reproducible-path/librsb-1.3.0.2+dfsg/debian/tmp/usr/lib/aarch64-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/aarch64-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; }; }) @@ -9582,7 +9579,7 @@ libtool: install: ranlib /build/reproducible-path/librsb-1.3.0.2+dfsg/debian/tmp/usr/lib/aarch64-linux-gnu/librsb.a libtool: warning: remember to run 'libtool --finish /usr/lib/aarch64-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/aarch64-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' @@ -9710,11 +9707,11 @@ dh_md5sums dh_builddeb dpkg-deb: building package 'librsb0t64' in '../librsb0t64_1.3.0.2+dfsg-6.1_arm64.deb'. -dpkg-deb: building package 'librsb-tools-dbgsym' in '../librsb-tools-dbgsym_1.3.0.2+dfsg-6.1_arm64.deb'. -dpkg-deb: building package 'librsb-dev' in '../librsb-dev_1.3.0.2+dfsg-6.1_arm64.deb'. dpkg-deb: building package 'librsb0t64-dbgsym' in '../librsb0t64-dbgsym_1.3.0.2+dfsg-6.1_arm64.deb'. -dpkg-deb: building package 'librsb-doc' in '../librsb-doc_1.3.0.2+dfsg-6.1_all.deb'. +dpkg-deb: building package 'librsb-dev' in '../librsb-dev_1.3.0.2+dfsg-6.1_arm64.deb'. dpkg-deb: building package 'librsb-tools' in '../librsb-tools_1.3.0.2+dfsg-6.1_arm64.deb'. +dpkg-deb: building package 'librsb-tools-dbgsym' in '../librsb-tools-dbgsym_1.3.0.2+dfsg-6.1_arm64.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_arm64.buildinfo dpkg-genchanges --build=binary -O../librsb_1.3.0.2+dfsg-6.1_arm64.changes dpkg-genchanges: info: binary-only upload (no source code included) @@ -9723,12 +9720,14 @@ 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/2591390/tmp/hooks/B01_cleanup starting +I: user script /srv/workspace/pbuilder/2591390/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/1272415 and its subdirectories -I: Current time: Wed May 15 16:04:06 -12 2024 -I: pbuilder-time-stamp: 1715832246 +I: removing directory /srv/workspace/pbuilder/2591390 and its subdirectories +I: Current time: Thu Jun 19 00:45:30 +14 2025 +I: pbuilder-time-stamp: 1750243530