Diff of the two buildlogs: -- --- b1/build.log 2024-12-04 07:49:30.408872011 +0000 +++ b2/build.log 2024-12-04 08:06:59.361472967 +0000 @@ -1,6 +1,6 @@ I: pbuilder: network access will be disabled during build -I: Current time: Tue Dec 3 19:35:34 -12 2024 -I: pbuilder-time-stamp: 1733297734 +I: Current time: Wed Jan 7 04:12:32 +14 2026 +I: pbuilder-time-stamp: 1767708752 I: Building the build Environment I: extracting base tarball [/var/cache/pbuilder/trixie-reproducible-base.tgz] I: copying local configuration @@ -30,53 +30,85 @@ dpkg-source: info: applying auto-gitignore I: Not using root during the build. I: Installing the build-deps -I: user script /srv/workspace/pbuilder/6877/tmp/hooks/D02_print_environment starting +I: user script /srv/workspace/pbuilder/13472/tmp/hooks/D01_modify_environment starting +debug: Running on infom08-i386. +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 Jan 6 14:12 /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/13472/tmp/hooks/D01_modify_environment finished +I: user script /srv/workspace/pbuilder/13472/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='i386' - DEBIAN_FRONTEND='noninteractive' - DEB_BUILD_OPTIONS='buildinfo=+all reproducible=+all parallel=6 ' - DISTRIBUTION='trixie' - HOME='/root' - HOST_ARCH='i386' + 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]="32" [3]="1" [4]="release" [5]="i686-pc-linux-gnu") + BASH_VERSION='5.2.32(1)-release' + BUILDDIR=/build/reproducible-path + BUILDUSERGECOS='second user,second room,second work-phone,second home-phone,second other' + BUILDUSERNAME=pbuilder2 + BUILD_ARCH=i386 + DEBIAN_FRONTEND=noninteractive + DEB_BUILD_OPTIONS='buildinfo=+all reproducible=+all parallel=5 ' + DIRSTACK=() + DISTRIBUTION=trixie + EUID=0 + FUNCNAME=([0]="Echo" [1]="main") + GROUPS=() + HOME=/root + HOSTNAME=i-capture-the-hostname + HOSTTYPE=i686 + HOST_ARCH=i386 IFS=' ' - INVOCATION_ID='8fc1b7279c9441838fd6289e779c479a' - LANG='C' - LANGUAGE='en_US:en' - LC_ALL='C' - LD_LIBRARY_PATH='/usr/lib/libeatmydata' - LD_PRELOAD='libeatmydata.so' - 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='6877' - PS1='# ' - PS2='> ' + INVOCATION_ID=9f0c222ad46b458f98332a4eb6cc5835 + LANG=C + LANGUAGE=de_CH:de + LC_ALL=C + LD_LIBRARY_PATH=/usr/lib/libeatmydata + LD_PRELOAD=libeatmydata.so + MACHTYPE=i686-pc-linux-gnu + MAIL=/var/mail/root + OPTERR=1 + OPTIND=1 + OSTYPE=linux-gnu + PATH=/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/i/capture/the/path + PBCURRENTCOMMANDLINEOPERATION=build + PBUILDER_OPERATION=build + PBUILDER_PKGDATADIR=/usr/share/pbuilder + PBUILDER_PKGLIBDIR=/usr/lib/pbuilder + PBUILDER_SYSCONFDIR=/etc + PIPESTATUS=([0]="0") + POSIXLY_CORRECT=y + PPID=13472 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.Q83olr0f/pbuilderrc_2yS8 --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.Q83olr0f/b1 --logfile b1/build.log librsb_1.3.0.2+dfsg-7.dsc' - SUDO_GID='111' - SUDO_UID='104' - SUDO_USER='jenkins' - TERM='unknown' - TZ='/usr/share/zoneinfo/Etc/GMT+12' - USER='root' - _='/usr/bin/systemd-run' + 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.Q83olr0f/pbuilderrc_9GuF --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.Q83olr0f/b2 --logfile b2/build.log librsb_1.3.0.2+dfsg-7.dsc' + SUDO_GID=111 + SUDO_UID=104 + SUDO_USER=jenkins + TERM=unknown + TZ=/usr/share/zoneinfo/Etc/GMT-14 + UID=0 + USER=root + _='I: set' I: uname -a - Linux infom07-i386 6.1.0-28-amd64 #1 SMP PREEMPT_DYNAMIC Debian 6.1.119-1 (2024-11-22) x86_64 GNU/Linux + Linux i-capture-the-hostname 6.11.5+bpo-amd64 #1 SMP PREEMPT_DYNAMIC Debian 6.11.5-1~bpo12+1 (2024-11-11) x86_64 GNU/Linux I: ls -l /bin - lrwxrwxrwx 1 root root 7 Nov 22 14:40 /bin -> usr/bin -I: user script /srv/workspace/pbuilder/6877/tmp/hooks/D02_print_environment finished + lrwxrwxrwx 1 root root 7 Nov 22 2024 /bin -> usr/bin +I: user script /srv/workspace/pbuilder/13472/tmp/hooks/D02_print_environment finished -> Attempting to satisfy build-dependencies -> Creating pbuilder-satisfydepends-dummy package Package: pbuilder-satisfydepends-dummy @@ -295,7 +327,7 @@ Get: 171 http://deb.debian.org/debian trixie/main i386 libltdl-dev i386 2.4.7-8 [167 kB] Get: 172 http://deb.debian.org/debian trixie/main i386 libhwloc-dev i386 2.11.2-1 [271 kB] Get: 173 http://deb.debian.org/debian trixie/main i386 zlib1g-dev i386 1:1.3.dfsg+really1.3.1-1+b1 [916 kB] -Fetched 385 MB in 3s (131 MB/s) +Fetched 385 MB in 4s (107 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 ... 19956 files and directories currently installed.) @@ -873,8 +905,8 @@ Setting up tzdata (2024b-3) ... Current default time zone: 'Etc/UTC' -Local time is now: Wed Dec 4 07:36:21 UTC 2024. -Universal Time is now: Wed Dec 4 07:36:21 UTC 2024. +Local time is now: Tue Jan 6 14:13:25 UTC 2026. +Universal Time is now: Tue Jan 6 14:13:25 UTC 2026. Run 'dpkg-reconfigure tzdata' if you wish to change it. Setting up libfontenc1:i386 (1:1.1.8-1+b1) ... @@ -1037,7 +1069,11 @@ 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-7_source.changes +I: user script /srv/workspace/pbuilder/13472/tmp/hooks/A99_set_merged_usr starting +Not re-configuring usrmerge for trixie +I: user script /srv/workspace/pbuilder/13472/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-7_source.changes dpkg-buildpackage: info: source package librsb dpkg-buildpackage: info: source version 1.3.0.2+dfsg-7 dpkg-buildpackage: info: source distribution unstable @@ -1057,62 +1093,62 @@ dh binary dh_update_autotools_config 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'. @@ -1154,90 +1190,90 @@ 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' @@ -1420,7 +1456,7 @@ 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 @@ -1537,7 +1573,7 @@ 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 @@ -1559,7 +1595,7 @@ 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=i686-linux-gnu' '--includedir=${prefix}/include' '--mandir=${prefix}/share/man' '--infodir=${prefix}/share/info' '--sysconfdir=/etc' '--localstatedir=/var' '--disable-silent-rules' '--libdir=${prefix}/lib/i386-linux-gnu' '--runstatedir=/run' '--disable-maintainer-mode' '--disable-dependency-tracking' '--with-hwloc' '--enable-matrix-types=blas' '--with-zlib=-lz' '--enable-doc-build' '--enable-fortran-module-install' '--enable-extra-patches' '--enable-pkg-config-install' '--disable-extra-patches' 'build_alias=i686-linux-gnu' 'CFLAGS=-g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -pipe' 'CXXFLAGS=-g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security' 'BASH=/bin/bash' --cache-file=/dev/null --srcdir=. +configure: running /bin/sh ./configure --disable-option-checking '--prefix=/usr' '--build=i686-linux-gnu' '--includedir=${prefix}/include' '--mandir=${prefix}/share/man' '--infodir=${prefix}/share/info' '--sysconfdir=/etc' '--localstatedir=/var' '--disable-silent-rules' '--libdir=${prefix}/lib/i386-linux-gnu' '--runstatedir=/run' '--disable-maintainer-mode' '--disable-dependency-tracking' '--with-hwloc' '--enable-matrix-types=blas' '--with-zlib=-lz' '--enable-doc-build' '--enable-fortran-module-install' '--enable-extra-patches' '--enable-pkg-config-install' '--disable-extra-patches' 'build_alias=i686-linux-gnu' 'CFLAGS=-g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -pipe' 'CXXFLAGS=-g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security' '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 @@ -1681,7 +1717,7 @@ 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 @@ -1690,7 +1726,7 @@ 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=i686-linux-gnu' '--includedir=${prefix}/include' '--mandir=${prefix}/share/man' '--infodir=${prefix}/share/info' '--sysconfdir=/etc' '--localstatedir=/var' '--disable-silent-rules' '--libdir=${prefix}/lib/i386-linux-gnu' '--runstatedir=/run' '--disable-maintainer-mode' '--disable-dependency-tracking' '--with-hwloc' '--enable-matrix-types=blas' '--with-zlib=-lz' '--enable-doc-build' '--enable-fortran-module-install' '--enable-extra-patches' '--enable-pkg-config-install' '--disable-extra-patches' 'build_alias=i686-linux-gnu' 'CFLAGS=-g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -pipe' 'CXXFLAGS=-g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security' 'BASH=/bin/bash' --cache-file=/dev/null --srcdir=. +configure: running /bin/sh ./configure --disable-option-checking '--prefix=/usr' '--build=i686-linux-gnu' '--includedir=${prefix}/include' '--mandir=${prefix}/share/man' '--infodir=${prefix}/share/info' '--sysconfdir=/etc' '--localstatedir=/var' '--disable-silent-rules' '--libdir=${prefix}/lib/i386-linux-gnu' '--runstatedir=/run' '--disable-maintainer-mode' '--disable-dependency-tracking' '--with-hwloc' '--enable-matrix-types=blas' '--with-zlib=-lz' '--enable-doc-build' '--enable-fortran-module-install' '--enable-extra-patches' '--enable-pkg-config-install' '--disable-extra-patches' 'build_alias=i686-linux-gnu' 'CFLAGS=-g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -pipe' 'CXXFLAGS=-g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security' '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 @@ -1799,7 +1835,7 @@ 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 @@ -1809,7 +1845,7 @@ 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=i686-linux-gnu' '--includedir=${prefix}/include' '--mandir=${prefix}/share/man' '--infodir=${prefix}/share/info' '--sysconfdir=/etc' '--localstatedir=/var' '--disable-silent-rules' '--libdir=${prefix}/lib/i386-linux-gnu' '--runstatedir=/run' '--disable-maintainer-mode' '--disable-dependency-tracking' '--with-hwloc' '--enable-matrix-types=blas' '--with-zlib=-lz' '--enable-doc-build' '--enable-fortran-module-install' '--enable-extra-patches' '--enable-pkg-config-install' '--disable-extra-patches' 'build_alias=i686-linux-gnu' 'CFLAGS=-g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -pipe' 'CXXFLAGS=-g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security' 'BASH=/bin/bash' --cache-file=/dev/null --srcdir=. +configure: running /bin/sh ./configure --disable-option-checking '--prefix=/usr' '--build=i686-linux-gnu' '--includedir=${prefix}/include' '--mandir=${prefix}/share/man' '--infodir=${prefix}/share/info' '--sysconfdir=/etc' '--localstatedir=/var' '--disable-silent-rules' '--libdir=${prefix}/lib/i386-linux-gnu' '--runstatedir=/run' '--disable-maintainer-mode' '--disable-dependency-tracking' '--with-hwloc' '--enable-matrix-types=blas' '--with-zlib=-lz' '--enable-doc-build' '--enable-fortran-module-install' '--enable-extra-patches' '--enable-pkg-config-install' '--disable-extra-patches' 'build_alias=i686-linux-gnu' 'CFLAGS=-g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -pipe' 'CXXFLAGS=-g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security' '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 @@ -1920,7 +1956,7 @@ 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 @@ -1952,7 +1988,7 @@ ARFLAGS : cru M4 : m4 MAKE : gmake - BASH : /bin/bash + BASH : /bin/sh OCTAVE : false DOXYGEN : doxygen HELP2MAN : help2man @@ -2001,30 +2037,30 @@ blhc: ignore-line-regexp: ^.*CC.*: gcc blhc: ignore-line-regexp: ^.*LD.*: /usr/bin/ld.* dh_auto_build - make -j6 + make -j5 make[2]: Entering directory '/build/reproducible-path/librsb-1.3.0.2+dfsg' gmake all-recursive gmake[3]: Entering directory '/build/reproducible-path/librsb-1.3.0.2+dfsg' Making all in librsbpp gmake[4]: Entering directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp' g++ -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -DRSBPP_HAS_RSB_H=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -DRSBPP_HAS_RSB_H=1 -Wl,-z -Wl,relro -o rsbct rsbct.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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' @@ -2043,42 +2079,32 @@ gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_nounroll_la-rsb_stropts.lo `test -f 'rsb_stropts.c' || echo './'`rsb_stropts.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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_stropts.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_stropts.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_stropts.c -o librsb_nounroll_la-rsb_stropts.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_vb.lo `test -f 'rsb_krnl_vb.c' || echo './'`rsb_krnl_vb.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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_strmif.c -o librsb_nounroll_la-rsb_strmif.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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_nounroll_la-rsb_strmif.lo `test -f 'rsb_strmif.c' || echo './'`rsb_strmif.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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_strmif.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_strmif.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_vb.lo `test -f 'rsb_krnl_vb.c' || echo './'`rsb_krnl_vb.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_lb.lo `test -f 'rsb_krnl_lb.c' || echo './'`rsb_krnl_lb.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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_krnl_vb.c -o librsb_nounroll_la-rsb_krnl_vb.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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl.lo `test -f 'rsb_krnl.c' || echo './'`rsb_krnl.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_nounroll_la-rsb_bench.lo `test -f 'rsb_bench.c' || echo './'`rsb_bench.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_nounroll_la-rsb_bench.lo `test -f 'rsb_bench.c' || echo './'`rsb_bench.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_nounroll_la-rsb_mergesort.lo `test -f 'rsb_mergesort.c' || echo './'`rsb_mergesort.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_nounroll_la-rsb_mergesort.lo `test -f 'rsb_mergesort.c' || echo './'`rsb_mergesort.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_mergesort.c -o librsb_nounroll_la-rsb_mergesort.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_bcss_l.lo `test -f 'rsb_krnl_bcss_l.c' || echo './'`rsb_krnl_bcss_l.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 -c rsb_krnl_bcss_l.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_bcss_l.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 -c rsb_krnl_bcss_l.c -o librsb_nounroll_la-rsb_krnl_bcss_l.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_krnl_bcss_u.c -o librsb_nounroll_la-rsb_krnl_bcss_u.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 -c rsb_bench.c -o librsb_nounroll_la-rsb_bench.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_permute.c -o librsb_nounroll_la-rsb_permute.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_krnl_bcss_spmv_u.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_bcss_spmv_u.o 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:"", @@ -2097,10 +2123,18 @@ | ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 32 | __va_arg_pack ()); | ~~~~~~~~~~~~~~~~~ -/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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_bcss_l.lo `test -f 'rsb_krnl_bcss_l.c' || echo './'`rsb_krnl_bcss_l.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 -c rsb_krnl_bcss_l.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_bcss_l.o +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 -c rsb_krnl_bcss_l.c -o librsb_nounroll_la-rsb_krnl_bcss_l.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_bcss_u.lo `test -f 'rsb_krnl_bcss_u.c' || echo './'`rsb_krnl_bcss_u.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_nounroll_la-rsb_krnl_bcss_misc_u.lo `test -f 'rsb_krnl_bcss_misc_u.c' || echo './'`rsb_krnl_bcss_misc_u.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_krnl_bcoo_spmv_u.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_bcoo_spmv_u.o 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:"", @@ -2131,215 +2165,217 @@ 32 | __va_arg_pack ()); | ~~~~~~~~~~~~~~~~~ libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 -c rsb_krnl.c -o librsb_nounroll_la-rsb_krnl.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_krnl_bcoo_spmv_u.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_bcoo_spmv_u.o +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_krnl_bcss.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_krnl_bcss.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 -c rsb_krnl_bcss.c -o librsb_nounroll_la-rsb_krnl_bcss.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_spmv.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_spmv.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_spmv.c -o librsb_nounroll_la-rsb_spmv.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_merge.c -o librsb_nounroll_la-rsb_merge.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_nounroll_la-rsb_util.lo `test -f 'rsb_util.c' || echo './'`rsb_util.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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/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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_nounroll_la-rsb_util.lo `test -f 'rsb_util.c' || echo './'`rsb_util.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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_util.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_util.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_spgemm_csr.c -fPIC -DPIC -o .libs/librsb_nounroll_la-rsb_spgemm_csr.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_nounroll_la-rsb_spsum_misc.lo `test -f 'rsb_spsum_misc.c' || echo './'`rsb_spsum_misc.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_nounroll_la-rsb_prec.lo `test -f 'rsb_prec.c' || echo './'`rsb_prec.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 -c rsb_prec.c -o librsb_nounroll_la-rsb_prec.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_base_la-rsb_is.lo `test -f 'rsb_is.c' || echo './'`rsb_is.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 -c rsb_is.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_is.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 -c rsb_is.c -o librsb_base_la-rsb_is.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_util.c -o librsb_nounroll_la-rsb_util.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 -Wformat -Werror=format-security -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 -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_mio.c -o librsb_base_la-rsb_mio.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_bio.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_bio.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 -c rsb_bio.c -o librsb_base_la-rsb_bio.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_base_la-rsb_get.lo `test -f 'rsb_get.c' || echo './'`rsb_get.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_get.c -o librsb_base_la-rsb_get.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_coo.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_coo.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_get.c -o librsb_base_la-rsb_get.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_coo.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_coo.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_base_la-rsb_coo_check.lo `test -f 'rsb_coo_check.c' || echo './'`rsb_coo_check.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_csr.c -o librsb_base_la-rsb_csr.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_base_la-rsb_coo_check.lo `test -f 'rsb_coo_check.c' || echo './'`rsb_coo_check.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_coo_check.c -o librsb_base_la-rsb_coo_check.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 -c rsb_util.c -o librsb_nounroll_la-rsb_util.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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_base_la-rsb_coo_symm.lo `test -f 'rsb_coo_symm.c' || echo './'`rsb_coo_symm.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_coo_symm.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_coo_symm.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_coo_symm.c -o librsb_base_la-rsb_coo_symm.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_coo_symm.c -o librsb_base_la-rsb_coo_symm.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_srt.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_srt.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_srt.c -o librsb_base_la-rsb_srt.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_base_la-rsb_srtp.lo `test -f 'rsb_srtp.c' || echo './'`rsb_srtp.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 -c rsb_srtp.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_srtp.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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_base_la-rsb_src.lo `test -f 'rsb_src.c' || echo './'`rsb_src.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_src.c -o librsb_base_la-rsb_src.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_base_la-rsb_clone.lo `test -f 'rsb_clone.c' || echo './'`rsb_clone.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_test_accuracy.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_test_accuracy.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_rec.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_rec.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_clone.c -o librsb_base_la-rsb_clone.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_rec.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_rec.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_render.c -o librsb_base_la-rsb_render.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_msort_up.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_msort_up.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 -c rsb_rec.c -o librsb_base_la-rsb_rec.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_eps.c -o librsb_base_la-rsb_eps.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_base_la-rsb_sys.lo `test -f 'rsb_sys.c' || echo './'`rsb_sys.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 -c rsb_sys.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_sys.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_sys.c -o librsb_base_la-rsb_sys.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 -c rsb_blas_stuff.c -o librsb_base_la-rsb_blas_stuff.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 -c rsb_gen.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_gen.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_perf.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_perf.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_rsb.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_rsb.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_gen.c -o librsb_base_la-rsb_gen.o >/dev/null 2>&1 +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_rsb.c -o librsb_base_la-rsb_rsb.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_base_la-rsb_err.lo `test -f 'rsb_err.c' || echo './'`rsb_err.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_err.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_err.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_rsb.c -o librsb_base_la-rsb_rsb.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_base_la-rsb_tune.lo `test -f 'rsb_tune.c' || echo './'`rsb_tune.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_tune.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_tune.o +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_do.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_do.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_base_la-rsb_internals.lo `test -f 'rsb_internals.c' || echo './'`rsb_internals.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_do.c -o librsb_base_la-rsb_do.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_base_la-rsb_garbage.lo `test -f 'rsb_garbage.c' || echo './'`rsb_garbage.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_internals.c -o librsb_base_la-rsb_internals.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_garbage.c -o librsb_base_la-rsb_garbage.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_base_la-rsb_mmio.lo `test -f 'rsb_mmio.c' || echo './'`rsb_mmio.c libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_mmio.c -o librsb_base_la-rsb_mmio.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_base_la-rsb_partition.lo `test -f 'rsb_partition.c' || echo './'`rsb_partition.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_partition.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_partition.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_base_la-rsb_mbw.lo `test -f 'rsb_mbw.c' || echo './'`rsb_mbw.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_partition.c -o librsb_base_la-rsb_partition.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_base_la-rsb_limiter.lo `test -f 'rsb_limiter.c' || echo './'`rsb_limiter.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_mbw.c -o librsb_base_la-rsb_mbw.o >/dev/null 2>&1 -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 -c rsb_fpb.c -o librsb_base_la-rsb_fpb.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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_base_la-rsb_spgemm.lo `test -f 'rsb_spgemm.c' || echo './'`rsb_spgemm.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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_base_la-rsb_fpb.lo `test -f 'rsb_fpb.c' || echo './'`rsb_fpb.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 -c rsb_fpb.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_fpb.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_spgemm.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_spgemm.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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_base_la-rsb_spsum.lo `test -f 'rsb_spsum.c' || echo './'`rsb_spsum.c -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_spsum.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_spsum.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_mbw.c -o librsb_base_la-rsb_mbw.o >/dev/null 2>&1 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_base_la-rsb_lock.lo `test -f 'rsb_lock.c' || echo './'`rsb_lock.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_spsum.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_spsum.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_base_la-rsb_spsv.lo `test -f 'rsb_spsv.c' || echo './'`rsb_spsv.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_base_la-rsb_lock.lo `test -f 'rsb_lock.c' || echo './'`rsb_lock.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_lock.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_lock.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 -c rsb_spsv.c -o librsb_base_la-rsb_spsv.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_dump.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_dump.o +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_init.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_init.o -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_base_la-rsb_asm.lo `test -f 'rsb_asm.c' || echo './'`rsb_asm.c -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_dump.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_dump.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_cpmv.c -o librsb_base_la-rsb_cpmv.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_cpmv.c -o librsb_base_la-rsb_cpmv.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_base_la-rsb_asm.lo `test -f 'rsb_asm.c' || echo './'`rsb_asm.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_base_la-rsb_user.lo `test -f 'rsb_user.c' || echo './'`rsb_user.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c -o librsb_base_la-rsb_coo2rec.lo `test -f 'rsb_coo2rec.c' || echo './'`rsb_coo2rec.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_coo2rec.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_coo2rec.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_rec2csr.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_rec2csr.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_rec2coo.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_rec2coo.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_rec2csr.c -o librsb_base_la-rsb_rec2csr.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 -Wformat -Werror=format-security -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 -pipe -fopenmp -c -o rsb_blas_sparse.lo rsb_blas_sparse.F90 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 -c -o rsb_libspblas_handle.lo rsb_libspblas_handle.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_csr2coo.c -fPIC -DPIC -o .libs/librsb_base_la-rsb_csr2coo.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 -pipe -fopenmp -c rsb_blas_sparse.F90 -fPIC -o .libs/rsb_blas_sparse.o -libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 -c rsb_libspblas_handle.c -fPIC -DPIC -o .libs/rsb_libspblas_handle.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 -Wformat -Werror=format-security -O3 -std=c99 -c rsb_coo2rec.c -o librsb_base_la-rsb_coo2rec.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 -pipe -fopenmp -c -o rsb_blas_sparse.lo rsb_blas_sparse.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 -pipe -fopenmp -c rsb_blas_sparse.F90 -fPIC -o .libs/rsb_blas_sparse.o libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 -c rsb_csr2coo.c -o librsb_base_la-rsb_csr2coo.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 -c -o rsb_libspblas.lo rsb_libspblas.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 -c -o rsb_libspblas_handle.lo rsb_libspblas_handle.c +libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 -c rsb_libspblas_handle.c -fPIC -DPIC -o .libs/rsb_libspblas_handle.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 -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 -c rsb_libspblas_handle.c -o rsb_libspblas_handle.o >/dev/null 2>&1 -gfortran -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -pipe -fopenmp -c -o rsb_blas_sparse.o rsb_blas_sparse.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 -pipe -fopenmp -c rsb_blas_sparse.F90 -o rsb_blas_sparse.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=link gcc -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-linux-gnu/14/../../.. -lgfortran -lm -lquadmath +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 -pipe -fopenmp -c -o rsb_blas_sparse.o rsb_blas_sparse.F90 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 -c rsb_libspblas.c -o rsb_libspblas.o >/dev/null 2>&1 +/bin/sh ./libtool --tag=CC --mode=link gcc -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-linux-gnu/14/../../.. -lgfortran -lm -lquadmath libtool: warning: '-version-info' is ignored for programs libtool: link: gcc -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 -Wl,-z -Wl,relro -o ch2icfb ch2icfb-ch2icfb.o -fopenmp -lhwloc -lz -L/usr/lib/gcc/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-linux-gnu/14/../../.. -lgfortran -lm -lquadmath -fopenmp +/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 -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-linux-gnu/14/../../.. -lgfortran -lm -lquadmath +libtool: warning: '-version-info/-version-number' is ignored for convenience libraries 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 -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 -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 -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 +/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 -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-linux-gnu/14/../../.. -lgfortran -lm -lquadmath 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 -pipe -fopenmp -c -o rsb.o rsb.F90 -/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 -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-linux-gnu/14/../../.. -lgfortran -lm -lquadmath -/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 -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-linux-gnu/14/../../.. -lgfortran -lm -lquadmath -libtool: warning: '-version-info/-version-number' is ignored for convenience libraries +/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 -pipe -fopenmp -c -o rsb.lo rsb.F90 libtool: warning: '-version-info/-version-number' is ignored for convenience libraries libtool: link: ar cr .libs/librsb_spblas.a .libs/rsb_libspblas_handle.o .libs/rsb_libspblas.o libtool: link: ranlib .libs/librsb_spblas.a libtool: link: ( cd ".libs" && rm -f "librsb_spblas.la" && ln -s "../librsb_spblas.la" "librsb_spblas.la" ) libtool: link: ar cr .libs/librsb_base.a .libs/librsb_base_la-rsb_is.o .libs/librsb_base_la-rsb_mio.o .libs/librsb_base_la-rsb_op.o .libs/librsb_base_la-rsb_bio.o .libs/librsb_base_la-rsb_get.o .libs/librsb_base_la-rsb_set.o .libs/librsb_base_la-rsb_coo.o .libs/librsb_base_la-rsb_csr.o .libs/librsb_base_la-rsb_coo_check.o .libs/librsb_base_la-rsb_coo_symm.o .libs/librsb_base_la-rsb_idx.o .libs/librsb_base_la-rsb_srt.o .libs/librsb_base_la-rsb_srtp.o .libs/librsb_base_la-rsb_src.o .libs/librsb_base_la-rsb_test_accuracy.o .libs/librsb_base_la-rsb_clone.o .libs/librsb_base_la-rsb_rec.o .libs/librsb_base_la-rsb_render.o .libs/librsb_base_la-rsb_eps.o .libs/librsb_base_la-rsb_msort_up.o .libs/librsb_base_la-rsb_sys.o .libs/librsb_base_la-rsb_blas_stuff.o .libs/librsb_base_la-rsb_gen.o .libs/librsb_base_la-rsb_perf.o .libs/librsb_base_la-rsb_rsb.o .libs/librsb_base_la-rsb_err.o .libs/librsb_base_la-rsb_tune.o .libs/librsb_base_la-rsb_do.o .libs/librsb_base_la-rsb_internals.o .libs/librsb_base_la-rsb_garbage.o .libs/librsb_base_la-rsb_mmio.o .libs/librsb_base_la-rsb_partition.o .libs/librsb_base_la-rsb_mbw.o .libs/librsb_base_la-rsb_limiter.o .libs/librsb_base_la-rsb_fpb.o .libs/librsb_base_la-rsb_spgemm.o .libs/librsb_base_la-rsb_spsum.o .libs/librsb_base_la-rsb_spsv.o .libs/librsb_base_la-rsb_lock.o .libs/librsb_base_la-rsb_swt.o .libs/librsb_base_la-rsb_init.o .libs/librsb_base_la-rsb_dump.o .libs/librsb_base_la-rsb_cpmv.o .libs/librsb_base_la-rsb_asm.o .libs/librsb_base_la-rsb_user.o .libs/librsb_base_la-rsb_coo2rec.o .libs/librsb_base_la-rsb_rec2coo.o .libs/librsb_base_la-rsb_rec2csr.o .libs/librsb_base_la-rsb_csr2coo.o .libs/rsb_blas_sparse.o +libtool: 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 -pipe -fopenmp -c rsb.F90 -fPIC -o .libs/rsb.o libtool: link: ranlib .libs/librsb_base.a libtool: link: ( cd ".libs" && rm -f "librsb_base.la" && ln -s "../librsb_base.la" "librsb_base.la" ) +libtool: compile: 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 -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 -fno-unroll-loops -fopenmp -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-linux-gnu/14/../../.. -lgfortran -lm -lquadmath +/bin/sh ./libtool --tag=CC --mode=link gcc -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-linux-gnu/14/../../.. -lgfortran -lm -lquadmath libtool: warning: '-version-info/-version-number' is ignored for convenience libraries libtool: link: ar cr .libs/librsb_nounroll.a .libs/librsb_nounroll_la-rsb_stropts.o .libs/librsb_nounroll_la-rsb_strmif.o .libs/librsb_nounroll_la-rsb_unroll.o .libs/librsb_nounroll_la-rsb_krnl_vb.o .libs/librsb_nounroll_la-rsb_krnl_lb.o .libs/librsb_nounroll_la-rsb_krnl.o .libs/librsb_nounroll_la-rsb_bench.o .libs/librsb_nounroll_la-rsb_mergesort.o .libs/librsb_nounroll_la-rsb_permute.o .libs/librsb_nounroll_la-rsb_krnl_bcss_l.o .libs/librsb_nounroll_la-rsb_krnl_bcss_u.o .libs/librsb_nounroll_la-rsb_krnl_bcss_spsv_u.o .libs/librsb_nounroll_la-rsb_krnl_bcss_spmv_u.o .libs/librsb_nounroll_la-rsb_krnl_bcss_misc_u.o .libs/librsb_nounroll_la-rsb_krnl_bcoo_spmv_u.o .libs/librsb_nounroll_la-rsb_krnl_bcss.o .libs/librsb_nounroll_la-rsb_spmv.o .libs/librsb_nounroll_la-rsb_merge.o .libs/librsb_nounroll_la-rsb_ompio.o .libs/librsb_nounroll_la-rsb_util.o .libs/librsb_nounroll_la-rsb_spgemm_csr.o .libs/librsb_nounroll_la-rsb_spsum_misc.o .libs/librsb_nounroll_la-rsb_prec.o libtool: link: ranlib .libs/librsb_nounroll.a libtool: link: ( cd ".libs" && rm -f "librsb_nounroll.la" && ln -s "../librsb_nounroll.la" "librsb_nounroll.la" ) -/bin/bash ./libtool --tag=CC --mode=link gcc -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 -no-undefined -version-info 0:0:0 -Wl,-z,relro -o librsb.la -rpath /usr/lib/i386-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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-linux-gnu/14/../../.. -lgfortran -lm -lquadmath +/bin/sh ./libtool --tag=CC --mode=link gcc -g -O2 -Werror=implicit-function-declaration -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 -no-undefined -version-info 0:0:0 -Wl,-z,relro -o librsb.la -rpath /usr/lib/i386-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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-linux-gnu/14/../../.. -lgfortran -lm -lquadmath libtool: link: gcc -shared -fPIC -DPIC .libs/rsb.o -Wl,--whole-archive ./.libs/librsb_nounroll.a ./.libs/librsb_base.a ./.libs/librsb_spblas.a /build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp/.libs/librsbpp.a -Wl,--no-whole-archive -L/usr/lib/gcc/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-linux-gnu/14/../../.. -lpthread -lstdc++fs -lstdc++ -lhwloc -lz -lgfortran -lm -lquadmath -g -O2 -fstack-protector-strong -O3 -Wl,-z -Wl,relro -fopenmp -fopenmp -Wl,-soname -Wl,librsb.so.0 -o .libs/librsb.so.0.0.0 libtool: link: (cd ".libs" && rm -f "librsb.so.0" && ln -s "librsb.so.0.0.0" "librsb.so.0") libtool: link: (cd ".libs" && rm -f "librsb.so" && ln -s "librsb.so.0.0.0" "librsb.so") @@ -2351,7 +2387,7 @@ 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 -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-linux-gnu/14/../../.. -lgfortran -lm -lquadmath +/bin/sh ./libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-linux-gnu/14/../../.. -lgfortran -lm -lquadmath libtool: warning: '-version-info' is ignored for programs libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-linux-gnu/14/../../.. -lgfortran -lm -lquadmath -fopenmp gmake[4]: Leaving directory '/build/reproducible-path/librsb-1.3.0.2+dfsg' @@ -2368,26 +2404,26 @@ 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 -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 -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-linux-gnu/14/../../.. -lgfortran -lm -lquadmath -/bin/bash ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-linux-gnu/14/../../.. -lgfortran -lm -lquadmath -/bin/bash ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-linux-gnu/14/../../.. -lgfortran -lm -lquadmath -/bin/bash ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-linux-gnu/14/../../.. -lgfortran -lm -lquadmath +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-linux-gnu/14/../../.. -lgfortran -lm -lquadmath +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-linux-gnu/14/../../.. -lgfortran -lm -lquadmath libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-linux-gnu/14/../../.. -lgfortran -lm -lquadmath -fopenmp -/bin/bash ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-linux-gnu/14/../../.. -lgfortran -lm -lquadmath -/bin/bash ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-linux-gnu/14/../../.. -lgfortran -lm -lquadmath +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-linux-gnu/14/../../.. -lgfortran -lm -lquadmath +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-linux-gnu/14/../../.. -lgfortran -lm -lquadmath +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-linux-gnu/14/../../.. -lgfortran -lm -lquadmath libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-linux-gnu/14/../../.. -lgfortran -lm -lquadmath -fopenmp +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-linux-gnu/14/../../.. -lgfortran -lm -lquadmath libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-linux-gnu/14/../../.. -lgfortran -lm -lquadmath -fopenmp libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-linux-gnu/14/../../.. -lgfortran -lm -lquadmath -fopenmp -/bin/bash ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-linux-gnu/14/../../.. -lgfortran -lm -lquadmath -/bin/bash ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-linux-gnu/14/../../.. -lgfortran -lm -lquadmath libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-linux-gnu/14/../../.. -lgfortran -lm -lquadmath -fopenmp -/bin/bash ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-linux-gnu/14/../../.. -lgfortran -lm -lquadmath +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-linux-gnu/14/../../.. -lgfortran -lm -lquadmath +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-linux-gnu/14/../../.. -lgfortran -lm -lquadmath +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-linux-gnu/14/../../.. -lgfortran -lm -lquadmath libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-linux-gnu/14/../../.. -lgfortran -lm -lquadmath -fopenmp -/bin/bash ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-linux-gnu/14/../../.. -lgfortran -lm -lquadmath -libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-linux-gnu/14/../../.. -lgfortran -lm -lquadmath -fopenmp +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-linux-gnu/14/../../.. -lgfortran -lm -lquadmath +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-linux-gnu/14/../../.. -lgfortran -lm -lquadmath libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-linux-gnu/14/../../.. -lgfortran -lm -lquadmath -fopenmp +libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-linux-gnu/14/../../.. -lgfortran -lm -lquadmath -fopenmp libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-linux-gnu/14/../../.. -lgfortran -lm -lquadmath -fopenmp -/bin/bash ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-linux-gnu/14/../../.. -lgfortran -lm -lquadmath libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-linux-gnu/14/../../.. -lgfortran -lm -lquadmath -fopenmp libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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/i686-linux-gnu/14 -L/usr/lib/gcc/i686-linux-gnu/14/../../../i386-linux-gnu -L/usr/lib/gcc/i686-linux-gnu/14/../../../../lib -L/lib/i386-linux-gnu -L/lib/../lib -L/usr/lib/i386-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/i686-linux-gnu/14/../../.. -lgfortran -lm -lquadmath -fopenmp gmake[4]: Leaving directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/examples' @@ -2408,10 +2444,10 @@ /usr/bin/mkdir -p man /usr/bin/mkdir -p man gmake makedox -SOURCE_DATE_EPOCH=1704114061 \ - 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 -SOURCE_DATE_EPOCH=1704114061 \ +SOURCE_DATE_EPOCH=1767178861 \ help2man --name="benchmark and test for librsb" --no-info ../rsbench | /usr/bin/sed 's/January //g' > man/rsbench.1 +SOURCE_DATE_EPOCH=1767178861 \ + 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 ?" warning: Tag 'HTML_TIMESTAMP' at line 1513 of file 'Doxyfile' has become obsolete. @@ -3122,13 +3158,13 @@ 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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -Wl,-z,relro -o rgt rgt-rgt.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -/bin/bash ./libtool --tag=CXX --mode=link g++ -DRSBP_NOTHROW=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -Wl,-z,relro -o rgt_ne rgt_ne-rgt.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -/bin/bash ./libtool --tag=CXX --mode=link g++ -DRSBP_NOTHROW=1 -DRSBP_WANT_REV=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -Wl,-z,relro -o rgt_rv rgt_rv-rgt.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la +/bin/sh ./libtool --tag=CXX --mode=link g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -Wl,-z,relro -o rgt_rv rgt_rv-rgt.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la libtool: link: g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -Wl,-z -Wl,relro -o .libs/rgt_rv rgt_rv-rgt.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp -/bin/bash ./libtool --tag=CXX --mode=link g++ -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 @@ -3143,24 +3179,24 @@ 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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -Wl,-z,relro -o build build.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 -Wformat -Werror=format-security -Wl,-z,relro -o assemble assemble.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la libtool: link: g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -Wl,-z -Wl,relro -o .libs/assemble assemble.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 -Wformat -Werror=format-security -Wl,-z,relro -o misc misc.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -Wl,-z,relro -o build build.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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -Wl,-z -Wl,relro -o .libs/misc misc.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp -/bin/bash ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -Wl,-z,relro -o render render.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la libtool: link: g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -Wl,-z -Wl,relro -o .libs/build build.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp -/bin/bash ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -Wl,-z,relro -o span span.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la libtool: link: g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -Wl,-z,relro -o autotune autotune.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la +/bin/sh ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -Wl,-z -Wl,relro -o .libs/render render.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp -/bin/bash ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -Wl,-z -Wl,relro -o .libs/autotune autotune.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp -/bin/bash ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -Wl,-z,relro -o mtx2bin mtx2bin.o -lstdc++fs -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -Wl,-z -Wl,relro -o .libs/bench bench.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 -Wformat -Werror=format-security -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 gmake[6]: Leaving directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib/examples' @@ -3171,7 +3207,7 @@ 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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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 -Wformat -Werror=format-security -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' @@ -3247,7 +3283,7 @@ 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 @@ -3257,15 +3293,15 @@ 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 1733298354 +# beginning run at 1767709280 # /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 -Wformat -Werror=format-security -O3 -std=c99 -# average timer granularity: 5.34e-08 s -# Will write a final performance record to file rsbench_pr__1733298354_gcc-14.2-1,4th.rpr and periodic checkpoints to rsbench_pr__1733298354_gcc-14.2-1,4th.rpr.tmp +# average timer granularity: 5.15e-08 s +# Will write a final performance record to file rsbench_pr__1767709280_gcc-14.2-1,4th.rpr and periodic checkpoints to rsbench_pr__1767709280_gcc-14.2-1,4th.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:/usr/lib/libeatmydata # env: HOSTNAME is not set # env: KMP_AFFINITY is not set @@ -3304,61 +3340,61 @@ # 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: infom07-i386 +# 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. # 3 cache levels detected Will fill struct with 50 samples... -# Memory benchmark took 9.358s +# Memory benchmark took 8.819s # auto-tuning oriented output implies times==0 iterations and sort-after-load. #pr: allocated a performance record for 8 samples (2016 bytes). # Cache block size total 16777216 bytes, per-thread 2097152 bytes -# so far, program took 9.361s 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 8.822s 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, 71494 nnz/s ) (2.19 MB/s ) -#pre-sorting (6 elements) took 0.0244319 s -#weeding duplicates (to 6 elements) took 1.90735e-06 s (and check, 2.14577e-06 s ) +# file input of A.mtx took 0.00 s (6 nnz, 64363 nnz/s ) (1.97 MB/s ) +#pre-sorting (6 elements) took 0.0153511 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 0.104s): (3 x 3)[0x56796fc0]{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 0.096s): (3 x 3)[0x58294000]{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 0.05198s; avg 0.01733s ( +/- 30.75/ 38.40 %); best 0.012s; worst 0.02398s; std dev. 0.00498 (taking best). -Reference operation time is 0.0119979 s (0.008001 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: 0.012 Mflops: 0.008) -Merge (3 -> 1 leaves) took w.c.t. of 2.098e-05s, ~8.106e-06s of computing time (of which 1.907e-06s sorting, 4.053e-06s analysis) -3 iterations (1 th.) took 1.907e-05s; avg 6.358e-06s ( +/- 99.12/185.00 %); best 5.594e-08s; worst 1.812e-05s; std dev. 8.326e-06 (taking best). -Reference operation time is 5.59449e-08 s (1716 Mflops) with 1 threads. -After merge step 1: tpop: 5.594e-08 s ~Mflops: 1715.974 nsubm:1 otn:1 -Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 214459.834x: 0.012s -> 5.594e-08s, so taking this instance. +3 iterations (1 th.) took 0.036s; avg 0.012s ( +/- 11.29/ 11.34 %); best 0.01064s; worst 0.01336s; std dev. 0.001108 (taking best). +Reference operation time is 0.010644 s (0.009019 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: 0.01064 Mflops: 0.009) +Merge (3 -> 1 leaves) took w.c.t. of 2.885e-05s, ~1.121e-05s of computing time (of which 2.861e-06s sorting, 5.007e-06s analysis) +3 iterations (1 th.) took 2.813e-05s; avg 9.378e-06s ( +/- 99.44/189.83 %); best 5.289e-08s; worst 2.718e-05s; std dev. 1.259e-05 (taking best). +Reference operation time is 5.28932e-08 s (1815 Mflops) with 1 threads. +After merge step 1: tpop: 5.289e-08 s ~Mflops: 1814.979 nsubm:1 otn:1 +Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 201235.069x: 0.01064s -> 5.289e-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 0.04806s (of which 2.408e-05s partitioning, 0s I/O); computing times: 8.106e-06s in par. loops, 1.907e-06s sorting, 4.053e-06s analyzing) -Total merge + benchmarking process took 0.04806s, equivalent to 859147.7/4.0 new/old ops (0.1079s for 2 clones -- as 1929256.3/9.0 ops, or 964628.2/4.5 ops per clone), SPEEDUP of 214459.834x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 214459.834x (0.012s -> 5.594e-08s), will amortize in 4.0 ops by saving 0.012s per op. -In 1 tuning rounds (tot. 0.16s, 0.11s for constructor, 2 clones) obtained a SPEEDUP of 21445883.4% (2.145e+05x) (from 0.008001 to 1716 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.03597s (of which 3.409e-05s partitioning, 0s I/O); computing times: 1.121e-05s in par. loops, 2.861e-06s sorting, 5.007e-06s analyzing) +Total merge + benchmarking process took 0.03597s, equivalent to 680108.2/3.4 new/old ops (0.05982s for 2 clones -- as 1130998.4/5.6 ops, or 565499.2/2.8 ops per clone), SPEEDUP of 201235.069x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 201235.069x (0.01064s -> 5.289e-08s), will amortize in 3.4 ops by saving 0.01064s per op. +In 1 tuning rounds (tot. 0.096s, 0.06s for constructor, 2 clones) obtained a SPEEDUP of 20123406.9% (2.012e+05x) (from 0.009019 to 1815 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 0.160067 s (1.200e-02 s -> 5.594e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.0959828 s (1.064e-02 s -> 5.289e-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 0.811905 s and estimated a speedup of 1.000000 x (5.594e-08 s -> 5.594e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.487961 s and estimated a speedup of 1.000000 x (5.289e-08 s -> 5.289e-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 0.023900 0.031986 0.055886 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 1 3 3 6 0.055886 -%:RSB_SUBDIVISION_TIME:A.mtx S N 1 3 3 6 0.023900 -%:RSB_SHUFFLE_TIME:A.mtx S N 1 3 3 6 0.031986 +%:CONSTRUCTOR_TIMES:A.mtx S N 1 3 3 6 0.000000 0.027886 0.028001 0.055887 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 1 3 3 6 0.055887 +%:RSB_SUBDIVISION_TIME:A.mtx S N 1 3 3 6 0.027886 +%:RSB_SHUFFLE_TIME:A.mtx S N 1 3 3 6 0.028001 %: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 0.055886 +%:SORTEDCOO2RSB_TIME:A.mtx S N 1 3 3 6 0.055887 %: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 @@ -3373,47 +3409,47 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 1 3 3 6 6 6 6 # # Using 4 threads -# Constructed matrix (took 0.132s): (3 x 3)[0x5679a700]{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 0.051s): (3 x 3)[0x58297740]{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 0.036s; avg 0.012s ( +/- 33.27/ 33.44 %); best 0.008007s; worst 0.01601s; std dev. 0.003268 (taking best). -Reference operation time is 0.00800705 s (0.01199 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: 0.008007 Mflops: 0.012) -Merge (3 -> 1 leaves) took w.c.t. of 1.812e-05s, ~6.199e-06s of computing time (of which 1.907e-06s sorting, 3.099e-06s analysis) -3 iterations (4 th.) took 3.815e-06s; avg 1.272e-06s ( +/- 95.60/125.00 %); best 5.594e-08s; worst 2.861e-06s; std dev. 1.189e-06 (taking best). -Reference operation time is 5.59449e-08 s (1716 Mflops) with 4 threads. -After merge step 1: tpop: 5.594e-08 s ~Mflops: 1715.974 nsubm:1 otn:1 -Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 143123.801x: 0.008007s -> 5.594e-08s, so taking this instance. +3 iterations (4 th.) took 0.024s; avg 0.008s ( +/- 0.02/ 0.03 %); best 0.007998s; worst 0.008002s; std dev. 1.73e-06 (taking best). +Reference operation time is 0.00799799 s (0.012 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: 0.007998 Mflops: 0.012) +Merge (3 -> 1 leaves) took w.c.t. of 1.192e-05s, ~2.861e-06s of computing time (of which 9.537e-07s sorting, 1.907e-06s analysis) +3 iterations (4 th.) took 4.053e-06s; avg 1.351e-06s ( +/- 96.09/129.41 %); best 5.289e-08s; worst 3.099e-06s; std dev. 1.296e-06 (taking best). +Reference operation time is 5.28932e-08 s (1815 Mflops) with 4 threads. +After merge step 1: tpop: 5.289e-08 s ~Mflops: 1814.979 nsubm:1 otn:1 +Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 151210.277x: 0.007998s -> 5.289e-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 0.04796s (of which 2.098e-05s partitioning, 0s I/O); computing times: 6.199e-06s in par. loops, 1.907e-06s sorting, 3.099e-06s analyzing) -Total merge + benchmarking process took 0.04796s, equivalent to 857323.7/6.0 new/old ops (0.09589s for 2 clones -- as 1713918.6/12.0 ops, or 856959.3/6.0 ops per clone), SPEEDUP of 143123.801x -Applying multi-merge (3 -> 1 leaves, 1 steps, 1 -> 1 th.sp.) yielded SPEEDUP of 143123.801x (0.008007s -> 5.594e-08s), will amortize in 6.0 ops by saving 0.008007s per op. -In 1 tuning rounds (tot. 0.13s, 0.096s for constructor, 2 clones) obtained a SPEEDUP of 14312280.1% (1.431e+05x) (from 0.01199 to 1716 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.02399s (of which 1.502e-05s partitioning, 0s I/O); computing times: 2.861e-06s in par. loops, 9.537e-07s sorting, 1.907e-06s analyzing) +Total merge + benchmarking process took 0.02399s, equivalent to 453518.1/3.0 new/old ops (0.04793s for 2 clones -- as 906076.2/6.0 ops, or 453038.1/3.0 ops per clone), SPEEDUP of 151210.277x +Applying multi-merge (3 -> 1 leaves, 1 steps, 1 -> 1 th.sp.) yielded SPEEDUP of 151210.277x (0.007998s -> 5.289e-08s), will amortize in 3.0 ops by saving 0.007998s per op. +In 1 tuning rounds (tot. 0.072s, 0.048s for constructor, 2 clones) obtained a SPEEDUP of 15120927.7% (1.512e+05x) (from 0.012 to 1815 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 0.131992 s (8.007e-03 s -> 5.594e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.072 s (7.998e-03 s -> 5.289e-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 0.831959 s and estimated a speedup of 1.000000 x (5.594e-08 s -> 5.594e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.451982 s and estimated a speedup of 1.000000 x (5.289e-08 s -> 5.289e-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 0.043617 0.048006 0.091623 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 4 3 3 6 0.091623 -%:RSB_SUBDIVISION_TIME:A.mtx S N 4 3 3 6 0.043617 -%:RSB_SHUFFLE_TIME:A.mtx S N 4 3 3 6 0.048006 +%:CONSTRUCTOR_TIMES:A.mtx S N 4 3 3 6 0.000000 0.013495 0.021039 0.034534 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 4 3 3 6 0.034534 +%:RSB_SUBDIVISION_TIME:A.mtx S N 4 3 3 6 0.013495 +%:RSB_SHUFFLE_TIME:A.mtx S N 4 3 3 6 0.021039 %: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 0.091623 +%:SORTEDCOO2RSB_TIME:A.mtx S N 4 3 3 6 0.034534 %: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 0.61 -%:SORTEDCOO2RSB_SCALING:A.mtx S N 4 3 3 6 0.61 -%:RSB_SUBDIVISION_SCALING:A.mtx S N 4 3 3 6 0.55 -%:RSB_SHUFFLE_SCALING:A.mtx S N 4 3 3 6 0.67 -%:CONSTRUCTOR_SCALING:A.mtx S N 4 3 3 6 -nan 0.55 0.67 0.61 +%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 4 3 3 6 1.62 +%:SORTEDCOO2RSB_SCALING:A.mtx S N 4 3 3 6 1.62 +%:RSB_SUBDIVISION_SCALING:A.mtx S N 4 3 3 6 2.07 +%:RSB_SHUFFLE_SCALING:A.mtx S N 4 3 3 6 1.33 +%:CONSTRUCTOR_SCALING:A.mtx S N 4 3 3 6 -nan 2.07 1.33 1.62 #%: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 @@ -3422,50 +3458,50 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 4 3 3 6 6 6 6 # %operation:matrix CONSTRUCTOR[1] SPMV[1] SPMV[4] -%operation:A.mtx 0.103904 1e+09 1e+09 +%operation:A.mtx 0.0958729 1e+09 1e+09 %constructor:matrix SORT[1] SCAN[1] SHUFFLE[1] INSERT[1] -%constructor:A.mtx 0 0.0239 0 0.031986 +%constructor:A.mtx 0 0.0278862 0 0.0280011 # 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 0.082s): (3 x 3)[0x5679a700]{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 0.035s): (3 x 3)[0x58297740]{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 0.05598s; avg 0.01866s ( +/- 14.26/ 28.49 %); best 0.016s; worst 0.02398s; std dev. 0.00376 (taking best). -Reference operation time is 0.0159998 s (0.012 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: 0.016 Mflops: 0.012) -Merge (3 -> 1 leaves) took w.c.t. of 1.502e-05s, ~4.053e-06s of computing time (of which 9.537e-07s sorting, 2.861e-06s analysis) -3 iterations (1 th.) took 4.053e-06s; avg 1.351e-06s ( +/- 95.86/129.41 %); best 5.594e-08s; worst 3.099e-06s; std dev. 1.296e-06 (taking best). -Reference operation time is 5.59449e-08 s (3432 Mflops) with 1 threads. -After merge step 1: tpop: 5.594e-08 s ~Mflops: 3431.947 nsubm:1 otn:1 -Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 285991.903x: 0.016s -> 5.594e-08s, so taking this instance. +3 iterations (1 th.) took 0.01817s; avg 0.006056s ( +/- 47.06/ 72.22 %); best 0.003206s; worst 0.01043s; std dev. 0.00314 (taking best). +Reference operation time is 0.00320578 s (0.05989 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: 0.003206 Mflops: 0.060) +Merge (3 -> 1 leaves) took w.c.t. of 1.788e-05s, ~4.768e-06s of computing time (of which 9.537e-07s sorting, 3.099e-06s analysis) +3 iterations (1 th.) took 1.502e-05s; avg 5.007e-06s ( +/- 98.94/200.00 %); best 5.289e-08s; worst 1.502e-05s; std dev. 7.081e-06 (taking best). +Reference operation time is 5.28932e-08 s (3630 Mflops) with 1 threads. +After merge step 1: tpop: 5.289e-08 s ~Mflops: 3629.959 nsubm:1 otn:1 +Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 60608.519x: 0.003206s -> 5.289e-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 0.04798s (of which 1.693e-05s partitioning, 0s I/O); computing times: 4.053e-06s in par. loops, 9.537e-07s sorting, 2.861e-06s analyzing) -Total merge + benchmarking process took 0.04798s, equivalent to 857575.1/3.0 new/old ops (0.09202s for 2 clones -- as 1644815.7/5.8 ops, or 822407.8/2.9 ops per clone), SPEEDUP of 285991.903x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 285991.903x (0.016s -> 5.594e-08s), will amortize in 3.0 ops by saving 0.016s per op. -In 1 tuning rounds (tot. 0.15s, 0.092s for constructor, 2 clones) obtained a SPEEDUP of 28599090.3% (2.86e+05x) (from 0.012 to 3432 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.03199s (of which 2.098e-05s partitioning, 0s I/O); computing times: 4.768e-06s in par. loops, 9.537e-07s sorting, 3.099e-06s analyzing) +Total merge + benchmarking process took 0.03199s, equivalent to 604841.1/10.0 new/old ops (0.05737s for 2 clones -- as 1084588.7/17.9 ops, or 542294.3/8.9 ops per clone), SPEEDUP of 60608.519x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 60608.519x (0.003206s -> 5.289e-08s), will amortize in 10.0 ops by saving 0.003206s per op. +In 1 tuning rounds (tot. 0.076s, 0.057s for constructor, 2 clones) obtained a SPEEDUP of 6060751.9% (6.061e+04x) (from 0.05989 to 3630 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 0.148092 s (1.600e-02 s -> 5.594e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.0756478 s (3.206e-03 s -> 5.289e-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 0.89601 s and estimated a speedup of 1.000000 x (5.594e-08 s -> 5.594e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.479976 s and estimated a speedup of 1.000000 x (5.289e-08 s -> 5.289e-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 0.018046 0.031979 0.050025 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 1 3 3 6 0.050025 -%:RSB_SUBDIVISION_TIME:A.mtx S N 1 3 3 6 0.018046 -%:RSB_SHUFFLE_TIME:A.mtx S N 1 3 3 6 0.031979 +%:CONSTRUCTOR_TIMES:A.mtx S N 1 3 3 6 0.000000 0.007131 0.015991 0.023122 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 1 3 3 6 0.023122 +%:RSB_SUBDIVISION_TIME:A.mtx S N 1 3 3 6 0.007131 +%:RSB_SHUFFLE_TIME:A.mtx S N 1 3 3 6 0.015991 %: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 0.050025 +%:SORTEDCOO2RSB_TIME:A.mtx S N 1 3 3 6 0.023122 %: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 @@ -3480,47 +3516,47 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 1 3 3 6 6 6 6 # # Using 4 threads -# Constructed matrix (took 0.100s): (3 x 3)[0x5679a700]{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 0.059s): (3 x 3)[0x58297740]{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 0.05608s; avg 0.01869s ( +/- 14.43/ 28.41 %); best 0.016s; worst 0.024s; std dev. 0.003756 (taking best). -Reference operation time is 0.015996 s (0.012 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: 0.016 Mflops: 0.012) -Merge (3 -> 1 leaves) took w.c.t. of 3.695e-05s, ~5.007e-06s of computing time (of which 2.146e-06s sorting, 2.289e-05s analysis) -3 iterations (4 th.) took 3.815e-06s; avg 1.272e-06s ( +/- 95.60/125.00 %); best 5.594e-08s; worst 2.861e-06s; std dev. 1.189e-06 (taking best). -Reference operation time is 5.59449e-08 s (3432 Mflops) with 4 threads. -After merge step 1: tpop: 5.594e-08 s ~Mflops: 3431.947 nsubm:1 otn:1 -Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 285923.716x: 0.016s -> 5.594e-08s, so taking this instance. +3 iterations (4 th.) took 0.044s; avg 0.01467s ( +/- 10.89/ 9.16 %); best 0.01307s; worst 0.01601s; std dev. 0.001214 (taking best). +Reference operation time is 0.013068 s (0.01469 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: 0.01307 Mflops: 0.015) +Merge (3 -> 1 leaves) took w.c.t. of 1.502e-05s, ~4.053e-06s of computing time (of which 9.537e-07s sorting, 4.053e-06s analysis) +3 iterations (4 th.) took 4.053e-06s; avg 1.351e-06s ( +/- 96.09/111.76 %); best 5.289e-08s; worst 2.861e-06s; std dev. 1.173e-06 (taking best). +Reference operation time is 5.28932e-08 s (3630 Mflops) with 4 threads. +After merge step 1: tpop: 5.289e-08 s ~Mflops: 3629.959 nsubm:1 otn:1 +Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 247063.331x: 0.01307s -> 5.289e-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 0.03992s (of which 3.886e-05s partitioning, 0s I/O); computing times: 5.007e-06s in par. loops, 2.146e-06s sorting, 2.289e-05s analyzing) -Total merge + benchmarking process took 0.03992s, equivalent to 713543.6/2.5 new/old ops (0.09181s for 2 clones -- as 1641078.2/5.7 ops, or 820539.1/2.9 ops per clone), SPEEDUP of 285923.716x -Applying multi-merge (3 -> 1 leaves, 1 steps, 1 -> 1 th.sp.) yielded SPEEDUP of 285923.716x (0.016s -> 5.594e-08s), will amortize in 2.5 ops by saving 0.016s per op. -In 1 tuning rounds (tot. 0.15s, 0.092s for constructor, 2 clones) obtained a SPEEDUP of 28592271.6% (2.859e+05x) (from 0.012 to 3432 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.02399s (of which 1.812e-05s partitioning, 0s I/O); computing times: 4.053e-06s in par. loops, 9.537e-07s sorting, 4.053e-06s analyzing) +Total merge + benchmarking process took 0.02399s, equivalent to 453648.9/1.8 new/old ops (0.04792s for 2 clones -- as 906067.2/3.7 ops, or 453033.6/1.8 ops per clone), SPEEDUP of 247063.331x +Applying multi-merge (3 -> 1 leaves, 1 steps, 1 -> 1 th.sp.) yielded SPEEDUP of 247063.331x (0.01307s -> 5.289e-08s), will amortize in 1.8 ops by saving 0.01307s per op. +In 1 tuning rounds (tot. 0.092s, 0.048s for constructor, 2 clones) obtained a SPEEDUP of 24706233.1% (2.471e+05x) (from 0.01469 to 3630 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 0.148006 s (1.600e-02 s -> 5.594e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.0920072 s (1.307e-02 s -> 5.289e-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 0.707949 s and estimated a speedup of 1.000000 x (5.594e-08 s -> 5.594e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.435965 s and estimated a speedup of 1.000000 x (5.289e-08 s -> 5.289e-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 0.035841 0.031996 0.067837 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 4 3 3 6 0.067837 -%:RSB_SUBDIVISION_TIME:A.mtx S N 4 3 3 6 0.035841 -%:RSB_SHUFFLE_TIME:A.mtx S N 4 3 3 6 0.031996 +%:CONSTRUCTOR_TIMES:A.mtx S N 4 3 3 6 0.000000 0.020480 0.022079 0.042559 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 4 3 3 6 0.042559 +%:RSB_SUBDIVISION_TIME:A.mtx S N 4 3 3 6 0.020480 +%:RSB_SHUFFLE_TIME:A.mtx S N 4 3 3 6 0.022079 %: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 0.067837 +%:SORTEDCOO2RSB_TIME:A.mtx S N 4 3 3 6 0.042559 %: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 0.74 -%:SORTEDCOO2RSB_SCALING:A.mtx S N 4 3 3 6 0.74 -%:RSB_SUBDIVISION_SCALING:A.mtx S N 4 3 3 6 0.50 -%:RSB_SHUFFLE_SCALING:A.mtx S N 4 3 3 6 1.00 -%:CONSTRUCTOR_SCALING:A.mtx S N 4 3 3 6 -nan 0.50 1.00 0.74 +%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 4 3 3 6 0.54 +%:SORTEDCOO2RSB_SCALING:A.mtx S N 4 3 3 6 0.54 +%:RSB_SUBDIVISION_SCALING:A.mtx S N 4 3 3 6 0.35 +%:RSB_SHUFFLE_SCALING:A.mtx S N 4 3 3 6 0.72 +%:CONSTRUCTOR_SCALING:A.mtx S N 4 3 3 6 -nan 0.35 0.72 0.54 #%: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 @@ -3529,184 +3565,184 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 4 3 3 6 6 6 6 # %operation:matrix CONSTRUCTOR[1] SPMV[1] SPMV[4] -%operation:A.mtx 0.081934 1e+09 1e+09 +%operation:A.mtx 0.0354872 1e+09 1e+09 %constructor:matrix SORT[1] SCAN[1] SHUFFLE[1] INSERT[1] -%constructor:A.mtx 0 0.0180459 0 0.0319791 +%constructor:A.mtx 0 0.00713086 0 0.015991 # symmetric matrix --- skipping transposed benchmarking -# so far, program took 14.332s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 3.836s/0.000s . +# so far, program took 11.930s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 2.192s/0.000s . getrusage() stats: ru_maxrss: 69 (maximum resident set size -- MB) -ru_stime : 0.4663s (system CPU time used) -ru_utime : 27.3s (user CPU time used) +ru_stime : 0.5974s (system CPU time used) +ru_utime : 24.25s (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 1715.97 1.200e-02 0.000e+00 5.594e-08 0.000e+00 1.601e-01 4.79e+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 1715.97 8.007e-03 0.000e+00 5.594e-08 0.000e+00 1.320e-01 4.79e+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 1814.98 1.064e-02 0.000e+00 5.289e-08 0.000e+00 9.598e-02 5.07e+00 2.29e+00 1 9.60e-05 +pr: 5:R_R A 3 3 6 1 Z S N 4 1 0 4.0000 4.6667 3 1 1814.98 7.998e-03 0.000e+00 5.289e-08 0.000e+00 7.200e-02 5.07e+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. 17879081.8 % faster, avg. sp. ratio 178791.818x, max sp. ratio 214459.834x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 2610236.5/2359318.1/2861154.9/5220473.0 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 14.9/ 13.3/ 16.5/ 29.8 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 14.9, min. 13.3, max. 16.5 ops) +#pr: (in succ. cases rsb autotuning gave avg. 17622167.3 % faster, avg. sp. ratio 176222.673x, max sp. ratio 201235.069x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 1587944.6/1361235.1/1814654.0/3175889.1 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 9.0/ 9.0/ 9.0/ 18.0 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 9.0, min. 9.0, max. 9.0 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 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 3.932/ 3.932/ 3.932,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 9.581/ 4.790/ 4.790,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 4.159/ 4.159/ 4.159,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 10.134/ 5.067/ 5.067,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.: 0.15 s, min 0.13 s, max 0.16 s, tot 0.29 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.15 s, min 0.13 s, max 0.16 s, tot 0.29 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 1.716e+03, min 1.716e+03, max 1.716e+03 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 9.995e-03, min 8.001e-03, max 1.199e-02 (2 samples) -#pr: best tun. rsb operation time was: on avg. 5.594e-08s, min 5.594e-08s, max 5.594e-08s, tot 1.119e-07s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 1.000e-02s, min 8.007e-03s, max 1.200e-02s, tot 2.000e-02s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 4.955e+00 4.955e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 2.486e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.08 s, min 0.07 s, max 0.10 s, tot 0.17 s (2 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.08 s, min 0.07 s, max 0.10 s, tot 0.17 s (2 samples) +#pr: best tun. rsb canon. mflops were: on avg. 1.815e+03, min 1.815e+03, max 1.815e+03 (2 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 1.051e-02, min 9.019e-03, max 1.200e-02 (2 samples) +#pr: best tun. rsb operation time was: on avg. 5.289e-08s, min 5.289e-08s, max 5.289e-08s, tot 1.058e-07s (2 samples) +#pr: ref. unt. rsb operation time was: on avg. 9.321e-03s, min 7.998e-03s, max 1.064e-02s, tot 1.864e-02s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 6.697e+00 6.697e+00 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.704e+00 #pr: ======== Limiting to nrhs=2: #pr: 2 samples (out of 4) matched the dump limiting criteria. #pr: Dump from a base of 4 samples (of max 8) ordered by (1,2,1,1,2,1,2) = (filename x cores x incX x incY x nrhs x typecode x transA). pr: BESTCODE MTX NR NC NNZ NRHS TYPE SYM TRANS NT AT-NT AT-MKL-NT BPNZ AT-BPNZ NSUBM AT-SUBM RSBBEST-MFLOPS OPTIME MKL-OPTIME AT-OPTIME AT-MKL-OPTIME AT-TIME RWminBW-GBps CB-bpf AT-MS CMFLOPS -pr: 3:R_R A 3 3 6 2 Z S N 1 1 0 4.0000 4.6667 3 1 3431.95 1.600e-02 0.000e+00 5.594e-08 0.000e+00 1.481e-01 7.36e+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 3431.95 1.600e-02 0.000e+00 5.594e-08 0.000e+00 1.480e-01 7.36e+00 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 3629.96 3.206e-03 0.000e+00 5.289e-08 0.000e+00 7.565e-02 7.79e+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 3629.96 1.307e-02 0.000e+00 5.289e-08 0.000e+00 9.201e-02 7.79e+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. 28595681.0 % faster, avg. sp. ratio 285957.810x, max sp. ratio 285991.903x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 2646335.0/2645565.7/2647104.2/5292669.9 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 9.3/ 9.3/ 9.3/ 18.5 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 9.3, min. 9.3, max. 9.3 ops) +#pr: (in succ. cases rsb autotuning gave avg. 15383492.5 % faster, avg. sp. ratio 153835.925x, max sp. ratio 247063.331x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 1584845.6/1430200.6/1739490.6/3169691.2 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 15.3/ 7.0/ 23.6/ 30.6 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 15.3, min. 7.0, max. 23.6 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 32/ 32/ 32) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 96/ 96/ 96) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 5.648/ 5.648/ 5.648,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 14.729/ 7.364/ 7.364,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 5.974/ 5.974/ 5.974,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 15.579/ 7.789/ 7.789,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.: 0.15 s, min 0.15 s, max 0.15 s, tot 0.30 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.15 s, min 0.15 s, max 0.15 s, tot 0.30 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 3.432e+03, min 3.432e+03, max 3.432e+03 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 1.200e-02, min 1.200e-02, max 1.200e-02 (2 samples) -#pr: best tun. rsb operation time was: on avg. 5.594e-08s, min 5.594e-08s, max 5.594e-08s, tot 1.119e-07s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 1.600e-02s, min 1.600e-02s, max 1.600e-02s, tot 3.200e-02s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 3.450e+00 3.450e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 2.486e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.08 s, min 0.08 s, max 0.09 s, tot 0.17 s (2 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.08 s, min 0.08 s, max 0.09 s, tot 0.17 s (2 samples) +#pr: best tun. rsb canon. mflops were: on avg. 3.630e+03, min 3.630e+03, max 3.630e+03 (2 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 3.729e-02, min 1.469e-02, max 5.989e-02 (2 samples) +#pr: best tun. rsb operation time was: on avg. 5.289e-08s, min 5.289e-08s, max 5.289e-08s, tot 1.058e-07s (2 samples) +#pr: ref. unt. rsb operation time was: on avg. 8.137e-03s, min 3.206e-03s, max 1.307e-02s, tot 1.627e-02s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 4.662e+00 4.662e+00 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.704e+00 #pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 2.000e+00 x, min 2.000e+00 x, max 2.000e+00 x (2 samples, the non-min-nrhs ones) #pr: ======== Limiting to transA=N: #pr: Dump from a base of 4 samples (of max 8) ordered by (1,2,1,1,2,1,2) = (filename x cores x incX x incY x nrhs x typecode x transA). pr: BESTCODE MTX NR NC NNZ NRHS TYPE SYM TRANS NT AT-NT AT-MKL-NT BPNZ AT-BPNZ NSUBM AT-SUBM RSBBEST-MFLOPS OPTIME MKL-OPTIME AT-OPTIME AT-MKL-OPTIME AT-TIME RWminBW-GBps CB-bpf AT-MS CMFLOPS -pr: 1:R_R A 3 3 6 1 Z S N 1 1 0 4.0000 4.6667 3 1 1715.97 1.200e-02 0.000e+00 5.594e-08 0.000e+00 1.601e-01 4.79e+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 3431.95 1.600e-02 0.000e+00 5.594e-08 0.000e+00 1.481e-01 7.36e+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 1715.97 8.007e-03 0.000e+00 5.594e-08 0.000e+00 1.320e-01 4.79e+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 3431.95 1.600e-02 0.000e+00 5.594e-08 0.000e+00 1.480e-01 7.36e+00 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 1814.98 1.064e-02 0.000e+00 5.289e-08 0.000e+00 9.598e-02 5.07e+00 2.29e+00 1 9.60e-05 +pr: 3:R_R A 3 3 6 2 Z S N 1 1 0 4.0000 4.6667 3 1 3629.96 3.206e-03 0.000e+00 5.289e-08 0.000e+00 7.565e-02 7.79e+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 1814.98 7.998e-03 0.000e+00 5.289e-08 0.000e+00 7.200e-02 5.07e+00 2.29e+00 1 9.60e-05 +pr: 7:R_R A 3 3 6 2 Z S N 4 1 0 4.0000 4.6667 3 1 3629.96 1.307e-02 0.000e+00 5.289e-08 0.000e+00 9.201e-02 7.79e+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. 23237381.4 % faster, avg. sp. ratio 232374.814x, max sp. ratio 285991.903x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 2628285.7/2359318.1/2861154.9/10513143.0 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 12.1/ 9.3/ 16.5/ 48.3 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 12.1, min. 9.3, max. 16.5 ops) +#pr: (in succ. cases rsb autotuning gave avg. 16502829.9 % faster, avg. sp. ratio 165029.299x, max sp. ratio 247063.331x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 1586395.1/1361235.1/1814654.0/6345580.3 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 12.2/ 7.0/ 23.6/ 48.7 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 12.2, min. 7.0, max. 23.6 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 32/ 32/ 32) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 96/ 96/ 96) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 4.790/ 3.932/ 5.648,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 24.310/ 4.790/ 7.364,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 5.067/ 4.159/ 5.974,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 25.712/ 5.067/ 7.789,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.: 0.15 s, min 0.13 s, max 0.16 s, tot 0.59 s (4 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.15 s, min 0.13 s, max 0.16 s, tot 0.59 s (4 samples) -#pr: best tun. rsb canon. mflops were: on avg. 2.574e+03, min 1.716e+03, max 3.432e+03 (4 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 1.100e-02, min 8.001e-03, max 1.200e-02 (4 samples) -#pr: best tun. rsb operation time was: on avg. 5.594e-08s, min 5.594e-08s, max 5.594e-08s, tot 2.238e-07s (4 samples) -#pr: ref. unt. rsb operation time was: on avg. 1.300e-02s, min 8.007e-03s, max 1.600e-02s, tot 5.200e-02s (4 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 3.450e+00 4.955e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 2.486e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.08 s, min 0.07 s, max 0.10 s, tot 0.34 s (4 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.08 s, min 0.07 s, max 0.10 s, tot 0.34 s (4 samples) +#pr: best tun. rsb canon. mflops were: on avg. 2.722e+03, min 1.815e+03, max 3.630e+03 (4 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 2.390e-02, min 9.019e-03, max 5.989e-02 (4 samples) +#pr: best tun. rsb operation time was: on avg. 5.289e-08s, min 5.289e-08s, max 5.289e-08s, tot 2.116e-07s (4 samples) +#pr: ref. unt. rsb operation time was: on avg. 8.729e-03s, min 3.206e-03s, max 1.307e-02s, tot 3.492e-02s (4 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 4.662e+00 6.697e+00 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.704e+00 #pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 2.000e+00 x, min 2.000e+00 x, max 2.000e+00 x (2 samples, the non-min-nrhs ones) #pr: ======== Limiting to both transA=N and nrhs=1: #pr: 2 samples (out of 4) matched the dump limiting criteria. #pr: Dump from a base of 4 samples (of max 8) ordered by (1,2,1,1,2,1,2) = (filename x cores x incX x incY x nrhs x typecode x transA). pr: BESTCODE MTX NR NC NNZ NRHS TYPE SYM TRANS NT AT-NT AT-MKL-NT BPNZ AT-BPNZ NSUBM AT-SUBM RSBBEST-MFLOPS OPTIME MKL-OPTIME AT-OPTIME AT-MKL-OPTIME AT-TIME RWminBW-GBps CB-bpf AT-MS CMFLOPS -pr: 1:R_R A 3 3 6 1 Z S N 1 1 0 4.0000 4.6667 3 1 1715.97 1.200e-02 0.000e+00 5.594e-08 0.000e+00 1.601e-01 4.79e+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 1715.97 8.007e-03 0.000e+00 5.594e-08 0.000e+00 1.320e-01 4.79e+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 1814.98 1.064e-02 0.000e+00 5.289e-08 0.000e+00 9.598e-02 5.07e+00 2.29e+00 1 9.60e-05 +pr: 5:R_R A 3 3 6 1 Z S N 4 1 0 4.0000 4.6667 3 1 1814.98 7.998e-03 0.000e+00 5.289e-08 0.000e+00 7.200e-02 5.07e+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. 17879081.8 % faster, avg. sp. ratio 178791.818x, max sp. ratio 214459.834x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 2610236.5/2359318.1/2861154.9/5220473.0 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 14.9/ 13.3/ 16.5/ 29.8 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 14.9, min. 13.3, max. 16.5 ops) +#pr: (in succ. cases rsb autotuning gave avg. 17622167.3 % faster, avg. sp. ratio 176222.673x, max sp. ratio 201235.069x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 1587944.6/1361235.1/1814654.0/3175889.1 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 9.0/ 9.0/ 9.0/ 18.0 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 9.0, min. 9.0, max. 9.0 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 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 3.932/ 3.932/ 3.932,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 9.581/ 4.790/ 4.790,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 4.159/ 4.159/ 4.159,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 10.134/ 5.067/ 5.067,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.: 0.15 s, min 0.13 s, max 0.16 s, tot 0.29 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.15 s, min 0.13 s, max 0.16 s, tot 0.29 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 1.716e+03, min 1.716e+03, max 1.716e+03 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 9.995e-03, min 8.001e-03, max 1.199e-02 (2 samples) -#pr: best tun. rsb operation time was: on avg. 5.594e-08s, min 5.594e-08s, max 5.594e-08s, tot 1.119e-07s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 1.000e-02s, min 8.007e-03s, max 1.200e-02s, tot 2.000e-02s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 4.955e+00 4.955e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 2.486e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.08 s, min 0.07 s, max 0.10 s, tot 0.17 s (2 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.08 s, min 0.07 s, max 0.10 s, tot 0.17 s (2 samples) +#pr: best tun. rsb canon. mflops were: on avg. 1.815e+03, min 1.815e+03, max 1.815e+03 (2 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 1.051e-02, min 9.019e-03, max 1.200e-02 (2 samples) +#pr: best tun. rsb operation time was: on avg. 5.289e-08s, min 5.289e-08s, max 5.289e-08s, tot 1.058e-07s (2 samples) +#pr: ref. unt. rsb operation time was: on avg. 9.321e-03s, min 7.998e-03s, max 1.064e-02s, tot 1.864e-02s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 6.697e+00 6.697e+00 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.704e+00 #pr: ======== Limiting to both transA=N and nrhs=2: #pr: 2 samples (out of 4) matched the dump limiting criteria. #pr: Dump from a base of 4 samples (of max 8) ordered by (1,2,1,1,2,1,2) = (filename x cores x incX x incY x nrhs x typecode x transA). pr: BESTCODE MTX NR NC NNZ NRHS TYPE SYM TRANS NT AT-NT AT-MKL-NT BPNZ AT-BPNZ NSUBM AT-SUBM RSBBEST-MFLOPS OPTIME MKL-OPTIME AT-OPTIME AT-MKL-OPTIME AT-TIME RWminBW-GBps CB-bpf AT-MS CMFLOPS -pr: 3:R_R A 3 3 6 2 Z S N 1 1 0 4.0000 4.6667 3 1 3431.95 1.600e-02 0.000e+00 5.594e-08 0.000e+00 1.481e-01 7.36e+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 3431.95 1.600e-02 0.000e+00 5.594e-08 0.000e+00 1.480e-01 7.36e+00 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 3629.96 3.206e-03 0.000e+00 5.289e-08 0.000e+00 7.565e-02 7.79e+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 3629.96 1.307e-02 0.000e+00 5.289e-08 0.000e+00 9.201e-02 7.79e+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. 28595681.0 % faster, avg. sp. ratio 285957.810x, max sp. ratio 285991.903x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 2646335.0/2645565.7/2647104.2/5292669.9 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 9.3/ 9.3/ 9.3/ 18.5 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 9.3, min. 9.3, max. 9.3 ops) +#pr: (in succ. cases rsb autotuning gave avg. 15383492.5 % faster, avg. sp. ratio 153835.925x, max sp. ratio 247063.331x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 1584845.6/1430200.6/1739490.6/3169691.2 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 15.3/ 7.0/ 23.6/ 30.6 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 15.3, min. 7.0, max. 23.6 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 32/ 32/ 32) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 96/ 96/ 96) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 5.648/ 5.648/ 5.648,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 14.729/ 7.364/ 7.364,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 5.974/ 5.974/ 5.974,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 15.579/ 7.789/ 7.789,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.: 0.15 s, min 0.15 s, max 0.15 s, tot 0.30 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.15 s, min 0.15 s, max 0.15 s, tot 0.30 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 3.432e+03, min 3.432e+03, max 3.432e+03 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 1.200e-02, min 1.200e-02, max 1.200e-02 (2 samples) -#pr: best tun. rsb operation time was: on avg. 5.594e-08s, min 5.594e-08s, max 5.594e-08s, tot 1.119e-07s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 1.600e-02s, min 1.600e-02s, max 1.600e-02s, tot 3.200e-02s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 3.450e+00 3.450e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 2.486e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.08 s, min 0.08 s, max 0.09 s, tot 0.17 s (2 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.08 s, min 0.08 s, max 0.09 s, tot 0.17 s (2 samples) +#pr: best tun. rsb canon. mflops were: on avg. 3.630e+03, min 3.630e+03, max 3.630e+03 (2 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 3.729e-02, min 1.469e-02, max 5.989e-02 (2 samples) +#pr: best tun. rsb operation time was: on avg. 5.289e-08s, min 5.289e-08s, max 5.289e-08s, tot 1.058e-07s (2 samples) +#pr: ref. unt. rsb operation time was: on avg. 8.137e-03s, min 3.206e-03s, max 1.307e-02s, tot 1.627e-02s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 4.662e+00 4.662e+00 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.704e+00 #pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 2.000e+00 x, min 2.000e+00 x, max 2.000e+00 x (2 samples, the non-min-nrhs ones) #pr: ======== Limiting to transA=T: #pr: No sample (out of 4) matched the dump criteria -- skipping dump round. @@ -3717,44 +3753,44 @@ #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 1715.97 1.200e-02 0.000e+00 5.594e-08 0.000e+00 1.601e-01 4.79e+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 3431.95 1.600e-02 0.000e+00 5.594e-08 0.000e+00 1.481e-01 7.36e+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 1715.97 8.007e-03 0.000e+00 5.594e-08 0.000e+00 1.320e-01 4.79e+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 3431.95 1.600e-02 0.000e+00 5.594e-08 0.000e+00 1.480e-01 7.36e+00 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 1814.98 1.064e-02 0.000e+00 5.289e-08 0.000e+00 9.598e-02 5.07e+00 2.29e+00 1 9.60e-05 +pr: 3:R_R A 3 3 6 2 Z S N 1 1 0 4.0000 4.6667 3 1 3629.96 3.206e-03 0.000e+00 5.289e-08 0.000e+00 7.565e-02 7.79e+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 1814.98 7.998e-03 0.000e+00 5.289e-08 0.000e+00 7.200e-02 5.07e+00 2.29e+00 1 9.60e-05 +pr: 7:R_R A 3 3 6 2 Z S N 4 1 0 4.0000 4.6667 3 1 3629.96 1.307e-02 0.000e+00 5.289e-08 0.000e+00 9.201e-02 7.79e+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. 23237381.4 % faster, avg. sp. ratio 232374.814x, max sp. ratio 285991.903x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 2628285.7/2359318.1/2861154.9/10513143.0 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 12.1/ 9.3/ 16.5/ 48.3 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 12.1, min. 9.3, max. 16.5 ops) +#pr: (in succ. cases rsb autotuning gave avg. 16502829.9 % faster, avg. sp. ratio 165029.299x, max sp. ratio 247063.331x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 1586395.1/1361235.1/1814654.0/6345580.3 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 12.2/ 7.0/ 23.6/ 48.7 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 12.2, min. 7.0, max. 23.6 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 32/ 32/ 32) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 96/ 96/ 96) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 4.790/ 3.932/ 5.648,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 24.310/ 4.790/ 7.364,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 5.067/ 4.159/ 5.974,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 25.712/ 5.067/ 7.789,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.: 0.15 s, min 0.13 s, max 0.16 s, tot 0.59 s (4 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.15 s, min 0.13 s, max 0.16 s, tot 0.59 s (4 samples) -#pr: best tun. rsb canon. mflops were: on avg. 2.574e+03, min 1.716e+03, max 3.432e+03 (4 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 1.100e-02, min 8.001e-03, max 1.200e-02 (4 samples) -#pr: best tun. rsb operation time was: on avg. 5.594e-08s, min 5.594e-08s, max 5.594e-08s, tot 2.238e-07s (4 samples) -#pr: ref. unt. rsb operation time was: on avg. 1.300e-02s, min 8.007e-03s, max 1.600e-02s, tot 5.200e-02s (4 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 3.450e+00 4.955e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 2.486e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.08 s, min 0.07 s, max 0.10 s, tot 0.34 s (4 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.08 s, min 0.07 s, max 0.10 s, tot 0.34 s (4 samples) +#pr: best tun. rsb canon. mflops were: on avg. 2.722e+03, min 1.815e+03, max 3.630e+03 (4 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 2.390e-02, min 9.019e-03, max 5.989e-02 (4 samples) +#pr: best tun. rsb operation time was: on avg. 5.289e-08s, min 5.289e-08s, max 5.289e-08s, tot 2.116e-07s (4 samples) +#pr: ref. unt. rsb operation time was: on avg. 8.729e-03s, min 3.206e-03s, max 1.307e-02s, tot 3.492e-02s (4 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 4.662e+00 6.697e+00 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.704e+00 #pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 2.000e+00 x, min 2.000e+00 x, max 2.000e+00 x (2 samples, the non-min-nrhs ones) -#pr: Record collection took 4.08 s. +#pr: Record collection took 2.50 s. #pr: Record comprises 50 memory benchmark samples (prepend RSB_PR_MBW=1 to dump this). -#pr: Record comprises 100 environment variables in 4755 bytes (prepend RSB_PR_ENV=1 to dump this). +#pr: Record comprises 100 environment variables in 4809 bytes (prepend RSB_PR_ENV=1 to dump this). # ====== END Total summary record. -#pr: ======== Saved a performance record of 8 samples to rsbench_pr__1733298354_gcc-14.2-1,4th.rpr -# Removing the temporary record file rsbench_pr__1733298354_gcc-14.2-1,4th.rpr.tmp. -# terminating run at 1733298369 (after 14.3s of w.c.t.) +#pr: ======== Saved a performance record of 8 samples to rsbench_pr__1767709280_gcc-14.2-1,4th.rpr +# Removing the temporary record file rsbench_pr__1767709280_gcc-14.2-1,4th.rpr.tmp. +# terminating run at 1767709292 (after 11.9s 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. @@ -4026,10 +4062,10 @@ L2 size: 524288 L3 size: 16777216 sysconf() : 4096 bytes per pagesize -sysconf() : 4093893 physical pages -sysconf() : 3883683840 bytes (3703 MB) of physical memory -sysconf() : 1273384 available (free) physical pages -sysconf() : 920813568 available (free) physical memory +sysconf() : 4095708 physical pages +sysconf() : 3891118080 bytes (3710 MB) of physical memory +sysconf() : 641018 available (free) physical pages +sysconf() : 2625609728 available (free) physical memory sysconf() , processors : 8 sysconf() , processors online : 8 sysconf() : level 1 cache size 32768 @@ -4060,35 +4096,35 @@ RSB_SUBM_IDX_MARKER : 2147483647 RSB_MAX_ALLOCATABLE_MEMORY_CHUNK: 4294967295 timing min delta (if negative, don't complain with us) : 0 s -timing granularity : 5.50985e-08 s +timing granularity : 5.10454e-08 s CFLAGS : -g -O2 -Werror=implicit-function-declaration -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 CXXFLAGS : -g -O2 -fstack-protector-strong -Wformat -Werror=format-security -fopenmp CC : gcc memhinfo : L3:16/64/16M,L2:8/64/512K,L1:8/64/32K -detected free memory : 920813568 -detected total memory : -411283456 -for array sized 16777216 elems, took 0.00599408 s for linear search and 0 s for binary search for element 16777215, in 16 tries, for a total of 0.100055 s (ignore this:536870880) -for array sized 16777216 elems, took 0.00295997 s for linear search and 0 s for binary search for element 8388607, in 33 tries, for a total of 0.102275 s (ignore this:1090518942) -for array sized 16777216 elems, took 0.00142002 s for linear search and 0 s for binary search for element 4194303, in 67 tries, for a total of 0.100184 s (ignore this:1652555544) -for array sized 16777216 elems, took 0.000692844 s for linear search and 0 s for binary search for element 2097151, in 129 tries, for a total of 0.100465 s (ignore this:-2101346794) -for array sized 16777216 elems, took 0.000345945 s for linear search and 0 s for binary search for element 1048575, in 274 tries, for a total of 0.100195 s (ignore this:-1526727694) -for array sized 16777216 elems, took 0.000172853 s for linear search and 0 s for binary search for element 524287, in 547 tries, for a total of 0.100076 s (ignore this:-953157716) -for array sized 16777216 elems, took 8.58307e-05 s for linear search and 0 s for binary search for element 262143, in 1105 tries, for a total of 0.100055 s (ignore this:-373821686) -for array sized 16777216 elems, took 4.29153e-05 s for linear search and 0 s for binary search for element 131071, in 2215 tries, for a total of 0.100042 s (ignore this:206822844) -for array sized 16777216 elems, took 2.09808e-05 s for linear search and 0 s for binary search for element 65535, in 4568 tries, for a total of 0.100010 s (ignore this:805550604) -for array sized 16777216 elems, took 9.77516e-06 s for linear search and 0 s for binary search for element 32767, in 9145 tries, for a total of 0.100011 s (ignore this:1404859034) -for array sized 16777216 elems, took 4.76837e-06 s for linear search and 0 s for binary search for element 16383, in 17424 tries, for a total of 0.100001 s (ignore this:1975773818) -for array sized 16777216 elems, took 1.90735e-06 s for linear search and 0 s for binary search for element 8191, in 34922 tries, for a total of 0.100002 s (ignore this:-1747101274) -for array sized 16777216 elems, took 9.53674e-07 s for linear search and 0 s for binary search for element 4095, in 62786 tries, for a total of 0.100002 s (ignore this:-1232883934) -for array sized 16777216 elems, took 0 s for linear search and 0 s for binary search for element 2047, in 120054 tries, for a total of 0.100106 s (ignore this:-741382858) -for array sized 16777216 elems, took 0 s for linear search and 0 s for binary search for element 1023, in 202333 tries, for a total of 0.100000 s (ignore this:-327409540) -for array sized 16777216 elems, took 0 s for linear search and 0 s for binary search for element 511, in 316092 tries, for a total of 0.100001 s (ignore this:-4363516) -for array sized 16777216 elems, took 0 s for linear search and 0 s for binary search for element 255, in 416377 tries, for a total of 0.100000 s (ignore this:207988754) -for array sized 16777216 elems, took 0 s for linear search and 0 s for binary search for element 127, in 523785 tries, for a total of 0.100001 s (ignore this:341030144) -for array sized 16777216 elems, took 0 s for linear search and 0 s for binary search for element 63, in 617001 tries, for a total of 0.100001 s (ignore this:418772270) -for array sized 16777216 elems, took 0 s for linear search and 0 s for binary search for element 31, in 695248 tries, for a total of 0.100001 s (ignore this:461877646) -for array sized 16777216 elems, took 0 s for linear search and 0 s for binary search for element 15, in 696601 tries, for a total of 0.100000 s (ignore this:482775676) -for array sized 16777216 elems, took 0 s for linear search and 0 s for binary search for element 7, in 700410 tries, for a total of 0.100001 s (ignore this:492581416) +detected free memory : -1669357568 +detected total memory : -403849216 +for array sized 16777216 elems, took 0.00581217 s for linear search and 0 s for binary search for element 16777215, in 17 tries, for a total of 0.100194 s (ignore this:570425310) +for array sized 16777216 elems, took 0.00287986 s for linear search and 0 s for binary search for element 8388607, in 34 tries, for a total of 0.100482 s (ignore this:1140850586) +for array sized 16777216 elems, took 0.00143504 s for linear search and 0 s for binary search for element 4194303, in 68 tries, for a total of 0.100361 s (ignore this:1711275794) +for array sized 16777216 elems, took 0.000706911 s for linear search and 0 s for binary search for element 2097151, in 138 tries, for a total of 0.100574 s (ignore this:-2004877826) +for array sized 16777216 elems, took 0.000351906 s for linear search and 0 s for binary search for element 1048575, in 272 tries, for a total of 0.100009 s (ignore this:-1434453026) +for array sized 16777216 elems, took 0.000174999 s for linear search and 0 s for binary search for element 524287, in 552 tries, for a total of 0.100127 s (ignore this:-855640178) +for array sized 16777216 elems, took 8.67844e-05 s for linear search and 0 s for binary search for element 262143, in 1109 tries, for a total of 0.100018 s (ignore this:-274207004) +for array sized 16777216 elems, took 4.29153e-05 s for linear search and 0 s for binary search for element 131071, in 2222 tries, for a total of 0.100031 s (ignore this:308272520) +for array sized 16777216 elems, took 2.09808e-05 s for linear search and 0 s for binary search for element 65535, in 4434 tries, for a total of 0.100013 s (ignore this:889436900) +for array sized 16777216 elems, took 1.00136e-05 s for linear search and 0 s for binary search for element 32767, in 8619 tries, for a total of 0.100005 s (ignore this:1454274446) +for array sized 16777216 elems, took 4.76837e-06 s for linear search and 0 s for binary search for element 16383, in 17284 tries, for a total of 0.100006 s (ignore this:2020601990) +for array sized 16777216 elems, took 1.90735e-06 s for linear search and 0 s for binary search for element 8191, in 33698 tries, for a total of 0.100001 s (ignore this:-1722324670) +for array sized 16777216 elems, took 9.53674e-07 s for linear search and 0 s for binary search for element 4095, in 60813 tries, for a total of 0.100002 s (ignore this:-1224266200) +for array sized 16777216 elems, took 0 s for linear search and 0 s for binary search for element 2047, in 100000 tries, for a total of 0.100001 s (ignore this:-814866200) +for array sized 16777216 elems, took 0 s for linear search and 0 s for binary search for element 1023, in 172445 tries, for a total of 0.100001 s (ignore this:-462043730) +for array sized 16777216 elems, took 0 s for linear search and 0 s for binary search for element 511, in 268289 tries, for a total of 0.100001 s (ignore this:-187852372) +for array sized 16777216 elems, took 0 s for linear search and 0 s for binary search for element 255, in 447633 tries, for a total of 0.100001 s (ignore this:40440458) +for array sized 16777216 elems, took 0 s for linear search and 0 s for binary search for element 127, in 555088 tries, for a total of 0.100000 s (ignore this:181432810) +for array sized 16777216 elems, took 0 s for linear search and 0 s for binary search for element 63, in 620612 tries, for a total of 0.100000 s (ignore this:259629922) +for array sized 16777216 elems, took 0 s for linear search and 0 s for binary search for element 31, in 667422 tries, for a total of 0.100000 s (ignore this:301010086) +for array sized 16777216 elems, took 0 s for linear search and 0 s for binary search for element 15, in 671894 tries, for a total of 0.100001 s (ignore this:321166906) +for array sized 16777216 elems, took 0 s for linear search and 0 s for binary search for element 7, in 652791 tries, for a total of 0.100000 s (ignore this:330305980) + ./rsbench -C /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/rsbench version: 1.3.0 format switches:br @@ -4135,17 +4171,17 @@ 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 1733298372 +# beginning run at 1767709295 # /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 -Wformat -Werror=format-security -O3 -std=c99 # User did not specify threads; assuming 1. Environment provides max 8 threads; this build supports max 128. # User did not specify threads; assuming 1. Environment provides max 8 threads; this build supports max 128. -# average timer granularity: 5.55e-08 s -# Will write a final performance record to file rsbench_pr__1733298372_gcc-14.2.rpr and periodic checkpoints to rsbench_pr__1733298372_gcc-14.2.rpr.tmp +# average timer granularity: 5.83e-08 s +# Will write a final performance record to file rsbench_pr__1767709295_gcc-14.2.rpr and periodic checkpoints to rsbench_pr__1767709295_gcc-14.2.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:/usr/lib/libeatmydata # env: HOSTNAME is not set # env: KMP_AFFINITY is not set @@ -4184,61 +4220,61 @@ # 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: infom07-i386 +# 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. # 3 cache levels detected Will fill struct with 50 samples... -# Memory benchmark took 8.925s +# Memory benchmark took 8.783s # auto-tuning oriented output implies times==0 iterations and sort-after-load. #pr: allocated a performance record for 16 samples (4032 bytes). # multi-type benchmarking (DSCZ) -- now using typecode D (last was D). # Cache block size total 16777216 bytes, per-thread 2097152 bytes -# so far, program took 8.928s 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 8.785s 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, 75122 nnz/s ) (2.30 MB/s ) -#pre-sorting (6 elements) took 0.0324879 s -#weeding duplicates (to 6 elements) took 3.09944e-06 s (and check, 1.90735e-06 s ) +# file input of A.mtx took 0.00 s (6 nnz, 62446 nnz/s ) (1.92 MB/s ) +#pre-sorting (6 elements) took 0.00712919 s +#weeding duplicates (to 6 elements) took 1.19209e-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 8 threads -# Constructed matrix (took 0.096s): (3 x 3)[0x56a667d0]{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 0.052s): (3 x 3)[0x570a3810]{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 (8 th.) took 0.04804s; avg 0.01601s ( +/- 25.71/ 25.79 %); best 0.0119s; worst 0.02014s; std dev. 0.003367 (taking best). -Reference operation time is 0.0118971 s (0.002017 Mflops) with 8 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: 0.0119 Mflops: 0.002) -Merge (3 -> 1 leaves) took w.c.t. of 2.003e-05s, ~5.96e-06s of computing time (of which 9.537e-07s sorting, 1.907e-06s analysis) -3 iterations (8 th.) took 1.597e-05s; avg 5.325e-06s ( +/- 99.00/182.09 %); best 5.336e-08s; worst 1.502e-05s; std dev. 6.867e-06 (taking best). -Reference operation time is 5.33581e-08 s (449.8 Mflops) with 8 threads. -After merge step 1: tpop: 5.336e-08 s ~Mflops: 449.791 nsubm:1 otn:8 -Applying merge (3 -> 1 leaves, 8 th.) yielded SPEEDUP of 222966.935x: 0.0119s -> 5.336e-08s, so taking this instance. +3 iterations (8 th.) took 0.024s; avg 0.008001s ( +/- 0.62/ 0.43 %); best 0.007951s; worst 0.008035s; std dev. 3.592e-05 (taking best). +Reference operation time is 0.00795102 s (0.003018 Mflops) with 8 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: 0.007951 Mflops: 0.003) +Merge (3 -> 1 leaves) took w.c.t. of 2.503e-05s, ~8.106e-06s of computing time (of which 9.537e-07s sorting, 2.861e-06s analysis) +3 iterations (8 th.) took 1.812e-05s; avg 6.04e-06s ( +/- 99.17/200.00 %); best 5.035e-08s; worst 1.812e-05s; std dev. 8.542e-06 (taking best). +Reference operation time is 5.0354e-08 s (476.6 Mflops) with 8 threads. +After merge step 1: tpop: 5.035e-08 s ~Mflops: 476.625 nsubm:1 otn:8 +Applying merge (3 -> 1 leaves, 8 th.) yielded SPEEDUP of 157902.462x: 0.007951s -> 5.035e-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 0.0441s (of which 2.217e-05s partitioning, 0s I/O); computing times: 5.96e-06s in par. loops, 9.537e-07s sorting, 1.907e-06s analyzing) -Total merge + benchmarking process took 0.0441s, equivalent to 826492.4/3.7 new/old ops (0.08794s for 2 clones -- as 1648203.8/7.4 ops, or 824101.9/3.7 ops per clone), SPEEDUP of 222966.935x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 8 th.sp.) yielded SPEEDUP of 222966.935x (0.0119s -> 5.336e-08s), will amortize in 3.7 ops by saving 0.0119s per op. -In 1 tuning rounds (tot. 0.14s, 0.088s for constructor, 2 clones) obtained a SPEEDUP of 22296593.5% (2.23e+05x) (from 0.002017 to 449.8 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.02397s (of which 2.813e-05s partitioning, 0s I/O); computing times: 8.106e-06s in par. loops, 9.537e-07s sorting, 2.861e-06s analyzing) +Total merge + benchmarking process took 0.02397s, equivalent to 476093.8/3.0 new/old ops (0.04784s for 2 clones -- as 950071.0/6.0 ops, or 475035.5/3.0 ops per clone), SPEEDUP of 157902.462x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 8 th.sp.) yielded SPEEDUP of 157902.462x (0.007951s -> 5.035e-08s), will amortize in 3.0 ops by saving 0.007951s per op. +In 1 tuning rounds (tot. 0.072s, 0.048s for constructor, 2 clones) obtained a SPEEDUP of 15790146.2% (1.579e+05x) (from 0.003018 to 476.6 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 0.136112 s (1.190e-02 s -> 5.336e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.0719912 s (7.951e-03 s -> 5.035e-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 0.727943 s and estimated a speedup of 1.000000 x (5.336e-08 s -> 5.336e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.39997 s and estimated a speedup of 1.000000 x (5.035e-08 s -> 5.035e-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 8 3 3 6 0.000000 0.035910 0.027948 0.063858 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 8 3 3 6 0.063858 -%:RSB_SUBDIVISION_TIME:A.mtx S N 8 3 3 6 0.035910 -%:RSB_SHUFFLE_TIME:A.mtx S N 8 3 3 6 0.027948 +%:CONSTRUCTOR_TIMES:A.mtx S N 8 3 3 6 0.000000 0.019868 0.015998 0.035866 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 8 3 3 6 0.035866 +%:RSB_SUBDIVISION_TIME:A.mtx S N 8 3 3 6 0.019868 +%:RSB_SHUFFLE_TIME:A.mtx S N 8 3 3 6 0.015998 %:ROW_MAJOR_SORT_TIME:A.mtx S N 8 3 3 6 0.000000 %:ROW_MAJOR_SORT_SCALING:A.mtx S N 8 3 3 6 -nan -%:SORTEDCOO2RSB_TIME:A.mtx S N 8 3 3 6 0.063858 +%:SORTEDCOO2RSB_TIME:A.mtx S N 8 3 3 6 0.035866 %:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 8 3 3 6 0.000 %:UNSORTEDCOO2RSB_SCALING:A.mtx S N 8 3 3 6 1.00 %:SORTEDCOO2RSB_SCALING:A.mtx S N 8 3 3 6 1.00 @@ -4253,50 +4289,50 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 8 3 3 6 6 6 6 # %operation:matrix CONSTRUCTOR[8] SPMV[8] SPMV[8] -%operation:A.mtx 0.0957508 1e+09 1e+09 +%operation:A.mtx 0.0518799 1e+09 1e+09 %constructor:matrix SORT[8] SCAN[8] SHUFFLE[8] INSERT[8] -%constructor:A.mtx 0 0.0359099 0 0.0279479 +%constructor:A.mtx 0 0.0198679 0 0.0159979 # 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 8 threads -# Constructed matrix (took 0.101s): (3 x 3)[0x56a667d0]{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 0.052s): (3 x 3)[0x570a3810]{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 (8 th.) took 0.06002s; avg 0.02001s ( +/- 40.04/ 40.26 %); best 0.012s; worst 0.02806s; std dev. 0.006559 (taking best). -Reference operation time is 0.011997 s (0.008002 Mflops) with 8 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: 0.012 Mflops: 0.008) -Merge (3 -> 1 leaves) took w.c.t. of 3.099e-05s, ~9.06e-06s of computing time (of which 2.861e-06s sorting, 5.96e-06s analysis) -3 iterations (8 th.) took 6.914e-06s; avg 2.305e-06s ( +/- 97.68/158.62 %); best 5.336e-08s; worst 5.96e-06s; std dev. 2.614e-06 (taking best). -Reference operation time is 5.33581e-08 s (1799 Mflops) with 8 threads. -After merge step 1: tpop: 5.336e-08 s ~Mflops: 1799.165 nsubm:1 otn:8 -Applying merge (3 -> 1 leaves, 8 th.) yielded SPEEDUP of 224839.142x: 0.012s -> 5.336e-08s, so taking this instance. +3 iterations (8 th.) took 0.024s; avg 0.007999s ( +/- 0.33/ 0.30 %); best 0.007973s; worst 0.008023s; std dev. 2.049e-05 (taking best). +Reference operation time is 0.00797296 s (0.01204 Mflops) with 8 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: 0.007973 Mflops: 0.012) +Merge (3 -> 1 leaves) took w.c.t. of 1.287e-05s, ~4.053e-06s of computing time (of which 2.146e-06s sorting, 1.907e-06s analysis) +3 iterations (8 th.) took 1.192e-05s; avg 3.974e-06s ( +/- 98.73/176.00 %); best 5.035e-08s; worst 1.097e-05s; std dev. 4.961e-06 (taking best). +Reference operation time is 5.0354e-08 s (1907 Mflops) with 8 threads. +After merge step 1: tpop: 5.035e-08 s ~Mflops: 1906.502 nsubm:1 otn:8 +Applying merge (3 -> 1 leaves, 8 th.) yielded SPEEDUP of 158338.068x: 0.007973s -> 5.035e-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 0.05996s (of which 3.505e-05s partitioning, 0s I/O); computing times: 9.06e-06s in par. loops, 2.861e-06s sorting, 5.96e-06s analyzing) -Total merge + benchmarking process took 0.05996s, equivalent to 1123766.8/5.0 new/old ops (0.1078s for 2 clones -- as 2021228.8/9.0 ops, or 1010614.4/4.5 ops per clone), SPEEDUP of 224839.142x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 8 th.sp.) yielded SPEEDUP of 224839.142x (0.012s -> 5.336e-08s), will amortize in 5.0 ops by saving 0.012s per op. -In 1 tuning rounds (tot. 0.17s, 0.11s for constructor, 2 clones) obtained a SPEEDUP of 22483814.2% (2.248e+05x) (from 0.008002 to 1799 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.024s (of which 1.502e-05s partitioning, 0s I/O); computing times: 4.053e-06s in par. loops, 2.146e-06s sorting, 1.907e-06s analyzing) +Total merge + benchmarking process took 0.024s, equivalent to 476666.7/3.0 new/old ops (0.04793s for 2 clones -- as 951879.7/6.0 ops, or 475939.9/3.0 ops per clone), SPEEDUP of 158338.068x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 8 th.sp.) yielded SPEEDUP of 158338.068x (0.007973s -> 5.035e-08s), will amortize in 3.0 ops by saving 0.007973s per op. +In 1 tuning rounds (tot. 0.072s, 0.048s for constructor, 2 clones) obtained a SPEEDUP of 15833706.8% (1.583e+05x) (from 0.01204 to 1907 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 0.16801 s (1.200e-02 s -> 5.336e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.0720172 s (7.973e-03 s -> 5.035e-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 0.615978 s and estimated a speedup of 1.000000 x (5.336e-08 s -> 5.336e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.351961 s and estimated a speedup of 1.000000 x (5.035e-08 s -> 5.035e-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 8 3 3 6 0.000000 0.040856 0.035994 0.076850 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 8 3 3 6 0.076850 -%:RSB_SUBDIVISION_TIME:A.mtx S N 8 3 3 6 0.040856 -%:RSB_SHUFFLE_TIME:A.mtx S N 8 3 3 6 0.035994 +%:CONSTRUCTOR_TIMES:A.mtx S N 8 3 3 6 0.000000 0.019848 0.016002 0.035850 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 8 3 3 6 0.035850 +%:RSB_SUBDIVISION_TIME:A.mtx S N 8 3 3 6 0.019848 +%:RSB_SHUFFLE_TIME:A.mtx S N 8 3 3 6 0.016002 %:ROW_MAJOR_SORT_TIME:A.mtx S N 8 3 3 6 0.000000 %:ROW_MAJOR_SORT_SCALING:A.mtx S N 8 3 3 6 -nan -%:SORTEDCOO2RSB_TIME:A.mtx S N 8 3 3 6 0.076850 +%:SORTEDCOO2RSB_TIME:A.mtx S N 8 3 3 6 0.035850 %:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 8 3 3 6 0.000 %:UNSORTEDCOO2RSB_SCALING:A.mtx S N 8 3 3 6 1.00 %:SORTEDCOO2RSB_SCALING:A.mtx S N 8 3 3 6 1.00 @@ -4311,65 +4347,65 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 8 3 3 6 6 6 6 # %operation:matrix CONSTRUCTOR[8] SPMV[8] SPMV[8] -%operation:A.mtx 0.100802 1e+09 1e+09 +%operation:A.mtx 0.0518532 1e+09 1e+09 %constructor:matrix SORT[8] SCAN[8] SHUFFLE[8] INSERT[8] -%constructor:A.mtx 0 0.0408561 0 0.0359941 +%constructor:A.mtx 0 0.0198481 0 0.0160019 # symmetric matrix --- skipping transposed benchmarking -# so far, program took 11.182s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 1.648s/0.000s . +# so far, program took 10.097s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.896s/0.000s . getrusage() stats: -ru_maxrss: 69 (maximum resident set size -- MB) -ru_stime : 0.2914s (system CPU time used) -ru_utime : 17.34s (user CPU time used) +ru_maxrss: 71 (maximum resident set size -- MB) +ru_stime : 0.4025s (system CPU time used) +ru_utime : 16.02s (user CPU time used) # multi-type benchmarking (DSCZ) -- now using typecode S (last was D). # Cache block size total 16777216 bytes, per-thread 2097152 bytes -# so far, program took 11.182s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 1.648s/0.000s . +# so far, program took 10.097s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.896s/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 8 threads -# Constructed matrix (took 0.107s): (3 x 3)[0x56a667d0]{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 0.052s): (3 x 3)[0x570a3810]{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 (8 th.) took 0.04611s; avg 0.01537s ( +/- 7.76/ 4.06 %); best 0.01418s; worst 0.01599s; std dev. 0.0008438 (taking best). -Reference operation time is 0.0141761 s (0.001693 Mflops) with 8 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: 0.01418 Mflops: 0.002) -Merge (3 -> 1 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 (8 th.) took 1.693e-05s; avg 5.643e-06s ( +/- 99.05/200.00 %); best 5.336e-08s; worst 1.693e-05s; std dev. 7.98e-06 (taking best). -Reference operation time is 5.33581e-08 s (449.8 Mflops) with 8 threads. -After merge step 1: tpop: 5.336e-08 s ~Mflops: 449.791 nsubm:1 otn:8 -Applying merge (3 -> 1 leaves, 8 th.) yielded SPEEDUP of 265679.178x: 0.01418s -> 5.336e-08s, so taking this instance. +3 iterations (8 th.) took 0.02399s; avg 0.007998s ( +/- 0.02/ 0.03 %); best 0.007996s; worst 0.008s; std dev. 1.701e-06 (taking best). +Reference operation time is 0.00799584 s (0.003002 Mflops) with 8 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: 0.007996 Mflops: 0.003) +Merge (3 -> 1 leaves) took w.c.t. of 1.311e-05s, ~3.099e-06s of computing time (of which 0s sorting, 2.146e-06s analysis) +3 iterations (8 th.) took 1.216e-05s; avg 4.053e-06s ( +/- 98.76/200.00 %); best 5.035e-08s; worst 1.216e-05s; std dev. 5.732e-06 (taking best). +Reference operation time is 5.0354e-08 s (476.6 Mflops) with 8 threads. +After merge step 1: tpop: 5.035e-08 s ~Mflops: 476.625 nsubm:1 otn:8 +Applying merge (3 -> 1 leaves, 8 th.) yielded SPEEDUP of 158792.614x: 0.007996s -> 5.035e-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 0.04802s (of which 1.884e-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 0.04802s, equivalent to 899973.2/3.4 new/old ops (0.1018s for 2 clones -- as 1907453.1/7.2 ops, or 953726.5/3.6 ops per clone), SPEEDUP of 265679.178x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 8 th.sp.) yielded SPEEDUP of 265679.178x (0.01418s -> 5.336e-08s), will amortize in 3.4 ops by saving 0.01418s per op. -In 1 tuning rounds (tot. 0.15s, 0.1s for constructor, 2 clones) obtained a SPEEDUP of 26567817.8% (2.657e+05x) (from 0.001693 to 449.8 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.024s (of which 1.502e-05s partitioning, 0s I/O); computing times: 3.099e-06s in par. loops, 0s sorting, 2.146e-06s analyzing) +Total merge + benchmarking process took 0.024s, equivalent to 476567.2/3.0 new/old ops (0.04793s for 2 clones -- as 951799.2/6.0 ops, or 475899.6/3.0 ops per clone), SPEEDUP of 158792.614x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 8 th.sp.) yielded SPEEDUP of 158792.614x (0.007996s -> 5.035e-08s), will amortize in 3.0 ops by saving 0.007996s per op. +In 1 tuning rounds (tot. 0.072s, 0.048s for constructor, 2 clones) obtained a SPEEDUP of 15879161.4% (1.588e+05x) (from 0.003002 to 476.6 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 0.14801 s (1.418e-02 s -> 5.336e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.072185 s (7.996e-03 s -> 5.035e-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 0.683928 s and estimated a speedup of 1.000000 x (5.336e-08 s -> 5.336e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.411792 s and estimated a speedup of 1.000000 x (5.035e-08 s -> 5.035e-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 8 3 3 6 0.000001 0.042494 0.031994 0.074488 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 8 3 3 6 0.074489 -%:RSB_SUBDIVISION_TIME:A.mtx S N 8 3 3 6 0.042494 -%:RSB_SHUFFLE_TIME:A.mtx S N 8 3 3 6 0.031994 -%:ROW_MAJOR_SORT_TIME:A.mtx S N 8 3 3 6 0.000001 -%:ROW_MAJOR_SORT_SCALING:A.mtx S N 8 3 3 6 1.000 -%:SORTEDCOO2RSB_TIME:A.mtx S N 8 3 3 6 0.074488 +%:CONSTRUCTOR_TIMES:A.mtx S N 8 3 3 6 0.000000 0.019716 0.015987 0.035703 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 8 3 3 6 0.035703 +%:RSB_SUBDIVISION_TIME:A.mtx S N 8 3 3 6 0.019716 +%:RSB_SHUFFLE_TIME:A.mtx S N 8 3 3 6 0.015987 +%:ROW_MAJOR_SORT_TIME:A.mtx S N 8 3 3 6 0.000000 +%:ROW_MAJOR_SORT_SCALING:A.mtx S N 8 3 3 6 -nan +%:SORTEDCOO2RSB_TIME:A.mtx S N 8 3 3 6 0.035703 %:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 8 3 3 6 0.000 %:UNSORTEDCOO2RSB_SCALING:A.mtx S N 8 3 3 6 1.00 %:SORTEDCOO2RSB_SCALING:A.mtx S N 8 3 3 6 1.00 %:RSB_SUBDIVISION_SCALING:A.mtx S N 8 3 3 6 1.00 %:RSB_SHUFFLE_SCALING:A.mtx S N 8 3 3 6 1.00 -%:CONSTRUCTOR_SCALING:A.mtx S N 8 3 3 6 1.00 1.00 1.00 1.00 +%:CONSTRUCTOR_SCALING:A.mtx S N 8 3 3 6 -nan 1.00 1.00 1.00 #%:SM_COUNTS: Tot HalfwordCsr FullwordCsr HalfwordCoo FullwordCoo %:SM_COUNTS:A.mtx S N 8 3 3 6 1 1 0 0 0 %:SM_IDXOCCUPATIONRSBVSCOOANDCSR:A.mtx S N 8 3 3 6 28 48 36 @@ -4378,50 +4414,50 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 8 3 3 6 6 6 6 # %operation:matrix CONSTRUCTOR[8] SPMV[8] SPMV[8] -%operation:A.mtx 0.106514 1e+09 1e+09 +%operation:A.mtx 0.0517061 1e+09 1e+09 %constructor:matrix SORT[8] SCAN[8] SHUFFLE[8] INSERT[8] -%constructor:A.mtx 9.53674e-07 0.0424941 0 0.0319939 +%constructor:A.mtx 0 0.019716 0 0.0159872 # 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 8 threads -# Constructed matrix (took 0.096s): (3 x 3)[0x56a667d0]{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 0.063s): (3 x 3)[0x570a3810]{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 (8 th.) took 0.04401s; avg 0.01467s ( +/- 18.18/ 9.22 %); best 0.012s; worst 0.01602s; std dev. 0.001886 (taking best). -Reference operation time is 0.0120029 s (0.007998 Mflops) with 8 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: 0.012 Mflops: 0.008) -Merge (3 -> 1 leaves) took w.c.t. of 1.812e-05s, ~6.199e-06s of computing time (of which 1.907e-06s sorting, 3.099e-06s analysis) -3 iterations (8 th.) took 4.053e-06s; avg 1.351e-06s ( +/- 96.05/129.41 %); best 5.336e-08s; worst 3.099e-06s; std dev. 1.296e-06 (taking best). -Reference operation time is 5.33581e-08 s (1799 Mflops) with 8 threads. -After merge step 1: tpop: 5.336e-08 s ~Mflops: 1799.165 nsubm:1 otn:8 -Applying merge (3 -> 1 leaves, 8 th.) yielded SPEEDUP of 224950.849x: 0.012s -> 5.336e-08s, so taking this instance. +3 iterations (8 th.) took 0.0243s; avg 0.008102s ( +/- 1.39/ 2.36 %); best 0.007989s; worst 0.008293s; std dev. 0.000136 (taking best). +Reference operation time is 0.00798893 s (0.01202 Mflops) with 8 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: 0.007989 Mflops: 0.012) +Merge (3 -> 1 leaves) took w.c.t. of 1.597e-05s, ~5.007e-06s of computing time (of which 9.537e-07s sorting, 3.099e-06s analysis) +3 iterations (8 th.) took 4.053e-06s; avg 1.351e-06s ( +/- 96.27/111.76 %); best 5.035e-08s; worst 2.861e-06s; std dev. 1.173e-06 (taking best). +Reference operation time is 5.0354e-08 s (1907 Mflops) with 8 threads. +After merge step 1: tpop: 5.035e-08 s ~Mflops: 1906.502 nsubm:1 otn:8 +Applying merge (3 -> 1 leaves, 8 th.) yielded SPEEDUP of 158655.303x: 0.007989s -> 5.035e-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 0.04798s (of which 2.098e-05s partitioning, 0s I/O); computing times: 6.199e-06s in par. loops, 1.907e-06s sorting, 3.099e-06s analyzing) -Total merge + benchmarking process took 0.04798s, equivalent to 899227.0/4.0 new/old ops (0.09573s for 2 clones -- as 1794146.6/8.0 ops, or 897073.3/4.0 ops per clone), SPEEDUP of 224950.849x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 8 th.sp.) yielded SPEEDUP of 224950.849x (0.012s -> 5.336e-08s), will amortize in 4.0 ops by saving 0.012s per op. -In 1 tuning rounds (tot. 0.14s, 0.096s for constructor, 2 clones) obtained a SPEEDUP of 22494984.9% (2.25e+05x) (from 0.007998 to 1799 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.03168s (of which 1.812e-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 0.03168s, equivalent to 629124.1/4.0 new/old ops (0.05561s for 2 clones -- as 1104337.1/7.0 ops, or 552168.6/3.5 ops per clone), SPEEDUP of 158655.303x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 8 th.sp.) yielded SPEEDUP of 158655.303x (0.007989s -> 5.035e-08s), will amortize in 4.0 ops by saving 0.007989s per op. +In 1 tuning rounds (tot. 0.08s, 0.056s for constructor, 2 clones) obtained a SPEEDUP of 15865430.3% (1.587e+05x) (from 0.01202 to 1907 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 0.139855 s (1.200e-02 s -> 5.336e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.080179 s (7.989e-03 s -> 5.035e-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 0.683937 s and estimated a speedup of 1.000000 x (5.336e-08 s -> 5.336e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.363781 s and estimated a speedup of 1.000000 x (5.035e-08 s -> 5.035e-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 8 3 3 6 0.000000 0.031446 0.031996 0.063442 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 8 3 3 6 0.063442 -%:RSB_SUBDIVISION_TIME:A.mtx S N 8 3 3 6 0.031446 -%:RSB_SHUFFLE_TIME:A.mtx S N 8 3 3 6 0.031996 +%:CONSTRUCTOR_TIMES:A.mtx S N 8 3 3 6 0.000000 0.031022 0.022323 0.053345 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 8 3 3 6 0.053345 +%:RSB_SUBDIVISION_TIME:A.mtx S N 8 3 3 6 0.031022 +%:RSB_SHUFFLE_TIME:A.mtx S N 8 3 3 6 0.022323 %:ROW_MAJOR_SORT_TIME:A.mtx S N 8 3 3 6 0.000000 %:ROW_MAJOR_SORT_SCALING:A.mtx S N 8 3 3 6 -nan -%:SORTEDCOO2RSB_TIME:A.mtx S N 8 3 3 6 0.063442 +%:SORTEDCOO2RSB_TIME:A.mtx S N 8 3 3 6 0.053345 %:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 8 3 3 6 0.000 %:UNSORTEDCOO2RSB_SCALING:A.mtx S N 8 3 3 6 1.00 %:SORTEDCOO2RSB_SCALING:A.mtx S N 8 3 3 6 1.00 @@ -4436,59 +4472,59 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 8 3 3 6 6 6 6 # %operation:matrix CONSTRUCTOR[8] SPMV[8] SPMV[8] -%operation:A.mtx 0.0956209 1e+09 1e+09 +%operation:A.mtx 0.06302 1e+09 1e+09 %constructor:matrix SORT[8] SCAN[8] SHUFFLE[8] INSERT[8] -%constructor:A.mtx 0 0.031446 0 0.031996 +%constructor:A.mtx 0 0.0310221 0 0.0223229 # symmetric matrix --- skipping transposed benchmarking -# so far, program took 13.367s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 3.304s/0.000s . +# so far, program took 11.469s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 1.824s/0.000s . getrusage() stats: -ru_maxrss: 69 (maximum resident set size -- MB) -ru_stime : 0.4519s (system CPU time used) -ru_utime : 26.38s (user CPU time used) +ru_maxrss: 71 (maximum resident set size -- MB) +ru_stime : 0.628s (system CPU time used) +ru_utime : 22.78s (user CPU time used) # multi-type benchmarking (DSCZ) -- now using typecode C (last was S). # Cache block size total 16777216 bytes, per-thread 2097152 bytes -# so far, program took 13.367s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 3.304s/0.000s . +# so far, program took 11.469s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 1.824s/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 8 threads -# Constructed matrix (took 0.102s): (3 x 3)[0x56a69140]{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 0.064s): (3 x 3)[0x570a6180]{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 (8 th.) took 0.04398s; avg 0.01466s ( +/- 9.03/ 9.08 %); best 0.01334s; worst 0.01599s; std dev. 0.001084 (taking best). -Reference operation time is 0.0133359 s (0.007199 Mflops) with 8 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: 0.01334 Mflops: 0.007) -Merge (3 -> 1 leaves) took w.c.t. of 1.907e-05s, ~5.96e-06s of computing time (of which 9.537e-07s sorting, 3.099e-06s analysis) -3 iterations (8 th.) took 2.503e-05s; avg 8.345e-06s ( +/- 99.36/200.00 %); best 5.336e-08s; worst 2.503e-05s; std dev. 1.18e-05 (taking best). -Reference operation time is 5.33581e-08 s (1799 Mflops) with 8 threads. -After merge step 1: tpop: 5.336e-08 s ~Mflops: 1799.165 nsubm:1 otn:8 -Applying merge (3 -> 1 leaves, 8 th.) yielded SPEEDUP of 249932.976x: 0.01334s -> 5.336e-08s, so taking this instance. +3 iterations (8 th.) took 0.02399s; avg 0.007998s ( +/- 0.03/ 0.03 %); best 0.007996s; worst 0.008001s; std dev. 2.153e-06 (taking best). +Reference operation time is 0.00799584 s (0.01201 Mflops) with 8 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: 0.007996 Mflops: 0.012) +Merge (3 -> 1 leaves) took w.c.t. of 1.287e-05s, ~2.861e-06s of computing time (of which 9.537e-07s sorting, 1.907e-06s analysis) +3 iterations (8 th.) took 1.597e-05s; avg 5.325e-06s ( +/- 99.05/182.09 %); best 5.035e-08s; worst 1.502e-05s; std dev. 6.867e-06 (taking best). +Reference operation time is 5.0354e-08 s (1907 Mflops) with 8 threads. +After merge step 1: tpop: 5.035e-08 s ~Mflops: 1906.502 nsubm:1 otn:8 +Applying merge (3 -> 1 leaves, 8 th.) yielded SPEEDUP of 158792.614x: 0.007996s -> 5.035e-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 0.03999s (of which 2.098e-05s partitioning, 0s I/O); computing times: 5.96e-06s in par. loops, 9.537e-07s sorting, 3.099e-06s analyzing) -Total merge + benchmarking process took 0.03999s, equivalent to 749557.6/3.0 new/old ops (0.09133s for 2 clones -- as 1711697.9/6.8 ops, or 855849.0/3.4 ops per clone), SPEEDUP of 249932.976x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 8 th.sp.) yielded SPEEDUP of 249932.976x (0.01334s -> 5.336e-08s), will amortize in 3.0 ops by saving 0.01334s per op. -In 1 tuning rounds (tot. 0.14s, 0.091s for constructor, 2 clones) obtained a SPEEDUP of 24993197.6% (2.499e+05x) (from 0.007199 to 1799 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.02013s (of which 1.502e-05s partitioning, 0s I/O); computing times: 2.861e-06s in par. loops, 9.537e-07s sorting, 1.907e-06s analyzing) +Total merge + benchmarking process took 0.02013s, equivalent to 399829.5/2.5 new/old ops (0.04403s for 2 clones -- as 874469.7/5.5 ops, or 437234.8/2.8 ops per clone), SPEEDUP of 158792.614x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 8 th.sp.) yielded SPEEDUP of 158792.614x (0.007996s -> 5.035e-08s), will amortize in 2.5 ops by saving 0.007996s per op. +In 1 tuning rounds (tot. 0.068s, 0.044s for constructor, 2 clones) obtained a SPEEDUP of 15879161.4% (1.588e+05x) (from 0.01201 to 1907 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 0.135451 s (1.334e-02 s -> 5.336e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.068145 s (7.996e-03 s -> 5.035e-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 0.707517 s and estimated a speedup of 1.000000 x (5.336e-08 s -> 5.336e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.423831 s and estimated a speedup of 1.000000 x (5.035e-08 s -> 5.035e-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 8 3 3 6 0.000000 0.040958 0.032011 0.072969 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 8 3 3 6 0.072969 -%:RSB_SUBDIVISION_TIME:A.mtx S N 8 3 3 6 0.040958 -%:RSB_SHUFFLE_TIME:A.mtx S N 8 3 3 6 0.032011 +%:CONSTRUCTOR_TIMES:A.mtx S N 8 3 3 6 0.000000 0.027983 0.019994 0.047977 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 8 3 3 6 0.047977 +%:RSB_SUBDIVISION_TIME:A.mtx S N 8 3 3 6 0.027983 +%:RSB_SHUFFLE_TIME:A.mtx S N 8 3 3 6 0.019994 %:ROW_MAJOR_SORT_TIME:A.mtx S N 8 3 3 6 0.000000 %:ROW_MAJOR_SORT_SCALING:A.mtx S N 8 3 3 6 -nan -%:SORTEDCOO2RSB_TIME:A.mtx S N 8 3 3 6 0.072969 +%:SORTEDCOO2RSB_TIME:A.mtx S N 8 3 3 6 0.047977 %:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 8 3 3 6 0.000 %:UNSORTEDCOO2RSB_SCALING:A.mtx S N 8 3 3 6 1.00 %:SORTEDCOO2RSB_SCALING:A.mtx S N 8 3 3 6 1.00 @@ -4503,56 +4539,56 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 8 3 3 6 6 6 6 # %operation:matrix CONSTRUCTOR[8] SPMV[8] SPMV[8] -%operation:A.mtx 0.101522 1e+09 1e+09 +%operation:A.mtx 0.0639861 1e+09 1e+09 %constructor:matrix SORT[8] SCAN[8] SHUFFLE[8] INSERT[8] -%constructor:A.mtx 0 0.0409579 0 0.032011 +%constructor:A.mtx 0 0.027983 0 0.019994 # 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 8 threads -# Constructed matrix (took 0.116s): (3 x 3)[0x56a69140]{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 0.055s): (3 x 3)[0x570a6180]{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 (8 th.) took 0.03999s; avg 0.01333s ( +/- 39.99/ 20.00 %); best 0.007998s; worst 0.01599s; std dev. 0.003769 (taking best). -Reference operation time is 0.00799799 s (0.04801 Mflops) with 8 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: 0.007998 Mflops: 0.048) -Merge (3 -> 1 leaves) took w.c.t. of 1.693e-05s, ~5.007e-06s of computing time (of which 2.146e-06s sorting, 2.861e-06s analysis) -3 iterations (8 th.) took 5.007e-06s; avg 1.669e-06s ( +/- 96.80/142.86 %); best 5.336e-08s; worst 4.053e-06s; std dev. 1.73e-06 (taking best). -Reference operation time is 5.33581e-08 s (7197 Mflops) with 8 threads. -After merge step 1: tpop: 5.336e-08 s ~Mflops: 7196.661 nsubm:1 otn:8 -Applying merge (3 -> 1 leaves, 8 th.) yielded SPEEDUP of 149892.761x: 0.007998s -> 5.336e-08s, so taking this instance. +3 iterations (8 th.) took 0.024s; avg 0.008s ( +/- 0.04/ 0.03 %); best 0.007996s; worst 0.008002s; std dev. 2.575e-06 (taking best). +Reference operation time is 0.00799608 s (0.04802 Mflops) with 8 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: 0.007996 Mflops: 0.048) +Merge (3 -> 1 leaves) took w.c.t. of 1.192e-05s, ~3.099e-06s of computing time (of which 9.537e-07s sorting, 1.192e-06s analysis) +3 iterations (8 th.) took 4.053e-06s; avg 1.351e-06s ( +/- 96.27/129.41 %); best 5.035e-08s; worst 3.099e-06s; std dev. 1.296e-06 (taking best). +Reference operation time is 5.0354e-08 s (7626 Mflops) with 8 threads. +After merge step 1: tpop: 5.035e-08 s ~Mflops: 7626.007 nsubm:1 otn:8 +Applying merge (3 -> 1 leaves, 8 th.) yielded SPEEDUP of 158797.348x: 0.007996s -> 5.035e-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 0.04799s (of which 2.003e-05s partitioning, 0s I/O); computing times: 5.007e-06s in par. loops, 2.146e-06s sorting, 2.861e-06s analyzing) -Total merge + benchmarking process took 0.04799s, equivalent to 899356.6/6.0 new/old ops (0.0919s for 2 clones -- as 1722399.5/11.5 ops, or 861199.7/5.7 ops per clone), SPEEDUP of 149892.761x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 8 th.sp.) yielded SPEEDUP of 149892.761x (0.007998s -> 5.336e-08s), will amortize in 6.0 ops by saving 0.007998s per op. -In 1 tuning rounds (tot. 0.13s, 0.092s for constructor, 2 clones) obtained a SPEEDUP of 14989176.1% (1.499e+05x) (from 0.04801 to 7197 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.02399s (of which 1.407e-05s partitioning, 0s I/O); computing times: 3.099e-06s in par. loops, 9.537e-07s sorting, 1.192e-06s analyzing) +Total merge + benchmarking process took 0.02399s, equivalent to 476406.2/3.0 new/old ops (0.04793s for 2 clones -- as 951898.7/6.0 ops, or 475949.3/3.0 ops per clone), SPEEDUP of 158797.348x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 8 th.sp.) yielded SPEEDUP of 158797.348x (0.007996s -> 5.035e-08s), will amortize in 3.0 ops by saving 0.007996s per op. +In 1 tuning rounds (tot. 0.072s, 0.048s for constructor, 2 clones) obtained a SPEEDUP of 15879634.8% (1.588e+05x) (from 0.04802 to 7626 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 0.131989 s (7.998e-03 s -> 5.336e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.072 s (7.996e-03 s -> 5.035e-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 0.711985 s and estimated a speedup of 1.000000 x (5.336e-08 s -> 5.336e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.425217 s and estimated a speedup of 1.000000 x (5.035e-08 s -> 5.035e-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 8 3 3 6 0.000001 0.051703 0.032019 0.083722 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 8 3 3 6 0.083723 -%:RSB_SUBDIVISION_TIME:A.mtx S N 8 3 3 6 0.051703 -%:RSB_SHUFFLE_TIME:A.mtx S N 8 3 3 6 0.032019 -%:ROW_MAJOR_SORT_TIME:A.mtx S N 8 3 3 6 0.000001 -%:ROW_MAJOR_SORT_SCALING:A.mtx S N 8 3 3 6 1.000 -%:SORTEDCOO2RSB_TIME:A.mtx S N 8 3 3 6 0.083722 +%:CONSTRUCTOR_TIMES:A.mtx S N 8 3 3 6 0.000000 0.022558 0.016004 0.038562 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 8 3 3 6 0.038562 +%:RSB_SUBDIVISION_TIME:A.mtx S N 8 3 3 6 0.022558 +%:RSB_SHUFFLE_TIME:A.mtx S N 8 3 3 6 0.016004 +%:ROW_MAJOR_SORT_TIME:A.mtx S N 8 3 3 6 0.000000 +%:ROW_MAJOR_SORT_SCALING:A.mtx S N 8 3 3 6 -nan +%:SORTEDCOO2RSB_TIME:A.mtx S N 8 3 3 6 0.038562 %:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 8 3 3 6 0.000 %:UNSORTEDCOO2RSB_SCALING:A.mtx S N 8 3 3 6 1.00 %:SORTEDCOO2RSB_SCALING:A.mtx S N 8 3 3 6 1.00 %:RSB_SUBDIVISION_SCALING:A.mtx S N 8 3 3 6 1.00 %:RSB_SHUFFLE_SCALING:A.mtx S N 8 3 3 6 1.00 -%:CONSTRUCTOR_SCALING:A.mtx S N 8 3 3 6 1.00 1.00 1.00 1.00 +%:CONSTRUCTOR_SCALING:A.mtx S N 8 3 3 6 -nan 1.00 1.00 1.00 #%:SM_COUNTS: Tot HalfwordCsr FullwordCsr HalfwordCoo FullwordCoo %:SM_COUNTS:A.mtx S N 8 3 3 6 1 1 0 0 0 %:SM_IDXOCCUPATIONRSBVSCOOANDCSR:A.mtx S N 8 3 3 6 28 48 36 @@ -4561,59 +4597,59 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 8 3 3 6 6 6 6 # %operation:matrix CONSTRUCTOR[8] SPMV[8] SPMV[8] -%operation:A.mtx 0.115729 1e+09 1e+09 +%operation:A.mtx 0.0545619 1e+09 1e+09 %constructor:matrix SORT[8] SCAN[8] SHUFFLE[8] INSERT[8] -%constructor:A.mtx 1.19209e-06 0.051703 0 0.0320191 +%constructor:A.mtx 0 0.022558 0 0.0160041 # symmetric matrix --- skipping transposed benchmarking -# so far, program took 15.622s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 4.991s/0.000s . +# so far, program took 12.909s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 2.813s/0.000s . getrusage() stats: -ru_maxrss: 69 (maximum resident set size -- MB) -ru_stime : 0.5614s (system CPU time used) -ru_utime : 35.54s (user CPU time used) +ru_maxrss: 71 (maximum resident set size -- MB) +ru_stime : 0.8506s (system CPU time used) +ru_utime : 29.94s (user CPU time used) # multi-type benchmarking (DSCZ) -- now using typecode Z (last was C). # Cache block size total 16777216 bytes, per-thread 2097152 bytes -# so far, program took 15.622s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 4.991s/0.000s . +# so far, program took 12.909s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 2.813s/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 8 threads -# Constructed matrix (took 0.110s): (3 x 3)[0x56a69140]{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 0.064s): (3 x 3)[0x570a6180]{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 (8 th.) took 0.04796s; avg 0.01599s ( +/- 0.09/ 0.12 %); best 0.01597s; worst 0.01601s; std dev. 1.429e-05 (taking best). -Reference operation time is 0.0159729 s (0.00601 Mflops) with 8 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: 0.01597 Mflops: 0.006) -Merge (3 -> 1 leaves) took w.c.t. of 1.502e-05s, ~5.007e-06s of computing time (of which 2.146e-06s sorting, 3.099e-06s analysis) -3 iterations (8 th.) took 2.003e-05s; avg 6.676e-06s ( +/- 99.20/185.71 %); best 5.336e-08s; worst 1.907e-05s; std dev. 8.775e-06 (taking best). -Reference operation time is 5.33581e-08 s (1799 Mflops) with 8 threads. -After merge step 1: tpop: 5.336e-08 s ~Mflops: 1799.165 nsubm:1 otn:8 -Applying merge (3 -> 1 leaves, 8 th.) yielded SPEEDUP of 299352.100x: 0.01597s -> 5.336e-08s, so taking this instance. +3 iterations (8 th.) took 0.02399s; avg 0.007996s ( +/- 10.89/ 10.88 %); best 0.007125s; worst 0.008866s; std dev. 0.0007108 (taking best). +Reference operation time is 0.0071249 s (0.01347 Mflops) with 8 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: 0.007125 Mflops: 0.013) +Merge (3 -> 1 leaves) took w.c.t. of 1.287e-05s, ~3.815e-06s of computing time (of which 9.537e-07s sorting, 1.907e-06s analysis) +3 iterations (8 th.) took 1.597e-05s; avg 5.325e-06s ( +/- 99.05/200.00 %); best 5.035e-08s; worst 1.597e-05s; std dev. 7.53e-06 (taking best). +Reference operation time is 5.0354e-08 s (1907 Mflops) with 8 threads. +After merge step 1: tpop: 5.035e-08 s ~Mflops: 1906.502 nsubm:1 otn:8 +Applying merge (3 -> 1 leaves, 8 th.) yielded SPEEDUP of 141496.212x: 0.007125s -> 5.035e-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 0.03997s (of which 1.693e-05s partitioning, 0s I/O); computing times: 5.007e-06s in par. loops, 2.146e-06s sorting, 3.099e-06s analyzing) -Total merge + benchmarking process took 0.03997s, equivalent to 749052.7/2.5 new/old ops (0.08791s for 2 clones -- as 1647551.4/5.5 ops, or 823775.7/2.8 ops per clone), SPEEDUP of 299352.100x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 8 th.sp.) yielded SPEEDUP of 299352.100x (0.01597s -> 5.336e-08s), will amortize in 2.5 ops by saving 0.01597s per op. -In 1 tuning rounds (tot. 0.14s, 0.088s for constructor, 2 clones) obtained a SPEEDUP of 29935110.0% (2.994e+05x) (from 0.00601 to 1799 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.02399s (of which 1.621e-05s partitioning, 0s I/O); computing times: 3.815e-06s in par. loops, 9.537e-07s sorting, 1.907e-06s analyzing) +Total merge + benchmarking process took 0.02399s, equivalent to 476330.5/3.4 new/old ops (0.0479s for 2 clones -- as 951344.7/6.7 ops, or 475672.3/3.4 ops per clone), SPEEDUP of 141496.212x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 8 th.sp.) yielded SPEEDUP of 141496.212x (0.007125s -> 5.035e-08s), will amortize in 3.4 ops by saving 0.007125s per op. +In 1 tuning rounds (tot. 0.072s, 0.048s for constructor, 2 clones) obtained a SPEEDUP of 14149521.2% (1.415e+05x) (from 0.01347 to 1907 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 0.135976 s (1.597e-02 s -> 5.336e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.071986 s (7.125e-03 s -> 5.035e-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 0.631975 s and estimated a speedup of 1.000000 x (5.336e-08 s -> 5.336e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.519988 s and estimated a speedup of 1.000000 x (5.035e-08 s -> 5.035e-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 8 3 3 6 0.000000 0.049767 0.031825 0.081592 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 8 3 3 6 0.081592 -%:RSB_SUBDIVISION_TIME:A.mtx S N 8 3 3 6 0.049767 -%:RSB_SHUFFLE_TIME:A.mtx S N 8 3 3 6 0.031825 +%:CONSTRUCTOR_TIMES:A.mtx S N 8 3 3 6 0.000000 0.015652 0.015996 0.031648 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 8 3 3 6 0.031648 +%:RSB_SUBDIVISION_TIME:A.mtx S N 8 3 3 6 0.015652 +%:RSB_SHUFFLE_TIME:A.mtx S N 8 3 3 6 0.015996 %:ROW_MAJOR_SORT_TIME:A.mtx S N 8 3 3 6 0.000000 %:ROW_MAJOR_SORT_SCALING:A.mtx S N 8 3 3 6 -nan -%:SORTEDCOO2RSB_TIME:A.mtx S N 8 3 3 6 0.081592 +%:SORTEDCOO2RSB_TIME:A.mtx S N 8 3 3 6 0.031648 %:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 8 3 3 6 0.000 %:UNSORTEDCOO2RSB_SCALING:A.mtx S N 8 3 3 6 1.00 %:SORTEDCOO2RSB_SCALING:A.mtx S N 8 3 3 6 1.00 @@ -4628,50 +4664,50 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 8 3 3 6 6 6 6 # %operation:matrix CONSTRUCTOR[8] SPMV[8] SPMV[8] -%operation:A.mtx 0.109791 1e+09 1e+09 +%operation:A.mtx 0.0636661 1e+09 1e+09 %constructor:matrix SORT[8] SCAN[8] SHUFFLE[8] INSERT[8] -%constructor:A.mtx 0 0.049767 0 0.0318251 +%constructor:A.mtx 0 0.0156519 0 0.015996 # 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 8 threads -# Constructed matrix (took 0.120s): (3 x 3)[0x56a69140]{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 0.064s): (3 x 3)[0x570a6180]{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 (8 th.) took 0.04799s; avg 0.016s ( +/- 0.04/ 0.02 %); best 0.01599s; worst 0.016s; std dev. 4.512e-06 (taking best). -Reference operation time is 0.01599 s (0.02401 Mflops) with 8 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: 0.01599 Mflops: 0.024) -Merge (3 -> 1 leaves) took w.c.t. of 1.621e-05s, ~5.007e-06s of computing time (of which 9.537e-07s sorting, 2.861e-06s analysis) -3 iterations (8 th.) took 5.007e-06s; avg 1.669e-06s ( +/- 96.80/142.86 %); best 5.336e-08s; worst 4.053e-06s; std dev. 1.73e-06 (taking best). -Reference operation time is 5.33581e-08 s (7197 Mflops) with 8 threads. -After merge step 1: tpop: 5.336e-08 s ~Mflops: 7196.661 nsubm:1 otn:8 -Applying merge (3 -> 1 leaves, 8 th.) yielded SPEEDUP of 299673.816x: 0.01599s -> 5.336e-08s, so taking this instance. +3 iterations (8 th.) took 0.02399s; avg 0.007998s ( +/- 0.11/ 0.19 %); best 0.007989s; worst 0.008013s; std dev. 1.088e-05 (taking best). +Reference operation time is 0.00798893 s (0.04807 Mflops) with 8 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: 0.007989 Mflops: 0.048) +Merge (3 -> 1 leaves) took w.c.t. of 1.287e-05s, ~3.815e-06s of computing time (of which 9.537e-07s sorting, 1.907e-06s analysis) +3 iterations (8 th.) took 5.007e-06s; avg 1.669e-06s ( +/- 96.98/128.57 %); best 5.035e-08s; worst 3.815e-06s; std dev. 1.593e-06 (taking best). +Reference operation time is 5.0354e-08 s (7626 Mflops) with 8 threads. +After merge step 1: tpop: 5.035e-08 s ~Mflops: 7626.007 nsubm:1 otn:8 +Applying merge (3 -> 1 leaves, 8 th.) yielded SPEEDUP of 158655.303x: 0.007989s -> 5.035e-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 0.04001s (of which 1.812e-05s partitioning, 0s I/O); computing times: 5.007e-06s in par. loops, 9.537e-07s sorting, 2.861e-06s analyzing) -Total merge + benchmarking process took 0.04001s, equivalent to 749843.6/2.5 new/old ops (0.09193s for 2 clones -- as 1722926.7/5.7 ops, or 861463.4/2.9 ops per clone), SPEEDUP of 299673.816x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 8 th.sp.) yielded SPEEDUP of 299673.816x (0.01599s -> 5.336e-08s), will amortize in 2.5 ops by saving 0.01599s per op. -In 1 tuning rounds (tot. 0.14s, 0.092s for constructor, 2 clones) obtained a SPEEDUP of 29967281.6% (2.997e+05x) (from 0.02401 to 7197 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.03999s (of which 1.502e-05s partitioning, 0s I/O); computing times: 3.815e-06s in par. loops, 9.537e-07s sorting, 1.907e-06s analyzing) +Total merge + benchmarking process took 0.03999s, equivalent to 794233.0/5.0 new/old ops (0.07193s for 2 clones -- as 1428522.7/9.0 ops, or 714261.4/4.5 ops per clone), SPEEDUP of 158655.303x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 8 th.sp.) yielded SPEEDUP of 158655.303x (0.007989s -> 5.035e-08s), will amortize in 5.0 ops by saving 0.007989s per op. +In 1 tuning rounds (tot. 0.096s, 0.072s for constructor, 2 clones) obtained a SPEEDUP of 15865430.3% (1.587e+05x) (from 0.04807 to 7626 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 0.140011 s (1.599e-02 s -> 5.336e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.0960031 s (7.989e-03 s -> 5.035e-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 0.755957 s and estimated a speedup of 1.000000 x (5.336e-08 s -> 5.336e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.748805 s and estimated a speedup of 1.000000 x (5.035e-08 s -> 5.035e-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 8 3 3 6 0.000000 0.048016 0.035998 0.084014 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 8 3 3 6 0.084014 -%:RSB_SUBDIVISION_TIME:A.mtx S N 8 3 3 6 0.048016 -%:RSB_SHUFFLE_TIME:A.mtx S N 8 3 3 6 0.035998 +%:CONSTRUCTOR_TIMES:A.mtx S N 8 3 3 6 0.000000 0.023843 0.023961 0.047804 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 8 3 3 6 0.047804 +%:RSB_SUBDIVISION_TIME:A.mtx S N 8 3 3 6 0.023843 +%:RSB_SHUFFLE_TIME:A.mtx S N 8 3 3 6 0.023961 %:ROW_MAJOR_SORT_TIME:A.mtx S N 8 3 3 6 0.000000 %:ROW_MAJOR_SORT_SCALING:A.mtx S N 8 3 3 6 -nan -%:SORTEDCOO2RSB_TIME:A.mtx S N 8 3 3 6 0.084014 +%:SORTEDCOO2RSB_TIME:A.mtx S N 8 3 3 6 0.047804 %:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 8 3 3 6 0.000 %:UNSORTEDCOO2RSB_SCALING:A.mtx S N 8 3 3 6 1.00 %:SORTEDCOO2RSB_SCALING:A.mtx S N 8 3 3 6 1.00 @@ -4686,332 +4722,332 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 8 3 3 6 6 6 6 # %operation:matrix CONSTRUCTOR[8] SPMV[8] SPMV[8] -%operation:A.mtx 0.12003 1e+09 1e+09 +%operation:A.mtx 0.063812 1e+09 1e+09 %constructor:matrix SORT[8] SCAN[8] SHUFFLE[8] INSERT[8] -%constructor:A.mtx 0 0.0480161 0 0.0359979 +%constructor:A.mtx 0 0.0238431 0 0.0239611 # symmetric matrix --- skipping transposed benchmarking -# so far, program took 17.876s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 6.655s/0.000s . +# so far, program took 14.878s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 4.250s/0.000s . getrusage() stats: -ru_maxrss: 69 (maximum resident set size -- MB) -ru_stime : 0.7147s (system CPU time used) -ru_utime : 44.62s (user CPU time used) +ru_maxrss: 71 (maximum resident set size -- MB) +ru_stime : 1.081s (system CPU time used) +ru_utime : 38.12s (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 8 8 0 4.0000 4.6667 3 1 449.79 1.190e-02 0.000e+00 5.336e-08 0.000e+00 1.361e-01 2.77e+00 5.17e+00 1 2.40e-05 -pr: 9:R_R A 3 3 6 4 D S N 8 8 0 4.0000 4.6667 3 1 1799.17 1.200e-02 0.000e+00 5.336e-08 0.000e+00 1.680e-01 6.82e+00 2.79e+00 1 9.60e-05 +pr: 1:R_R A 3 3 6 1 D S N 8 8 0 4.0000 4.6667 3 1 476.63 7.951e-03 0.000e+00 5.035e-08 0.000e+00 7.199e-02 2.94e+00 5.17e+00 1 2.40e-05 +pr: 9:R_R A 3 3 6 4 D S N 8 8 0 4.0000 4.6667 3 1 1906.50 7.973e-03 0.000e+00 5.035e-08 0.000e+00 7.202e-02 7.23e+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. 22390203.8 % faster, avg. sp. ratio 223903.038x, max sp. ratio 224839.142x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 2849823.5/2550920.5/3148726.5/5699647.0 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 12.7/ 11.4/ 14.0/ 25.4 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 12.7, min. 11.4, max. 14.0 ops) +#pr: (in succ. cases rsb autotuning gave avg. 15811926.5 % faster, avg. sp. ratio 158120.265x, max sp. ratio 158338.068x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 1429959.8/1429701.7/1430217.8/2859919.5 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 9.0/ 9.0/ 9.1/ 18.1 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 9.0, min. 9.0, max. 9.1 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 3.673/ 2.324/ 5.023,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 9.596/ 2.774/ 6.822,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 3.892/ 2.463/ 5.322,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 10.168/ 2.939/ 7.229,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.: 0.15 s, min 0.14 s, max 0.17 s, tot 0.30 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.15 s, min 0.14 s, max 0.17 s, tot 0.30 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 1.124e+03, min 4.498e+02, max 1.799e+03 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 5.010e-03, min 2.017e-03, max 8.002e-03 (2 samples) -#pr: best tun. rsb operation time was: on avg. 5.336e-08s, min 5.336e-08s, max 5.336e-08s, tot 1.067e-07s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 1.195e-02s, min 1.190e-02s, max 1.200e-02s, tot 2.389e-02s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 4.440e+00 9.595e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 2.182e+00 +#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. 1.192e+03, min 4.766e+02, max 1.907e+03 (2 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 7.530e-03, min 3.018e-03, max 1.204e-02 (2 samples) +#pr: best tun. rsb operation time was: on avg. 5.035e-08s, min 5.035e-08s, max 5.035e-08s, tot 1.007e-07s (2 samples) +#pr: ref. unt. rsb operation time was: on avg. 7.962e-03s, min 7.951e-03s, max 7.973e-03s, tot 1.592e-02s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 5.048e+00 1.091e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.773e+00 #pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 4.000e+00 x, min 4.000e+00 x, max 4.000e+00 x (1 samples, the non-min-nrhs ones) #pr: ======== Limiting to type S: #pr: 2 samples (out of 8) matched the dump limiting criteria. #pr: Dump from a base of 8 samples (of max 16) ordered by (1,1,1,1,2,4,2) = (filename x cores x incX x incY x nrhs x typecode x transA). pr: BESTCODE MTX NR NC NNZ NRHS TYPE SYM TRANS NT AT-NT AT-MKL-NT BPNZ AT-BPNZ NSUBM AT-SUBM RSBBEST-MFLOPS OPTIME MKL-OPTIME AT-OPTIME AT-MKL-OPTIME AT-TIME RWminBW-GBps CB-bpf AT-MS CMFLOPS -pr: 3:R_R A 3 3 6 1 S S N 8 8 0 4.0000 4.6667 3 1 449.79 1.418e-02 0.000e+00 5.336e-08 0.000e+00 1.480e-01 1.65e+00 3.17e+00 1 2.40e-05 -pr: 11:R_R A 3 3 6 4 S S N 8 8 0 4.0000 4.6667 3 1 1799.17 1.200e-02 0.000e+00 5.336e-08 0.000e+00 1.399e-01 3.67e+00 1.54e+00 1 9.60e-05 +pr: 3:R_R A 3 3 6 1 S S N 8 8 0 4.0000 4.6667 3 1 476.63 7.996e-03 0.000e+00 5.035e-08 0.000e+00 7.219e-02 1.75e+00 3.17e+00 1 2.40e-05 +pr: 11:R_R A 3 3 6 4 S S N 8 8 0 4.0000 4.6667 3 1 1906.50 7.989e-03 0.000e+00 5.035e-08 0.000e+00 8.018e-02 3.89e+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. 24531401.3 % faster, avg. sp. ratio 245315.013x, max sp. ratio 265679.178x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 2697482.1/2621063.4/2773900.8/5394964.3 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 11.0/ 10.4/ 11.7/ 22.1 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 11.0, min. 10.4, max. 11.7 ops) +#pr: (in succ. cases rsb autotuning gave avg. 15872295.8 % faster, avg. sp. ratio 158723.958x, max sp. ratio 158792.614x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 1512928.5/1433551.1/1592305.9/3025857.0 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 9.5/ 9.0/ 10.0/ 19.1 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 9.5, min. 9.0, max. 10.0 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 2.099/ 1.424/ 2.774,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 5.323/ 1.649/ 3.673,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 2.224/ 1.509/ 2.939,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 5.640/ 1.748/ 3.892,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.: 0.14 s, min 0.14 s, max 0.15 s, tot 0.29 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.14 s, min 0.14 s, max 0.15 s, tot 0.29 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 1.124e+03, min 4.498e+02, max 1.799e+03 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 4.846e-03, min 1.693e-03, max 7.998e-03 (2 samples) -#pr: best tun. rsb operation time was: on avg. 5.336e-08s, min 5.336e-08s, max 5.336e-08s, tot 1.067e-07s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 1.309e-02s, min 1.200e-02s, max 1.418e-02s, tot 2.618e-02s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 8.039e+00 1.566e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 2.182e+00 +#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. 1.192e+03, min 4.766e+02, max 1.907e+03 (2 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 7.509e-03, min 3.002e-03, max 1.202e-02 (2 samples) +#pr: best tun. rsb operation time was: on avg. 5.035e-08s, min 5.035e-08s, max 5.035e-08s, tot 1.007e-07s (2 samples) +#pr: ref. unt. rsb operation time was: on avg. 7.992e-03s, min 7.989e-03s, max 7.996e-03s, tot 1.598e-02s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 9.141e+00 1.780e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.773e+00 #pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 4.000e+00 x, min 4.000e+00 x, max 4.000e+00 x (1 samples, the non-min-nrhs ones) #pr: ======== Limiting to type C: #pr: 2 samples (out of 8) matched the dump limiting criteria. #pr: Dump from a base of 8 samples (of max 16) ordered by (1,1,1,1,2,4,2) = (filename x cores x incX x incY x nrhs x typecode x transA). pr: BESTCODE MTX NR NC NNZ NRHS TYPE SYM TRANS NT AT-NT AT-MKL-NT BPNZ AT-BPNZ NSUBM AT-SUBM RSBBEST-MFLOPS OPTIME MKL-OPTIME AT-OPTIME AT-MKL-OPTIME AT-TIME RWminBW-GBps CB-bpf AT-MS CMFLOPS -pr: 5:R_R A 3 3 6 1 C S N 8 8 0 4.0000 4.6667 3 1 1799.17 1.334e-02 0.000e+00 5.336e-08 0.000e+00 1.355e-01 2.77e+00 1.29e+00 1 9.60e-05 -pr: 13:R_R A 3 3 6 4 C S N 8 8 0 4.0000 4.6667 3 1 7196.66 7.998e-03 0.000e+00 5.336e-08 0.000e+00 1.320e-01 6.82e+00 6.98e-01 1 3.84e-04 +pr: 5:R_R A 3 3 6 1 C S N 8 8 0 4.0000 4.6667 3 1 1906.50 7.996e-03 0.000e+00 5.035e-08 0.000e+00 6.815e-02 2.94e+00 1.29e+00 1 9.60e-05 +pr: 13:R_R A 3 3 6 4 C S N 8 8 0 4.0000 4.6667 3 1 7626.01 7.996e-03 0.000e+00 5.035e-08 0.000e+00 7.200e-02 7.23e+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. 19991186.9 % faster, avg. sp. ratio 199912.869x, max sp. ratio 249932.976x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 2506088.0/2473646.1/2538529.9/5012176.1 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 13.3/ 10.2/ 16.5/ 26.7 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 13.3, min. 10.2, max. 16.5 ops) +#pr: (in succ. cases rsb autotuning gave avg. 15879398.1 % faster, avg. sp. ratio 158794.981x, max sp. ratio 158797.348x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 1391598.0/1353319.1/1429876.9/2783196.0 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 8.8/ 8.5/ 9.0/ 17.5 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 8.8, min. 8.5, max. 9.0 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 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 3.673/ 2.324/ 5.023,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 9.596/ 2.774/ 6.822,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 3.892/ 2.463/ 5.322,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 10.168/ 2.939/ 7.229,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.: 0.13 s, min 0.13 s, max 0.14 s, tot 0.27 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.13 s, min 0.13 s, max 0.14 s, tot 0.27 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 4.498e+03, min 1.799e+03, max 7.197e+03 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 2.761e-02, min 7.199e-03, max 4.801e-02 (2 samples) -#pr: best tun. rsb operation time was: on avg. 5.336e-08s, min 5.336e-08s, max 5.336e-08s, tot 1.067e-07s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 1.067e-02s, min 7.998e-03s, max 1.334e-02s, tot 2.133e-02s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 4.440e+00 9.595e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 2.182e+00 +#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. 4.766e+03, min 1.907e+03, max 7.626e+03 (2 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 3.001e-02, min 1.201e-02, max 4.802e-02 (2 samples) +#pr: best tun. rsb operation time was: on avg. 5.035e-08s, min 5.035e-08s, max 5.035e-08s, tot 1.007e-07s (2 samples) +#pr: ref. unt. rsb operation time was: on avg. 7.996e-03s, min 7.996e-03s, max 7.996e-03s, tot 1.599e-02s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 5.048e+00 1.091e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.773e+00 #pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 4.000e+00 x, min 4.000e+00 x, max 4.000e+00 x (1 samples, the non-min-nrhs ones) #pr: ======== Limiting to type Z: #pr: 2 samples (out of 8) matched the dump limiting criteria. #pr: Dump from a base of 8 samples (of max 16) ordered by (1,1,1,1,2,4,2) = (filename x cores x incX x incY x nrhs x typecode x transA). pr: BESTCODE MTX NR NC NNZ NRHS TYPE SYM TRANS NT AT-NT AT-MKL-NT BPNZ AT-BPNZ NSUBM AT-SUBM RSBBEST-MFLOPS OPTIME MKL-OPTIME AT-OPTIME AT-MKL-OPTIME AT-TIME RWminBW-GBps CB-bpf AT-MS CMFLOPS -pr: 7:R_R A 3 3 6 1 Z S N 8 8 0 4.0000 4.6667 3 1 1799.17 1.597e-02 0.000e+00 5.336e-08 0.000e+00 1.360e-01 5.02e+00 2.29e+00 1 9.60e-05 -pr: 15:R_R A 3 3 6 4 Z S N 8 8 0 4.0000 4.6667 3 1 7196.66 1.599e-02 0.000e+00 5.336e-08 0.000e+00 1.400e-01 1.31e+01 1.32e+00 1 3.84e-04 +pr: 7:R_R A 3 3 6 1 Z S N 8 8 0 4.0000 4.6667 3 1 1906.50 7.125e-03 0.000e+00 5.035e-08 0.000e+00 7.199e-02 5.32e+00 2.29e+00 1 9.60e-05 +pr: 15:R_R A 3 3 6 4 Z S N 8 8 0 4.0000 4.6667 3 1 7626.01 7.989e-03 0.000e+00 5.035e-08 0.000e+00 9.600e-02 1.39e+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. 29951195.8 % faster, avg. sp. ratio 299512.958x, max sp. ratio 299673.816x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 2586177.4/2548364.6/2623990.2/5172354.8 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 8.6/ 8.5/ 8.8/ 17.3 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 8.6, min. 8.5, max. 8.8 ops) +#pr: (in succ. cases rsb autotuning gave avg. 15007475.8 % faster, avg. sp. ratio 150075.758x, max sp. ratio 158655.303x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 1668080.0/1429597.5/1906562.5/3336160.0 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 11.1/ 10.1/ 12.0/ 22.1 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 11.1, min. 10.1, max. 12.0 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 32/ 32/ 32) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 96/ 96/ 96) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 6.822/ 4.123/ 9.521,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 18.142/ 5.023/ 13.119,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 7.229/ 4.369/ 10.089,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 19.224/ 5.322/ 13.902,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.: 0.14 s, min 0.14 s, max 0.14 s, tot 0.28 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.14 s, min 0.14 s, max 0.14 s, tot 0.28 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 4.498e+03, min 1.799e+03, max 7.197e+03 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 1.501e-02, min 6.010e-03, max 2.401e-02 (2 samples) -#pr: best tun. rsb operation time was: on avg. 5.336e-08s, min 5.336e-08s, max 5.336e-08s, tot 1.067e-07s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 1.598e-02s, min 1.597e-02s, max 1.599e-02s, tot 3.196e-02s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 2.342e+00 5.408e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 2.182e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.08 s, min 0.07 s, max 0.10 s, tot 0.17 s (2 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.08 s, min 0.07 s, max 0.10 s, tot 0.17 s (2 samples) +#pr: best tun. rsb canon. mflops were: on avg. 4.766e+03, min 1.907e+03, max 7.626e+03 (2 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 3.077e-02, min 1.347e-02, max 4.807e-02 (2 samples) +#pr: best tun. rsb operation time was: on avg. 5.035e-08s, min 5.035e-08s, max 5.035e-08s, tot 1.007e-07s (2 samples) +#pr: ref. unt. rsb operation time was: on avg. 7.557e-03s, min 7.125e-03s, max 7.989e-03s, tot 1.511e-02s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 2.663e+00 6.149e+00 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.773e+00 #pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 4.000e+00 x, min 4.000e+00 x, max 4.000e+00 x (1 samples, the non-min-nrhs ones) #pr: ======== Limiting to nrhs=1: #pr: 4 samples (out of 8) matched the dump limiting criteria. #pr: Dump from a base of 8 samples (of max 16) ordered by (1,1,1,1,2,4,2) = (filename x cores x incX x incY x nrhs x typecode x transA). pr: BESTCODE MTX NR NC NNZ NRHS TYPE SYM TRANS NT AT-NT AT-MKL-NT BPNZ AT-BPNZ NSUBM AT-SUBM RSBBEST-MFLOPS OPTIME MKL-OPTIME AT-OPTIME AT-MKL-OPTIME AT-TIME RWminBW-GBps CB-bpf AT-MS CMFLOPS -pr: 1:R_R A 3 3 6 1 D S N 8 8 0 4.0000 4.6667 3 1 449.79 1.190e-02 0.000e+00 5.336e-08 0.000e+00 1.361e-01 2.77e+00 5.17e+00 1 2.40e-05 -pr: 3:R_R A 3 3 6 1 S S N 8 8 0 4.0000 4.6667 3 1 449.79 1.418e-02 0.000e+00 5.336e-08 0.000e+00 1.480e-01 1.65e+00 3.17e+00 1 2.40e-05 -pr: 5:R_R A 3 3 6 1 C S N 8 8 0 4.0000 4.6667 3 1 1799.17 1.334e-02 0.000e+00 5.336e-08 0.000e+00 1.355e-01 2.77e+00 1.29e+00 1 9.60e-05 -pr: 7:R_R A 3 3 6 1 Z S N 8 8 0 4.0000 4.6667 3 1 1799.17 1.597e-02 0.000e+00 5.336e-08 0.000e+00 1.360e-01 5.02e+00 2.29e+00 1 9.60e-05 +pr: 1:R_R A 3 3 6 1 D S N 8 8 0 4.0000 4.6667 3 1 476.63 7.951e-03 0.000e+00 5.035e-08 0.000e+00 7.199e-02 2.94e+00 5.17e+00 1 2.40e-05 +pr: 3:R_R A 3 3 6 1 S S N 8 8 0 4.0000 4.6667 3 1 476.63 7.996e-03 0.000e+00 5.035e-08 0.000e+00 7.219e-02 1.75e+00 3.17e+00 1 2.40e-05 +pr: 5:R_R A 3 3 6 1 C S N 8 8 0 4.0000 4.6667 3 1 1906.50 7.996e-03 0.000e+00 5.035e-08 0.000e+00 6.815e-02 2.94e+00 1.29e+00 1 9.60e-05 +pr: 7:R_R A 3 3 6 1 Z S N 8 8 0 4.0000 4.6667 3 1 1906.50 7.125e-03 0.000e+00 5.035e-08 0.000e+00 7.199e-02 5.32e+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. 25948179.7 % faster, avg. sp. ratio 259482.797x, max sp. ratio 299352.100x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 2602929.0/2538529.9/2773900.8/10411715.8 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 10.1/ 8.5/ 11.4/ 40.6 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 10.1, min. 8.5, max. 11.4 ops) +#pr: (in succ. cases rsb autotuning gave avg. 15424497.5 % faster, avg. sp. ratio 154245.975x, max sp. ratio 158792.614x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 1411542.4/1353319.1/1433551.1/5646169.5 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 9.2/ 8.5/ 10.1/ 36.7 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 9.2, min. 8.5, max. 10.1 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 2.549/ 1.424/ 4.123,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 12.219/ 1.649/ 5.023,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 2.701/ 1.509/ 4.369,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 12.948/ 1.748/ 5.322,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.: 0.14 s, min 0.14 s, max 0.15 s, tot 0.56 s (4 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.14 s, min 0.14 s, max 0.15 s, tot 0.56 s (4 samples) -#pr: best tun. rsb canon. mflops were: on avg. 1.124e+03, min 4.498e+02, max 1.799e+03 (4 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 4.230e-03, min 1.693e-03, max 7.199e-03 (4 samples) -#pr: best tun. rsb operation time was: on avg. 5.336e-08s, min 5.336e-08s, max 5.336e-08s, tot 2.134e-07s (4 samples) -#pr: ref. unt. rsb operation time was: on avg. 1.385e-02s, min 1.190e-02s, max 1.597e-02s, tot 5.538e-02s (4 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 5.408e+00 1.566e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 2.182e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.07 s, min 0.07 s, max 0.07 s, tot 0.28 s (4 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.07 s, min 0.07 s, max 0.07 s, tot 0.28 s (4 samples) +#pr: best tun. rsb canon. mflops were: on avg. 1.192e+03, min 4.766e+02, max 1.907e+03 (4 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 7.875e-03, min 3.002e-03, max 1.347e-02 (4 samples) +#pr: best tun. rsb operation time was: on avg. 5.035e-08s, min 5.035e-08s, max 5.035e-08s, tot 2.014e-07s (4 samples) +#pr: ref. unt. rsb operation time was: on avg. 7.767e-03s, min 7.125e-03s, max 7.996e-03s, tot 3.107e-02s (4 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 6.149e+00 1.780e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.773e+00 #pr: ======== Limiting to nrhs=4: #pr: 4 samples (out of 8) matched the dump limiting criteria. #pr: Dump from a base of 8 samples (of max 16) ordered by (1,1,1,1,2,4,2) = (filename x cores x incX x incY x nrhs x typecode x transA). pr: BESTCODE MTX NR NC NNZ NRHS TYPE SYM TRANS NT AT-NT AT-MKL-NT BPNZ AT-BPNZ NSUBM AT-SUBM RSBBEST-MFLOPS OPTIME MKL-OPTIME AT-OPTIME AT-MKL-OPTIME AT-TIME RWminBW-GBps CB-bpf AT-MS CMFLOPS -pr: 9:R_R A 3 3 6 4 D S N 8 8 0 4.0000 4.6667 3 1 1799.17 1.200e-02 0.000e+00 5.336e-08 0.000e+00 1.680e-01 6.82e+00 2.79e+00 1 9.60e-05 -pr: 11:R_R A 3 3 6 4 S S N 8 8 0 4.0000 4.6667 3 1 1799.17 1.200e-02 0.000e+00 5.336e-08 0.000e+00 1.399e-01 3.67e+00 1.54e+00 1 9.60e-05 -pr: 13:R_R A 3 3 6 4 C S N 8 8 0 4.0000 4.6667 3 1 7196.66 7.998e-03 0.000e+00 5.336e-08 0.000e+00 1.320e-01 6.82e+00 6.98e-01 1 3.84e-04 -pr: 15:R_R A 3 3 6 4 Z S N 8 8 0 4.0000 4.6667 3 1 7196.66 1.599e-02 0.000e+00 5.336e-08 0.000e+00 1.400e-01 1.31e+01 1.32e+00 1 3.84e-04 +pr: 9:R_R A 3 3 6 4 D S N 8 8 0 4.0000 4.6667 3 1 1906.50 7.973e-03 0.000e+00 5.035e-08 0.000e+00 7.202e-02 7.23e+00 2.79e+00 1 9.60e-05 +pr: 11:R_R A 3 3 6 4 S S N 8 8 0 4.0000 4.6667 3 1 1906.50 7.989e-03 0.000e+00 5.035e-08 0.000e+00 8.018e-02 3.89e+00 1.54e+00 1 9.60e-05 +pr: 13:R_R A 3 3 6 4 C S N 8 8 0 4.0000 4.6667 3 1 7626.01 7.996e-03 0.000e+00 5.035e-08 0.000e+00 7.200e-02 7.23e+00 6.98e-01 1 3.84e-04 +pr: 15:R_R A 3 3 6 4 Z S N 8 8 0 4.0000 4.6667 3 1 7626.01 7.989e-03 0.000e+00 5.035e-08 0.000e+00 9.600e-02 1.39e+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. 22483814.2 % faster, avg. sp. ratio 224839.142x, max sp. ratio 299673.816x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 2716856.6/2473646.1/3148726.5/10867426.3 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 12.7/ 8.8/ 16.5/ 50.9 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 12.7, min. 8.8, max. 16.5 ops) +#pr: (in succ. cases rsb autotuning gave avg. 15861050.6 % faster, avg. sp. ratio 158611.506x, max sp. ratio 158797.348x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 1589740.8/1429876.9/1906562.5/6358963.1 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 10.0/ 9.0/ 12.0/ 40.1 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 10.0, min. 9.0, max. 12.0 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 18/ 8/ 32) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 54/ 24/ 96) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 5.585/ 2.774/ 9.521,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 30.436/ 3.673/ 13.119,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 5.918/ 2.939/ 10.089,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 32.252/ 3.892/ 13.902,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.: 0.14 s, min 0.13 s, max 0.17 s, tot 0.58 s (4 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.14 s, min 0.13 s, max 0.17 s, tot 0.58 s (4 samples) -#pr: best tun. rsb canon. mflops were: on avg. 4.498e+03, min 1.799e+03, max 7.197e+03 (4 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 2.201e-02, min 7.998e-03, max 4.801e-02 (4 samples) -#pr: best tun. rsb operation time was: on avg. 5.336e-08s, min 5.336e-08s, max 5.336e-08s, tot 2.134e-07s (4 samples) -#pr: ref. unt. rsb operation time was: on avg. 1.200e-02s, min 7.998e-03s, max 1.599e-02s, tot 4.799e-02s (4 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 2.342e+00 8.039e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 2.182e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.08 s, min 0.07 s, max 0.10 s, tot 0.32 s (4 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.08 s, min 0.07 s, max 0.10 s, tot 0.32 s (4 samples) +#pr: best tun. rsb canon. mflops were: on avg. 4.766e+03, min 1.907e+03, max 7.626e+03 (4 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 3.004e-02, min 1.202e-02, max 4.807e-02 (4 samples) +#pr: best tun. rsb operation time was: on avg. 5.035e-08s, min 5.035e-08s, max 5.035e-08s, tot 2.014e-07s (4 samples) +#pr: ref. unt. rsb operation time was: on avg. 7.987e-03s, min 7.973e-03s, max 7.996e-03s, tot 3.195e-02s (4 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 2.663e+00 9.141e+00 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.773e+00 #pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 4.000e+00 x, min 4.000e+00 x, max 4.000e+00 x (4 samples, the non-min-nrhs ones) #pr: ======== Limiting to transA=N: #pr: Dump from a base of 8 samples (of max 16) ordered by (1,1,1,1,2,4,2) = (filename x cores x incX x incY x nrhs x typecode x transA). pr: BESTCODE MTX NR NC NNZ NRHS TYPE SYM TRANS NT AT-NT AT-MKL-NT BPNZ AT-BPNZ NSUBM AT-SUBM RSBBEST-MFLOPS OPTIME MKL-OPTIME AT-OPTIME AT-MKL-OPTIME AT-TIME RWminBW-GBps CB-bpf AT-MS CMFLOPS -pr: 1:R_R A 3 3 6 1 D S N 8 8 0 4.0000 4.6667 3 1 449.79 1.190e-02 0.000e+00 5.336e-08 0.000e+00 1.361e-01 2.77e+00 5.17e+00 1 2.40e-05 -pr: 3:R_R A 3 3 6 1 S S N 8 8 0 4.0000 4.6667 3 1 449.79 1.418e-02 0.000e+00 5.336e-08 0.000e+00 1.480e-01 1.65e+00 3.17e+00 1 2.40e-05 -pr: 5:R_R A 3 3 6 1 C S N 8 8 0 4.0000 4.6667 3 1 1799.17 1.334e-02 0.000e+00 5.336e-08 0.000e+00 1.355e-01 2.77e+00 1.29e+00 1 9.60e-05 -pr: 7:R_R A 3 3 6 1 Z S N 8 8 0 4.0000 4.6667 3 1 1799.17 1.597e-02 0.000e+00 5.336e-08 0.000e+00 1.360e-01 5.02e+00 2.29e+00 1 9.60e-05 -pr: 9:R_R A 3 3 6 4 D S N 8 8 0 4.0000 4.6667 3 1 1799.17 1.200e-02 0.000e+00 5.336e-08 0.000e+00 1.680e-01 6.82e+00 2.79e+00 1 9.60e-05 -pr: 11:R_R A 3 3 6 4 S S N 8 8 0 4.0000 4.6667 3 1 1799.17 1.200e-02 0.000e+00 5.336e-08 0.000e+00 1.399e-01 3.67e+00 1.54e+00 1 9.60e-05 -pr: 13:R_R A 3 3 6 4 C S N 8 8 0 4.0000 4.6667 3 1 7196.66 7.998e-03 0.000e+00 5.336e-08 0.000e+00 1.320e-01 6.82e+00 6.98e-01 1 3.84e-04 -pr: 15:R_R A 3 3 6 4 Z S N 8 8 0 4.0000 4.6667 3 1 7196.66 1.599e-02 0.000e+00 5.336e-08 0.000e+00 1.400e-01 1.31e+01 1.32e+00 1 3.84e-04 +pr: 1:R_R A 3 3 6 1 D S N 8 8 0 4.0000 4.6667 3 1 476.63 7.951e-03 0.000e+00 5.035e-08 0.000e+00 7.199e-02 2.94e+00 5.17e+00 1 2.40e-05 +pr: 3:R_R A 3 3 6 1 S S N 8 8 0 4.0000 4.6667 3 1 476.63 7.996e-03 0.000e+00 5.035e-08 0.000e+00 7.219e-02 1.75e+00 3.17e+00 1 2.40e-05 +pr: 5:R_R A 3 3 6 1 C S N 8 8 0 4.0000 4.6667 3 1 1906.50 7.996e-03 0.000e+00 5.035e-08 0.000e+00 6.815e-02 2.94e+00 1.29e+00 1 9.60e-05 +pr: 7:R_R A 3 3 6 1 Z S N 8 8 0 4.0000 4.6667 3 1 1906.50 7.125e-03 0.000e+00 5.035e-08 0.000e+00 7.199e-02 5.32e+00 2.29e+00 1 9.60e-05 +pr: 9:R_R A 3 3 6 4 D S N 8 8 0 4.0000 4.6667 3 1 1906.50 7.973e-03 0.000e+00 5.035e-08 0.000e+00 7.202e-02 7.23e+00 2.79e+00 1 9.60e-05 +pr: 11:R_R A 3 3 6 4 S S N 8 8 0 4.0000 4.6667 3 1 1906.50 7.989e-03 0.000e+00 5.035e-08 0.000e+00 8.018e-02 3.89e+00 1.54e+00 1 9.60e-05 +pr: 13:R_R A 3 3 6 4 C S N 8 8 0 4.0000 4.6667 3 1 7626.01 7.996e-03 0.000e+00 5.035e-08 0.000e+00 7.200e-02 7.23e+00 6.98e-01 1 3.84e-04 +pr: 15:R_R A 3 3 6 4 Z S N 8 8 0 4.0000 4.6667 3 1 7626.01 7.989e-03 0.000e+00 5.035e-08 0.000e+00 9.600e-02 1.39e+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. 24215997.0 % faster, avg. sp. ratio 242160.970x, max sp. ratio 299673.816x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 2659892.8/2473646.1/3148726.5/21279142.1 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 11.4/ 8.5/ 16.5/ 91.5 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 11.4, min. 8.5, max. 16.5 ops) +#pr: (in succ. cases rsb autotuning gave avg. 15642774.1 % faster, avg. sp. ratio 156428.741x, max sp. ratio 158797.348x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 1500641.6/1353319.1/1906562.5/12005132.6 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 9.6/ 8.5/ 12.0/ 76.8 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 9.6, min. 8.5, max. 12.0 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 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 4.067/ 1.424/ 9.521,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 42.655/ 1.649/ 13.119,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 4.309/ 1.509/ 10.089,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 45.200/ 1.748/ 13.902,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.: 0.14 s, min 0.13 s, max 0.17 s, tot 1.14 s (8 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.14 s, min 0.13 s, max 0.17 s, tot 1.14 s (8 samples) -#pr: best tun. rsb canon. mflops were: on avg. 2.811e+03, min 4.498e+02, max 7.197e+03 (8 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 1.312e-02, min 1.693e-03, max 4.801e-02 (8 samples) -#pr: best tun. rsb operation time was: on avg. 5.336e-08s, min 5.336e-08s, max 5.336e-08s, tot 4.269e-07s (8 samples) -#pr: ref. unt. rsb operation time was: on avg. 1.292e-02s, min 7.998e-03s, max 1.599e-02s, tot 1.034e-01s (8 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 2.342e+00 1.566e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 2.182e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.08 s, min 0.07 s, max 0.10 s, tot 0.60 s (8 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.08 s, min 0.07 s, max 0.10 s, tot 0.60 s (8 samples) +#pr: best tun. rsb canon. mflops were: on avg. 2.979e+03, min 4.766e+02, max 7.626e+03 (8 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 1.896e-02, min 3.002e-03, max 4.807e-02 (8 samples) +#pr: best tun. rsb operation time was: on avg. 5.035e-08s, min 5.035e-08s, max 5.035e-08s, tot 4.028e-07s (8 samples) +#pr: ref. unt. rsb operation time was: on avg. 7.877e-03s, min 7.125e-03s, max 7.996e-03s, tot 6.301e-02s (8 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 2.663e+00 1.780e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.773e+00 #pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 4.000e+00 x, min 4.000e+00 x, max 4.000e+00 x (4 samples, the non-min-nrhs ones) #pr: ======== Limiting to both transA=N and nrhs=1: #pr: 4 samples (out of 8) matched the dump limiting criteria. #pr: Dump from a base of 8 samples (of max 16) ordered by (1,1,1,1,2,4,2) = (filename x cores x incX x incY x nrhs x typecode x transA). pr: BESTCODE MTX NR NC NNZ NRHS TYPE SYM TRANS NT AT-NT AT-MKL-NT BPNZ AT-BPNZ NSUBM AT-SUBM RSBBEST-MFLOPS OPTIME MKL-OPTIME AT-OPTIME AT-MKL-OPTIME AT-TIME RWminBW-GBps CB-bpf AT-MS CMFLOPS -pr: 1:R_R A 3 3 6 1 D S N 8 8 0 4.0000 4.6667 3 1 449.79 1.190e-02 0.000e+00 5.336e-08 0.000e+00 1.361e-01 2.77e+00 5.17e+00 1 2.40e-05 -pr: 3:R_R A 3 3 6 1 S S N 8 8 0 4.0000 4.6667 3 1 449.79 1.418e-02 0.000e+00 5.336e-08 0.000e+00 1.480e-01 1.65e+00 3.17e+00 1 2.40e-05 -pr: 5:R_R A 3 3 6 1 C S N 8 8 0 4.0000 4.6667 3 1 1799.17 1.334e-02 0.000e+00 5.336e-08 0.000e+00 1.355e-01 2.77e+00 1.29e+00 1 9.60e-05 -pr: 7:R_R A 3 3 6 1 Z S N 8 8 0 4.0000 4.6667 3 1 1799.17 1.597e-02 0.000e+00 5.336e-08 0.000e+00 1.360e-01 5.02e+00 2.29e+00 1 9.60e-05 +pr: 1:R_R A 3 3 6 1 D S N 8 8 0 4.0000 4.6667 3 1 476.63 7.951e-03 0.000e+00 5.035e-08 0.000e+00 7.199e-02 2.94e+00 5.17e+00 1 2.40e-05 +pr: 3:R_R A 3 3 6 1 S S N 8 8 0 4.0000 4.6667 3 1 476.63 7.996e-03 0.000e+00 5.035e-08 0.000e+00 7.219e-02 1.75e+00 3.17e+00 1 2.40e-05 +pr: 5:R_R A 3 3 6 1 C S N 8 8 0 4.0000 4.6667 3 1 1906.50 7.996e-03 0.000e+00 5.035e-08 0.000e+00 6.815e-02 2.94e+00 1.29e+00 1 9.60e-05 +pr: 7:R_R A 3 3 6 1 Z S N 8 8 0 4.0000 4.6667 3 1 1906.50 7.125e-03 0.000e+00 5.035e-08 0.000e+00 7.199e-02 5.32e+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. 25948179.7 % faster, avg. sp. ratio 259482.797x, max sp. ratio 299352.100x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 2602929.0/2538529.9/2773900.8/10411715.8 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 10.1/ 8.5/ 11.4/ 40.6 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 10.1, min. 8.5, max. 11.4 ops) +#pr: (in succ. cases rsb autotuning gave avg. 15424497.5 % faster, avg. sp. ratio 154245.975x, max sp. ratio 158792.614x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 1411542.4/1353319.1/1433551.1/5646169.5 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 9.2/ 8.5/ 10.1/ 36.7 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 9.2, min. 8.5, max. 10.1 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 2.549/ 1.424/ 4.123,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 12.219/ 1.649/ 5.023,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 2.701/ 1.509/ 4.369,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 12.948/ 1.748/ 5.322,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.: 0.14 s, min 0.14 s, max 0.15 s, tot 0.56 s (4 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.14 s, min 0.14 s, max 0.15 s, tot 0.56 s (4 samples) -#pr: best tun. rsb canon. mflops were: on avg. 1.124e+03, min 4.498e+02, max 1.799e+03 (4 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 4.230e-03, min 1.693e-03, max 7.199e-03 (4 samples) -#pr: best tun. rsb operation time was: on avg. 5.336e-08s, min 5.336e-08s, max 5.336e-08s, tot 2.134e-07s (4 samples) -#pr: ref. unt. rsb operation time was: on avg. 1.385e-02s, min 1.190e-02s, max 1.597e-02s, tot 5.538e-02s (4 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 5.408e+00 1.566e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 2.182e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.07 s, min 0.07 s, max 0.07 s, tot 0.28 s (4 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.07 s, min 0.07 s, max 0.07 s, tot 0.28 s (4 samples) +#pr: best tun. rsb canon. mflops were: on avg. 1.192e+03, min 4.766e+02, max 1.907e+03 (4 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 7.875e-03, min 3.002e-03, max 1.347e-02 (4 samples) +#pr: best tun. rsb operation time was: on avg. 5.035e-08s, min 5.035e-08s, max 5.035e-08s, tot 2.014e-07s (4 samples) +#pr: ref. unt. rsb operation time was: on avg. 7.767e-03s, min 7.125e-03s, max 7.996e-03s, tot 3.107e-02s (4 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 6.149e+00 1.780e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.773e+00 #pr: ======== Limiting to both transA=N and nrhs=4: #pr: 4 samples (out of 8) matched the dump limiting criteria. #pr: Dump from a base of 8 samples (of max 16) ordered by (1,1,1,1,2,4,2) = (filename x cores x incX x incY x nrhs x typecode x transA). pr: BESTCODE MTX NR NC NNZ NRHS TYPE SYM TRANS NT AT-NT AT-MKL-NT BPNZ AT-BPNZ NSUBM AT-SUBM RSBBEST-MFLOPS OPTIME MKL-OPTIME AT-OPTIME AT-MKL-OPTIME AT-TIME RWminBW-GBps CB-bpf AT-MS CMFLOPS -pr: 9:R_R A 3 3 6 4 D S N 8 8 0 4.0000 4.6667 3 1 1799.17 1.200e-02 0.000e+00 5.336e-08 0.000e+00 1.680e-01 6.82e+00 2.79e+00 1 9.60e-05 -pr: 11:R_R A 3 3 6 4 S S N 8 8 0 4.0000 4.6667 3 1 1799.17 1.200e-02 0.000e+00 5.336e-08 0.000e+00 1.399e-01 3.67e+00 1.54e+00 1 9.60e-05 -pr: 13:R_R A 3 3 6 4 C S N 8 8 0 4.0000 4.6667 3 1 7196.66 7.998e-03 0.000e+00 5.336e-08 0.000e+00 1.320e-01 6.82e+00 6.98e-01 1 3.84e-04 -pr: 15:R_R A 3 3 6 4 Z S N 8 8 0 4.0000 4.6667 3 1 7196.66 1.599e-02 0.000e+00 5.336e-08 0.000e+00 1.400e-01 1.31e+01 1.32e+00 1 3.84e-04 +pr: 9:R_R A 3 3 6 4 D S N 8 8 0 4.0000 4.6667 3 1 1906.50 7.973e-03 0.000e+00 5.035e-08 0.000e+00 7.202e-02 7.23e+00 2.79e+00 1 9.60e-05 +pr: 11:R_R A 3 3 6 4 S S N 8 8 0 4.0000 4.6667 3 1 1906.50 7.989e-03 0.000e+00 5.035e-08 0.000e+00 8.018e-02 3.89e+00 1.54e+00 1 9.60e-05 +pr: 13:R_R A 3 3 6 4 C S N 8 8 0 4.0000 4.6667 3 1 7626.01 7.996e-03 0.000e+00 5.035e-08 0.000e+00 7.200e-02 7.23e+00 6.98e-01 1 3.84e-04 +pr: 15:R_R A 3 3 6 4 Z S N 8 8 0 4.0000 4.6667 3 1 7626.01 7.989e-03 0.000e+00 5.035e-08 0.000e+00 9.600e-02 1.39e+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. 22483814.2 % faster, avg. sp. ratio 224839.142x, max sp. ratio 299673.816x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 2716856.6/2473646.1/3148726.5/10867426.3 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 12.7/ 8.8/ 16.5/ 50.9 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 12.7, min. 8.8, max. 16.5 ops) +#pr: (in succ. cases rsb autotuning gave avg. 15861050.6 % faster, avg. sp. ratio 158611.506x, max sp. ratio 158797.348x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 1589740.8/1429876.9/1906562.5/6358963.1 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 10.0/ 9.0/ 12.0/ 40.1 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 10.0, min. 9.0, max. 12.0 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 18/ 8/ 32) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 54/ 24/ 96) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 5.585/ 2.774/ 9.521,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 30.436/ 3.673/ 13.119,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 5.918/ 2.939/ 10.089,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 32.252/ 3.892/ 13.902,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.: 0.14 s, min 0.13 s, max 0.17 s, tot 0.58 s (4 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.14 s, min 0.13 s, max 0.17 s, tot 0.58 s (4 samples) -#pr: best tun. rsb canon. mflops were: on avg. 4.498e+03, min 1.799e+03, max 7.197e+03 (4 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 2.201e-02, min 7.998e-03, max 4.801e-02 (4 samples) -#pr: best tun. rsb operation time was: on avg. 5.336e-08s, min 5.336e-08s, max 5.336e-08s, tot 2.134e-07s (4 samples) -#pr: ref. unt. rsb operation time was: on avg. 1.200e-02s, min 7.998e-03s, max 1.599e-02s, tot 4.799e-02s (4 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 2.342e+00 8.039e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 2.182e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.08 s, min 0.07 s, max 0.10 s, tot 0.32 s (4 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.08 s, min 0.07 s, max 0.10 s, tot 0.32 s (4 samples) +#pr: best tun. rsb canon. mflops were: on avg. 4.766e+03, min 1.907e+03, max 7.626e+03 (4 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 3.004e-02, min 1.202e-02, max 4.807e-02 (4 samples) +#pr: best tun. rsb operation time was: on avg. 5.035e-08s, min 5.035e-08s, max 5.035e-08s, tot 2.014e-07s (4 samples) +#pr: ref. unt. rsb operation time was: on avg. 7.987e-03s, min 7.973e-03s, max 7.996e-03s, tot 3.195e-02s (4 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 2.663e+00 9.141e+00 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.773e+00 #pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 4.000e+00 x, min 4.000e+00 x, max 4.000e+00 x (4 samples, the non-min-nrhs ones) #pr: ======== Limiting to transA=T: #pr: No sample (out of 8) matched the dump criteria -- skipping dump round. @@ -5022,53 +5058,53 @@ #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 8 8 0 4.0000 4.6667 3 1 449.79 1.190e-02 0.000e+00 5.336e-08 0.000e+00 1.361e-01 2.77e+00 5.17e+00 1 2.40e-05 -pr: 3:R_R A 3 3 6 1 S S N 8 8 0 4.0000 4.6667 3 1 449.79 1.418e-02 0.000e+00 5.336e-08 0.000e+00 1.480e-01 1.65e+00 3.17e+00 1 2.40e-05 -pr: 5:R_R A 3 3 6 1 C S N 8 8 0 4.0000 4.6667 3 1 1799.17 1.334e-02 0.000e+00 5.336e-08 0.000e+00 1.355e-01 2.77e+00 1.29e+00 1 9.60e-05 -pr: 7:R_R A 3 3 6 1 Z S N 8 8 0 4.0000 4.6667 3 1 1799.17 1.597e-02 0.000e+00 5.336e-08 0.000e+00 1.360e-01 5.02e+00 2.29e+00 1 9.60e-05 -pr: 9:R_R A 3 3 6 4 D S N 8 8 0 4.0000 4.6667 3 1 1799.17 1.200e-02 0.000e+00 5.336e-08 0.000e+00 1.680e-01 6.82e+00 2.79e+00 1 9.60e-05 -pr: 11:R_R A 3 3 6 4 S S N 8 8 0 4.0000 4.6667 3 1 1799.17 1.200e-02 0.000e+00 5.336e-08 0.000e+00 1.399e-01 3.67e+00 1.54e+00 1 9.60e-05 -pr: 13:R_R A 3 3 6 4 C S N 8 8 0 4.0000 4.6667 3 1 7196.66 7.998e-03 0.000e+00 5.336e-08 0.000e+00 1.320e-01 6.82e+00 6.98e-01 1 3.84e-04 -pr: 15:R_R A 3 3 6 4 Z S N 8 8 0 4.0000 4.6667 3 1 7196.66 1.599e-02 0.000e+00 5.336e-08 0.000e+00 1.400e-01 1.31e+01 1.32e+00 1 3.84e-04 +pr: 1:R_R A 3 3 6 1 D S N 8 8 0 4.0000 4.6667 3 1 476.63 7.951e-03 0.000e+00 5.035e-08 0.000e+00 7.199e-02 2.94e+00 5.17e+00 1 2.40e-05 +pr: 3:R_R A 3 3 6 1 S S N 8 8 0 4.0000 4.6667 3 1 476.63 7.996e-03 0.000e+00 5.035e-08 0.000e+00 7.219e-02 1.75e+00 3.17e+00 1 2.40e-05 +pr: 5:R_R A 3 3 6 1 C S N 8 8 0 4.0000 4.6667 3 1 1906.50 7.996e-03 0.000e+00 5.035e-08 0.000e+00 6.815e-02 2.94e+00 1.29e+00 1 9.60e-05 +pr: 7:R_R A 3 3 6 1 Z S N 8 8 0 4.0000 4.6667 3 1 1906.50 7.125e-03 0.000e+00 5.035e-08 0.000e+00 7.199e-02 5.32e+00 2.29e+00 1 9.60e-05 +pr: 9:R_R A 3 3 6 4 D S N 8 8 0 4.0000 4.6667 3 1 1906.50 7.973e-03 0.000e+00 5.035e-08 0.000e+00 7.202e-02 7.23e+00 2.79e+00 1 9.60e-05 +pr: 11:R_R A 3 3 6 4 S S N 8 8 0 4.0000 4.6667 3 1 1906.50 7.989e-03 0.000e+00 5.035e-08 0.000e+00 8.018e-02 3.89e+00 1.54e+00 1 9.60e-05 +pr: 13:R_R A 3 3 6 4 C S N 8 8 0 4.0000 4.6667 3 1 7626.01 7.996e-03 0.000e+00 5.035e-08 0.000e+00 7.200e-02 7.23e+00 6.98e-01 1 3.84e-04 +pr: 15:R_R A 3 3 6 4 Z S N 8 8 0 4.0000 4.6667 3 1 7626.01 7.989e-03 0.000e+00 5.035e-08 0.000e+00 9.600e-02 1.39e+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. 24215997.0 % faster, avg. sp. ratio 242160.970x, max sp. ratio 299673.816x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 2659892.8/2473646.1/3148726.5/21279142.1 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 11.4/ 8.5/ 16.5/ 91.5 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 11.4, min. 8.5, max. 16.5 ops) +#pr: (in succ. cases rsb autotuning gave avg. 15642774.1 % faster, avg. sp. ratio 156428.741x, max sp. ratio 158797.348x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 1500641.6/1353319.1/1906562.5/12005132.6 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 9.6/ 8.5/ 12.0/ 76.8 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 9.6, min. 8.5, max. 12.0 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 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 4.067/ 1.424/ 9.521,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 42.655/ 1.649/ 13.119,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 4.309/ 1.509/ 10.089,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 45.200/ 1.748/ 13.902,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.: 0.14 s, min 0.13 s, max 0.17 s, tot 1.14 s (8 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.14 s, min 0.13 s, max 0.17 s, tot 1.14 s (8 samples) -#pr: best tun. rsb canon. mflops were: on avg. 2.811e+03, min 4.498e+02, max 7.197e+03 (8 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 1.312e-02, min 1.693e-03, max 4.801e-02 (8 samples) -#pr: best tun. rsb operation time was: on avg. 5.336e-08s, min 5.336e-08s, max 5.336e-08s, tot 4.269e-07s (8 samples) -#pr: ref. unt. rsb operation time was: on avg. 1.292e-02s, min 7.998e-03s, max 1.599e-02s, tot 1.034e-01s (8 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 2.342e+00 1.566e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 2.182e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.08 s, min 0.07 s, max 0.10 s, tot 0.60 s (8 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.08 s, min 0.07 s, max 0.10 s, tot 0.60 s (8 samples) +#pr: best tun. rsb canon. mflops were: on avg. 2.979e+03, min 4.766e+02, max 7.626e+03 (8 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 1.896e-02, min 3.002e-03, max 4.807e-02 (8 samples) +#pr: best tun. rsb operation time was: on avg. 5.035e-08s, min 5.035e-08s, max 5.035e-08s, tot 4.028e-07s (8 samples) +#pr: ref. unt. rsb operation time was: on avg. 7.877e-03s, min 7.125e-03s, max 7.996e-03s, tot 6.301e-02s (8 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 2.663e+00 1.780e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.773e+00 #pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 4.000e+00 x, min 4.000e+00 x, max 4.000e+00 x (4 samples, the non-min-nrhs ones) -#pr: Record collection took 8.02 s. +#pr: Record collection took 5.14 s. #pr: Record comprises 50 memory benchmark samples (prepend RSB_PR_MBW=1 to dump this). -#pr: Record comprises 100 environment variables in 4755 bytes (prepend RSB_PR_ENV=1 to dump this). +#pr: Record comprises 100 environment variables in 4809 bytes (prepend RSB_PR_ENV=1 to dump this). # ====== END Total summary record. -#pr: ======== Saved a performance record of 16 samples to rsbench_pr__1733298372_gcc-14.2.rpr -# Removing the temporary record file rsbench_pr__1733298372_gcc-14.2.rpr.tmp. -# terminating run at 1733298389 (after 17.9s 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__1767709295_gcc-14.2.rpr +# Removing the temporary record file rsbench_pr__1767709295_gcc-14.2.rpr.tmp. +# terminating run at 1767709310 (after 14.9s 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,\}' @@ -5118,7 +5154,7 @@ 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 @@ -5128,15 +5164,15 @@ 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 1733298390 +# beginning run at 1767709310 # /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 -Wformat -Werror=format-security -O3 -std=c99 -# average timer granularity: 6.76e-08 s +# average timer granularity: 5.02e-08 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:/usr/lib/libeatmydata # env: HOSTNAME is not set # env: KMP_AFFINITY is not set @@ -5175,7 +5211,7 @@ # 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: infom07-i386 +# 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 16777216 bytes, per-thread 2097152 bytes @@ -5195,29 +5231,29 @@ # This test will measure times in scanning arrays sized and aligned to fit in caches. # 3 cache levels detected Will fill struct with 50 samples... -# Memory benchmark took 9.047s +# Memory benchmark took 8.833s # auto-tuning oriented output implies times==0 iterations and sort-after-load. #pr: allocated a performance record for 4 samples (1008 bytes). # multi-type benchmarking (DSCZ) -- now using typecode D (last was D). # Cache block size total 16777216 bytes, per-thread 2097152 bytes -# so far, program took 9.050s 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 8.835s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.000s/0.000s . # Using 1 threads # Using alpha=1 beta=1 order=cols for rsb_spmv/rsb_spsv/rsb_spmm/rsb_spsm. # will use input matrix flags: RSB_FLAG_USE_HALFWORD_INDICES, RSB_FLAG_SORTED_INPUT, RSB_FLAG_LOWER, RSB_FLAG_QUAD_PARTITIONING, RSB_FLAG_SYMMETRIC, RSB_FLAG_OWN_PARTITIONING_ARRAYS # Using 1 threads Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 1.563e-01 s (100.00 %) - analyzed arrays in 4.827e-02 s (30.89 %) - cleaned-up arrays in 1.311e-05 s (0.01 %) - deduplicated arrays in 5.960e-06 s (0.00 %) + converted COO to RSB in 1.984e-01 s (100.00 %) + analyzed arrays in 3.841e-02 s (19.36 %) + cleaned-up arrays in 1.287e-05 s (0.01 %) + deduplicated arrays in 7.153e-06 s (0.00 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 7.595e-02 s (48.61 %) - memory allocations took 1.478e-05 s (0.01 %) + shuffled partitions in 9.997e-02 s (50.38 %) + memory allocations took 1.693e-05 s (0.01 %) leafs setup took 6.914e-06 s (0.00 %) - halfword conversion took 3.199e-02 s (20.47 %) -Built (100 x 100)[0x573f2fa0]{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 0.156s): (100 x 100)[0x573f2fa0]{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' + halfword conversion took 5.999e-02 s (30.24 %) +Built (100 x 100)[0x57964fd0]{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 0.199s): (100 x 100)[0x57964fd0]{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. @@ -5268,10 +5304,10 @@ # 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 0.04397s; avg 0.01466s ( +/- 18.11/ 9.59 %); best 0.012s; worst 0.01606s; std dev. 0.001878 (taking best). -Reference operation time is 0.0120029 s (1.683 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: 0.012 Mflops: 1.683) -Merge (3 -> 1 leaves) took w.c.t. of 6.008e-05s, ~4.101e-05s of computing time (of which 1.812e-05s sorting, 6.199e-06s analysis) +3 iterations (1 th.) took 0.05597s; avg 0.01866s ( +/- 14.33/ 28.49 %); best 0.01598s; worst 0.02397s; std dev. 0.003759 (taking best). +Reference operation time is 0.0159831 s (1.264 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: 0.01598 Mflops: 1.264) +Merge (3 -> 1 leaves) took w.c.t. of 4.792e-05s, ~3.219e-05s of computing time (of which 1.192e-05s sorting, 5.007e-06s analysis) # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 16777216 bytes, per-thread 16777216 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -5302,8 +5338,8 @@ # 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 4.196e-05s; avg 1.399e-05s ( +/- 7.95/ 14.20 %); best 1.287e-05s; worst 1.597e-05s; std dev. 1.408e-06 (taking best). -Reference operation time is 1.28746e-05 s (1569 Mflops) with 1 threads. +3 iterations (1 th.) took 3.099e-05s; avg 1.033e-05s ( +/- 3.08/ 6.15 %); best 1.001e-05s; worst 1.097e-05s; std dev. 4.496e-07 (taking best). +Reference operation time is 1.00136e-05 s (2017 Mflops) with 1 threads. # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 16777216 bytes, per-thread 16777216 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -5319,16 +5355,16 @@ # 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: 1.287e-05 s ~Mflops: 1568.980 nsubm:1 otn:1 -Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 932.296x: 0.012s -> 1.287e-05s, so taking this instance. +After merge step 1: tpop: 1.001e-05 s ~Mflops: 2017.260 nsubm:1 otn:1 +Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 1596.143x: 0.01598s -> 1.001e-05s, so taking this instance. Saved plot to test-tuning-lower-100x100-5050nz--D-N-1--mv-tuned_merge1_1x1th.eps Merged all the matrix leaves: no reason to continue merging. -A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.144s (of which 6.413e-05s partitioning, 0.09607s I/O); computing times: 4.101e-05s in par. loops, 1.812e-05s sorting, 6.199e-06s analyzing) -Total merge + benchmarking process took 0.144s, equivalent to 11187.8/12.0 new/old ops (0.08772s for 2 clones -- as 6813.6/7.3 ops, or 3406.8/3.7 ops per clone), SPEEDUP of 932.296x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 932.296x (0.012s -> 1.287e-05s), will amortize in 12.0 ops by saving 0.01199s per op. -In 1 tuning rounds (tot. 0.23s, 0.088s for constructor, 2 clones) obtained a SPEEDUP of 93129.6% (932.3x) (from 1.683 to 1569 Mflops). Employed 0.096s for I/O of matrix plots. +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.1361s (of which 5.198e-05s partitioning, 0.08802s I/O); computing times: 3.219e-05s in par. loops, 1.192e-05s sorting, 5.007e-06s analyzing) +Total merge + benchmarking process took 0.1361s, equivalent to 13586.9/8.5 new/old ops (0.09972s for 2 clones -- as 9958.7/6.2 ops, or 4979.3/3.1 ops per clone), SPEEDUP of 1596.143x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 1596.143x (0.01598s -> 1.001e-05s), will amortize in 8.5 ops by saving 0.01597s per op. +In 1 tuning rounds (tot. 0.24s, 0.1s for constructor, 2 clones) obtained a SPEEDUP of 159514.3% (1596x) (from 1.264 to 2017 Mflops). Employed 0.11s 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 0.324066 s (1.200e-02 s -> 1.287e-05 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.356031 s (1.598e-02 s -> 1.001e-05 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). RSB Sparse Blocks Autotuner invoked requesting max 0 splits and max 0 merges in 1 rounds, auto threads spec. Will autotune matrix: 100 x 100, type D, 5050 nnz, 50 nnz/r, 1 subms, 1 lsubms, 2.0800 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:10 @@ -5394,20 +5430,20 @@ # 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 4.506e-05s; avg 1.502e-05s ( +/- 14.29/ 20.63 %); best 1.287e-05s; worst 1.812e-05s; std dev. 2.245e-06 (taking best). -Reference operation time is 1.28746e-05 s (1569 Mflops) with 1 threads. +3 iterations (1 th.) took 3.481e-05s; avg 1.16e-05s ( +/- 15.75/ 29.45 %); best 9.775e-06s; worst 1.502e-05s; std dev. 2.418e-06 (taking best). +Reference operation time is 9.77516e-06 s (2066 Mflops) with 1 threads. Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 5.571e-02 s (100.00 %) - analyzed arrays in 2.368e-02 s (42.52 %) - cleaned-up arrays in 9.060e-06 s (0.02 %) - deduplicated arrays in 8.106e-06 s (0.01 %) + converted COO to RSB in 6.358e-02 s (100.00 %) + analyzed arrays in 3.158e-02 s (49.68 %) + cleaned-up arrays in 6.914e-06 s (0.01 %) + deduplicated arrays in 6.199e-06 s (0.01 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 3.199e-02 s (57.43 %) - memory allocations took 3.815e-06 s (0.01 %) - leafs setup took 1.907e-06 s (0.00 %) - halfword conversion took 7.153e-06 s (0.01 %) -Built (100 x 100)[0x573fbaa0]{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 3.197e-02 s (50.29 %) + memory allocations took 2.861e-06 s (0.00 %) + leafs setup took 9.537e-07 s (0.00 %) + halfword conversion took 6.914e-06 s (0.01 %) +Built (100 x 100)[0x5796dad0]{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 = 8). # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 16777216 bytes, per-thread 16777216 bytes @@ -5441,16 +5477,16 @@ # 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 1.159e-01 s (100.00 %) - analyzed arrays in 3.988e-02 s (34.41 %) - cleaned-up arrays in 8.106e-06 s (0.01 %) - deduplicated arrays in 7.868e-06 s (0.01 %) + converted COO to RSB in 1.299e-01 s (100.00 %) + analyzed arrays in 3.989e-02 s (30.71 %) + cleaned-up arrays in 6.914e-06 s (0.01 %) + deduplicated arrays in 6.199e-06 s (0.00 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 3.201e-02 s (27.62 %) + shuffled partitions in 4.799e-02 s (36.94 %) memory allocations took 4.053e-06 s (0.00 %) - leafs setup took 1.907e-06 s (0.00 %) - halfword conversion took 4.399e-02 s (37.95 %) -Built (100 x 100)[0x573f32e0]{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' + leafs setup took 2.861e-06 s (0.00 %) + halfword conversion took 4.201e-02 s (32.34 %) +Built (100 x 100)[0x57965310]{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 16777216 bytes, per-thread 16777216 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -5496,9 +5532,9 @@ # 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 0.04793s; avg 0.01598s ( +/- 0.31/ 0.16 %); best 0.01593s; worst 0.016s; std dev. 3.535e-05 (taking best). -Reference operation time is 0.0159271 s (1.268 Mflops) with 1 threads. -Challenging best inner round reference (1.28746e-05 s/1 threads) with: subdivision 0.25, 3 leaves, 2.121 bytes/nz, 0.0159271 s/0 threads (speedup 0.000808347 x), same?n. +3 iterations (1 th.) took 0.07015s; avg 0.02338s ( +/- 40.42/ 39.34 %); best 0.01393s; worst 0.03258s; std dev. 0.007616 (taking best). +Reference operation time is 0.0139301 s (1.45 Mflops) with 1 threads. +Challenging best inner round reference (9.77516e-06 s/1 threads) with: subdivision 0.25, 3 leaves, 2.121 bytes/nz, 0.0139301 s/0 threads (speedup 0.00070173 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 16777216 bytes, per-thread 16777216 bytes @@ -5532,16 +5568,16 @@ # 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 9.185e-02 s (100.00 %) - analyzed arrays in 3.981e-02 s (43.35 %) - cleaned-up arrays in 6.914e-06 s (0.01 %) - deduplicated arrays in 6.199e-06 s (0.01 %) + converted COO to RSB in 1.637e-01 s (100.00 %) + analyzed arrays in 5.565e-02 s (34.00 %) + cleaned-up arrays in 6.914e-06 s (0.00 %) + deduplicated arrays in 7.153e-06 s (0.00 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 2.004e-02 s (21.81 %) - memory allocations took 5.007e-06 s (0.01 %) - leafs setup took 5.007e-06 s (0.01 %) - halfword conversion took 3.198e-02 s (34.81 %) -Built (100 x 100)[0x573f3a70]{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 4.006e-02 s (24.48 %) + memory allocations took 5.007e-06 s (0.00 %) + leafs setup took 5.007e-06 s (0.00 %) + halfword conversion took 6.792e-02 s (41.50 %) +Built (100 x 100)[0x57965aa0]{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 16777216 bytes, per-thread 16777216 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -5587,9 +5623,9 @@ # 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 0.04792s; avg 0.01597s ( +/- 0.37/ 0.20 %); best 0.01591s; worst 0.01601s; std dev. 4.205e-05 (taking best). -Reference operation time is 0.015913 s (1.269 Mflops) with 1 threads. -Challenging best inner round reference (1.28746e-05 s/1 threads) with: subdivision 0.5, 10 leaves, 2.206 bytes/nz, 0.015913 s/0 threads (speedup 0.000809061 x), same?n. +3 iterations (1 th.) took 0.07196s; avg 0.02399s ( +/- 33.35/ 16.73 %); best 0.01599s; worst 0.028s; std dev. 0.005657 (taking best). +Reference operation time is 0.015986 s (1.264 Mflops) with 1 threads. +Challenging best inner round reference (9.77516e-06 s/1 threads) with: subdivision 0.5, 10 leaves, 2.206 bytes/nz, 0.015986 s/0 threads (speedup 0.000611484 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 16777216 bytes, per-thread 16777216 bytes @@ -5623,16 +5659,16 @@ # 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 8.786e-02 s (100.00 %) - analyzed arrays in 3.187e-02 s (36.28 %) - cleaned-up arrays in 7.153e-06 s (0.01 %) - deduplicated arrays in 6.914e-06 s (0.01 %) + converted COO to RSB in 1.598e-01 s (100.00 %) + analyzed arrays in 6.782e-02 s (42.44 %) + cleaned-up arrays in 7.153e-06 s (0.00 %) + deduplicated arrays in 5.960e-06 s (0.00 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 2.402e-02 s (27.34 %) - memory allocations took 3.815e-06 s (0.00 %) - leafs setup took 2.861e-06 s (0.00 %) - halfword conversion took 3.194e-02 s (36.36 %) -Built (100 x 100)[0x573fbb80]{D} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 22, symflags:'LS' + shuffled partitions in 4.401e-02 s (27.53 %) + memory allocations took 5.722e-06 s (0.00 %) + leafs setup took 5.960e-06 s (0.00 %) + halfword conversion took 4.797e-02 s (30.01 %) +Built (100 x 100)[0x5796dbb0]{D} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 22, symflags:'LS' # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 16777216 bytes, per-thread 16777216 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -5678,9 +5714,9 @@ # 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 0.02397s; avg 0.007991s ( +/- 5.06/ 5.55 %); best 0.007587s; worst 0.008435s; std dev. 0.0003473 (taking best). -Reference operation time is 0.00758696 s (2.662 Mflops) with 1 threads. -Challenging best inner round reference (1.28746e-05 s/1 threads) with: subdivision 1, 22 leaves, 2.295 bytes/nz, 0.00758696 s/0 threads (speedup 0.00169694 x), same?n. +3 iterations (1 th.) took 0.07188s; avg 0.02396s ( +/- 9.60/ 9.54 %); best 0.02166s; worst 0.02624s; std dev. 0.001872 (taking best). +Reference operation time is 0.0216582 s (0.9327 Mflops) with 1 threads. +Challenging best inner round reference (9.77516e-06 s/1 threads) with: subdivision 1, 22 leaves, 2.295 bytes/nz, 0.0216582 s/0 threads (speedup 0.000451338 x), same?n. New candidate clone performs slowly; discarding it: 100 x 100, type D, 5050 nnz, 50 nnz/r, 30 subms, 22 lsubms, 2.2947 bpnz # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 16777216 bytes, per-thread 16777216 bytes @@ -5714,16 +5750,16 @@ # 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 1.038e-01 s (100.00 %) - analyzed arrays in 4.765e-02 s (45.88 %) + converted COO to RSB in 1.342e-01 s (100.00 %) + analyzed arrays in 4.785e-02 s (35.65 %) cleaned-up arrays in 7.153e-06 s (0.01 %) deduplicated arrays in 6.914e-06 s (0.01 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 2.418e-02 s (23.28 %) - memory allocations took 5.960e-06 s (0.01 %) - leafs setup took 4.053e-06 s (0.00 %) - halfword conversion took 3.199e-02 s (30.81 %) -Built (100 x 100)[0x573fbb80]{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 5.180e-02 s (38.59 %) + memory allocations took 5.722e-06 s (0.00 %) + leafs setup took 6.914e-06 s (0.01 %) + halfword conversion took 3.455e-02 s (25.74 %) +Built (100 x 100)[0x5796dbb0]{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 16777216 bytes, per-thread 16777216 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -5769,9 +5805,9 @@ # 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 0.04794s; avg 0.01598s ( +/- 0.26/ 0.15 %); best 0.01594s; worst 0.016s; std dev. 2.951e-05 (taking best). -Reference operation time is 0.015938 s (1.267 Mflops) with 1 threads. -Challenging best inner round reference (1.28746e-05 s/1 threads) with: subdivision 2, 36 leaves, 2.383 bytes/nz, 0.015938 s/0 threads (speedup 0.000807791 x), same?n. +3 iterations (1 th.) took 0.06556s; avg 0.02185s ( +/- 45.15/ 35.31 %); best 0.01199s; worst 0.02957s; std dev. 0.007338 (taking best). +Reference operation time is 0.011987 s (1.685 Mflops) with 1 threads. +Challenging best inner round reference (9.77516e-06 s/1 threads) with: subdivision 2, 36 leaves, 2.383 bytes/nz, 0.011987 s/0 threads (speedup 0.000815482 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 16777216 bytes, per-thread 16777216 bytes @@ -5805,16 +5841,16 @@ # 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 9.575e-02 s (100.00 %) - analyzed arrays in 3.184e-02 s (33.25 %) - cleaned-up arrays in 5.960e-06 s (0.01 %) - deduplicated arrays in 6.914e-06 s (0.01 %) + converted COO to RSB in 1.598e-01 s (100.00 %) + analyzed arrays in 6.383e-02 s (39.93 %) + cleaned-up arrays in 7.153e-06 s (0.00 %) + deduplicated arrays in 5.960e-06 s (0.00 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 3.202e-02 s (33.44 %) - memory allocations took 5.960e-06 s (0.01 %) - leafs setup took 1.097e-05 s (0.01 %) - halfword conversion took 3.186e-02 s (33.28 %) -Built (100 x 100)[0x57422a00]{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 3.604e-02 s (22.55 %) + memory allocations took 8.821e-06 s (0.01 %) + leafs setup took 3.815e-06 s (0.00 %) + halfword conversion took 5.995e-02 s (37.50 %) +Built (100 x 100)[0x57994a30]{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 16777216 bytes, per-thread 16777216 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -5860,11 +5896,11 @@ # 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 0.04776s; avg 0.01592s ( +/- 0.36/ 0.45 %); best 0.01586s; worst 0.01599s; std dev. 5.395e-05 (taking best). -Reference operation time is 0.015861 s (1.274 Mflops) with 1 threads. -Challenging best inner round reference (1.28746e-05 s/1 threads) with: subdivision 4, 36 leaves, 2.383 bytes/nz, 0.015861 s/0 threads (speedup 0.000811713 x), same?n. +3 iterations (1 th.) took 0.08379s; avg 0.02793s ( +/- 0.49/ 0.45 %); best 0.0278s; worst 0.02806s; std dev. 0.0001075 (taking best). +Reference operation time is 0.0277951 s (0.7267 Mflops) with 1 threads. +Challenging best inner round reference (9.77516e-06 s/1 threads) with: subdivision 4, 36 leaves, 2.383 bytes/nz, 0.0277951 s/0 threads (speedup 0.000351687 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: 1568.98 Mflops. +Best sparse multiply performance with subdivision multiplier of 1: 2066.46 Mflops. # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 16777216 bytes, per-thread 16777216 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -5880,23 +5916,23 @@ # 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 0.7676 s (eq. to 6e+04/ 6e+04 old/new op.times), gained local/global speedup 1 x (1.28746e-05 : 1.28746e-05) / 1 x (1.28746e-05 : 1.28746e-05). This is not amortizable ! +Last tuner inner round (1 of 1) took 1.17595 s (eq. to 1e+05/ 1e+05 old/new op.times), gained local/global speedup 1 x (9.77516e-06 : 9.77516e-06) / 1 x (9.77516e-06 : 9.77516e-06). This is not amortizable ! Auto tuning inner round 1 did not find a configuration better than the original. -In 1 tuning rounds (tot. 0.77s, 0.55s for constructor, 0 clones) obtained NO speedup (best stays 1569 Mflops). -Second run of RSB Autotuner took 0.767639 s and estimated a speedup of 1.000000 x (1.287e-05 s -> 1.287e-05 s per op) in same matrix (1 -> 1 lsubm) +In 1 tuning rounds (tot. 1.2s, 0.81s for constructor, 0 clones) obtained NO speedup (best stays 2066 Mflops). +Second run of RSB Autotuner took 1.17598 s and estimated a speedup of 1.000000 x (9.775e-06 s -> 9.775e-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 0.048267 0.075951 0.124218 -%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.124218 -%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.048267 -%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.075951 +%:CONSTRUCTOR_TIMES:lower-100x100-5050nz S N 1 100 100 5050 0.000000 0.038407 0.099968 0.138375 +%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.138375 +%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.038407 +%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.099968 %: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 0.124218 +%:SORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.138375 %: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 @@ -5911,34 +5947,34 @@ %: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 0.156251 1e+09 1e+09 +%operation:lower-100x100-5050nz 0.198414 1e+09 1e+09 %constructor:matrix SORT[1] SCAN[1] SHUFFLE[1] INSERT[1] -%constructor:lower-100x100-5050nz 0 0.0482669 0 0.0759511 -# so far, program took 10.483s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 1.092s/0.000s . +%constructor:lower-100x100-5050nz 0 0.0384071 0 0.099968 +# so far, program took 10.874s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 1.532s/0.000s . getrusage() stats: ru_maxrss: 69 (maximum resident set size -- MB) -ru_stime : 0.1357s (system CPU time used) -ru_utime : 14.72s (user CPU time used) +ru_stime : 0.2962s (system CPU time used) +ru_utime : 13.7s (user CPU time used) # multi-type benchmarking (DSCZ) -- now using typecode S (last was D). # Cache block size total 16777216 bytes, per-thread 16777216 bytes -# so far, program took 10.483s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 1.092s/0.000s . +# so far, program took 10.874s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 1.532s/0.000s . # Using 1 threads # Using alpha=1 beta=1 order=cols for rsb_spmv/rsb_spsv/rsb_spmm/rsb_spsm. # will use input matrix flags: RSB_FLAG_USE_HALFWORD_INDICES, RSB_FLAG_SORTED_INPUT, RSB_FLAG_LOWER, RSB_FLAG_QUAD_PARTITIONING, RSB_FLAG_SYMMETRIC, RSB_FLAG_OWN_PARTITIONING_ARRAYS # Using 1 threads Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 1.241e-01 s (100.00 %) - analyzed arrays in 4.011e-02 s (32.32 %) - cleaned-up arrays in 5.960e-06 s (0.00 %) - deduplicated arrays in 6.914e-06 s (0.01 %) + converted COO to RSB in 1.445e-01 s (100.00 %) + analyzed arrays in 2.239e-02 s (15.50 %) + cleaned-up arrays in 7.153e-06 s (0.00 %) + deduplicated arrays in 6.914e-06 s (0.00 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 6.033e-02 s (48.61 %) - memory allocations took 5.007e-06 s (0.00 %) - leafs setup took 5.007e-06 s (0.00 %) - halfword conversion took 2.364e-02 s (19.05 %) -Built (100 x 100)[0x573fbb80]{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 0.124s): (100 x 100)[0x573fbb80]{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 8.230e-02 s (56.97 %) + memory allocations took 1.907e-06 s (0.00 %) + leafs setup took 2.861e-06 s (0.00 %) + halfword conversion took 3.976e-02 s (27.52 %) +Built (100 x 100)[0x5796dbb0]{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 0.145s): (100 x 100)[0x5796dbb0]{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. @@ -5989,10 +6025,10 @@ # 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 0.04798s; avg 0.01599s ( +/- 20.00/ 19.94 %); best 0.01279s; worst 0.01918s; std dev. 0.002607 (taking best). -Reference operation time is 0.0127931 s (1.579 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: 0.01279 Mflops: 1.579) -Merge (3 -> 1 leaves) took w.c.t. of 4.196e-05s, ~3.099e-05s of computing time (of which 1.311e-05s sorting, 2.146e-06s analysis) +3 iterations (1 th.) took 0.06825s; avg 0.02275s ( +/- 27.97/ 42.65 %); best 0.01639s; worst 0.03245s; std dev. 0.006971 (taking best). +Reference operation time is 0.016387 s (1.233 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: 0.01639 Mflops: 1.233) +Merge (3 -> 1 leaves) took w.c.t. of 4.315e-05s, ~3.099e-05s of computing time (of which 1.192e-05s sorting, 2.861e-06s analysis) # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 16777216 bytes, per-thread 16777216 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -6023,7 +6059,7 @@ # 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 3.195e-05s; avg 1.065e-05s ( +/- 5.97/ 2.99 %); best 1.001e-05s; worst 1.097e-05s; std dev. 4.496e-07 (taking best). +3 iterations (1 th.) took 3.314e-05s; avg 1.105e-05s ( +/- 9.35/ 10.07 %); best 1.001e-05s; worst 1.216e-05s; std dev. 8.778e-07 (taking best). Reference operation time is 1.00136e-05 s (2017 Mflops) with 1 threads. # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 16777216 bytes, per-thread 16777216 bytes @@ -6041,15 +6077,15 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success After merge step 1: tpop: 1.001e-05 s ~Mflops: 2017.260 nsubm:1 otn:1 -Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 1277.571x: 0.01279s -> 1.001e-05s, so taking this instance. +Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 1636.476x: 0.01639s -> 1.001e-05s, so taking this instance. Saved plot to test-tuning-lower-100x100-5050nz--S-N-1--mv-tuned_merge1_1x1th.eps Merged all the matrix leaves: no reason to continue merging. -A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.1161s (of which 4.411e-05s partitioning, 0.07604s I/O); computing times: 3.099e-05s in par. loops, 1.311e-05s sorting, 2.146e-06s analyzing) -Total merge + benchmarking process took 0.1161s, equivalent to 11589.5/9.1 new/old ops (0.08372s for 2 clones -- as 8361.0/6.5 ops, or 4180.5/3.3 ops per clone), SPEEDUP of 1277.571x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 1277.571x (0.01279s -> 1.001e-05s), will amortize in 9.1 ops by saving 0.01278s per op. -In 1 tuning rounds (tot. 0.21s, 0.084s for constructor, 2 clones) obtained a SPEEDUP of 127657.1% (1278x) (from 1.579 to 2017 Mflops). Employed 0.096s for I/O of matrix plots. +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.2358s (of which 4.506e-05s partitioning, 0.16s I/O); computing times: 3.099e-05s in par. loops, 1.192e-05s sorting, 2.861e-06s analyzing) +Total merge + benchmarking process took 0.2358s, equivalent to 23546.1/14.4 new/old ops (0.1235s for 2 clones -- as 12330.4/7.5 ops, or 6165.2/3.8 ops per clone), SPEEDUP of 1636.476x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 1636.476x (0.01639s -> 1.001e-05s), will amortize in 14.4 ops by saving 0.01638s per op. +In 1 tuning rounds (tot. 0.35s, 0.12s for constructor, 2 clones) obtained a SPEEDUP of 163547.6% (1636x) (from 1.233 to 2017 Mflops). Employed 0.1s 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 0.304054 s (1.279e-02 s -> 1.001e-05 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.456046 s (1.639e-02 s -> 1.001e-05 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). RSB Sparse Blocks Autotuner invoked requesting max 0 splits and max 0 merges in 1 rounds, auto threads spec. Will autotune matrix: 100 x 100, type S, 5050 nnz, 50 nnz/r, 1 subms, 1 lsubms, 2.0800 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:10 @@ -6115,20 +6151,20 @@ # 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 4.387e-05s; avg 1.462e-05s ( +/- 11.96/ 22.28 %); best 1.287e-05s; worst 1.788e-05s; std dev. 2.306e-06 (taking best). -Reference operation time is 1.28746e-05 s (1569 Mflops) with 1 threads. +3 iterations (1 th.) took 3.6e-05s; avg 1.2e-05s ( +/- 16.56/ 25.17 %); best 1.001e-05s; worst 1.502e-05s; std dev. 2.171e-06 (taking best). +Reference operation time is 1.00136e-05 s (2017 Mflops) with 1 threads. Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 5.577e-02 s (100.00 %) - analyzed arrays in 2.373e-02 s (42.55 %) - cleaned-up arrays in 7.153e-06 s (0.01 %) - deduplicated arrays in 6.914e-06 s (0.01 %) + converted COO to RSB in 7.580e-02 s (100.00 %) + analyzed arrays in 3.175e-02 s (41.89 %) + cleaned-up arrays in 6.199e-06 s (0.01 %) + deduplicated arrays in 5.960e-06 s (0.01 %) sorted arrays in 9.537e-07 s (0.00 %) - shuffled partitions in 3.200e-02 s (57.38 %) - memory allocations took 1.693e-05 s (0.03 %) - leafs setup took 1.192e-06 s (0.00 %) - halfword conversion took 5.007e-06 s (0.01 %) -Built (100 x 100)[0x573fbaa0]{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 4.399e-02 s (58.04 %) + memory allocations took 2.980e-05 s (0.04 %) + leafs setup took 3.099e-06 s (0.00 %) + halfword conversion took 5.960e-06 s (0.01 %) +Built (100 x 100)[0x5796dad0]{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 = 8). # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 16777216 bytes, per-thread 16777216 bytes @@ -6162,16 +6198,16 @@ # 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 3.994e-02 s (100.00 %) - analyzed arrays in 3.193e-02 s (79.93 %) - cleaned-up arrays in 8.106e-06 s (0.02 %) - deduplicated arrays in 6.914e-06 s (0.02 %) + converted COO to RSB in 3.998e-02 s (100.00 %) + analyzed arrays in 2.794e-02 s (69.89 %) + cleaned-up arrays in 7.153e-06 s (0.02 %) + deduplicated arrays in 5.960e-06 s (0.01 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 7.983e-03 s (19.99 %) - memory allocations took 4.292e-06 s (0.01 %) - leafs setup took 2.861e-06 s (0.01 %) - halfword conversion took 9.060e-06 s (0.02 %) -Built (100 x 100)[0x573f3db0]{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 1.201e-02 s (30.04 %) + memory allocations took 2.861e-06 s (0.01 %) + leafs setup took 2.146e-06 s (0.01 %) + halfword conversion took 7.868e-06 s (0.02 %) +Built (100 x 100)[0x57965de0]{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 16777216 bytes, per-thread 16777216 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -6217,9 +6253,9 @@ # 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 4.506e-05s; avg 1.502e-05s ( +/- 14.29/ 26.98 %); best 1.287e-05s; worst 1.907e-05s; std dev. 2.868e-06 (taking best). -Reference operation time is 1.28746e-05 s (1569 Mflops) with 1 threads. -Challenging best inner round reference (1.28746e-05 s/1 threads) with: subdivision 0.25, 1 leaves, 2.08 bytes/nz, 1.28746e-05 s/0 threads (speedup 1 x), same?n. +3 iterations (1 th.) took 3.505e-05s; avg 1.168e-05s ( +/- 14.29/ 28.57 %); best 1.001e-05s; worst 1.502e-05s; std dev. 2.36e-06 (taking best). +Reference operation time is 1.00136e-05 s (2017 Mflops) with 1 threads. +Challenging best inner round reference (1.00136e-05 s/1 threads) with: subdivision 0.25, 1 leaves, 2.08 bytes/nz, 1.00136e-05 s/0 threads (speedup 1 x), same?n. New candidate clone performs slowly; discarding it: 100 x 100, type S, 5050 nnz, 50 nnz/r, 1 subms, 1 lsubms, 2.0800 bpnz # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 16777216 bytes, per-thread 16777216 bytes @@ -6253,16 +6289,16 @@ # 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 9.826e-02 s (100.00 %) - analyzed arrays in 3.182e-02 s (32.38 %) - cleaned-up arrays in 7.153e-06 s (0.01 %) - deduplicated arrays in 7.868e-06 s (0.01 %) + converted COO to RSB in 1.278e-01 s (100.00 %) + analyzed arrays in 5.175e-02 s (40.50 %) + cleaned-up arrays in 5.960e-06 s (0.00 %) + deduplicated arrays in 6.914e-06 s (0.01 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 3.999e-02 s (40.70 %) - memory allocations took 5.722e-06 s (0.01 %) - leafs setup took 3.099e-06 s (0.00 %) - halfword conversion took 2.642e-02 s (26.89 %) -Built (100 x 100)[0x573f3db0]{S} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 6, symflags:'LS' + shuffled partitions in 4.001e-02 s (31.32 %) + memory allocations took 5.007e-06 s (0.00 %) + leafs setup took 3.815e-06 s (0.00 %) + halfword conversion took 3.598e-02 s (28.16 %) +Built (100 x 100)[0x57965de0]{S} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 6, symflags:'LS' # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 16777216 bytes, per-thread 16777216 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -6308,9 +6344,9 @@ # 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 0.04153s; avg 0.01384s ( +/- 5.45/ 7.44 %); best 0.01309s; worst 0.01487s; std dev. 0.000754 (taking best). -Reference operation time is 0.0130889 s (1.543 Mflops) with 1 threads. -Challenging best inner round reference (1.28746e-05 s/1 threads) with: subdivision 0.5, 6 leaves, 2.163 bytes/nz, 0.0130889 s/0 threads (speedup 0.000983624 x), same?n. +3 iterations (1 th.) took 0.05998s; avg 0.01999s ( +/- 29.69/ 49.77 %); best 0.01406s; worst 0.02994s; std dev. 0.00708 (taking best). +Reference operation time is 0.0140581 s (1.437 Mflops) with 1 threads. +Challenging best inner round reference (1.00136e-05 s/1 threads) with: subdivision 0.5, 6 leaves, 2.163 bytes/nz, 0.0140581 s/0 threads (speedup 0.000712299 x), same?n. New candidate clone performs slowly; discarding it: 100 x 100, type S, 5050 nnz, 50 nnz/r, 8 subms, 6 lsubms, 2.1632 bpnz # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 16777216 bytes, per-thread 16777216 bytes @@ -6344,16 +6380,16 @@ # 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 1.640e-01 s (100.00 %) - analyzed arrays in 3.990e-02 s (24.34 %) - cleaned-up arrays in 7.868e-06 s (0.00 %) - deduplicated arrays in 7.153e-06 s (0.00 %) + converted COO to RSB in 1.519e-01 s (100.00 %) + analyzed arrays in 6.389e-02 s (42.05 %) + cleaned-up arrays in 6.914e-06 s (0.00 %) + deduplicated arrays in 5.960e-06 s (0.00 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 7.632e-02 s (46.54 %) - memory allocations took 4.768e-06 s (0.00 %) - leafs setup took 7.153e-06 s (0.00 %) - halfword conversion took 4.772e-02 s (29.10 %) -Built (100 x 100)[0x573fbb80]{S} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 16, symflags:'LS' + shuffled partitions in 5.202e-02 s (34.24 %) + memory allocations took 7.153e-06 s (0.00 %) + leafs setup took 4.053e-06 s (0.00 %) + halfword conversion took 3.601e-02 s (23.70 %) +Built (100 x 100)[0x5796dbb0]{S} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 16, symflags:'LS' # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 16777216 bytes, per-thread 16777216 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -6399,9 +6435,9 @@ # 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 0.04793s; avg 0.01598s ( +/- 24.86/ 45.73 %); best 0.01201s; worst 0.02328s; std dev. 0.005173 (taking best). -Reference operation time is 0.0120051 s (1.683 Mflops) with 1 threads. -Challenging best inner round reference (1.28746e-05 s/1 threads) with: subdivision 1, 16 leaves, 2.25 bytes/nz, 0.0120051 s/0 threads (speedup 0.00107243 x), same?n. +3 iterations (1 th.) took 0.07576s; avg 0.02525s ( +/- 20.81/ 25.63 %); best 0.02s; worst 0.03173s; std dev. 0.004865 (taking best). +Reference operation time is 0.0199981 s (1.01 Mflops) with 1 threads. +Challenging best inner round reference (1.00136e-05 s/1 threads) with: subdivision 1, 16 leaves, 2.25 bytes/nz, 0.0199981 s/0 threads (speedup 0.000500727 x), same?n. New candidate clone performs slowly; discarding it: 100 x 100, type S, 5050 nnz, 50 nnz/r, 22 subms, 16 lsubms, 2.2503 bpnz # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 16777216 bytes, per-thread 16777216 bytes @@ -6435,16 +6471,16 @@ # 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 1.079e-01 s (100.00 %) - analyzed arrays in 4.387e-02 s (40.66 %) - cleaned-up arrays in 8.821e-06 s (0.01 %) - deduplicated arrays in 8.106e-06 s (0.01 %) + converted COO to RSB in 1.480e-01 s (100.00 %) + analyzed arrays in 7.589e-02 s (51.27 %) + cleaned-up arrays in 6.199e-06 s (0.00 %) + deduplicated arrays in 6.914e-06 s (0.00 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 3.600e-02 s (33.36 %) - memory allocations took 6.199e-06 s (0.01 %) + shuffled partitions in 4.014e-02 s (27.12 %) + memory allocations took 8.821e-06 s (0.01 %) leafs setup took 5.007e-06 s (0.00 %) - halfword conversion took 2.800e-02 s (25.95 %) -Built (100 x 100)[0x573fbb80]{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' + halfword conversion took 3.196e-02 s (21.59 %) +Built (100 x 100)[0x5796dbb0]{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 16777216 bytes, per-thread 16777216 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -6490,9 +6526,9 @@ # 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 0.04378s; avg 0.01459s ( +/- 18.06/ 9.62 %); best 0.01196s; worst 0.016s; std dev. 0.001865 (taking best). -Reference operation time is 0.0119579 s (1.689 Mflops) with 1 threads. -Challenging best inner round reference (1.28746e-05 s/1 threads) with: subdivision 2, 36 leaves, 2.383 bytes/nz, 0.0119579 s/0 threads (speedup 0.00107666 x), same?n. +3 iterations (1 th.) took 0.08372s; avg 0.02791s ( +/- 28.78/ 42.54 %); best 0.01988s; worst 0.03978s; std dev. 0.008567 (taking best). +Reference operation time is 0.019877 s (1.016 Mflops) with 1 threads. +Challenging best inner round reference (1.00136e-05 s/1 threads) with: subdivision 2, 36 leaves, 2.383 bytes/nz, 0.019877 s/0 threads (speedup 0.000503778 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 16777216 bytes, per-thread 16777216 bytes @@ -6526,16 +6562,16 @@ # 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 1.121e-01 s (100.00 %) - analyzed arrays in 4.805e-02 s (42.86 %) - cleaned-up arrays in 7.153e-06 s (0.01 %) - deduplicated arrays in 5.960e-06 s (0.01 %) + converted COO to RSB in 1.241e-01 s (100.00 %) + analyzed arrays in 4.385e-02 s (35.33 %) + cleaned-up arrays in 5.960e-06 s (0.00 %) + deduplicated arrays in 7.153e-06 s (0.01 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 3.603e-02 s (32.14 %) - memory allocations took 1.478e-05 s (0.01 %) - leafs setup took 5.007e-06 s (0.00 %) - halfword conversion took 2.798e-02 s (24.96 %) -Built (100 x 100)[0x5740ee40]{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 5.224e-02 s (42.08 %) + memory allocations took 8.106e-06 s (0.01 %) + leafs setup took 5.960e-06 s (0.00 %) + halfword conversion took 2.801e-02 s (22.57 %) +Built (100 x 100)[0x57980e70]{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 16777216 bytes, per-thread 16777216 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -6581,11 +6617,11 @@ # 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 0.04789s; avg 0.01596s ( +/- 25.27/ 25.19 %); best 0.01193s; worst 0.01998s; std dev. 0.003289 (taking best). -Reference operation time is 0.0119281 s (1.693 Mflops) with 1 threads. -Challenging best inner round reference (1.28746e-05 s/1 threads) with: subdivision 4, 36 leaves, 2.383 bytes/nz, 0.0119281 s/0 threads (speedup 0.00107935 x), same?n. +3 iterations (1 th.) took 0.05176s; avg 0.01725s ( +/- 10.02/ 15.71 %); best 0.01552s; worst 0.01996s; std dev. 0.001941 (taking best). +Reference operation time is 0.0155239 s (1.301 Mflops) with 1 threads. +Challenging best inner round reference (1.00136e-05 s/1 threads) with: subdivision 4, 36 leaves, 2.383 bytes/nz, 0.0155239 s/0 threads (speedup 0.000645042 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: 1568.98 Mflops. +Best sparse multiply performance with subdivision multiplier of 1: 2017.26 Mflops. # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 16777216 bytes, per-thread 16777216 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -6601,23 +6637,23 @@ # 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 0.759843 s (eq. to 6e+04/ 6e+04 old/new op.times), gained local/global speedup 1 x (1.28746e-05 : 1.28746e-05) / 1 x (1.28746e-05 : 1.28746e-05). This is not amortizable ! +Last tuner inner round (1 of 1) took 0.94017 s (eq. to 9e+04/ 9e+04 old/new op.times), gained local/global speedup 1 x (1.00136e-05 : 1.00136e-05) / 1 x (1.00136e-05 : 1.00136e-05). This is not amortizable ! Auto tuning inner round 1 did not find a configuration better than the original. -In 1 tuning rounds (tot. 0.76s, 0.58s for constructor, 0 clones) obtained NO speedup (best stays 1569 Mflops). -Second run of RSB Autotuner took 0.759877 s and estimated a speedup of 1.000000 x (1.287e-05 s -> 1.287e-05 s per op) in same matrix (1 -> 1 lsubm) +In 1 tuning rounds (tot. 0.94s, 0.67s for constructor, 0 clones) obtained NO speedup (best stays 2017 Mflops). +Second run of RSB Autotuner took 0.940201 s and estimated a speedup of 1.000000 x (1.001e-05 s -> 1.001e-05 s per op) in same matrix (1 -> 1 lsubm) #min:1 #max:1 #sum:100 #norm:10 #used index storage compared to COO:10504 vs 40400 bytes (26.00%) ; compared to CSR:10504 vs 20604 bytes (50.99%) #%:CONSTRUCTOR_*:SORT SCAN INSERT SCAN+INSERT -%:CONSTRUCTOR_TIMES:lower-100x100-5050nz S N 1 100 100 5050 0.000000 0.040107 0.060332 0.100439 -%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.100439 -%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.040107 -%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.060332 +%:CONSTRUCTOR_TIMES:lower-100x100-5050nz S N 1 100 100 5050 0.000000 0.022391 0.082301 0.104692 +%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.104692 +%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.022391 +%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.082301 %: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 0.100439 +%:SORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.104692 %: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 @@ -6632,34 +6668,34 @@ %: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 0.124104 1e+09 1e+09 +%operation:lower-100x100-5050nz 0.144471 1e+09 1e+09 %constructor:matrix SORT[1] SCAN[1] SHUFFLE[1] INSERT[1] -%constructor:lower-100x100-5050nz 0 0.040107 0 0.0603321 -# so far, program took 11.827s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 2.156s/0.000s . +%constructor:lower-100x100-5050nz 0 0.0223911 0 0.0823011 +# so far, program took 12.677s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 2.928s/0.000s . getrusage() stats: ru_maxrss: 69 (maximum resident set size -- MB) -ru_stime : 0.2114s (system CPU time used) -ru_utime : 19.88s (user CPU time used) +ru_stime : 0.3849s (system CPU time used) +ru_utime : 18.2s (user CPU time used) # multi-type benchmarking (DSCZ) -- now using typecode C (last was D). # Cache block size total 16777216 bytes, per-thread 16777216 bytes -# so far, program took 11.827s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 2.156s/0.000s . +# so far, program took 12.692s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 2.928s/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 9.910e-02 s (100.00 %) - analyzed arrays in 1.948e-02 s (19.65 %) - cleaned-up arrays in 8.106e-06 s (0.01 %) - deduplicated arrays in 9.060e-06 s (0.01 %) + converted COO to RSB in 1.538e-01 s (100.00 %) + analyzed arrays in 3.382e-02 s (21.99 %) + cleaned-up arrays in 6.199e-06 s (0.00 %) + deduplicated arrays in 6.914e-06 s (0.00 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 6.333e-02 s (63.90 %) - memory allocations took 3.815e-06 s (0.00 %) - leafs setup took 4.053e-06 s (0.00 %) - halfword conversion took 1.627e-02 s (16.41 %) -Built (100 x 100)[0x573fbb80]{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 0.099s): (100 x 100)[0x573fbb80]{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 7.200e-02 s (46.81 %) + memory allocations took 5.007e-06 s (0.00 %) + leafs setup took 1.907e-06 s (0.00 %) + halfword conversion took 4.798e-02 s (31.19 %) +Built (100 x 100)[0x5796dbb0]{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 0.154s): (100 x 100)[0x5796dbb0]{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. @@ -6710,10 +6746,10 @@ # 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 0.05196s; avg 0.01732s ( +/- 30.77/ 38.12 %); best 0.01199s; worst 0.02392s; std dev. 0.004954 (taking best). -Reference operation time is 0.011991 s (6.738 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: 0.01199 Mflops: 6.738) -Merge (3 -> 1 leaves) took w.c.t. of 4.601e-05s, ~3.409e-05s of computing time (of which 1.383e-05s sorting, 3.099e-06s analysis) +3 iterations (1 th.) took 0.04823s; avg 0.01608s ( +/- 25.41/ 50.47 %); best 0.01199s; worst 0.02419s; std dev. 0.005737 (taking best). +Reference operation time is 0.0119901 s (6.739 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: 0.01199 Mflops: 6.739) +Merge (3 -> 1 leaves) took w.c.t. of 4.196e-05s, ~2.909e-05s of computing time (of which 1.311e-05s sorting, 2.146e-06s analysis) # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 16777216 bytes, per-thread 16777216 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -6744,7 +6780,7 @@ # 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 0.0001099s; avg 3.664e-05s ( +/- 1.74/ 0.87 %); best 3.6e-05s; worst 3.695e-05s; std dev. 4.496e-07 (taking best). +3 iterations (1 th.) took 0.0001121s; avg 3.735e-05s ( +/- 3.62/ 4.04 %); best 3.6e-05s; worst 3.886e-05s; std dev. 1.173e-06 (taking best). Reference operation time is 3.60012e-05 s (2244 Mflops) with 1 threads. # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 16777216 bytes, per-thread 16777216 bytes @@ -6762,15 +6798,15 @@ # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success After merge step 1: tpop: 3.6e-05 s ~Mflops: 2244.369 nsubm:1 otn:1 -Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 333.073x: 0.01199s -> 3.6e-05s, so taking this instance. +Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 333.046x: 0.01199s -> 3.6e-05s, so taking this instance. Saved plot to test-tuning-lower-100x100-5050nz--C-N-1--mv-tuned_merge1_1x1th.eps Merged all the matrix leaves: no reason to continue merging. -A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.1441s (of which 4.911e-05s partitioning, 0.09604s I/O); computing times: 3.409e-05s in par. loops, 1.383e-05s sorting, 3.099e-06s analyzing) -Total merge + benchmarking process took 0.1441s, equivalent to 4001.6/12.0 new/old ops (0.112s for 2 clones -- as 3111.0/9.3 ops, or 1555.5/4.7 ops per clone), SPEEDUP of 333.073x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 333.073x (0.01199s -> 3.6e-05s), will amortize in 12.1 ops by saving 0.01196s per op. -In 1 tuning rounds (tot. 0.26s, 0.11s for constructor, 2 clones) obtained a SPEEDUP of 33207.3% (333.1x) (from 6.738 to 2244 Mflops). Employed 0.096s for I/O of matrix plots. +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.1718s (of which 0.0001121s partitioning, 0.1121s I/O); computing times: 2.909e-05s in par. loops, 1.311e-05s sorting, 2.146e-06s analyzing) +Total merge + benchmarking process took 0.1718s, equivalent to 4772.2/14.3 new/old ops (0.1194s for 2 clones -- as 3316.5/10.0 ops, or 1658.3/5.0 ops per clone), SPEEDUP of 333.046x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 333.046x (0.01199s -> 3.6e-05s), will amortize in 14.4 ops by saving 0.01195s per op. +In 1 tuning rounds (tot. 0.28s, 0.12s for constructor, 2 clones) obtained a SPEEDUP of 33204.6% (333x) (from 6.739 to 2244 Mflops). Employed 0.11s 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 0.356084 s (1.199e-02 s -> 3.600e-05 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.388069 s (1.199e-02 s -> 3.600e-05 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). RSB Sparse Blocks Autotuner invoked requesting max 0 splits and max 0 merges in 1 rounds, auto threads spec. Will autotune matrix: 100 x 100, type C, 5050 nnz, 50 nnz/r, 1 subms, 1 lsubms, 2.0800 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:10 @@ -6836,20 +6872,20 @@ # 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 0.000113s; avg 3.767e-05s ( +/- 4.43/ 8.86 %); best 3.6e-05s; worst 4.101e-05s; std dev. 2.36e-06 (taking best). +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. Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 4.768e-02 s (100.00 %) - analyzed arrays in 1.566e-02 s (32.84 %) - cleaned-up arrays in 6.199e-06 s (0.01 %) - deduplicated arrays in 5.960e-06 s (0.01 %) + converted COO to RSB in 6.355e-02 s (100.00 %) + analyzed arrays in 2.355e-02 s (37.05 %) + cleaned-up arrays in 5.960e-06 s (0.01 %) + deduplicated arrays in 7.153e-06 s (0.01 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 3.200e-02 s (67.11 %) - memory allocations took 2.861e-06 s (0.01 %) - leafs setup took 3.815e-06 s (0.01 %) - halfword conversion took 5.007e-06 s (0.01 %) -Built (100 x 100)[0x573fbaa0]{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 3.998e-02 s (62.91 %) + memory allocations took 1.907e-06 s (0.00 %) + leafs setup took 4.053e-06 s (0.01 %) + halfword conversion took 5.960e-06 s (0.01 %) +Built (100 x 100)[0x5796dad0]{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 = 8). # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 16777216 bytes, per-thread 16777216 bytes @@ -6883,16 +6919,16 @@ # 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 1.038e-01 s (100.00 %) - analyzed arrays in 4.788e-02 s (46.12 %) - cleaned-up arrays in 6.914e-06 s (0.01 %) - deduplicated arrays in 5.960e-06 s (0.01 %) + converted COO to RSB in 1.359e-01 s (100.00 %) + analyzed arrays in 4.772e-02 s (35.12 %) + cleaned-up arrays in 5.960e-06 s (0.00 %) + deduplicated arrays in 6.914e-06 s (0.01 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 2.393e-02 s (23.05 %) - memory allocations took 6.437e-06 s (0.01 %) - leafs setup took 2.861e-06 s (0.00 %) - halfword conversion took 3.199e-02 s (30.82 %) -Built (100 x 100)[0x573f4070]{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 3.998e-02 s (29.42 %) + memory allocations took 1.903e-04 s (0.14 %) + leafs setup took 4.053e-06 s (0.00 %) + halfword conversion took 4.797e-02 s (35.31 %) +Built (100 x 100)[0x579660a0]{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 16777216 bytes, per-thread 16777216 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -6938,9 +6974,9 @@ # 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 0.03579s; avg 0.01193s ( +/- 33.30/ 33.97 %); best 0.007957s; worst 0.01598s; std dev. 0.003277 (taking best). -Reference operation time is 0.00795698 s (10.15 Mflops) with 1 threads. -Challenging best inner round reference (3.60012e-05 s/1 threads) with: subdivision 0.25, 3 leaves, 2.121 bytes/nz, 0.00795698 s/0 threads (speedup 0.00452448 x), same?n. +3 iterations (1 th.) took 0.07196s; avg 0.02399s ( +/- 33.31/ 33.33 %); best 0.016s; worst 0.03198s; std dev. 0.006525 (taking best). +Reference operation time is 0.0159969 s (5.051 Mflops) with 1 threads. +Challenging best inner round reference (3.60012e-05 s/1 threads) with: subdivision 0.25, 3 leaves, 2.121 bytes/nz, 0.0159969 s/0 threads (speedup 0.00225051 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 16777216 bytes, per-thread 16777216 bytes @@ -6974,16 +7010,16 @@ # 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 1.039e-01 s (100.00 %) - analyzed arrays in 3.587e-02 s (34.51 %) - cleaned-up arrays in 6.199e-06 s (0.01 %) - deduplicated arrays in 5.960e-06 s (0.01 %) - sorted arrays in 9.537e-07 s (0.00 %) - shuffled partitions in 3.183e-02 s (30.62 %) - memory allocations took 4.023e-03 s (3.87 %) + converted COO to RSB in 1.438e-01 s (100.00 %) + analyzed arrays in 5.962e-02 s (41.45 %) + cleaned-up arrays in 7.153e-06 s (0.00 %) + deduplicated arrays in 6.914e-06 s (0.00 %) + sorted arrays in 0.000e+00 s (0.00 %) + shuffled partitions in 4.801e-02 s (33.38 %) + memory allocations took 2.050e-04 s (0.14 %) leafs setup took 3.099e-06 s (0.00 %) - halfword conversion took 3.220e-02 s (30.98 %) -Built (100 x 100)[0x573fbb80]{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' + halfword conversion took 3.599e-02 s (25.02 %) +Built (100 x 100)[0x5796dbb0]{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 16777216 bytes, per-thread 16777216 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -7029,9 +7065,9 @@ # 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 0.04799s; avg 0.016s ( +/- 25.76/ 25.83 %); best 0.01188s; worst 0.02013s; std dev. 0.00337 (taking best). -Reference operation time is 0.0118752 s (6.804 Mflops) with 1 threads. -Challenging best inner round reference (3.60012e-05 s/1 threads) with: subdivision 0.5, 10 leaves, 2.206 bytes/nz, 0.0118752 s/0 threads (speedup 0.00303164 x), same?n. +3 iterations (1 th.) took 0.07196s; avg 0.02399s ( +/- 49.04/ 49.16 %); best 0.01223s; worst 0.03578s; std dev. 0.009617 (taking best). +Reference operation time is 0.0122252 s (6.609 Mflops) with 1 threads. +Challenging best inner round reference (3.60012e-05 s/1 threads) with: subdivision 0.5, 10 leaves, 2.206 bytes/nz, 0.0122252 s/0 threads (speedup 0.00294485 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 16777216 bytes, per-thread 16777216 bytes @@ -7065,16 +7101,16 @@ # 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 6.386e-02 s (100.00 %) - analyzed arrays in 2.384e-02 s (37.34 %) - cleaned-up arrays in 6.914e-06 s (0.01 %) - deduplicated arrays in 5.960e-06 s (0.01 %) + converted COO to RSB in 1.439e-01 s (100.00 %) + analyzed arrays in 5.983e-02 s (41.58 %) + cleaned-up arrays in 7.153e-06 s (0.00 %) + deduplicated arrays in 5.960e-06 s (0.00 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 2.400e-02 s (37.58 %) - memory allocations took 5.245e-06 s (0.01 %) - leafs setup took 3.099e-06 s (0.00 %) - halfword conversion took 1.599e-02 s (25.05 %) -Built (100 x 100)[0x573fbb80]{C} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 22, symflags:'LS' + shuffled partitions in 5.206e-02 s (36.18 %) + memory allocations took 8.106e-06 s (0.01 %) + leafs setup took 5.007e-06 s (0.00 %) + halfword conversion took 3.198e-02 s (22.22 %) +Built (100 x 100)[0x5796dbb0]{C} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 22, symflags:'LS' # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 16777216 bytes, per-thread 16777216 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -7120,9 +7156,9 @@ # 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 0.02409s; avg 0.008028s ( +/- 0.37/ 0.71 %); best 0.007999s; worst 0.008085s; std dev. 4.008e-05 (taking best). -Reference operation time is 0.00799894 s (10.1 Mflops) with 1 threads. -Challenging best inner round reference (3.60012e-05 s/1 threads) with: subdivision 1, 22 leaves, 2.295 bytes/nz, 0.00799894 s/0 threads (speedup 0.00450075 x), same?n. +3 iterations (1 th.) took 0.0559s; avg 0.01863s ( +/- 14.62/ 28.72 %); best 0.01591s; worst 0.02399s; std dev. 0.003785 (taking best). +Reference operation time is 0.015908 s (5.079 Mflops) with 1 threads. +Challenging best inner round reference (3.60012e-05 s/1 threads) with: subdivision 1, 22 leaves, 2.295 bytes/nz, 0.015908 s/0 threads (speedup 0.00226309 x), same?n. New candidate clone performs slowly; discarding it: 100 x 100, type C, 5050 nnz, 50 nnz/r, 30 subms, 22 lsubms, 2.2947 bpnz # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 16777216 bytes, per-thread 16777216 bytes @@ -7156,16 +7192,16 @@ # 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 9.963e-02 s (100.00 %) - analyzed arrays in 3.965e-02 s (39.80 %) + converted COO to RSB in 1.039e-01 s (100.00 %) + analyzed arrays in 4.384e-02 s (42.21 %) cleaned-up arrays in 6.914e-06 s (0.01 %) - deduplicated arrays in 5.960e-06 s (0.01 %) + deduplicated arrays in 6.914e-06 s (0.01 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 2.802e-02 s (28.12 %) - memory allocations took 7.391e-06 s (0.01 %) - leafs setup took 5.007e-06 s (0.01 %) - halfword conversion took 3.193e-02 s (32.05 %) -Built (100 x 100)[0x573fbb80]{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 3.602e-02 s (34.67 %) + memory allocations took 5.007e-06 s (0.00 %) + leafs setup took 5.960e-06 s (0.01 %) + halfword conversion took 2.399e-02 s (23.10 %) +Built (100 x 100)[0x5796dbb0]{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 16777216 bytes, per-thread 16777216 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -7211,9 +7247,9 @@ # 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 0.04797s; avg 0.01599s ( +/- 4.00/ 4.07 %); best 0.01535s; worst 0.01664s; std dev. 0.0005267 (taking best). -Reference operation time is 0.0153499 s (5.264 Mflops) with 1 threads. -Challenging best inner round reference (3.60012e-05 s/1 threads) with: subdivision 2, 36 leaves, 2.383 bytes/nz, 0.0153499 s/0 threads (speedup 0.00234538 x), same?n. +3 iterations (1 th.) took 0.05185s; avg 0.01728s ( +/- 8.27/ 15.14 %); best 0.01586s; worst 0.0199s; std dev. 0.001853 (taking best). +Reference operation time is 0.015856 s (5.096 Mflops) with 1 threads. +Challenging best inner round reference (3.60012e-05 s/1 threads) with: subdivision 2, 36 leaves, 2.383 bytes/nz, 0.015856 s/0 threads (speedup 0.00227051 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 16777216 bytes, per-thread 16777216 bytes @@ -7247,16 +7283,16 @@ # 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 1.038e-01 s (100.00 %) - analyzed arrays in 3.982e-02 s (38.35 %) - cleaned-up arrays in 6.914e-06 s (0.01 %) - deduplicated arrays in 6.914e-06 s (0.01 %) - sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 3.201e-02 s (30.82 %) - memory allocations took 6.914e-06 s (0.01 %) - leafs setup took 5.007e-06 s (0.00 %) - halfword conversion took 3.198e-02 s (30.80 %) -Built (100 x 100)[0x57422a00]{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' + converted COO to RSB in 1.439e-01 s (100.00 %) + analyzed arrays in 3.985e-02 s (27.70 %) + cleaned-up arrays in 5.960e-06 s (0.00 %) + deduplicated arrays in 6.199e-06 s (0.00 %) + sorted arrays in 9.537e-07 s (0.00 %) + shuffled partitions in 5.238e-02 s (36.41 %) + memory allocations took 5.960e-06 s (0.00 %) + leafs setup took 5.960e-06 s (0.00 %) + halfword conversion took 5.160e-02 s (35.87 %) +Built (100 x 100)[0x57994a30]{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 16777216 bytes, per-thread 16777216 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -7302,9 +7338,9 @@ # 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 0.05201s; avg 0.01734s ( +/- 8.43/ 15.44 %); best 0.01587s; worst 0.02001s; std dev. 0.001895 (taking best). -Reference operation time is 0.0158741 s (5.09 Mflops) with 1 threads. -Challenging best inner round reference (3.60012e-05 s/1 threads) with: subdivision 4, 36 leaves, 2.383 bytes/nz, 0.0158741 s/0 threads (speedup 0.00226791 x), same?n. +3 iterations (1 th.) took 0.04777s; avg 0.01592s ( +/- 17.58/ 22.14 %); best 0.01312s; worst 0.01945s; std dev. 0.002633 (taking best). +Reference operation time is 0.013124 s (6.157 Mflops) with 1 threads. +Challenging best inner round reference (3.60012e-05 s/1 threads) with: subdivision 4, 36 leaves, 2.383 bytes/nz, 0.013124 s/0 threads (speedup 0.00274316 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: 2244.37 Mflops. # librsb version 1.3.0.2 - 202212201855: Initializing @@ -7322,23 +7358,23 @@ # 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 0.74 s (eq. to 2e+04/ 2e+04 old/new op.times), gained local/global speedup 1 x (3.60012e-05 : 3.60012e-05) / 1 x (3.60012e-05 : 3.60012e-05). This is not amortizable ! +Last tuner inner round (1 of 1) took 1.03594 s (eq. to 3e+04/ 3e+04 old/new op.times), gained local/global speedup 1 x (3.60012e-05 : 3.60012e-05) / 1 x (3.60012e-05 : 3.60012e-05). This is not amortizable ! Auto tuning inner round 1 did not find a configuration better than the original. -In 1 tuning rounds (tot. 0.74s, 0.53s for constructor, 0 clones) obtained NO speedup (best stays 2244 Mflops). -Second run of RSB Autotuner took 0.740034 s and estimated a speedup of 1.000000 x (3.600e-05 s -> 3.600e-05 s per op) in same matrix (1 -> 1 lsubm) +In 1 tuning rounds (tot. 1s, 0.74s for constructor, 0 clones) obtained NO speedup (best stays 2244 Mflops). +Second run of RSB Autotuner took 1.03597 s and estimated a speedup of 1.000000 x (3.600e-05 s -> 3.600e-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 0.019478 0.063330 0.082808 -%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.082808 -%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.019478 -%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.063330 +%:CONSTRUCTOR_TIMES:lower-100x100-5050nz S N 1 100 100 5050 0.000000 0.033819 0.071997 0.105816 +%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.105816 +%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.033819 +%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.071997 %: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 0.082808 +%:SORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.105816 %: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 @@ -7353,34 +7389,34 @@ %: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 0.099102 1e+09 1e+09 +%operation:lower-100x100-5050nz 0.153816 1e+09 1e+09 %constructor:matrix SORT[1] SCAN[1] SHUFFLE[1] INSERT[1] -%constructor:lower-100x100-5050nz 0 0.0194781 0 0.0633299 -# so far, program took 13.168s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 3.252s/0.000s . +%constructor:lower-100x100-5050nz 0 0.033819 0 0.0719969 +# so far, program took 14.501s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 4.352s/0.000s . getrusage() stats: ru_maxrss: 69 (maximum resident set size -- MB) -ru_stime : 0.3111s (system CPU time used) -ru_utime : 26.26s (user CPU time used) +ru_stime : 0.494s (system CPU time used) +ru_utime : 23.57s (user CPU time used) # multi-type benchmarking (DSCZ) -- now using typecode Z (last was D). # Cache block size total 16777216 bytes, per-thread 16777216 bytes -# so far, program took 13.168s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 3.252s/0.000s . +# so far, program took 14.501s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 4.352s/0.000s . # Using 1 threads # Using alpha=1 beta=1 order=cols for rsb_spmv/rsb_spsv/rsb_spmm/rsb_spsm. # will use input matrix flags: RSB_FLAG_USE_HALFWORD_INDICES, RSB_FLAG_SORTED_INPUT, RSB_FLAG_LOWER, RSB_FLAG_QUAD_PARTITIONING, RSB_FLAG_SYMMETRIC, RSB_FLAG_OWN_PARTITIONING_ARRAYS # Using 1 threads Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 1.105e-01 s (100.00 %) - analyzed arrays in 2.954e-02 s (26.73 %) - cleaned-up arrays in 1.097e-05 s (0.01 %) - deduplicated arrays in 1.192e-05 s (0.01 %) + converted COO to RSB in 1.612e-01 s (100.00 %) + analyzed arrays in 4.114e-02 s (25.53 %) + cleaned-up arrays in 6.914e-06 s (0.00 %) + deduplicated arrays in 7.153e-06 s (0.00 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 4.894e-02 s (44.28 %) - memory allocations took 1.597e-05 s (0.01 %) - leafs setup took 5.007e-06 s (0.00 %) - halfword conversion took 3.199e-02 s (28.95 %) -Built (100 x 100)[0x573fbb80]{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 0.111s): (100 x 100)[0x573fbb80]{Z} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x2446196 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LS' + shuffled partitions in 8.399e-02 s (52.11 %) + memory allocations took 2.289e-05 s (0.01 %) + leafs setup took 2.146e-06 s (0.00 %) + halfword conversion took 3.600e-02 s (22.34 %) +Built (100 x 100)[0x5796dbb0]{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 0.161s): (100 x 100)[0x5796dbb0]{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. @@ -7431,10 +7467,10 @@ # 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 0.02767s; avg 0.009222s ( +/- 30.79/ 30.02 %); best 0.006383s; worst 0.01199s; std dev. 0.00229 (taking best). -Reference operation time is 0.00638294 s (12.66 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: 0.006383 Mflops: 12.659) -Merge (3 -> 1 leaves) took w.c.t. of 0.0001192s, ~9.108e-05s of computing time (of which 5.102e-05s sorting, 2.861e-06s analysis) +3 iterations (1 th.) took 0.07998s; avg 0.02666s ( +/- 10.06/ 20.02 %); best 0.02398s; worst 0.032s; std dev. 0.003774 (taking best). +Reference operation time is 0.023978 s (3.37 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: 0.02398 Mflops: 3.370) +Merge (3 -> 1 leaves) took w.c.t. of 0.0001149s, ~8.321e-05s of computing time (of which 4.196e-05s sorting, 4.053e-06s analysis) # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 16777216 bytes, per-thread 16777216 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -7465,8 +7501,8 @@ # 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 0.0001419s; avg 4.729e-05s ( +/- 0.67/ 1.34 %); best 4.697e-05s; worst 4.792e-05s; std dev. 4.496e-07 (taking best). -Reference operation time is 4.69685e-05 s (1720 Mflops) with 1 threads. +3 iterations (1 th.) took 0.000124s; avg 4.133e-05s ( +/- 8.27/ 6.73 %); best 3.791e-05s; worst 4.411e-05s; std dev. 2.57e-06 (taking best). +Reference operation time is 3.79086e-05 s (2131 Mflops) with 1 threads. # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 16777216 bytes, per-thread 16777216 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -7482,16 +7518,16 @@ # 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: 4.697e-05 s ~Mflops: 1720.303 nsubm:1 otn:1 -Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 135.898x: 0.006383s -> 4.697e-05s, so taking this instance. +After merge step 1: tpop: 3.791e-05 s ~Mflops: 2131.445 nsubm:1 otn:1 +Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 632.522x: 0.02398s -> 3.791e-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 0.1107s (of which 0.000123s partitioning, 0.08509s I/O); computing times: 9.108e-05s in par. loops, 5.102e-05s sorting, 2.861e-06s analyzing) -Total merge + benchmarking process took 0.1107s, equivalent to 2357.5/17.3 new/old ops (0.07081s for 2 clones -- as 1507.6/11.1 ops, or 753.8/5.5 ops per clone), SPEEDUP of 135.898x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 135.898x (0.006383s -> 4.697e-05s), will amortize in 17.5 ops by saving 0.006336s per op. -In 1 tuning rounds (tot. 0.18s, 0.071s for constructor, 2 clones) obtained a SPEEDUP of 13489.8% (135.9x) (from 12.66 to 1720 Mflops). Employed 0.088s for I/O of matrix plots. +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.1961s (of which 0.0001168s partitioning, 0.1361s I/O); computing times: 8.321e-05s in par. loops, 4.196e-05s sorting, 4.053e-06s analyzing) +Total merge + benchmarking process took 0.1961s, equivalent to 5172.8/8.2 new/old ops (0.1151s for 2 clones -- as 3036.5/4.8 ops, or 1518.3/2.4 ops per clone), SPEEDUP of 632.522x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 632.522x (0.02398s -> 3.791e-05s), will amortize in 8.2 ops by saving 0.02394s per op. +In 1 tuning rounds (tot. 0.33s, 0.12s for constructor, 2 clones) obtained a SPEEDUP of 63152.2% (632.5x) (from 3.37 to 2131 Mflops). Employed 0.11s 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 0.272063 s (6.383e-03 s -> 4.697e-05 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.440094 s (2.398e-02 s -> 3.791e-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 @@ -7557,20 +7593,20 @@ # 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 0.0001459s; avg 4.864e-05s ( +/- 5.39/ 8.82 %); best 4.601e-05s; worst 5.293e-05s; std dev. 3.059e-06 (taking best). -Reference operation time is 4.60148e-05 s (1756 Mflops) with 1 threads. +3 iterations (1 th.) took 0.0001161s; avg 3.87e-05s ( +/- 4.52/ 8.42 %); best 3.695e-05s; worst 4.196e-05s; std dev. 2.306e-06 (taking best). +Reference operation time is 3.69549e-05 s (2186 Mflops) with 1 threads. Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 4.329e-02 s (100.00 %) - analyzed arrays in 1.910e-02 s (44.13 %) - cleaned-up arrays in 8.106e-06 s (0.02 %) - deduplicated arrays in 7.868e-06 s (0.02 %) + converted COO to RSB in 8.366e-02 s (100.00 %) + analyzed arrays in 4.330e-02 s (51.75 %) + cleaned-up arrays in 6.914e-06 s (0.01 %) + deduplicated arrays in 6.199e-06 s (0.01 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 2.416e-02 s (55.81 %) - memory allocations took 3.815e-06 s (0.01 %) - leafs setup took 9.537e-07 s (0.00 %) - halfword conversion took 6.199e-06 s (0.01 %) -Built (100 x 100)[0x573fbaa0]{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 4.033e-02 s (48.21 %) + memory allocations took 4.768e-06 s (0.01 %) + leafs setup took 4.053e-06 s (0.00 %) + halfword conversion took 5.007e-06 s (0.01 %) +Built (100 x 100)[0x5796dad0]{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 = 8). # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 16777216 bytes, per-thread 16777216 bytes @@ -7604,16 +7640,16 @@ # 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 7.172e-02 s (100.00 %) - analyzed arrays in 2.757e-02 s (38.44 %) - cleaned-up arrays in 9.060e-06 s (0.01 %) - deduplicated arrays in 7.868e-06 s (0.01 %) + converted COO to RSB in 1.234e-01 s (100.00 %) + analyzed arrays in 6.336e-02 s (51.35 %) + cleaned-up arrays in 6.914e-06 s (0.01 %) + deduplicated arrays in 7.153e-06 s (0.01 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 2.622e-02 s (36.56 %) - memory allocations took 5.960e-06 s (0.01 %) - leafs setup took 2.146e-06 s (0.00 %) - halfword conversion took 1.790e-02 s (24.96 %) -Built (100 x 100)[0x573fec30]{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 3.601e-02 s (29.18 %) + memory allocations took 4.768e-06 s (0.00 %) + leafs setup took 3.099e-06 s (0.00 %) + halfword conversion took 2.399e-02 s (19.45 %) +Built (100 x 100)[0x57970c60]{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 16777216 bytes, per-thread 16777216 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -7659,9 +7695,9 @@ # 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 0.03198s; avg 0.01066s ( +/- 23.38/ 12.30 %); best 0.008169s; worst 0.01197s; std dev. 0.001763 (taking best). -Reference operation time is 0.00816894 s (9.891 Mflops) with 1 threads. -Challenging best inner round reference (4.60148e-05 s/1 threads) with: subdivision 0.25, 6 leaves, 2.163 bytes/nz, 0.00816894 s/0 threads (speedup 0.0056329 x), same?n. +3 iterations (1 th.) took 0.04792s; avg 0.01597s ( +/- 24.82/ 49.38 %); best 0.01201s; worst 0.02386s; std dev. 0.005577 (taking best). +Reference operation time is 0.0120089 s (6.728 Mflops) with 1 threads. +Challenging best inner round reference (3.69549e-05 s/1 threads) with: subdivision 0.25, 6 leaves, 2.163 bytes/nz, 0.0120089 s/0 threads (speedup 0.00307729 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 16777216 bytes, per-thread 16777216 bytes @@ -7695,16 +7731,16 @@ # 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 5.555e-02 s (100.00 %) - analyzed arrays in 2.351e-02 s (42.33 %) - cleaned-up arrays in 4.005e-05 s (0.07 %) - deduplicated arrays in 7.153e-06 s (0.01 %) + converted COO to RSB in 1.236e-01 s (100.00 %) + analyzed arrays in 4.760e-02 s (38.50 %) + cleaned-up arrays in 6.914e-06 s (0.01 %) + deduplicated arrays in 5.960e-06 s (0.00 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.600e-02 s (28.79 %) - 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 (28.78 %) -Built (100 x 100)[0x573fbb80]{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 2.402e-02 s (19.43 %) + memory allocations took 5.007e-06 s (0.00 %) + leafs setup took 1.907e-06 s (0.00 %) + halfword conversion took 5.198e-02 s (42.05 %) +Built (100 x 100)[0x5796dbb0]{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 16777216 bytes, per-thread 16777216 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -7750,10 +7786,10 @@ # 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 0.03203s; avg 0.01068s ( +/- 25.24/ 49.80 %); best 0.007982s; worst 0.01599s; std dev. 0.00376 (taking best). -Reference operation time is 0.00798178 s (10.12 Mflops) with 1 threads. -Challenging best inner round reference (4.60148e-05 s/1 threads) with: subdivision 0.5, 16 leaves, 2.24 bytes/nz, 0.00798178 s/0 threads (speedup 0.00576498 x), same?n. -New candidate clone performs slowly; discarding it: 100 x 100, type Z, 5050 nnz, 50 nnz/r, 22 subms, 16 lsubms, 2.2400 bpnz +3 iterations (1 th.) took 0.05994s; avg 0.01998s ( +/- 39.61/ 20.09 %); best 0.01207s; worst 0.02399s; std dev. 0.005597 (taking best). +Reference operation time is 0.0120652 s (6.697 Mflops) with 1 threads. +Challenging best inner round reference (3.69549e-05 s/1 threads) with: subdivision 0.5, 16 leaves, 2.25 bytes/nz, 0.0120652 s/0 threads (speedup 0.00306294 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 16777216 bytes, per-thread 16777216 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -7786,16 +7822,16 @@ # 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 7.164e-02 s (100.00 %) - analyzed arrays in 2.364e-02 s (33.00 %) - cleaned-up arrays in 7.153e-06 s (0.01 %) - deduplicated arrays in 6.914e-06 s (0.01 %) + converted COO to RSB in 1.437e-01 s (100.00 %) + analyzed arrays in 6.014e-02 s (41.86 %) + cleaned-up arrays in 6.914e-06 s (0.00 %) + deduplicated arrays in 6.199e-06 s (0.00 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 2.398e-02 s (33.48 %) - memory allocations took 4.768e-06 s (0.01 %) - leafs setup took 3.815e-06 s (0.01 %) - halfword conversion took 2.399e-02 s (33.49 %) -Built (100 x 100)[0x573fbb80]{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: 34, symflags:'LS' + shuffled partitions in 3.949e-02 s (27.49 %) + memory allocations took 6.914e-06 s (0.00 %) + leafs setup took 4.053e-06 s (0.00 %) + halfword conversion took 4.401e-02 s (30.63 %) +Built (100 x 100)[0x5796dbb0]{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: 34, symflags:'LS' # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 16777216 bytes, per-thread 16777216 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -7841,9 +7877,9 @@ # 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 0.02503s; avg 0.008343s ( +/- 4.57/ 8.86 %); best 0.007961s; worst 0.009082s; std dev. 0.0005229 (taking best). -Reference operation time is 0.00796103 s (10.15 Mflops) with 1 threads. -Challenging best inner round reference (4.60148e-05 s/1 threads) with: subdivision 1, 34 leaves, 2.372 bytes/nz, 0.00796103 s/0 threads (speedup 0.00578 x), same?n. +3 iterations (1 th.) took 0.09574s; avg 0.03191s ( +/- 41.57/ 37.07 %); best 0.01865s; worst 0.04374s; std dev. 0.01029 (taking best). +Reference operation time is 0.0186481 s (4.333 Mflops) with 1 threads. +Challenging best inner round reference (3.69549e-05 s/1 threads) with: subdivision 1, 34 leaves, 2.372 bytes/nz, 0.0186481 s/0 threads (speedup 0.00198169 x), same?n. New candidate clone performs slowly; discarding it: 100 x 100, type Z, 5050 nnz, 50 nnz/r, 47 subms, 34 lsubms, 2.3723 bpnz # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 16777216 bytes, per-thread 16777216 bytes @@ -7877,16 +7913,16 @@ # 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 8.064e-02 s (100.00 %) - analyzed arrays in 3.072e-02 s (38.09 %) - cleaned-up arrays in 6.914e-06 s (0.01 %) - deduplicated arrays in 5.960e-06 s (0.01 %) + converted COO to RSB in 1.517e-01 s (100.00 %) + analyzed arrays in 3.966e-02 s (26.15 %) + cleaned-up arrays in 7.153e-06 s (0.00 %) + deduplicated arrays in 6.914e-06 s (0.00 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 2.394e-02 s (29.69 %) - memory allocations took 7.868e-06 s (0.01 %) - leafs setup took 3.099e-06 s (0.00 %) - halfword conversion took 2.596e-02 s (32.19 %) -Built (100 x 100)[0x5744a150]{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 5.599e-02 s (36.92 %) + memory allocations took 1.001e-05 s (0.01 %) + leafs setup took 5.007e-06 s (0.00 %) + halfword conversion took 5.599e-02 s (36.92 %) +Built (100 x 100)[0x579bc180]{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 16777216 bytes, per-thread 16777216 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -7932,9 +7968,9 @@ # 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 0.03739s; avg 0.01246s ( +/- 27.37/ 23.73 %); best 0.009052s; worst 0.01542s; std dev. 0.00262 (taking best). -Reference operation time is 0.00905204 s (8.926 Mflops) with 1 threads. -Challenging best inner round reference (4.60148e-05 s/1 threads) with: subdivision 2, 36 leaves, 2.383 bytes/nz, 0.00905204 s/0 threads (speedup 0.00508336 x), same?n. +3 iterations (1 th.) took 0.06388s; avg 0.02129s ( +/- 25.02/ 49.89 %); best 0.01596s; worst 0.03192s; std dev. 0.007513 (taking best). +Reference operation time is 0.015965 s (5.061 Mflops) with 1 threads. +Challenging best inner round reference (3.69549e-05 s/1 threads) with: subdivision 2, 36 leaves, 2.383 bytes/nz, 0.015965 s/0 threads (speedup 0.00231475 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 16777216 bytes, per-thread 16777216 bytes @@ -7968,16 +8004,16 @@ # 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 7.627e-02 s (100.00 %) - analyzed arrays in 2.241e-02 s (29.39 %) - cleaned-up arrays in 6.914e-06 s (0.01 %) - deduplicated arrays in 5.960e-06 s (0.01 %) + converted COO to RSB in 1.477e-01 s (100.00 %) + analyzed arrays in 6.365e-02 s (43.09 %) + cleaned-up arrays in 7.868e-06 s (0.01 %) + deduplicated arrays in 5.960e-06 s (0.00 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 2.982e-02 s (39.10 %) - memory allocations took 2.098e-05 s (0.03 %) - leafs setup took 3.815e-06 s (0.01 %) - halfword conversion took 2.399e-02 s (31.46 %) -Built (100 x 100)[0x5744a150]{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 3.600e-02 s (24.37 %) + memory allocations took 2.933e-05 s (0.02 %) + leafs setup took 4.053e-06 s (0.00 %) + halfword conversion took 4.801e-02 s (32.50 %) +Built (100 x 100)[0x579bc180]{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 16777216 bytes, per-thread 16777216 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -8023,11 +8059,11 @@ # 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 0.03995s; avg 0.01332s ( +/- 39.66/ 20.18 %); best 0.008035s; worst 0.016s; std dev. 0.003735 (taking best). -Reference operation time is 0.00803494 s (10.06 Mflops) with 1 threads. -Challenging best inner round reference (4.60148e-05 s/1 threads) with: subdivision 4, 36 leaves, 2.383 bytes/nz, 0.00803494 s/0 threads (speedup 0.00572683 x), same?n. +3 iterations (1 th.) took 0.05312s; avg 0.01771s ( +/- 31.88/ 20.38 %); best 0.01206s; worst 0.02132s; std dev. 0.004044 (taking best). +Reference operation time is 0.0120618 s (6.699 Mflops) with 1 threads. +Challenging best inner round reference (3.69549e-05 s/1 threads) with: subdivision 4, 36 leaves, 2.383 bytes/nz, 0.0120618 s/0 threads (speedup 0.00306379 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: 1755.96 Mflops. +Best sparse multiply performance with subdivision multiplier of 1: 2186.45 Mflops. # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 16777216 bytes, per-thread 16777216 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -8043,23 +8079,23 @@ # 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 0.567898 s (eq. to 1e+04/ 1e+04 old/new op.times), gained local/global speedup 1 x (4.60148e-05 : 4.60148e-05) / 1 x (4.60148e-05 : 4.60148e-05). This is not amortizable ! +Last tuner inner round (1 of 1) took 1.09727 s (eq. to 3e+04/ 3e+04 old/new op.times), gained local/global speedup 1 x (3.69549e-05 : 3.69549e-05) / 1 x (3.69549e-05 : 3.69549e-05). This is not amortizable ! Auto tuning inner round 1 did not find a configuration better than the original. -In 1 tuning rounds (tot. 0.57s, 0.4s for constructor, 0 clones) obtained NO speedup (best stays 1756 Mflops). -Second run of RSB Autotuner took 0.567933 s and estimated a speedup of 1.000000 x (4.601e-05 s -> 4.601e-05 s per op) in same matrix (1 -> 1 lsubm) +In 1 tuning rounds (tot. 1.1s, 0.78s for constructor, 0 clones) obtained NO speedup (best stays 2186 Mflops). +Second run of RSB Autotuner took 1.0973 s and estimated a speedup of 1.000000 x (3.695e-05 s -> 3.695e-05 s per op) in same matrix (1 -> 1 lsubm) #min:1 0 #max:1 0 #sum:100 0 #norm:10 0 #used index storage compared to COO:10504 vs 40400 bytes (26.00%) ; compared to CSR:10504 vs 20604 bytes (50.99%) #%:CONSTRUCTOR_*:SORT SCAN INSERT SCAN+INSERT -%:CONSTRUCTOR_TIMES:lower-100x100-5050nz S N 1 100 100 5050 0.000000 0.029544 0.048938 0.078482 -%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.078482 -%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.029544 -%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.048938 +%:CONSTRUCTOR_TIMES:lower-100x100-5050nz S N 1 100 100 5050 0.000000 0.041141 0.083990 0.125131 +%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.125131 +%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.041141 +%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.083990 %: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 0.078482 +%:SORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.125131 %: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 @@ -8074,68 +8110,68 @@ %: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 0.110517 1e+09 1e+09 +%operation:lower-100x100-5050nz 0.161173 1e+09 1e+09 %constructor:matrix SORT[1] SCAN[1] SHUFFLE[1] INSERT[1] -%constructor:lower-100x100-5050nz 0 0.0295441 0 0.048938 -# so far, program took 14.336s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 4.092s/0.000s . +%constructor:lower-100x100-5050nz 0 0.041141 0 0.0839899 +# so far, program took 16.518s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 5.890s/0.000s . getrusage() stats: ru_maxrss: 69 (maximum resident set size -- MB) -ru_stime : 0.3687s (system CPU time used) -ru_utime : 31.5s (user CPU time used) +ru_stime : 0.5803s (system CPU time used) +ru_utime : 28.86s (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 1568.98 1.200e-02 0.000e+00 1.287e-05 0.000e+00 3.241e-01 4.14e+00 2.60e+00 1 2.02e-02 -pr: 2:R_R lower-100x100-5050nz 100 100 5050 1 S S N 1 1 0 2.1212 2.0800 3 1 2017.26 1.279e-02 0.000e+00 1.001e-05 0.000e+00 3.041e-01 3.19e+00 1.56e+00 1 2.02e-02 -pr: 3:R_R lower-100x100-5050nz 100 100 5050 1 C S N 1 1 0 2.1212 2.0800 3 1 2244.37 1.199e-02 0.000e+00 3.600e-05 0.000e+00 3.561e-01 1.48e+00 6.50e-01 1 8.08e-02 -pr: 4:R_R lower-100x100-5050nz 100 100 5050 1 Z S N 1 1 0 2.1212 2.0800 3 1 1720.30 6.383e-03 0.000e+00 4.697e-05 0.000e+00 2.721e-01 2.05e+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 2017.26 1.598e-02 0.000e+00 1.001e-05 0.000e+00 3.560e-01 5.32e+00 2.60e+00 1 2.02e-02 +pr: 2:R_R lower-100x100-5050nz 100 100 5050 1 S S N 1 1 0 2.1212 2.0800 3 1 2017.26 1.639e-02 0.000e+00 1.001e-05 0.000e+00 4.560e-01 3.19e+00 1.56e+00 1 2.02e-02 +pr: 3:R_R lower-100x100-5050nz 100 100 5050 1 C S N 1 1 0 2.1212 2.0800 3 1 2244.37 1.199e-02 0.000e+00 3.600e-05 0.000e+00 3.881e-01 1.48e+00 6.50e-01 1 8.08e-02 +pr: 4:R_R lower-100x100-5050nz 100 100 5050 1 Z S N 1 1 0 2.1212 2.0800 3 1 2131.45 2.398e-02 0.000e+00 3.791e-05 0.000e+00 4.401e-01 2.54e+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. 66871.0 % faster, avg. sp. ratio 669.710x, max sp. ratio 1277.571x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 17804.6/5792.5/30364.2/71218.5 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 30.8/ 23.8/ 42.6/123.1 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 30.9, min. 23.8, max. 42.9 ops) +#pr: (in succ. cases rsb autotuning gave avg. 104854.7 % faster, avg. sp. ratio 1049.547x, max sp. ratio 1636.476x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 25871.6/10779.3/45542.7/103486.3 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 25.2/ 18.4/ 32.4/100.8 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 25.2, min. 18.4, max. 32.5 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 1683/ 1683/ 1683) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 5050/ 5050/ 5050) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 15150/ 6733/ 26933) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 45450/ 20200/ 80800) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 2.121/ 2.121/ 2.121) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 2.674/ 1.458/ 4.078,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 10.853/ 1.481/ 4.140,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 3.085/ 1.458/ 5.243,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 12.525/ 1.481/ 5.323,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.: 0.31 s, min 0.27 s, max 0.36 s, tot 1.26 s (4 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.31 s, min 0.27 s, max 0.36 s, tot 1.26 s (4 samples) -#pr: best tun. rsb canon. mflops were: on avg. 1.888e+03, min 1.569e+03, max 2.244e+03 (4 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 5.665e+00, min 1.579e+00, max 1.266e+01 (4 samples) -#pr: best tun. rsb operation time was: on avg. 2.646e-05s, min 1.001e-05s, max 4.697e-05s, tot 1.059e-04s (4 samples) -#pr: ref. unt. rsb operation time was: on avg. 1.079e-02s, min 6.383e-03s, max 1.279e-02s, tot 4.317e-02s (4 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 5.396e+00 1.509e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.569e+00 -#pr: Record collection took 4.50 s. +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.41 s, min 0.36 s, max 0.46 s, tot 1.64 s (4 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.41 s, min 0.36 s, max 0.46 s, tot 1.64 s (4 samples) +#pr: best tun. rsb canon. mflops were: on avg. 2.103e+03, min 2.017e+03, max 2.244e+03 (4 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 3.151e+00, min 1.233e+00, max 6.739e+00 (4 samples) +#pr: best tun. rsb operation time was: on avg. 2.348e-05s, min 1.001e-05s, max 3.791e-05s, tot 9.394e-05s (4 samples) +#pr: ref. unt. rsb operation time was: on avg. 1.708e-02s, min 1.199e-02s, max 2.398e-02s, tot 6.834e-02s (4 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 5.025e+00 1.807e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.809e+00 +#pr: Record collection took 6.27 s. #pr: Record comprises 50 memory benchmark samples (prepend RSB_PR_MBW=1 to dump this). -#pr: Record comprises 99 environment variables in 4801 bytes (prepend RSB_PR_ENV=1 to dump this). +#pr: Record comprises 99 environment variables in 4855 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 1733298404 (after 14.3s of w.c.t.) +# terminating run at 1767709326 (after 16.5s 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 85629 Dec 3 19:46 test-tuning-lower-100x100-5050nz--D-N-1--base.eps --rw-r--r-- 1 pbuilder1 pbuilder1 84551 Dec 3 19:46 test-tuning-lower-100x100-5050nz--D-N-1--mv-tuned_merge1_1x1th.eps --rw-r--r-- 1 pbuilder1 pbuilder1 85629 Dec 3 19:46 test-tuning-lower-100x100-5050nz--S-N-1--base.eps --rw-r--r-- 1 pbuilder1 pbuilder1 84551 Dec 3 19:46 test-tuning-lower-100x100-5050nz--S-N-1--mv-tuned_merge1_1x1th.eps --rw-r--r-- 1 pbuilder1 pbuilder1 85629 Dec 3 19:46 test-tuning-lower-100x100-5050nz--C-N-1--base.eps --rw-r--r-- 1 pbuilder1 pbuilder1 84551 Dec 3 19:46 test-tuning-lower-100x100-5050nz--C-N-1--mv-tuned_merge1_1x1th.eps --rw-r--r-- 1 pbuilder1 pbuilder1 85629 Dec 3 19:46 test-tuning-lower-100x100-5050nz--Z-N-1--base.eps --rw-r--r-- 1 pbuilder1 pbuilder1 84551 Dec 3 19:46 test-tuning-lower-100x100-5050nz--Z-N-1--mv-tuned_merge1_1x1th.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 85638 Jan 7 04:21 test-tuning-lower-100x100-5050nz--D-N-1--base.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 84561 Jan 7 04:21 test-tuning-lower-100x100-5050nz--D-N-1--mv-tuned_merge1_1x1th.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 85638 Jan 7 04:22 test-tuning-lower-100x100-5050nz--S-N-1--base.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 84560 Jan 7 04:22 test-tuning-lower-100x100-5050nz--S-N-1--mv-tuned_merge1_1x1th.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 85638 Jan 7 04:22 test-tuning-lower-100x100-5050nz--C-N-1--base.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 84560 Jan 7 04:22 test-tuning-lower-100x100-5050nz--C-N-1--mv-tuned_merge1_1x1th.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 85638 Jan 7 04:22 test-tuning-lower-100x100-5050nz--Z-N-1--base.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 84560 Jan 7 04:22 test-tuning-lower-100x100-5050nz--Z-N-1--mv-tuned_merge1_1x1th.eps + rsbench --read-performance-record test.rpr + ls -ltr test.txt --rw-r--r-- 1 pbuilder1 pbuilder1 4095 Dec 3 19:46 test.txt +-rw-r--r-- 1 pbuilder2 pbuilder2 4099 Jan 7 04:22 test.txt + RSB_PR_WLTC=2 + RSB_PR_SR=0 + rsbench --read-performance-record test.rpr @@ -8143,31 +8179,31 @@ /usr/bin/latex + which kpsepath /usr/bin/kpsepath -++ sed 's/!!//g;s/:/\n/g;' ++ kpsepath tex -+ find . /nonexistent/first-build/.texlive2024/texmf-config/tex/kpsewhich// /nonexistent/first-build/.texlive2024/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/.texlive2024/texmf-config/tex/generic// /nonexistent/first-build/.texlive2024/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/.texlive2024/texmf-config/tex/latex// /nonexistent/first-build/.texlive2024/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/.texlive2024/texmf-config/tex/// /nonexistent/first-build/.texlive2024/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/.texlive2024/texmf-config/tex/kpsewhich//': No such file or directory -find: '/nonexistent/first-build/.texlive2024/texmf-var/tex/kpsewhich//': No such file or directory -find: '/nonexistent/first-build/texmf/tex/kpsewhich//': No such file or directory +++ sed 's/!!//g;s/:/\n/g;' ++ find . /nonexistent/second-build/.texlive2024/texmf-config/tex/kpsewhich// /nonexistent/second-build/.texlive2024/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/.texlive2024/texmf-config/tex/generic// /nonexistent/second-build/.texlive2024/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/.texlive2024/texmf-config/tex/latex// /nonexistent/second-build/.texlive2024/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/.texlive2024/texmf-config/tex/// /nonexistent/second-build/.texlive2024/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/.texlive2024/texmf-config/tex/kpsewhich//': No such file or directory +find: '/nonexistent/second-build/.texlive2024/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/.texlive2024/texmf-config/tex/generic//': No such file or directory -find: '/nonexistent/first-build/.texlive2024/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/.texlive2024/texmf-config/tex/generic//': No such file or directory +find: '/nonexistent/second-build/.texlive2024/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/.texlive2024/texmf-config/tex/latex//': No such file or directory -find: '/nonexistent/first-build/.texlive2024/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/.texlive2024/texmf-config/tex/latex//': No such file or directory +find: '/nonexistent/second-build/.texlive2024/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/.texlive2024/texmf-config/tex///': No such file or directory -find: '/nonexistent/first-build/.texlive2024/texmf-var/tex///': No such file or directory -find: '/nonexistent/first-build/texmf/tex///': No such file or directory +find: '/nonexistent/second-build/.texlive2024/texmf-config/tex///': No such file or directory +find: '/nonexistent/second-build/.texlive2024/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 @@ -8182,7 +8218,7 @@ This error may be safely ignored. Correctly allocated a matrix. Summary information of the matrix: -(3 x 3)[0x577fc530]{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)[0x56c8a530]{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. @@ -8197,7 +8233,7 @@ This error may be safely ignored. Correctly allocated a matrix. Summary information of the matrix: -(3 x 3)[0x57b0b530]{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)[0x5825e530]{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. @@ -8261,51 +8297,51 @@ Done. Building a matrix with 5 nnz, 5 x 5 Duplicates check: 5 - 0 = 5 - converted COO to RSB in 1.187e-01 s (100.00 %) - analyzed arrays in 4.798e-02 s (40.43 %) + converted COO to RSB in 1.826e-01 s (100.00 %) + analyzed arrays in 8.877e-02 s (48.60 %) cleaned-up arrays in 9.537e-07 s (0.00 %) deduplicated arrays in 0.000e+00 s (0.00 %) - sorted arrays in 1.069e-02 s (9.01 %) - shuffled partitions in 2.401e-02 s (20.23 %) - memory allocations took 6.199e-06 s (0.01 %) - leafs setup took 2.146e-06 s (0.00 %) - halfword conversion took 3.598e-02 s (30.32 %) -Built (5 x 5)[0x57b0c700]{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:'' + sorted arrays in 1.386e-02 s (7.59 %) + shuffled partitions in 4.800e-02 s (26.28 %) + memory allocations took 8.106e-06 s (0.00 %) + leafs setup took 3.099e-06 s (0.00 %) + halfword conversion took 3.199e-02 s (17.52 %) +Built (5 x 5)[0x5825f700]{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)[0x57b0c700]{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)[0x5825f700]{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 1.307546s. +Before auto-tuning, 100 multiplications took 2.075989s. 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.=5.45502e-08), 8 suggested as starting thread count(default). -3 iterations (8 th.) took 0.04038s; avg 0.01346s ( +/- 10.94/ 17.88 %); best 0.01199s; worst 0.01587s; std dev. 0.001716 (taking best). -Reference operation time is 0.011986 s (0.001669 Mflops) with 8 threads. -3 iterations (8 th.) took 0.04434s; avg 0.01478s ( +/- 14.41/ 7.39 %); best 0.01265s; worst 0.01587s; std dev. 0.001506 (taking best). -Reference operation time is 0.012651 s (0.001581 Mflops) with 8 threads. -After 0.084783s, autotuning routine did not find a better threads count configuration. -(5 x 5)[0x57b0c700]{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 1.363638s -- effective speedup of 0.958866 x +Sampling (15 x 0.1 s stages, transA=N, nrhs=2, timer gran.=5.10454e-08), 8 suggested as starting thread count(default). +3 iterations (8 th.) took 0.07196s; avg 0.02399s ( +/- 0.14/ 0.11 %); best 0.02395s; worst 0.02401s; std dev. 2.465e-05 (taking best). +Reference operation time is 0.0239532 s (0.000835 Mflops) with 8 threads. +3 iterations (8 th.) took 0.09196s; avg 0.03065s ( +/- 8.67/ 4.40 %); best 0.028s; worst 0.032s; std dev. 0.001879 (taking best). +Reference operation time is 0.0279961 s (0.0007144 Mflops) with 8 threads. +After 0.164004s, autotuning routine did not find a better threads count configuration. +(5 x 5)[0x5825f700]{D} @ (0(0..0),0(0..0)) (5 nnz, 1 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 2, symflags:'' +After threads auto-tuning, 100 multiplications took 2.155953s -- effective speedup of 0.96291 x Matrix autotuning (may take more than 1.500000s; using 8 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.=5.45502e-08), 8 suggested as starting thread count. -3 iterations (8 th.) took 0.03998s; avg 0.01333s ( +/- 40.74/ 49.99 %); best 0.007898s; worst 0.01999s; std dev. 0.005013 (taking best). -Reference operation time is 0.00789809 s (0.002532 Mflops) with 8 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: 0.007898 Mflops: 0.003) -Merge (2 -> 1 leaves) took w.c.t. of 2.003e-05s, ~2.861e-06s of computing time (of which 0s sorting, 5.007e-06s analysis) -3 iterations (8 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 91.42/200.00 %); best 5.455e-08s; worst 1.907e-06s; std dev. 8.991e-07 (taking best). -Reference operation time is 5.45502e-08 s (366.6 Mflops) with 8 threads. -After merge step 1: tpop: 5.455e-08 s ~Mflops: 366.635 nsubm:1 otn:8 -Applying merge (2 -> 1 leaves, 8 th.) yielded SPEEDUP of 144785.839x: 0.007898s -> 5.455e-08s, so taking this instance. +Starting autotuning (15 x 0.1 s stages, transA=N, nrhs=2, timer gran.=5.10454e-08), 8 suggested as starting thread count. +3 iterations (8 th.) took 0.052s; avg 0.01733s ( +/- 53.87/ 61.46 %); best 0.007996s; worst 0.02798s; std dev. 0.008213 (taking best). +Reference operation time is 0.00799608 s (0.002501 Mflops) with 8 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: 0.007996 Mflops: 0.003) +Merge (2 -> 1 leaves) took w.c.t. of 1.907e-05s, ~3.099e-06s of computing time (of which 0s sorting, 4.053e-06s analysis) +3 iterations (8 th.) took 4.053e-06s; avg 1.351e-06s ( +/- 96.22/200.00 %); best 5.105e-08s; worst 4.053e-06s; std dev. 1.911e-06 (taking best). +Reference operation time is 5.10454e-08 s (391.8 Mflops) with 8 threads. +After merge step 1: tpop: 5.105e-08 s ~Mflops: 391.808 nsubm:1 otn:8 +Applying merge (2 -> 1 leaves, 8 th.) yielded SPEEDUP of 156646.427x: 0.007996s -> 5.105e-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 0.052s (of which 3.695e-05s partitioning, 0s I/O); computing times: 2.861e-06s in par. loops, 0s sorting, 5.007e-06s analyzing) -Total merge + benchmarking process took 0.052s, equivalent to 953234.3/6.6 new/old ops (0.09992s for 2 clones -- as 1831743.9/12.7 ops, or 915871.9/6.3 ops per clone), SPEEDUP of 144785.839x -Applying multi-merge (2 -> 1 leaves, 1 steps, 8 -> 8 th.sp.) yielded SPEEDUP of 144785.839x (0.007898s -> 5.455e-08s), will amortize in 6.6 ops by saving 0.007898s per op. -In 1 tuning rounds (tot. 0.14s, 0.1s for constructor, 2 clones) obtained a SPEEDUP of 14478483.9% (1.448e+05x) (from 0.002532 to 366.6 Mflops). -After 0.140023s, autotuning routine declared speedup of 144786 x, when using threads count of 8. -(5 x 5)[0x57b0e6a0]{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 0.000018s -- further speedup of 76260.2 x +A total of 1 merge steps (of max 6) (2 -> 1 subms) took 0.07601s (of which 4.315e-05s partitioning, 0s I/O); computing times: 3.099e-06s in par. loops, 0s sorting, 4.053e-06s analyzing) +Total merge + benchmarking process took 0.07601s, equivalent to 1489028.5/9.5 new/old ops (0.1359s for 2 clones -- as 2662844.5/17.0 ops, or 1331422.2/8.5 ops per clone), SPEEDUP of 156646.427x +Applying multi-merge (2 -> 1 leaves, 1 steps, 8 -> 8 th.sp.) yielded SPEEDUP of 156646.427x (0.007996s -> 5.105e-08s), will amortize in 9.5 ops by saving 0.007996s per op. +In 1 tuning rounds (tot. 0.19s, 0.14s for constructor, 2 clones) obtained a SPEEDUP of 15664542.7% (1.566e+05x) (from 0.002501 to 391.8 Mflops). +After 0.188054s, autotuning routine declared speedup of 156646 x, when using threads count of 8. +(5 x 5)[0x582616a0]{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 0.000017s -- further speedup of 127362 x 0/2 0 0 -> 0 1/2 1 0 -> 5 0/2 0 3 -> 0 @@ -8316,7 +8352,7 @@ Correctly initialized the library. Correctly allocated a matrix with 7 nonzeroes. Summary information of the matrix: -(6 x 6)[0x57b0c700]{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)[0x5825f700]{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 @@ -8470,66 +8506,66 @@ 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 2.842e-01 s (100.00 %) - analyzed arrays in 6.779e-02 s (23.85 %) - cleaned-up arrays in 7.820e-05 s (0.03 %) - deduplicated arrays in 6.795e-05 s (0.02 %) - sorted arrays in 1.123e-01 s (39.50 %) - shuffled partitions in 6.401e-02 s (22.52 %) - memory allocations took 2.599e-05 s (0.01 %) - leafs setup took 6.914e-06 s (0.00 %) - halfword conversion took 3.999e-02 s (14.07 %) -Built (500 x 500)[0x56a58360]{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: 22, symflags:'' + converted COO to RSB in 3.300e-01 s (100.00 %) + analyzed arrays in 4.781e-02 s (14.49 %) + cleaned-up arrays in 8.416e-05 s (0.03 %) + deduplicated arrays in 7.415e-05 s (0.02 %) + sorted arrays in 9.801e-02 s (29.70 %) + shuffled partitions in 1.160e-01 s (35.15 %) + memory allocations took 2.766e-05 s (0.01 %) + leafs setup took 8.106e-06 s (0.00 %) + halfword conversion took 6.798e-02 s (20.60 %) +Built (500 x 500)[0x57dc6360]{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: 22, symflags:'' Allocated matrix of 62500 nonzeroes: -(500 x 500)[0x56a58360]{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: 22, symflags:'' +(500 x 500)[0x57dc6360]{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: 22, symflags:'' -Before auto-tuning, 100 multiplications took 1.871854s. +Before auto-tuning, 100 multiplications took 2.267775s. 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, 31 subms, 22 lsubms, 2.0735 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.=5.39541e-08), 8 suggested as starting thread count(default). -3 iterations (8 th.) took 0.04796s; avg 0.01599s ( +/- 27.58/ 49.55 %); best 0.01158s; worst 0.02391s; std dev. 0.005613 (taking best). -Reference operation time is 0.0115769 s (21.59 Mflops) with 8 threads. -3 iterations (8 th.) took 0.04809s; avg 0.01603s ( +/- 3.52/ 2.99 %); best 0.01547s; worst 0.01651s; std dev. 0.00043 (taking best). -Reference operation time is 0.0154679 s (16.16 Mflops) with 8 threads. -After 0.096139s, autotuning routine did not find a better threads count configuration. -(500 x 500)[0x56a58360]{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: 22, symflags:'' -After threads auto-tuning, 100 multiplications took 1.989709s -- effective speedup of 0.940768 x +Sampling (15 x 0.1 s stages, transA=N, nrhs=2, timer gran.=5.07474e-08), 8 suggested as starting thread count(default). +3 iterations (8 th.) took 0.08445s; avg 0.02815s ( +/- 13.16/ 8.48 %); best 0.02444s; worst 0.03053s; std dev. 0.002656 (taking best). +Reference operation time is 0.0244429 s (10.23 Mflops) with 8 threads. +3 iterations (8 th.) took 0.08346s; avg 0.02782s ( +/- 28.15/ 43.78 %); best 0.01999s; worst 0.04s; std dev. 0.008729 (taking best). +Reference operation time is 0.019989 s (12.51 Mflops) with 8 threads. +After 0.168007s, autotuning routine did not find a better threads count configuration. +(500 x 500)[0x57dc6360]{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: 22, symflags:'' +After threads auto-tuning, 100 multiplications took 2.063949s -- effective speedup of 1.09876 x Matrix autotuning (may take more than 1.500000s; using 8 threads )... Will autotune matrix: 500 x 500, type D, 62500 nnz, 1.2e+02 nnz/r, 31 subms, 22 lsubms, 2.0735 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.=5.39541e-08), 8 suggested as starting thread count. -3 iterations (8 th.) took 0.0798s; avg 0.0266s ( +/- 39.20/ 21.88 %); best 0.01617s; worst 0.03242s; std dev. 0.007388 (taking best). -Reference operation time is 0.0161731 s (15.46 Mflops) with 8 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, 31 subms, 22 lsubms, 2.0735 bpnz (tpop: 0.01617 Mflops: 15.458) -Merge (22 -> 16 leaves) took w.c.t. of 0.001634s, ~0.0001459s of computing time (of which 4.506e-05s sorting, 5.96e-06s analysis) -3 iterations (8 th.) took 0.06993s; avg 0.02331s ( +/- 38.59/ 61.59 %); best 0.01431s; worst 0.03767s; std dev. 0.01026 (taking best). -Reference operation time is 0.0143139 s (17.47 Mflops) with 8 threads. -After merge step 1: tpop: 0.01431 s ~Mflops: 17.465 nsubm:16 otn:8 -Applying merge (22 -> 16 leaves, 8 th.) yielded SPEEDUP of 1.130x: 0.01617s -> 0.01431s, so taking this instance. -Merge (16 -> 10 leaves) took w.c.t. of 0.01484s, ~0.0002337s of computing time (of which 0.0001452s sorting, 5.007e-06s analysis) -3 iterations (8 th.) took 0.07146s; avg 0.02382s ( +/- 32.87/ 57.90 %); best 0.01599s; worst 0.03761s; std dev. 0.009782 (taking best). -Reference operation time is 0.0159881 s (15.64 Mflops) with 8 threads. -After merge step 2: tpop: 0.01599 s ~Mflops: 15.637 nsubm:10 otn:8 -Applying merge (16 -> 10 leaves, 8 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.117x: 0.01431s -> 0.01599s. -Merge (10 -> 7 leaves) took w.c.t. of 0.0001109s, ~9.513e-05s of computing time (of which 5.198e-05s sorting, 5.007e-06s analysis) -3 iterations (8 th.) took 0.0901s; avg 0.03003s ( +/- 54.45/ 60.06 %); best 0.01368s; worst 0.04807s; std dev. 0.01409 (taking best). -Reference operation time is 0.01368 s (18.27 Mflops) with 8 threads. -After merge step 3: tpop: 0.01368 s ~Mflops: 18.275 nsubm:7 otn:8 -Applying merge (10 -> 7 leaves, 8 th.) yielded SPEEDUP of 1.046x: 0.01431s -> 0.01368s, so taking this instance. -Merge (7 -> 4 leaves) took w.c.t. of 0.0001149s, ~0.000103s of computing time (of which 6.199e-05s sorting, 4.053e-06s analysis) -3 iterations (8 th.) took 0.05799s; avg 0.01933s ( +/- 8.98/ 17.37 %); best 0.01759s; worst 0.02269s; std dev. 0.002375 (taking best). -Reference operation time is 0.0175941 s (14.21 Mflops) with 8 threads. -After merge step 4: tpop: 0.01759 s ~Mflops: 14.209 nsubm:4 otn:8 -Applying merge (7 -> 4 leaves, 8 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.286x: 0.01368s -> 0.01759s. +Starting autotuning (15 x 0.1 s stages, transA=N, nrhs=2, timer gran.=5.07474e-08), 8 suggested as starting thread count. +3 iterations (8 th.) took 0.0631s; avg 0.02103s ( +/- 16.86/ 11.38 %); best 0.01749s; worst 0.02343s; std dev. 0.002558 (taking best). +Reference operation time is 0.0174868 s (14.3 Mflops) with 8 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, 31 subms, 22 lsubms, 2.0735 bpnz (tpop: 0.01749 Mflops: 14.296) +Merge (22 -> 16 leaves) took w.c.t. of 0.008204s, ~0.0002811s of computing time (of which 4.196e-05s sorting, 7.153e-06s analysis) +3 iterations (8 th.) took 0.08374s; avg 0.02791s ( +/- 42.73/ 28.66 %); best 0.01599s; worst 0.03591s; std dev. 0.008596 (taking best). +Reference operation time is 0.0159879 s (15.64 Mflops) with 8 threads. +After merge step 1: tpop: 0.01599 s ~Mflops: 15.637 nsubm:16 otn:8 +Applying merge (22 -> 16 leaves, 8 th.) yielded SPEEDUP of 1.094x: 0.01749s -> 0.01599s, so taking this instance. +Merge (16 -> 10 leaves) took w.c.t. of 0.0002s, ~0.0003531s of computing time (of which 0.0002279s sorting, 5.007e-06s analysis) +3 iterations (8 th.) took 0.05978s; avg 0.01993s ( +/- 20.81/ 28.70 %); best 0.01578s; worst 0.02565s; std dev. 0.004178 (taking best). +Reference operation time is 0.0157812 s (15.84 Mflops) with 8 threads. +After merge step 2: tpop: 0.01578 s ~Mflops: 15.842 nsubm:10 otn:8 +Applying merge (16 -> 10 leaves, 8 th.) yielded SPEEDUP of 1.013x: 0.01599s -> 0.01578s, so taking this instance. +Merge (10 -> 7 leaves) took w.c.t. of 9.799e-05s, ~8.106e-05s of computing time (of which 4.506e-05s sorting, 5.007e-06s analysis) +3 iterations (8 th.) took 0.05982s; avg 0.01994s ( +/- 39.92/ 20.37 %); best 0.01198s; worst 0.024s; std dev. 0.005629 (taking best). +Reference operation time is 0.0119789 s (20.87 Mflops) with 8 threads. +After merge step 3: tpop: 0.01198 s ~Mflops: 20.870 nsubm:7 otn:8 +Applying merge (10 -> 7 leaves, 8 th.) yielded SPEEDUP of 1.317x: 0.01578s -> 0.01198s, so taking this instance. +Merge (7 -> 4 leaves) took w.c.t. of 0.00016s, ~0.000144s of computing time (of which 9.608e-05s sorting, 5.96e-06s analysis) +3 iterations (8 th.) took 0.1238s; avg 0.04127s ( +/- 10.39/ 16.30 %); best 0.03698s; worst 0.048s; std dev. 0.004817 (taking best). +Reference operation time is 0.0369811 s (6.76 Mflops) with 8 threads. +After merge step 4: tpop: 0.03698 s ~Mflops: 6.760 nsubm:4 otn:8 +Applying merge (7 -> 4 leaves, 8 th.) yielded SLOWDOWN (1th of 3 tolerable) of 3.087x: 0.01198s -> 0.03698s. Skipping further merge based tests after 1 definite performance degradations in a row (and last exceeding limit). -A total of 4 merge steps (of max 6) (22 -> 4 subms) took 0.4195s (of which 0.01673s partitioning, 0s I/O); computing times: 0.0005777s in par. loops, 0.0003042s sorting, 2.003e-05s analyzing) -Total merge + benchmarking process took 0.4195s, equivalent to 30.7/25.9 new/old ops (0.162s for 3 clones -- as 11.8/10.0 ops, or 3.9/3.3 ops per clone), SPEEDUP of 1.182x -Applying multi-merge (22 -> 7 leaves, 3 steps, 8 -> 8 th.sp.) yielded SPEEDUP of 1.182x (0.01617s -> 0.01368s), will amortize in 168.3 ops by saving 0.002493s per op. -In 1 tuning rounds (tot. 0.55s, 0.16s for constructor, 3 clones) obtained a SPEEDUP of 18.2% (1.182x) (from 15.46 to 18.27 Mflops). -After 0.548283s, autotuning routine declared speedup of 1.18225 x, when using threads count of 8. -(500 x 500)[0x56b52630]{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: 7, symflags:'' -After threads auto-tuning, 100 multiplications took 2.110023s -- further speedup of 0.94298 x +A total of 4 merge steps (of max 6) (22 -> 4 subms) took 0.56s (of which 0.00868s partitioning, 0s I/O); computing times: 0.0008593s in par. loops, 0.000411s sorting, 2.313e-05s analyzing) +Total merge + benchmarking process took 0.56s, equivalent to 46.7/32.0 new/old ops (0.2809s for 4 clones -- as 23.4/16.1 ops, or 5.9/4.0 ops per clone), SPEEDUP of 1.460x +Applying multi-merge (22 -> 7 leaves, 3 steps, 8 -> 8 th.sp.) yielded SPEEDUP of 1.460x (0.01749s -> 0.01198s), will amortize in 101.7 ops by saving 0.005508s per op. +In 1 tuning rounds (tot. 0.68s, 0.28s for constructor, 4 clones) obtained a SPEEDUP of 46.0% (1.46x) (from 14.3 to 20.87 Mflops). +After 0.680268s, autotuning routine declared speedup of 1.45981 x, when using threads count of 8. +(500 x 500)[0x57dc9a90]{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: 7, symflags:'' +After threads auto-tuning, 100 multiplications took 1.955687s -- further speedup of 1.05536 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! @@ -8537,19 +8573,19 @@ Correctly initialized the library. Building a matrix with 7 nnz, 6 x 6 Duplicates check: 1 - 0 = 1 - converted COO to RSB in 1.038e-01 s (100.00 %) - analyzed arrays in 6.928e-02 s (66.77 %) - cleaned-up arrays in 7.153e-06 s (0.01 %) - deduplicated arrays in 9.537e-07 s (0.00 %) - sorted arrays in 9.537e-07 s (0.00 %) - shuffled partitions in 3.444e-02 s (33.19 %) - memory allocations took 1.383e-05 s (0.01 %) - leafs setup took 5.007e-06 s (0.00 %) - halfword conversion took 7.153e-06 s (0.01 %) -Built (6 x 6)[0x57df3540]{D} @ (0(0..1),0(5..6)) (1 nnz, 0.17 nnz/r) flags 0x20443ee (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 1, symflags:'UT' + converted COO to RSB in 9.559e-02 s (100.00 %) + analyzed arrays in 5.955e-02 s (62.30 %) + cleaned-up arrays in 9.060e-06 s (0.01 %) + deduplicated arrays in 0.000e+00 s (0.00 %) + sorted arrays in 1.907e-06 s (0.00 %) + shuffled partitions in 3.600e-02 s (37.66 %) + memory allocations took 1.502e-05 s (0.02 %) + leafs setup took 4.053e-06 s (0.00 %) + halfword conversion took 5.960e-06 s (0.01 %) +Built (6 x 6)[0x56a1d540]{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)[0x57df3540]{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)[0x56a1d540]{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 @@ -8575,55 +8611,55 @@ 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:5.485e-08 -3 iterations (8 th.) took 2.408e-05s; avg 8.027e-06s ( +/- 99.32/200.00 %); best 5.485e-08s; worst 2.408e-05s; std dev. 1.135e-05 (taking best). -Reference operation time is 5.48482e-08 s (36.46 Mflops) with 8 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: 5.485e-08 Mflops: 36.464) +Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:5.13e-08 +3 iterations (8 th.) took 2.813e-05s; avg 9.378e-06s ( +/- 99.45/187.29 %); best 5.13e-08s; worst 2.694e-05s; std dev. 1.243e-05 (taking best). +Reference operation time is 5.12958e-08 s (38.99 Mflops) with 8 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: 5.13e-08 Mflops: 38.990) Merge (1 -> 1 leaves) took w.c.t. of 0s, ~0s of computing time (of which 0s sorting, 0s analysis) -3 iterations (8 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 82.75/200.00 %); best 5.485e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). -Reference operation time is 5.48482e-08 s (36.46 Mflops) with 8 threads. -After merge step 1: tpop: 5.485e-08 s ~Mflops: 36.464 nsubm:1 otn:8 -Applying merge (1 -> 1 leaves, 8 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=1.00000x): 5.485e-08s -> 5.485e-08s, so IGNORING this instance. +3 iterations (8 th.) took 0s; avg 0s ( +/- -inf/ -nan %); best 5.13e-08s; worst 0s; std dev. 0 (taking best). +Reference operation time is 5.12958e-08 s (38.99 Mflops) with 8 threads. +After merge step 1: tpop: 5.13e-08 s ~Mflops: 38.990 nsubm:1 otn:8 +Applying merge (1 -> 1 leaves, 8 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=1.00000x): 5.13e-08s -> 5.13e-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 1.192e-05s (of which 2.861e-06s partitioning, 0s I/O); computing times: 0s in par. loops, 0s sorting, 0s analyzing) -Total merge + benchmarking process took 1.192e-05s, equivalent to 217.3/217.3 new/old ops (0.06789s for 1 clones -- as 1237835.3/1237835.3 ops, or 1237835.3/1237835.3 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) +A total of 1 merge steps (of max 6) (1 -> 1 subms) took 1.001e-05s (of which 1.907e-06s partitioning, 0s I/O); computing times: 0s in par. loops, 0s sorting, 0s analyzing) +Total merge + benchmarking process took 1.001e-05s, equivalent to 195.2/195.2 new/old ops (0.05989s for 1 clones -- as 1167483.2/1167483.2 ops, or 1167483.2/1167483.2 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) Merging based autotuning FAILED (=NO SPEEDUP); let's try splitting then... -3 iterations (8 th.) took 6.914e-06s; avg 2.305e-06s ( +/- 97.62/158.62 %); best 5.485e-08s; worst 5.96e-06s; std dev. 2.614e-06 (taking best). -Reference operation time is 5.48482e-08 s (36.46 Mflops) with 8 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: 5.485e-08 Mflops: 36.464) -Split (1 -> 1 leaves, 1 -> 1 subms) took 2.003e-05s (of which: 2.146e-06s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. -3 iterations (8 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 82.75/200.00 %); best 5.485e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). -Reference operation time is 5.48482e-08 s (36.46 Mflops) with 8 threads. -After split step 1: tpop: 5.485e-08 s ~Mflops: 36.464 nsubm:1 otn:8 -Applying split (1 -> 1 leaves, 8 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=1.00000x): 5.485e-08s -> 5.485e-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 (8 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 82.75/200.00 %); best 5.485e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). -Reference operation time is 5.48482e-08 s (36.46 Mflops) with 8 threads. -After split step 2: tpop: 5.485e-08 s ~Mflops: 36.464 nsubm:1 otn:8 -Applying split (1 -> 1 leaves, 8 th.) yielded NEGLIGIBLE change (2th in a row) (old/new=1.00000x): 5.485e-08s -> 5.485e-08s, so IGNORING this instance. -Split (1 -> 1 leaves, 1 -> 1 subms) took 5.007e-06s (of which: 1.192e-06s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. -3 iterations (8 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 82.75/200.00 %); best 5.485e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). -Reference operation time is 5.48482e-08 s (36.46 Mflops) with 8 threads. -After split step 3: tpop: 5.485e-08 s ~Mflops: 36.464 nsubm:1 otn:8 -Applying split (1 -> 1 leaves, 8 th.) yielded NEGLIGIBLE change (3th in a row) (old/new=1.00000x): 5.485e-08s -> 5.485e-08s, so IGNORING this instance. -Split (1 -> 1 leaves, 1 -> 1 subms) took 4.053e-06s (of which: 9.537e-07s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. -3 iterations (8 th.) took 0s; avg 0s ( +/- -inf/ -nan %); best 5.485e-08s; worst 0s; std dev. 0 (taking best). -Reference operation time is 5.48482e-08 s (36.46 Mflops) with 8 threads. -After split step 4: tpop: 5.485e-08 s ~Mflops: 36.464 nsubm:1 otn:8 -Applying split (1 -> 1 leaves, 8 th.) yielded NEGLIGIBLE change (4th in a row) (old/new=1.00000x): 5.485e-08s -> 5.485e-08s, so IGNORING this instance. -Split (1 -> 1 leaves, 1 -> 1 subms) took 4.053e-06s (of which: 0s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. -3 iterations (8 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 82.75/200.00 %); best 5.485e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). -Reference operation time is 5.48482e-08 s (36.46 Mflops) with 8 threads. -After split step 5: tpop: 5.485e-08 s ~Mflops: 36.464 nsubm:1 otn:8 -Applying split (1 -> 1 leaves, 8 th.) yielded NEGLIGIBLE change (5th in a row) (old/new=1.00000x): 5.485e-08s -> 5.485e-08s, so IGNORING this instance. -Split (1 -> 1 leaves, 1 -> 1 subms) took 3.815e-06s (of which: 0s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. -3 iterations (8 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 82.75/200.00 %); best 5.485e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). -Reference operation time is 5.48482e-08 s (36.46 Mflops) with 8 threads. -After split step 6: tpop: 5.485e-08 s ~Mflops: 36.464 nsubm:1 otn:8 -Applying split (1 -> 1 leaves, 8 th.) yielded NEGLIGIBLE change (6th in a row) (old/new=1.00000x): 5.485e-08s -> 5.485e-08s, so IGNORING this instance. -A total of 6 split steps (of max 6) (1 -> 1 subms) took 0.0001152s (of which 6.223e-05s partitioning, 0s I/O); computing times: 0s in par. loops, 0s sorting, 4.292e-06s analyzing) -Total split + benchmarking process took 0.0001152s, equivalent to 2099.5/2099.5 new/old ops (0.07991s for 1 clones -- as 1456948.5/1456948.5 ops, or 1456948.5/1456948.5 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) -In 1 tuning rounds (tot. 0.15s, 0.15s for constructor, 2 clones) obtained NO speedup (best stays 36.46 Mflops). +3 iterations (8 th.) took 4.053e-06s; avg 1.351e-06s ( +/- 96.20/200.00 %); best 5.13e-08s; worst 4.053e-06s; std dev. 1.911e-06 (taking best). +Reference operation time is 5.12958e-08 s (38.99 Mflops) with 8 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: 5.13e-08 Mflops: 38.990) +Split (1 -> 1 leaves, 1 -> 1 subms) took 1.884e-05s (of which: 2.861e-06s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. +3 iterations (8 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 83.86/200.00 %); best 5.13e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). +Reference operation time is 5.12958e-08 s (38.99 Mflops) with 8 threads. +After split step 1: tpop: 5.13e-08 s ~Mflops: 38.990 nsubm:1 otn:8 +Applying split (1 -> 1 leaves, 8 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=1.00000x): 5.13e-08s -> 5.13e-08s, so IGNORING this instance. +Split (1 -> 1 leaves, 1 -> 1 subms) took 3.099e-06s (of which: 0s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. +3 iterations (8 th.) took 1.192e-06s; avg 3.974e-07s ( +/- 87.09/200.00 %); best 5.13e-08s; worst 1.192e-06s; std dev. 5.62e-07 (taking best). +Reference operation time is 5.12958e-08 s (38.99 Mflops) with 8 threads. +After split step 2: tpop: 5.13e-08 s ~Mflops: 38.990 nsubm:1 otn:8 +Applying split (1 -> 1 leaves, 8 th.) yielded NEGLIGIBLE change (2th in a row) (old/new=1.00000x): 5.13e-08s -> 5.13e-08s, so IGNORING this instance. +Split (1 -> 1 leaves, 1 -> 1 subms) took 2.861e-06s (of which: 0s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. +3 iterations (8 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 83.86/200.00 %); best 5.13e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). +Reference operation time is 5.12958e-08 s (38.99 Mflops) with 8 threads. +After split step 3: tpop: 5.13e-08 s ~Mflops: 38.990 nsubm:1 otn:8 +Applying split (1 -> 1 leaves, 8 th.) yielded NEGLIGIBLE change (3th in a row) (old/new=1.00000x): 5.13e-08s -> 5.13e-08s, so IGNORING this instance. +Split (1 -> 1 leaves, 1 -> 1 subms) took 2.861e-06s (of which: 0s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. +3 iterations (8 th.) took 0s; avg 0s ( +/- -inf/ -nan %); best 5.13e-08s; worst 0s; std dev. 0 (taking best). +Reference operation time is 5.12958e-08 s (38.99 Mflops) with 8 threads. +After split step 4: tpop: 5.13e-08 s ~Mflops: 38.990 nsubm:1 otn:8 +Applying split (1 -> 1 leaves, 8 th.) yielded NEGLIGIBLE change (4th in a row) (old/new=1.00000x): 5.13e-08s -> 5.13e-08s, so IGNORING this instance. +Split (1 -> 1 leaves, 1 -> 1 subms) took 2.861e-06s (of which: 0s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. +3 iterations (8 th.) took 0s; avg 0s ( +/- -inf/ -nan %); best 5.13e-08s; worst 0s; std dev. 0 (taking best). +Reference operation time is 5.12958e-08 s (38.99 Mflops) with 8 threads. +After split step 5: tpop: 5.13e-08 s ~Mflops: 38.990 nsubm:1 otn:8 +Applying split (1 -> 1 leaves, 8 th.) yielded NEGLIGIBLE change (5th in a row) (old/new=1.00000x): 5.13e-08s -> 5.13e-08s, so IGNORING this instance. +Split (1 -> 1 leaves, 1 -> 1 subms) took 2.861e-06s (of which: 0s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. +3 iterations (8 th.) took 1.192e-06s; avg 3.974e-07s ( +/- 87.09/200.00 %); best 5.13e-08s; worst 1.192e-06s; std dev. 5.62e-07 (taking best). +Reference operation time is 5.12958e-08 s (38.99 Mflops) with 8 threads. +After split step 6: tpop: 5.13e-08 s ~Mflops: 38.990 nsubm:1 otn:8 +Applying split (1 -> 1 leaves, 8 th.) yielded NEGLIGIBLE change (6th in a row) (old/new=1.00000x): 5.13e-08s -> 5.13e-08s, so IGNORING this instance. +A total of 6 split steps (of max 6) (1 -> 1 subms) took 0.000104s (of which 5.507e-05s partitioning, 0s I/O); computing times: 0s in par. loops, 0s sorting, 2.861e-06s analyzing) +Total split + benchmarking process took 0.000104s, equivalent to 2026.5/2026.5 new/old ops (0.05993s for 1 clones -- as 1168380.2/1168380.2 ops, or 1168380.2/1168380.2 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) +In 1 tuning rounds (tot. 0.12s, 0.12s for constructor, 2 clones) obtained NO speedup (best stays 38.99 Mflops). Backsolving we should get a unitary vector: %%MatrixMarket matrix array real general @@ -8658,186 +8694,109 @@ /build/reproducible-path/librsb-1.3.0.2+dfsg/examples/fortran Building a matrix with 210 nnz, 20 x 20 Duplicates check: 210 - 0 = 210 - converted COO to RSB in 2.094e-01 s (100.00 %) - analyzed arrays in 5.998e-02 s (28.64 %) - cleaned-up arrays in 5.007e-06 s (0.00 %) - deduplicated arrays in 9.537e-07 s (0.00 %) - sorted arrays in 3.274e-02 s (15.63 %) - shuffled partitions in 6.414e-02 s (30.63 %) - memory allocations took 2.408e-05 s (0.01 %) - leafs setup took 8.106e-06 s (0.00 %) - halfword conversion took 5.250e-02 s (25.07 %) -Built (20 x 20)[0x56743440]{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 1.677e-01 s (100.00 %) + analyzed arrays in 6.397e-02 s (38.16 %) + cleaned-up arrays in 5.960e-06 s (0.00 %) + deduplicated arrays in 1.907e-06 s (0.00 %) + sorted arrays in 3.160e-02 s (18.85 %) + shuffled partitions in 3.437e-02 s (20.50 %) + memory allocations took 6.080e-05 s (0.04 %) + leafs setup took 7.153e-06 s (0.00 %) + halfword conversion took 3.762e-02 s (22.44 %) +Built (20 x 20)[0x56da6440]{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:5.325e-08 -Starting autotuning (16 x 5.32508e-08 s stages, transA=N, nrhs=1, timer gran.=5.32508e-08), 8 suggested as starting thread count(default). -3 iterations (8 th.) took 0.06008s; avg 0.02003s ( +/- 20.16/ 19.85 %); best 0.01599s; worst 0.024s; std dev. 0.003271 (taking best). -Reference operation time is 0.0159891 s (0.05254 Mflops) with 8 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: 0.01599 Mflops: 0.053) -Merge (22 -> 16 leaves) took w.c.t. of 0.01592s, ~6.413e-05s of computing time (of which 3.815e-06s sorting, 5.007e-06s analysis) -3 iterations (8 th.) took 0.09212s; avg 0.03071s ( +/- 21.28/ 30.27 %); best 0.02417s; worst 0.04s; std dev. 0.00675 (taking best). -Reference operation time is 0.0241702 s (0.03475 Mflops) with 8 threads. -After merge step 1: tpop: 0.02417 s ~Mflops: 0.035 nsubm:16 otn:8 -Applying merge (22 -> 16 leaves, 8 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.512x: 0.01599s -> 0.02417s. +Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:5.155e-08 +Starting autotuning (16 x 5.15461e-08 s stages, transA=N, nrhs=1, timer gran.=5.15461e-08), 8 suggested as starting thread count(default). +3 iterations (8 th.) took 0.05999s; avg 0.02s ( +/- 48.20/ 48.16 %); best 0.01036s; worst 0.02963s; std dev. 0.007867 (taking best). +Reference operation time is 0.010359 s (0.08109 Mflops) with 8 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: 0.01036 Mflops: 0.081) +Merge (22 -> 16 leaves) took w.c.t. of 0.000155s, ~5.388e-05s of computing time (of which 4.053e-06s sorting, 6.914e-06s analysis) +3 iterations (8 th.) took 0.06781s; avg 0.0226s ( +/- 11.51/ 6.08 %); best 0.02s; worst 0.02398s; std dev. 0.00184 (taking best). +Reference operation time is 0.0200028 s (0.04199 Mflops) with 8 threads. +After merge step 1: tpop: 0.02 s ~Mflops: 0.042 nsubm:16 otn:8 +Applying merge (22 -> 16 leaves, 8 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.931x: 0.01036s -> 0.02s. Skipping further merge based tests after 1 definite performance degradations in a row (and last exceeding limit). -A total of 1 merge steps (of max 6) (22 -> 16 subms) took 0.1081s (of which 0.01593s partitioning, 0s I/O); computing times: 6.413e-05s in par. loops, 3.815e-06s sorting, 5.007e-06s analyzing) -Total merge + benchmarking process took 0.1081s, equivalent to 6.8/6.8 new/old ops (0.06728s for 1 clones -- as 4.2/4.2 ops, or 4.2/4.2 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) +A total of 1 merge steps (of max 6) (22 -> 16 subms) took 0.06799s (of which 0.000159s partitioning, 0s I/O); computing times: 5.388e-05s in par. loops, 4.053e-06s sorting, 6.914e-06s analyzing) +Total merge + benchmarking process took 0.06799s, equivalent to 6.6/6.6 new/old ops (0.05192s for 1 clones -- as 5.0/5.0 ops, or 5.0/5.0 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) Merging based autotuning FAILED (=NO SPEEDUP); let's try splitting then... -3 iterations (8 th.) took 0.096s; avg 0.032s ( +/- 49.21/ 49.93 %); best 0.01625s; worst 0.04798s; std dev. 0.01295 (taking best). -Reference operation time is 0.0162511 s (0.05169 Mflops) with 8 threads. -Starting split (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=cols) (max 6 steps, inclusive 3 grace steps) on: 20 x 20, type D, 210 nnz, 10 nnz/r, 30 subms, 22 lsubms, 3.7524 bpnz (tpop: 0.01625 Mflops: 0.052) -Split (22 -> 51 leaves, 30 -> 70 subms) took 0.04396s (of which: 5.007e-06s analysis, -1.907e+10s mem.mgmt); compute time: 0.0003822s overall, 1.335e-05s searches, 0.0003688s shuffle, 0.00015s switch, 1.144e-05s quadrants. -3 iterations (8 th.) took 0.09193s; avg 0.03064s ( +/- 47.92/ 30.39 %); best 0.01596s; worst 0.03996s; std dev. 0.01051 (taking best). -Reference operation time is 0.0159581 s (0.05264 Mflops) with 8 threads. -After split step 1: tpop: 0.01596 s ~Mflops: 0.053 nsubm:51 otn:8 -Applying split (22 -> 51 leaves, 8 th.) yielded SPEEDUP of 1.018x: 0.01625s -> 0.01596s, so taking this instance. -Split (51 -> 122 leaves, 70 -> 166 subms) took 0.03594s (of which: 1.216e-05s analysis, -4.333e+10s mem.mgmt); compute time: 0.0003579s overall, 1.502e-05s searches, 0.0003428s shuffle, 0.0001349s switch, 3.29e-05s quadrants. -3 iterations (8 th.) took 0.07593s; avg 0.02531s ( +/- 28.28/ 17.54 %); best 0.01815s; worst 0.02975s; std dev. 0.00511 (taking best). -Reference operation time is 0.018153 s (0.04627 Mflops) with 8 threads. -After split step 2: tpop: 0.01815 s ~Mflops: 0.046 nsubm:122 otn:8 -Applying split (51 -> 122 leaves, 8 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.138x: 0.01596s -> 0.01815s. -Split (122 -> 146 leaves, 166 -> 198 subms) took 0.04753s (of which: 1.907e-05s analysis, -1.387e+10s mem.mgmt); compute time: 3.195e-05s overall, 2.146e-06s searches, 2.98e-05s shuffle, 1.383e-05s switch, 4.768e-06s quadrants. -3 iterations (8 th.) took 0.08433s; avg 0.02811s ( +/- 14.49/ 13.72 %); best 0.02404s; worst 0.03197s; std dev. 0.003241 (taking best). -Reference operation time is 0.0240362 s (0.03495 Mflops) with 8 threads. -After split step 3: tpop: 0.02404 s ~Mflops: 0.035 nsubm:146 otn:8 -Applying split (122 -> 146 leaves, 8 th.) yielded SLOWDOWN (2th of 3 tolerable) of 1.506x: 0.01596s -> 0.02404s. -Skipping further split based tests after 2 definite performance degradations in a row (and last exceeding limit). -A total of 3 split steps (of max 6) (22 -> 146 subms) took 0.452s (of which 0.1277s partitioning, 0s I/O); computing times: 0.000772s in par. loops, 3.052e-05s sorting, 3.624e-05s analyzing) -Total split + benchmarking process took 0.452s, equivalent to 28.3/27.8 new/old ops (0.1438s for 2 clones -- as 9.0/8.8 ops, or 4.5/4.4 ops per clone), SPEEDUP of 1.018x -Applying multi-split (22 -> 51 leaves, 1 steps, 0 -> 8 th.sp.) yielded SPEEDUP of 1.018x (0.01625s -> 0.01596s), will amortize in 1542.5 ops by saving 0.000293s per op. -In 1 tuning rounds (tot. 0.86s, 0.21s for constructor, 3 clones) obtained a SPEEDUP of 1.8% (1.018x) (from 0.05169 to 0.05264 Mflops). +3 iterations (8 th.) took 0.04002s; avg 0.01334s ( +/- 39.89/ 20.03 %); best 0.008019s; worst 0.01601s; std dev. 0.003763 (taking best). +Reference operation time is 0.00801897 s (0.1048 Mflops) with 8 threads. +Starting split (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=cols) (max 6 steps, inclusive 3 grace steps) on: 20 x 20, type D, 210 nnz, 10 nnz/r, 30 subms, 22 lsubms, 3.7524 bpnz (tpop: 0.008019 Mflops: 0.105) +Split (22 -> 51 leaves, 30 -> 70 subms) took 0.03594s (of which: 5.007e-06s analysis, -1.944e+10s mem.mgmt); compute time: 0.001016s overall, 1.311e-05s searches, 0.001003s shuffle, 0.0004678s switch, 0.0002036s quadrants. +3 iterations (8 th.) took 0.05599s; avg 0.01866s ( +/- 35.82/ 28.59 %); best 0.01198s; worst 0.024s; std dev. 0.005 (taking best). +Reference operation time is 0.0119789 s (0.07012 Mflops) with 8 threads. +After split step 1: tpop: 0.01198 s ~Mflops: 0.070 nsubm:51 otn:8 +Applying split (22 -> 51 leaves, 8 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.494x: 0.008019s -> 0.01198s. +Skipping further split based tests after 1 definite performance degradations in a row (and last exceeding limit). +A total of 1 split steps (of max 6) (22 -> 51 subms) took 0.09199s (of which 0.03598s partitioning, 0s I/O); computing times: 0.001016s in par. loops, 1.311e-05s sorting, 5.007e-06s analyzing) +Total split + benchmarking process took 0.09199s, equivalent to 11.5/11.5 new/old ops (0.05196s for 1 clones -- as 6.5/6.5 ops, or 6.5/6.5 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) +In 1 tuning rounds (tot. 0.36s, 0.1s for constructor, 2 clones) obtained NO speedup (best stays 0.1048 Mflops). autotuner chose 8 threads -Will autotune matrix: 20 x 20, type D, 210 nnz, 10 nnz/r, 70 subms, 51 lsubms, 4.4571 bpnz. -Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:5.325e-08 -Starting autotuning (16 x 5.32508e-08 s stages, transA=N, nrhs=1, timer gran.=5.32508e-08), 8 suggested as starting thread count(default). -3 iterations (8 th.) took 0.07995s; avg 0.02665s ( +/- 24.92/ 35.03 %); best 0.02001s; worst 0.03598s; std dev. 0.006795 (taking best). -~ 8 threads: 0.02001s (0.042 Mflops) (0/2 degradations so far) - -3 iterations (7 th.) took 0.07998s; avg 0.02666s ( +/- 25.08/ 50.06 %); best 0.01997s; worst 0.04001s; std dev. 0.009437 (taking best). - 7 threads: 0.01997s (0.042 Mflops) (0/2 degradations so far) - -3 iterations (6 th.) took 0.084s; avg 0.028s ( +/- 42.82/ 28.55 %); best 0.01601s; worst 0.03599s; std dev. 0.008634 (taking best). - 6 threads: 0.01601s (0.052 Mflops) (0/2 degradations so far) - -3 iterations (5 th.) took 0.09596s; avg 0.03199s ( +/- 0.06/ 0.04 %); best 0.03197s; worst 0.032s; std dev. 1.301e-05 (taking best). - 5 threads: 0.03197s (0.026 Mflops) (1/2 degradations so far) - -3 iterations (4 th.) took 0.07636s; avg 0.02545s ( +/- 35.66/ 25.68 %); best 0.01638s; worst 0.03199s; std dev. 0.006622 (taking best). - 4 threads: 0.01638s (0.051 Mflops) (2/2 degradations so far) - -Best threads choice is 6; starting threads were 8; max speed gap is 2x; search took 0.42s. -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, 70 subms, 51 lsubms, 4.4571 bpnz (tpop: 0.01601 Mflops: 0.052) -Merge (51 -> 36 leaves) took w.c.t. of 0.01165s, ~4.721e-05s of computing time (of which 8.106e-06s sorting, 5.96e-06s analysis) -3 iterations (8 th.) took 0.03595s; avg 0.01198s ( +/- 0.09/ 0.13 %); best 0.01197s; worst 0.012s; std dev. 1.142e-05 (taking best). -~ 8 threads: 0.01197s (0.07 Mflops) (0/2 degradations so far) - -3 iterations (7 th.) took 0.03602s; avg 0.01201s ( +/- 0.18/ 0.24 %); best 0.01198s; worst 0.01203s; std dev. 2.106e-05 (taking best). - 7 threads: 0.01198s (0.07 Mflops) (1/2 degradations so far) - -3 iterations (6 th.) took 0.04794s; avg 0.01598s ( +/- 24.92/ 25.13 %); best 0.012s; worst 0.01999s; std dev. 0.003265 (taking best). - 6 threads: 0.012s (0.07 Mflops) (2/2 degradations so far) - -Best threads choice is 8; starting threads were 8; max speed gap is 1x; search took 0.12s. -After merge step 1: tpop: 0.01197 s ~Mflops: 0.070 nsubm:36 otn:8 -Applying merge (51 -> 36 leaves, 8 th.) yielded SPEEDUP of 1.337x: 0.01601s -> 0.01197s, so taking this instance. -Merge (36 -> 25 leaves) took w.c.t. of 0.01208s, ~4.172e-05s of computing time (of which 5.722e-06s sorting, 5.96e-06s analysis) -3 iterations (8 th.) took 0.0359s; avg 0.01197s ( +/- 5.72/ 5.63 %); best 0.01128s; worst 0.01264s; std dev. 0.0005545 (taking best). -~ 8 threads: 0.01128s (0.074 Mflops) (0/2 degradations so far) - -3 iterations (7 th.) took 0.04799s; avg 0.016s ( +/- 25.15/ 50.10 %); best 0.01197s; worst 0.02401s; std dev. 0.005667 (taking best). - 7 threads: 0.01197s (0.07 Mflops) (1/2 degradations so far) - -3 iterations (6 th.) took 0.084s; avg 0.028s ( +/- 57.14/ 42.79 %); best 0.012s; worst 0.03998s; std dev. 0.01177 (taking best). +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:5.155e-08 +Starting autotuning (16 x 5.15461e-08 s stages, transA=N, nrhs=1, timer gran.=5.15461e-08), 8 suggested as starting thread count(default). +3 iterations (8 th.) took 0.06034s; avg 0.02011s ( +/- 38.54/ 39.11 %); best 0.01236s; worst 0.02798s; std dev. 0.006377 (taking best). +~ 8 threads: 0.01236s (0.068 Mflops) (0/2 degradations so far) - +3 iterations (7 th.) took 0.04766s; avg 0.01589s ( +/- 24.14/ 25.74 %); best 0.01205s; worst 0.01998s; std dev. 0.00324 (taking best). + 7 threads: 0.01205s (0.07 Mflops) (0/2 degradations so far) - +3 iterations (6 th.) took 0.04794s; avg 0.01598s ( +/- 22.61/ 24.76 %); best 0.01237s; worst 0.01994s; std dev. 0.0031 (taking best). + 6 threads: 0.01237s (0.068 Mflops) (1/2 degradations so far) - +3 iterations (5 th.) took 0.048s; avg 0.016s ( +/- 14.83/ 25.09 %); best 0.01363s; worst 0.02001s; std dev. 0.002854 (taking best). + 5 threads: 0.01363s (0.062 Mflops) (2/2 degradations so far) - +Best threads choice is 7; starting threads were 8; max speed gap is 1.1x; search took 0.2s. +Starting merge (and threads) based auto-tuning procedure (transA=N, nrhs=1, order=cols) (max 6 steps, inclusive 3 grace steps) on: 20 x 20, type D, 210 nnz, 10 nnz/r, 30 subms, 22 lsubms, 3.7524 bpnz (tpop: 0.01205 Mflops: 0.070) +Merge (22 -> 16 leaves) took w.c.t. of 0.01199s, ~1.907e-05s of computing time (of which 4.053e-06s sorting, 4.053e-06s analysis) +3 iterations (8 th.) took 0.05998s; avg 0.01999s ( +/- 39.95/ 39.97 %); best 0.01201s; worst 0.02798s; std dev. 0.006523 (taking best). +~ 8 threads: 0.01201s (0.07 Mflops) (0/2 degradations so far) - +3 iterations (7 th.) took 0.05998s; avg 0.01999s ( +/- 9.60/ 9.59 %); best 0.01807s; worst 0.02191s; std dev. 0.001567 (taking best). + 7 threads: 0.01807s (0.046 Mflops) (1/2 degradations so far) - +3 iterations (6 th.) took 0.04803s; avg 0.01601s ( +/- 25.14/ 48.87 %); best 0.01199s; worst 0.02383s; std dev. 0.005533 (taking best). + 6 threads: 0.01199s (0.07 Mflops) (0/2 degradations so far) - +3 iterations (5 th.) took 0.05994s; avg 0.01998s ( +/- 40.18/ 40.18 %); best 0.01195s; worst 0.02801s; std dev. 0.006554 (taking best). + 5 threads: 0.01195s (0.07 Mflops) (0/2 degradations so far) - +3 iterations (4 th.) took 0.03998s; avg 0.01333s ( +/- 39.97/ 50.07 %); best 0.007999s; worst 0.02s; std dev. 0.00499 (taking best). + 4 threads: 0.007999s (0.11 Mflops) (0/2 degradations so far) - +3 iterations (3 th.) took 0.05198s; avg 0.01733s ( +/- 44.52/ 52.14 %); best 0.009612s; worst 0.02636s; std dev. 0.006901 (taking best). + 3 threads: 0.009612s (0.087 Mflops) (1/2 degradations so far) - +3 iterations (2 th.) took 0.07196s; avg 0.02399s ( +/- 16.61/ 16.56 %); best 0.02s; worst 0.02796s; std dev. 0.003249 (taking best). + 2 threads: 0.02s (0.042 Mflops) (2/2 degradations so far) - +Best threads choice is 4; starting threads were 8; max speed gap is 2.5x; search took 0.39s. +After merge step 1: tpop: 0.007999 s ~Mflops: 0.105 nsubm:16 otn:4 +Applying merge (22 -> 16 leaves, 4 th.) yielded SPEEDUP of 1.507x: 0.01205s -> 0.007999s, so taking this instance. +Merge (16 -> 10 leaves) took w.c.t. of 0.008014s, ~1.931e-05s of computing time (of which 3.815e-06s sorting, 5.007e-06s analysis) +3 iterations (8 th.) took 0.05596s; avg 0.01865s ( +/- 35.96/ 71.61 %); best 0.01195s; worst 0.03201s; std dev. 0.009445 (taking best). +~ 8 threads: 0.01195s (0.07 Mflops) (0/2 degradations so far) - +3 iterations (7 th.) took 0.048s; avg 0.016s ( +/- 24.99/ 49.90 %); best 0.012s; worst 0.02398s; std dev. 0.005645 (taking best). + 7 threads: 0.012s (0.07 Mflops) (1/2 degradations so far) - +3 iterations (6 th.) took 0.04797s; avg 0.01599s ( +/- 24.96/ 49.91 %); best 0.012s; worst 0.02397s; std dev. 0.005643 (taking best). 6 threads: 0.012s (0.07 Mflops) (2/2 degradations so far) - -Best threads choice is 8; starting threads were 8; max speed gap is 1.1x; search took 0.17s. -After merge step 2: tpop: 0.01128 s ~Mflops: 0.074 nsubm:25 otn:8 -Applying merge (36 -> 25 leaves, 8 th.) yielded SPEEDUP of 1.061x: 0.01197s -> 0.01128s, so taking this instance. -Merge (25 -> 16 leaves) took w.c.t. of 0.01596s, ~2.909e-05s of computing time (of which 4.053e-06s sorting, 5.96e-06s analysis) -3 iterations (8 th.) took 0.116s; avg 0.03866s ( +/- 6.89/ 13.73 %); best 0.036s; worst 0.04397s; std dev. 0.003752 (taking best). -~ 8 threads: 0.036s (0.023 Mflops) (0/2 degradations so far) - -3 iterations (7 th.) took 0.06398s; avg 0.02133s ( +/- 25.09/ 50.04 %); best 0.01598s; worst 0.032s; std dev. 0.007546 (taking best). - 7 threads: 0.01598s (0.053 Mflops) (0/2 degradations so far) - -3 iterations (6 th.) took 0.06401s; avg 0.02134s ( +/- 25.17/ 49.98 %); best 0.01596s; worst 0.032s; std dev. 0.007541 (taking best). - 6 threads: 0.01596s (0.053 Mflops) (0/2 degradations so far) - -3 iterations (5 th.) took 0.0974s; avg 0.03247s ( +/- 38.40/ 60.07 %); best 0.02s; worst 0.05197s; std dev. 0.01397 (taking best). - 5 threads: 0.02s (0.042 Mflops) (1/2 degradations so far) - -3 iterations (4 th.) took 0.05457s; avg 0.01819s ( +/- 33.73/ 31.94 %); best 0.01205s; worst 0.024s; std dev. 0.004882 (taking best). - 4 threads: 0.01205s (0.07 Mflops) (0/2 degradations so far) - -3 iterations (3 th.) took 0.06394s; avg 0.02131s ( +/- 43.61/ 29.70 %); best 0.01202s; worst 0.02764s; std dev. 0.006714 (taking best). - 3 threads: 0.01202s (0.07 Mflops) (0/2 degradations so far) - -3 iterations (2 th.) took 0.08397s; avg 0.02799s ( +/- 43.47/ 28.52 %); best 0.01582s; worst 0.03597s; std dev. 0.008742 (taking best). - 2 threads: 0.01582s (0.053 Mflops) (1/2 degradations so far) - -3 iterations (1 th.) took 0.064s; avg 0.02133s ( +/- 6.33/ 12.49 %); best 0.01998s; worst 0.024s; std dev. 0.001884 (taking best). - 1 threads: 0.01998s (0.042 Mflops) (2/2 degradations so far) - -Best threads choice is 3; starting threads were 8; max speed gap is 3x; search took 0.61s. -After merge step 3: tpop: 0.01202 s ~Mflops: 0.070 nsubm:16 otn:3 -Applying merge (25 -> 16 leaves, 3 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.065x: 0.01128s -> 0.01202s. -Merge (16 -> 13 leaves) took w.c.t. of 2.408e-05s, ~7.153e-06s of computing time (of which 1.192e-06s sorting, 5.007e-06s analysis) -3 iterations (8 th.) took 0.09593s; avg 0.03198s ( +/- 13.69/ 26.29 %); best 0.0276s; worst 0.04038s; std dev. 0.005946 (taking best). -~ 8 threads: 0.0276s (0.03 Mflops) (0/2 degradations so far) - -3 iterations (7 th.) took 0.104s; avg 0.03466s ( +/- 19.28/ 38.48 %); best 0.02798s; worst 0.048s; std dev. 0.009431 (taking best). - 7 threads: 0.02798s (0.03 Mflops) (1/2 degradations so far) - -3 iterations (6 th.) took 0.05198s; avg 0.01733s ( +/- 30.64/ 38.49 %); best 0.01202s; worst 0.02399s; std dev. 0.004983 (taking best). - 6 threads: 0.01202s (0.07 Mflops) (0/2 degradations so far) - -3 iterations (5 th.) took 0.04798s; avg 0.01599s ( +/- 25.08/ 49.98 %); best 0.01198s; worst 0.02399s; std dev. 0.005652 (taking best). - 5 threads: 0.01198s (0.07 Mflops) (0/2 degradations so far) - -3 iterations (4 th.) took 0.03598s; avg 0.01199s ( +/- 0.22/ 0.13 %); best 0.01197s; worst 0.01201s; std dev. 1.916e-05 (taking best). - 4 threads: 0.01197s (0.07 Mflops) (0/2 degradations so far) - -3 iterations (3 th.) took 0.05622s; avg 0.01874s ( +/- 34.75/ 49.49 %); best 0.01223s; worst 0.02802s; std dev. 0.006735 (taking best). - 3 threads: 0.01223s (0.069 Mflops) (1/2 degradations so far) - -3 iterations (2 th.) took 0.05175s; avg 0.01725s ( +/- 31.90/ 62.28 %); best 0.01175s; worst 0.028s; std dev. 0.007598 (taking best). - 2 threads: 0.01175s (0.072 Mflops) (0/2 degradations so far) - -3 iterations (1 th.) took 0.05997s; avg 0.01999s ( +/- 20.14/ 19.82 %); best 0.01596s; worst 0.02395s; std dev. 0.003262 (taking best). - 1 threads: 0.01596s (0.053 Mflops) (1/2 degradations so far) - -Best threads choice is 2; starting threads were 8; max speed gap is 2.4x; search took 0.5s. -After merge step 4: tpop: 0.01175 s ~Mflops: 0.072 nsubm:13 otn:2 -Applying merge (16 -> 13 leaves, 2 th.) yielded SLOWDOWN (2th of 3 tolerable) of 1.041x: 0.01128s -> 0.01175s. -Merge (13 -> 10 leaves) took w.c.t. of 2.313e-05s, ~5.96e-06s of computing time (of which 1.907e-06s sorting, 5.007e-06s analysis) -3 iterations (8 th.) took 0.04794s; avg 0.01598s ( +/- 49.45/ 74.33 %); best 0.008079s; worst 0.02786s; std dev. 0.008552 (taking best). -~ 8 threads: 0.008079s (0.1 Mflops) (0/2 degradations so far) - -3 iterations (7 th.) took 0.03998s; avg 0.01333s ( +/- 10.20/ 20.07 %); best 0.01197s; worst 0.016s; std dev. 0.001892 (taking best). - 7 threads: 0.01197s (0.07 Mflops) (1/2 degradations so far) - -3 iterations (6 th.) took 0.03692s; avg 0.01231s ( +/- 66.34/ 36.54 %); best 0.004142s; worst 0.0168s; std dev. 0.005784 (taking best). - 6 threads: 0.004142s (0.2 Mflops) (0/2 degradations so far) - -3 iterations (5 th.) took 0.04305s; avg 0.01435s ( +/- 16.24/ 11.50 %); best 0.01202s; worst 0.016s; std dev. 0.001695 (taking best). - 5 threads: 0.01202s (0.07 Mflops) (1/2 degradations so far) - -3 iterations (4 th.) took 0.03599s; avg 0.012s ( +/- 66.70/ 33.58 %); best 0.003995s; worst 0.01603s; std dev. 0.005659 (taking best). - 4 threads: 0.003995s (0.21 Mflops) (0/2 degradations so far) - -3 iterations (3 th.) took 0.03595s; avg 0.01198s ( +/- 24.90/ 25.09 %); best 0.008999s; worst 0.01499s; std dev. 0.002446 (taking best). - 3 threads: 0.008999s (0.093 Mflops) (1/2 degradations so far) - -3 iterations (2 th.) took 0.04399s; avg 0.01466s ( +/- 20.60/ 13.67 %); best 0.01164s; worst 0.01667s; std dev. 0.002174 (taking best). - 2 threads: 0.01164s (0.072 Mflops) (2/2 degradations so far) - -Best threads choice is 4; starting threads were 8; max speed gap is 3x; search took 0.28s. -After merge step 5: tpop: 0.003995 s ~Mflops: 0.210 nsubm:10 otn:4 -Applying merge (13 -> 10 leaves, 4 th.) yielded SPEEDUP of 2.824x: 0.01128s -> 0.003995s, so taking this instance. -Merge (10 -> 8 leaves) took w.c.t. of 2.313e-05s, ~8.106e-06s of computing time (of which 9.537e-07s sorting, 3.815e-06s analysis) -3 iterations (8 th.) took 0.04801s; avg 0.016s ( +/- 2.21/ 4.02 %); best 0.01565s; worst 0.01664s; std dev. 0.0004552 (taking best). -~ 8 threads: 0.01565s (0.054 Mflops) (0/2 degradations so far) - -3 iterations (7 th.) took 0.04353s; avg 0.01451s ( +/- 22.72/ 18.14 %); best 0.01121s; worst 0.01714s; std dev. 0.002466 (taking best). - 7 threads: 0.01121s (0.075 Mflops) (0/2 degradations so far) - -3 iterations (6 th.) took 0.03569s; avg 0.0119s ( +/- 11.88/ 12.46 %); best 0.01048s; worst 0.01338s; std dev. 0.001183 (taking best). - 6 threads: 0.01048s (0.08 Mflops) (0/2 degradations so far) - -3 iterations (5 th.) took 0.04799s; avg 0.016s ( +/- 1.17/ 0.89 %); best 0.01581s; worst 0.01614s; std dev. 0.0001382 (taking best). - 5 threads: 0.01581s (0.053 Mflops) (1/2 degradations so far) - -3 iterations (4 th.) took 0.04431s; avg 0.01477s ( +/- 19.09/ 16.64 %); best 0.01195s; worst 0.01723s; std dev. 0.00217 (taking best). - 4 threads: 0.01195s (0.07 Mflops) (2/2 degradations so far) - -Best threads choice is 6; starting threads were 8; max speed gap is 1.5x; search took 0.22s. -After merge step 6: tpop: 0.01048 s ~Mflops: 0.080 nsubm:8 otn:6 -Applying merge (10 -> 8 leaves, 6 th.) yielded SLOWDOWN (1th of 3 tolerable) of 2.624x: 0.003995s -> 0.01048s. +Best threads choice is 8; starting threads were 8; max speed gap is 1x; search took 0.15s. +After merge step 2: tpop: 0.01195 s ~Mflops: 0.070 nsubm:10 otn:8 +Applying merge (16 -> 10 leaves, 8 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.493x: 0.007999s -> 0.01195s. Skipping further merge based tests after 1 definite performance degradations in a row (and last exceeding limit). -A total of 6 merge steps (of max 6) (51 -> 8 subms) took 2.072s (of which 0.03979s partitioning, 0s I/O); computing times: 0.0001392s in par. loops, 2.193e-05s sorting, 3.171e-05s analyzing) -Total merge + benchmarking process took 2.072s, equivalent to 518.6/129.4 new/old ops (0.2127s for 4 clones -- as 53.2/13.3 ops, or 13.3/3.3 ops per clone), SPEEDUP of 4.008x -Applying multi-merge (51 -> 10 leaves, 5 steps, 6 -> 4 th.sp.) yielded SPEEDUP of 4.008x (0.01601s -> 0.003995s), will amortize in 172.4 ops by saving 0.01202s per op. -In 1 tuning rounds (tot. 2.6s, 0.21s for constructor, 4 clones) obtained a SPEEDUP of 300.8% (4.008x) (from 0.05247 to 0.2103 Mflops). +A total of 2 merge steps (of max 6) (22 -> 10 subms) took 0.628s (of which 0.02002s partitioning, 0s I/O); computing times: 3.839e-05s in par. loops, 7.868e-06s sorting, 9.06e-06s analyzing) +Total merge + benchmarking process took 0.628s, equivalent to 78.5/52.1 new/old ops (0.12s for 2 clones -- as 15.0/10.0 ops, or 7.5/5.0 ops per clone), SPEEDUP of 1.507x +Applying multi-merge (22 -> 16 leaves, 1 steps, 7 -> 4 th.sp.) yielded SPEEDUP of 1.507x (0.01205s -> 0.007999s), will amortize in 154.9 ops by saving 0.004053s per op. +In 1 tuning rounds (tot. 0.89s, 0.12s for constructor, 2 clones) obtained a SPEEDUP of 50.7% (1.507x) (from 0.0697 to 0.105 Mflops). check results are ok Building a matrix with 36 nnz, 6 x 6 Duplicates check: 36 - 0 = 36 - converted COO to RSB in 3.481e-02 s (100.00 %) - analyzed arrays in 1.455e-02 s (41.82 %) - cleaned-up arrays in 9.537e-07 s (0.00 %) - deduplicated arrays in 9.537e-07 s (0.00 %) - sorted arrays in 8.251e-03 s (23.71 %) - shuffled partitions in 1.199e-02 s (34.44 %) - memory allocations took 6.199e-06 s (0.02 %) - leafs setup took 1.907e-06 s (0.01 %) - halfword conversion took 9.537e-07 s (0.00 %) -Built (6 x 6)[0x56747430]{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 7.583e-02 s (100.00 %) + analyzed arrays in 3.200e-02 s (42.20 %) + cleaned-up arrays in 1.192e-06 s (0.00 %) + deduplicated arrays in 0.000e+00 s (0.00 %) + sorted arrays in 2.381e-02 s (31.40 %) + shuffled partitions in 2.000e-02 s (26.38 %) + memory allocations took 9.060e-06 s (0.01 %) + leafs setup took 1.907e-06 s (0.00 %) + halfword conversion took 2.146e-06 s (0.00 %) +Built (6 x 6)[0x56dac800]{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 0.1884E-04 s +Repeated USMV took 0.2289E-04 s A single USMM took 0.1001E-04 s -USMM-to-USMV speed ratio is is 1.881 x +USMM-to-USMV speed ratio is is 2.286 x Call auto-tuning routine.. Repeat measurement. Tuned USMM took 0.3099E-05 s @@ -8890,238 +8849,230 @@ 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 1.670e-01 s (100.00 %) - analyzed arrays in 4.804e-02 s (28.77 %) - cleaned-up arrays in 1.001e-05 s (0.01 %) - deduplicated arrays in 2.861e-06 s (0.00 %) - sorted arrays in 4.699e-02 s (28.14 %) - shuffled partitions in 2.794e-02 s (16.73 %) - memory allocations took 1.502e-05 s (0.01 %) - leafs setup took 5.960e-06 s (0.00 %) - halfword conversion took 4.398e-02 s (26.34 %) -Built (6 x 6)[0x5756e9b0]{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 1.198e-01 s (100.00 %) + analyzed arrays in 3.596e-02 s (30.00 %) + cleaned-up arrays in 6.199e-06 s (0.01 %) + deduplicated arrays in 3.099e-06 s (0.00 %) + sorted arrays in 2.384e-02 s (19.89 %) + shuffled partitions in 3.600e-02 s (30.04 %) + memory allocations took 1.478e-05 s (0.01 %) + leafs setup took 8.106e-06 s (0.01 %) + halfword conversion took 2.400e-02 s (20.03 %) +Built (6 x 6)[0x581749b0]{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)[0x57570d50]{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)[0x58176d50]{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, 4.2778 bpnz. +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 (8 th.) took 0.05996s; avg 0.01999s ( +/- 40.03/ 20.20 %); best 0.01199s; worst 0.02402s; std dev. 0.005658 (taking best). -Reference operation time is 0.011986 s (0.01201 Mflops) with 8 threads. -After 0.060033s, autotuning routine did not find a better threads count configuration. +3 iterations (8 th.) took 0.05993s; avg 0.01998s ( +/- 39.85/ 20.06 %); best 0.01201s; worst 0.02398s; std dev. 0.00563 (taking best). +Reference operation time is 0.0120149 s (0.01199 Mflops) with 8 threads. +After 0.059988s, 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, 4.2778 bpnz. +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 (8 th.) took 0.04286s; avg 0.01429s ( +/- 16.04/ 32.03 %); best 0.01199s; worst 0.01886s; std dev. 0.003236 (taking best). -Reference operation time is 0.0119941 s (0.01201 Mflops) with 8 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, 4.2778 bpnz (tpop: 0.01199 Mflops: 0.012) -Merge (22 -> 19 leaves) took w.c.t. of 3.099e-05s, ~1.121e-05s of computing time (of which 9.537e-07s sorting, 5.96e-06s analysis) -3 iterations (8 th.) took 0.04508s; avg 0.01503s ( +/- 19.81/ 13.67 %); best 0.01205s; worst 0.01708s; std dev. 0.002155 (taking best). -Reference operation time is 0.0120511 s (0.01195 Mflops) with 8 threads. -After merge step 1: tpop: 0.01205 s ~Mflops: 0.012 nsubm:19 otn:8 -Applying merge (22 -> 19 leaves, 8 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=0.99527x): 0.01199s -> 0.01205s, so IGNORING this instance. -Merge (19 -> 16 leaves) took w.c.t. of 2.48e-05s, ~5.96e-06s of computing time (of which 1.192e-06s sorting, 5.007e-06s analysis) -3 iterations (8 th.) took 0.04795s; avg 0.01598s ( +/- 14.00/ 12.37 %); best 0.01375s; worst 0.01796s; std dev. 0.001731 (taking best). -Reference operation time is 0.0137451 s (0.01048 Mflops) with 8 threads. -After merge step 2: tpop: 0.01375 s ~Mflops: 0.010 nsubm:16 otn:8 -Applying merge (19 -> 16 leaves, 8 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.146x: 0.01199s -> 0.01375s. -Merge (16 -> 13 leaves) took w.c.t. of 2.408e-05s, ~6.914e-06s of computing time (of which 2.146e-06s sorting, 6.199e-06s analysis) -3 iterations (8 th.) took 0.04395s; avg 0.01465s ( +/- 16.75/ 9.21 %); best 0.0122s; worst 0.016s; std dev. 0.001738 (taking best). -Reference operation time is 0.012197 s (0.01181 Mflops) with 8 threads. -After merge step 3: tpop: 0.0122 s ~Mflops: 0.012 nsubm:13 otn:8 -Applying merge (16 -> 13 leaves, 8 th.) yielded NEGLIGIBLE change (2th in a row) (old/new=0.98337x): 0.01199s -> 0.0122s, so IGNORING this instance. -Merge (13 -> 10 leaves) took w.c.t. of 2.384e-05s, ~9.06e-06s of computing time (of which 0s sorting, 5.007e-06s analysis) -3 iterations (8 th.) took 0.05193s; avg 0.01731s ( +/- 31.04/ 19.75 %); best 0.01194s; worst 0.02073s; std dev. 0.003846 (taking best). -Reference operation time is 0.0119369 s (0.01206 Mflops) with 8 threads. -After merge step 4: tpop: 0.01194 s ~Mflops: 0.012 nsubm:10 otn:8 -Applying merge (13 -> 10 leaves, 8 th.) yielded NEGLIGIBLE change (3th in a row) (old/new=1.00479x): 0.01199s -> 0.01194s, so IGNORING this instance. -Merge (10 -> 7 leaves) took w.c.t. of 1.884e-05s, ~6.199e-06s of computing time (of which 1.907e-06s sorting, 4.053e-06s analysis) -3 iterations (8 th.) took 0.0478s; avg 0.01593s ( +/- 3.35/ 3.98 %); best 0.0154s; worst 0.01657s; std dev. 0.000482 (taking best). -Reference operation time is 0.015398 s (0.009352 Mflops) with 8 threads. -After merge step 5: tpop: 0.0154 s ~Mflops: 0.009 nsubm:7 otn:8 -Applying merge (10 -> 7 leaves, 8 th.) yielded SLOWDOWN (2th of 3 tolerable) of 1.284x: 0.01199s -> 0.0154s. -Skipping further merge based tests after 2 definite performance degradations in a row (and last exceeding limit). -A total of 5 merge steps (of max 6) (22 -> 7 subms) took 0.237s (of which 0.0001388s partitioning, 0s I/O); computing times: 3.934e-05s in par. loops, 6.199e-06s sorting, 2.623e-05s analyzing) -Total merge + benchmarking process took 0.237s, equivalent to 19.8/19.8 new/old ops (0.05994s for 1 clones -- as 5.0/5.0 ops, or 5.0/5.0 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) -Merging based autotuning FAILED (=NO SPEEDUP); let's try splitting then... -3 iterations (8 th.) took 0.02014s; avg 0.006715s ( +/- 46.86/ 25.29 %); best 0.003568s; worst 0.008413s; std dev. 0.002227 (taking best). -Reference operation time is 0.00356793 s (0.04036 Mflops) with 8 threads. -Starting split (same threads) based auto-tuning procedure (transA=N, nrhs=2, order=cols) (max 6 steps, inclusive 3 grace steps) on: 6 x 6, type D, 36 nnz, 6 nnz/r, 29 subms, 22 lsubms, 4.2778 bpnz (tpop: 0.003568 Mflops: 0.040) -Split (22 -> 25 leaves, 29 -> 33 subms) took 0.01138s (of which: 4.053e-06s analysis, -1.733e+09s mem.mgmt); compute time: 5.198e-05s overall, 3.099e-06s searches, 4.888e-05s shuffle, 4.101e-05s switch, 0s quadrants. -3 iterations (8 th.) took 0.036s; avg 0.012s ( +/- 33.54/ 33.33 %); best 0.007975s; worst 0.016s; std dev. 0.003276 (taking best). -Reference operation time is 0.00797486 s (0.01806 Mflops) with 8 threads. -After split step 1: tpop: 0.007975 s ~Mflops: 0.018 nsubm:25 otn:8 -Applying split (22 -> 25 leaves, 8 th.) yielded SLOWDOWN (1th of 3 tolerable) of 2.235x: 0.003568s -> 0.007975s. -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 -> 25 subms) took 0.04744s (of which 0.01143s partitioning, 0s I/O); computing times: 5.198e-05s in par. loops, 3.099e-06s sorting, 4.053e-06s analyzing) -Total split + benchmarking process took 0.04744s, equivalent to 13.3/13.3 new/old ops (0.02854s for 1 clones -- as 8.0/8.0 ops, or 8.0/8.0 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) -In 1 tuning rounds (tot. 0.44s, 0.088s for constructor, 2 clones) obtained NO speedup (best stays 0.04036 Mflops). -After 0.436000s, global autotuning found old matrix optimal, with declared speedup 1 x when using 8 threads +3 iterations (8 th.) took 0.05999s; avg 0.02s ( +/- 39.97/ 20.03 %); best 0.012s; worst 0.024s; std dev. 0.005652 (taking best). +Reference operation time is 0.0120029 s (0.012 Mflops) with 8 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: 0.012 Mflops: 0.012) +Merge (22 -> 16 leaves) took w.c.t. of 0.008055s, ~0.004159s of computing time (of which 2.861e-06s sorting, 6.199e-06s analysis) +3 iterations (8 th.) took 0.03989s; avg 0.0133s ( +/- 40.32/ 20.31 %); best 0.007936s; worst 0.016s; std dev. 0.003791 (taking best). +Reference operation time is 0.007936 s (0.01815 Mflops) with 8 threads. +After merge step 1: tpop: 0.007936 s ~Mflops: 0.018 nsubm:16 otn:8 +Applying merge (22 -> 16 leaves, 8 th.) yielded SPEEDUP of 1.512x: 0.012s -> 0.007936s, so taking this instance. +Merge (16 -> 10 leaves) took w.c.t. of 0.004101s, ~1.597e-05s of computing time (of which 1.907e-06s sorting, 4.053e-06s analysis) +3 iterations (8 th.) took 0.05991s; avg 0.01997s ( +/- 19.78/ 19.62 %); best 0.01602s; worst 0.02389s; std dev. 0.003212 (taking best). +Reference operation time is 0.0160182 s (0.00899 Mflops) with 8 threads. +After merge step 2: tpop: 0.01602 s ~Mflops: 0.009 nsubm:10 otn:8 +Applying merge (16 -> 10 leaves, 8 th.) yielded SLOWDOWN (1th of 3 tolerable) of 2.018x: 0.007936s -> 0.01602s. +Skipping further merge based tests after 1 definite performance degradations in a row (and last exceeding limit). +A total of 2 merge steps (of max 6) (22 -> 10 subms) took 0.156s (of which 0.01218s partitioning, 0s I/O); computing times: 0.004175s in par. loops, 4.768e-06s sorting, 1.025e-05s analyzing) +Total merge + benchmarking process took 0.156s, equivalent to 19.7/13.0 new/old ops (0.09196s for 2 clones -- as 11.6/7.7 ops, or 5.8/3.8 ops per clone), SPEEDUP of 1.512x +Applying multi-merge (22 -> 16 leaves, 1 steps, 0 -> 8 th.sp.) yielded SPEEDUP of 1.512x (0.012s -> 0.007936s), will amortize in 38.4 ops by saving 0.004067s per op. +In 1 tuning rounds (tot. 0.26s, 0.092s for constructor, 2 clones) obtained a SPEEDUP of 51.2% (1.512x) (from 0.012 to 0.01815 Mflops). +After 0.264038s, global autotuning declared speedup of 1.51247 x, when using threads count of 8 and a new matrix: +(6 x 6)[0x58178890]{D} @ (0(0..0),0(0..0)) (36 nnz, 6 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 16, symflags:'' Considering S clone. Building a matrix with 36 nnz, 6 x 6 Duplicates check: 36 - 0 = 36 - converted COO to RSB in 8.793e-02 s (100.00 %) - analyzed arrays in 2.392e-02 s (27.20 %) - cleaned-up arrays in 9.537e-07 s (0.00 %) + converted COO to RSB in 1.759e-01 s (100.00 %) + analyzed arrays in 5.191e-02 s (29.51 %) + cleaned-up arrays in 1.192e-06 s (0.00 %) deduplicated arrays in 9.537e-07 s (0.00 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 4.000e-02 s (45.49 %) - memory allocations took 5.245e-06 s (0.01 %) - leafs setup took 3.099e-06 s (0.00 %) - halfword conversion took 2.401e-02 s (27.30 %) -Built (6 x 6)[0x57570d50]{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 5.643e-02 s (32.07 %) + memory allocations took 2.098e-05 s (0.01 %) + leafs setup took 4.053e-06 s (0.00 %) + halfword conversion took 6.756e-02 s (38.40 %) +Built (6 x 6)[0x58178890]{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)[0x57570d50]{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)[0x58178890]{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, 4.5000 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:0.1 -3 iterations (8 th.) took 0.04385s; avg 0.01462s ( +/- 18.58/ 9.44 %); best 0.0119s; worst 0.016s; std dev. 0.001921 (taking best). -Reference operation time is 0.0119019 s (0.0121 Mflops) with 8 threads. -After 0.043882s, autotuning routine did not find a better threads count configuration. +3 iterations (8 th.) took 0.05993s; avg 0.01998s ( +/- 39.84/ 20.06 %); best 0.01202s; worst 0.02398s; std dev. 0.005628 (taking best). +Reference operation time is 0.012017 s (0.01198 Mflops) with 8 threads. +After 0.059960s, 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, 4.5000 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:0.1 -3 iterations (8 th.) took 0.05203s; avg 0.01734s ( +/- 8.12/ 15.46 %); best 0.01593s; worst 0.02002s; std dev. 0.001896 (taking best). -Reference operation time is 0.015934 s (0.009037 Mflops) with 8 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, 4.5000 bpnz (tpop: 0.01593 Mflops: 0.009) -Merge (16 -> 13 leaves) took w.c.t. of 1.907e-05s, ~5.007e-06s of computing time (of which 9.537e-07s sorting, 4.053e-06s analysis) -3 iterations (8 th.) took 0.06395s; avg 0.02132s ( +/- 24.43/ 30.72 %); best 0.01611s; worst 0.02787s; std dev. 0.004892 (taking best). -Reference operation time is 0.0161099 s (0.008939 Mflops) with 8 threads. -After merge step 1: tpop: 0.01611 s ~Mflops: 0.009 nsubm:13 otn:8 -Applying merge (16 -> 13 leaves, 8 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=0.98908x): 0.01593s -> 0.01611s, so IGNORING this instance. -Merge (13 -> 10 leaves) took w.c.t. of 2.193e-05s, ~6.914e-06s of computing time (of which 0s sorting, 5.007e-06s analysis) -3 iterations (8 th.) took 0.04396s; avg 0.01465s ( +/- 18.05/ 9.63 %); best 0.01201s; worst 0.01607s; std dev. 0.001871 (taking best). -Reference operation time is 0.0120099 s (0.01199 Mflops) with 8 threads. -After merge step 2: tpop: 0.01201 s ~Mflops: 0.012 nsubm:10 otn:8 -Applying merge (13 -> 10 leaves, 8 th.) yielded SPEEDUP of 1.327x: 0.01593s -> 0.01201s, so taking this instance. -Merge (10 -> 7 leaves) took w.c.t. of 1.884e-05s, ~5.007e-06s of computing time (of which 9.537e-07s sorting, 4.053e-06s analysis) -3 iterations (8 th.) took 0.04797s; avg 0.01599s ( +/- 24.95/ 49.88 %); best 0.012s; worst 0.02397s; std dev. 0.005639 (taking best). -Reference operation time is 0.012001 s (0.012 Mflops) with 8 threads. -After merge step 3: tpop: 0.012 s ~Mflops: 0.012 nsubm:7 otn:8 -Applying merge (10 -> 7 leaves, 8 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=1.00074x): 0.01201s -> 0.012s, so IGNORING this instance. -Merge (7 -> 4 leaves) took w.c.t. of 2.003e-05s, ~6.914e-06s of computing time (of which 1.192e-06s sorting, 5.007e-06s analysis) -3 iterations (8 th.) took 0.07195s; avg 0.02398s ( +/- 0.09/ 0.05 %); best 0.02396s; worst 0.024s; std dev. 1.578e-05 (taking best). -Reference operation time is 0.0239611 s (0.00601 Mflops) with 8 threads. -After merge step 4: tpop: 0.02396 s ~Mflops: 0.006 nsubm:4 otn:8 -Applying merge (7 -> 4 leaves, 8 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.995x: 0.01201s -> 0.02396s. +3 iterations (8 th.) took 0.06001s; avg 0.02s ( +/- 49.58/ 56.33 %); best 0.01009s; worst 0.03127s; std dev. 0.008701 (taking best). +Reference operation time is 0.0100858 s (0.01428 Mflops) with 8 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, 4.5000 bpnz (tpop: 0.01009 Mflops: 0.014) +Merge (16 -> 13 leaves) took w.c.t. of 2.003e-05s, ~5.007e-06s of computing time (of which 2.146e-06s sorting, 5.007e-06s analysis) +3 iterations (8 th.) took 0.07593s; avg 0.02531s ( +/- 23.12/ 12.55 %); best 0.01946s; worst 0.02849s; std dev. 0.004143 (taking best). +Reference operation time is 0.0194581 s (0.007401 Mflops) with 8 threads. +After merge step 1: tpop: 0.01946 s ~Mflops: 0.007 nsubm:13 otn:8 +Applying merge (16 -> 13 leaves, 8 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.929x: 0.01009s -> 0.01946s. 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 -> 4 subms) took 0.28s (of which 9.227e-05s partitioning, 0s I/O); computing times: 2.384e-05s in par. loops, 3.099e-06s sorting, 1.812e-05s analyzing) -Total merge + benchmarking process took 0.28s, equivalent to 23.3/17.6 new/old ops (0.092s for 2 clones -- as 7.7/5.8 ops, or 3.8/2.9 ops per clone), SPEEDUP of 1.327x -Applying multi-merge (16 -> 10 leaves, 2 steps, 0 -> 8 th.sp.) yielded SPEEDUP of 1.327x (0.01593s -> 0.01201s), will amortize in 71.4 ops by saving 0.003924s per op. -In 1 tuning rounds (tot. 0.37s, 0.092s for constructor, 2 clones) obtained a SPEEDUP of 32.7% (1.327x) (from 0.009037 to 0.01199 Mflops). -After 0.372098s, global autotuning declared speedup of 1.32674 x, when using threads count of 8 and a new matrix: -(6 x 6)[0x57572890]{S} @ (0(0..0),0(0..0)) (36 nnz, 6 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 10, symflags:'' +A total of 1 merge steps (of max 6) (16 -> 13 subms) took 0.07598s (of which 2.217e-05s partitioning, 0s I/O); computing times: 5.007e-06s in par. loops, 2.146e-06s sorting, 5.007e-06s analyzing) +Total merge + benchmarking process took 0.07598s, equivalent to 7.5/7.5 new/old ops (0.05599s for 1 clones -- as 5.6/5.6 ops, or 5.6/5.6 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) +Merging based autotuning FAILED (=NO SPEEDUP); let's try splitting then... +3 iterations (8 th.) took 0.05602s; avg 0.01867s ( +/- 42.50/ 57.77 %); best 0.01074s; worst 0.02946s; std dev. 0.007905 (taking best). +Reference operation time is 0.0107379 s (0.01341 Mflops) with 8 threads. +Starting split (same threads) based auto-tuning procedure (transA=N, nrhs=2, order=cols) (max 6 steps, inclusive 3 grace steps) on: 6 x 6, type S, 36 nnz, 6 nnz/r, 21 subms, 16 lsubms, 4.5000 bpnz (tpop: 0.01074 Mflops: 0.013) +Split (16 -> 25 leaves, 21 -> 33 subms) took 0.03598s (of which: 3.099e-06s analysis, -5.303e+09s mem.mgmt); compute time: 0.000484s overall, 1.192e-05s searches, 0.0004721s shuffle, 0.0002086s switch, 1.192e-06s quadrants. +3 iterations (8 th.) took 0.06794s; avg 0.02265s ( +/- 29.27/ 40.94 %); best 0.01602s; worst 0.03192s; std dev. 0.006754 (taking best). +Reference operation time is 0.0160179 s (0.00899 Mflops) with 8 threads. +After split step 1: tpop: 0.01602 s ~Mflops: 0.009 nsubm:25 otn:8 +Applying split (16 -> 25 leaves, 8 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.492x: 0.01074s -> 0.01602s. +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) (16 -> 25 subms) took 0.104s (of which 0.03603s partitioning, 0s I/O); computing times: 0.000484s in par. loops, 1.192e-05s sorting, 3.099e-06s analyzing) +Total split + benchmarking process took 0.104s, equivalent to 9.7/9.7 new/old ops (0.04398s for 1 clones -- as 4.1/4.1 ops, or 4.1/4.1 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) +In 1 tuning rounds (tot. 0.4s, 0.1s for constructor, 2 clones) obtained NO speedup (best stays 0.01341 Mflops). +After 0.396240s, global autotuning found old matrix optimal, with declared speedup 1 x when using 8 threads Considering C clone. Building a matrix with 36 nnz, 6 x 6 Duplicates check: 36 - 0 = 36 - converted COO to RSB in 1.400e-01 s (100.00 %) - analyzed arrays in 5.994e-02 s (42.83 %) - cleaned-up arrays in 1.907e-06 s (0.00 %) + converted COO to RSB in 1.362e-01 s (100.00 %) + analyzed arrays in 5.337e-02 s (39.18 %) + cleaned-up arrays in 9.537e-07 s (0.00 %) deduplicated arrays in 0.000e+00 s (0.00 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 4.402e-02 s (31.45 %) - memory allocations took 5.007e-06 s (0.00 %) - leafs setup took 5.007e-06 s (0.00 %) - halfword conversion took 3.598e-02 s (25.71 %) -Built (6 x 6)[0x57575310]{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 4.237e-02 s (31.10 %) + memory allocations took 9.060e-06 s (0.01 %) + leafs setup took 2.861e-06 s (0.00 %) + halfword conversion took 4.048e-02 s (29.71 %) +Built (6 x 6)[0x5817ce00]{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)[0x57575310]{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)[0x5817ce00]{C} @ (0(0..0),0(0..0)) (36 nnz, 6 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 22, symflags:'' -Will use autotuning routine to sample matrix: 6 x 6, type C, 36 nnz, 6 nnz/r, 29 subms, 22 lsubms, 4.6667 bpnz. +Will use autotuning routine to sample matrix: 6 x 6, type C, 36 nnz, 6 nnz/r, 29 subms, 22 lsubms, 4.2778 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:0.1 -3 iterations (8 th.) took 0.03989s; avg 0.0133s ( +/- 10.41/ 19.78 %); best 0.01191s; worst 0.01593s; std dev. 0.001861 (taking best). -Reference operation time is 0.0119131 s (0.04835 Mflops) with 8 threads. -After 0.039921s, autotuning routine did not find a better threads count configuration. +3 iterations (8 th.) took 0.06747s; avg 0.02249s ( +/- 46.63/ 77.87 %); best 0.012s; worst 0.04s; std dev. 0.01246 (taking best). +Reference operation time is 0.012002 s (0.04799 Mflops) with 8 threads. +After 0.067502s, autotuning routine did not find a better threads count configuration. -Will autotune matrix: 6 x 6, type C, 36 nnz, 6 nnz/r, 29 subms, 22 lsubms, 4.6667 bpnz. +Will autotune matrix: 6 x 6, type C, 36 nnz, 6 nnz/r, 29 subms, 22 lsubms, 4.2778 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:0.1 -3 iterations (8 th.) took 0.04798s; avg 0.01599s ( +/- 2.67/ 3.03 %); best 0.01557s; worst 0.01648s; std dev. 0.0003746 (taking best). -Reference operation time is 0.0155671 s (0.037 Mflops) with 8 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: 0.01557 Mflops: 0.037) -Merge (22 -> 16 leaves) took w.c.t. of 0.0006671s, ~1.597e-05s of computing time (of which 1.907e-06s sorting, 5.007e-06s analysis) -3 iterations (8 th.) took 0.06732s; avg 0.02244s ( +/- 46.43/ 39.64 %); best 0.01202s; worst 0.03134s; std dev. 0.007958 (taking best). -Reference operation time is 0.012022 s (0.04791 Mflops) with 8 threads. -After merge step 1: tpop: 0.01202 s ~Mflops: 0.048 nsubm:16 otn:8 -Applying merge (22 -> 16 leaves, 8 th.) yielded SPEEDUP of 1.295x: 0.01557s -> 0.01202s, so taking this instance. -Merge (16 -> 10 leaves) took w.c.t. of 0.004049s, ~2.003e-05s of computing time (of which 2.861e-06s sorting, 5.96e-06s analysis) -3 iterations (8 th.) took 0.06394s; avg 0.02131s ( +/- 43.76/ 50.13 %); best 0.01199s; worst 0.032s; std dev. 0.008225 (taking best). -Reference operation time is 0.011987 s (0.04805 Mflops) with 8 threads. -After merge step 2: tpop: 0.01199 s ~Mflops: 0.048 nsubm:10 otn:8 -Applying merge (16 -> 10 leaves, 8 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=1.00292x): 0.01202s -> 0.01199s, so IGNORING this instance. -Merge (10 -> 7 leaves) took w.c.t. of 1.788e-05s, ~5.96e-06s of computing time (of which 9.537e-07s sorting, 3.815e-06s analysis) -3 iterations (8 th.) took 0.06395s; avg 0.02132s ( +/- 43.73/ 30.88 %); best 0.012s; worst 0.0279s; std dev. 0.006776 (taking best). -Reference operation time is 0.011996 s (0.04802 Mflops) with 8 threads. -After merge step 3: tpop: 0.012 s ~Mflops: 0.048 nsubm:7 otn:8 -Applying merge (10 -> 7 leaves, 8 th.) yielded NEGLIGIBLE change (2th in a row) (old/new=1.00217x): 0.01202s -> 0.012s, so IGNORING this instance. -Merge (7 -> 4 leaves) took w.c.t. of 1.788e-05s, ~6.914e-06s of computing time (of which 9.537e-07s sorting, 3.099e-06s analysis) -3 iterations (8 th.) took 0.044s; avg 0.01467s ( +/- 18.42/ 9.28 %); best 0.01197s; worst 0.01603s; std dev. 0.00191 (taking best). +3 iterations (8 th.) took 0.08001s; avg 0.02667s ( +/- 55.10/ 35.02 %); best 0.01198s; worst 0.03601s; std dev. 0.01052 (taking best). +Reference operation time is 0.011975 s (0.0481 Mflops) with 8 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: 0.01198 Mflops: 0.048) +Merge (22 -> 19 leaves) took w.c.t. of 1.979e-05s, ~5.007e-06s of computing time (of which 9.537e-07s sorting, 5.007e-06s analysis) +3 iterations (8 th.) took 0.05595s; avg 0.01865s ( +/- 35.98/ 50.12 %); best 0.01194s; worst 0.028s; std dev. 0.006816 (taking best). +Reference operation time is 0.01194 s (0.04824 Mflops) with 8 threads. +After merge step 1: tpop: 0.01194 s ~Mflops: 0.048 nsubm:19 otn:8 +Applying merge (22 -> 19 leaves, 8 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=1.00294x): 0.01198s -> 0.01194s, so IGNORING this instance. +Merge (19 -> 16 leaves) took w.c.t. of 2.098e-05s, ~5.007e-06s of computing time (of which 1.907e-06s sorting, 6.199e-06s analysis) +3 iterations (8 th.) took 0.07195s; avg 0.02398s ( +/- 33.30/ 16.78 %); best 0.016s; worst 0.02801s; std dev. 0.005647 (taking best). +Reference operation time is 0.0159981 s (0.036 Mflops) with 8 threads. +After merge step 2: tpop: 0.016 s ~Mflops: 0.036 nsubm:16 otn:8 +Applying merge (19 -> 16 leaves, 8 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.336x: 0.01198s -> 0.016s. +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 -> 16 subms) took 0.128s (of which 4.625e-05s partitioning, 0s I/O); computing times: 1.001e-05s in par. loops, 2.861e-06s sorting, 1.121e-05s analyzing) +Total merge + benchmarking process took 0.128s, equivalent to 10.7/10.7 new/old ops (0.07196s for 1 clones -- as 6.0/6.0 ops, or 6.0/6.0 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) +Merging based autotuning FAILED (=NO SPEEDUP); let's try splitting then... +3 iterations (8 th.) took 0.05198s; avg 0.01733s ( +/- 30.83/ 61.62 %); best 0.01199s; worst 0.02801s; std dev. 0.00755 (taking best). +Reference operation time is 0.011986 s (0.04806 Mflops) with 8 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, 4.2778 bpnz (tpop: 0.01199 Mflops: 0.048) +Split (22 -> 25 leaves, 29 -> 33 subms) took 0.03994s (of which: 4.053e-06s analysis, -1.768e+09s mem.mgmt); compute time: 8.106e-05s overall, 2.146e-06s searches, 7.892e-05s shuffle, 7.105e-05s switch, 9.537e-07s quadrants. +3 iterations (8 th.) took 0.04399s; avg 0.01466s ( +/- 18.40/ 9.27 %); best 0.01197s; worst 0.01602s; std dev. 0.001908 (taking best). Reference operation time is 0.011966 s (0.04814 Mflops) with 8 threads. -After merge step 4: tpop: 0.01197 s ~Mflops: 0.048 nsubm:4 otn:8 -Applying merge (7 -> 4 leaves, 8 th.) yielded NEGLIGIBLE change (3th in a row) (old/new=1.00468x): 0.01202s -> 0.01197s, so IGNORING this instance. -Merge (4 -> 1 leaves) took w.c.t. of 1.287e-05s, ~3.815e-06s of computing time (of which 9.537e-07s sorting, 1.907e-06s analysis) -3 iterations (8 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 89.00/ 50.00 %); best 6.995e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). -Reference operation time is 6.9952e-08 s (8234 Mflops) with 8 threads. -After merge step 5: tpop: 6.995e-08 s ~Mflops: 8234.216 nsubm:1 otn:8 -Applying merge (4 -> 1 leaves, 8 th.) yielded SPEEDUP of 171860.941x: 0.01202s -> 6.995e-08s, so taking this instance. -Merged all the matrix leaves: no reason to continue merging. -A total of 5 merge steps (of max 6) (22 -> 1 subms) took 0.332s (of which 0.004782s partitioning, 0s I/O); computing times: 5.269e-05s in par. loops, 7.629e-06s sorting, 1.979e-05s analyzing) -Total merge + benchmarking process took 0.332s, equivalent to 4746210.0/21.3 new/old ops (0.1399s for 3 clones -- as 2000470.3/9.0 ops, or 666823.4/3.0 ops per clone), SPEEDUP of 222539.196x -Applying multi-merge (22 -> 1 leaves, 5 steps, 0 -> 8 th.sp.) yielded SPEEDUP of 222539.196x (0.01557s -> 6.995e-08s), will amortize in 21.3 ops by saving 0.01557s per op. -In 1 tuning rounds (tot. 0.43s, 0.14s for constructor, 3 clones) obtained a SPEEDUP of 22253819.6% (2.225e+05x) (from 0.037 to 8234 Mflops). -After 0.432080s, global autotuning declared speedup of 222539 x, when using threads count of 8 and a new matrix: -(6 x 6)[0x57570d50]{C} @ (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:'' +After split step 1: tpop: 0.01197 s ~Mflops: 0.048 nsubm:25 otn:8 +Applying split (22 -> 25 leaves, 8 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=1.00167x): 0.01199s -> 0.01197s, so IGNORING this instance. +Split (25 -> 28 leaves, 33 -> 37 subms) took 0.03556s (of which: 5.96e-06s analysis, -1.768e+09s mem.mgmt); compute time: 1.407e-05s overall, 1.907e-06s searches, 1.216e-05s shuffle, 5.96e-06s switch, 9.537e-07s quadrants. +3 iterations (8 th.) took 0.04438s; avg 0.01479s ( +/- 18.34/ 10.68 %); best 0.01208s; worst 0.01637s; std dev. 0.001927 (taking best). +Reference operation time is 0.0120802 s (0.04768 Mflops) with 8 threads. +After split step 2: tpop: 0.01208 s ~Mflops: 0.048 nsubm:28 otn:8 +Applying split (25 -> 28 leaves, 8 th.) yielded NEGLIGIBLE change (2th in a row) (old/new=0.99220x): 0.01199s -> 0.01208s, so IGNORING this instance. +Split (28 -> 28 leaves, 37 -> 37 subms) took 0.04165s (of which: 5.007e-06s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. +3 iterations (8 th.) took 0.06233s; avg 0.02078s ( +/- 42.03/ 34.78 %); best 0.01204s; worst 0.028s; std dev. 0.006602 (taking best). +Reference operation time is 0.012044 s (0.04782 Mflops) with 8 threads. +After split step 3: tpop: 0.01204 s ~Mflops: 0.048 nsubm:28 otn:8 +Applying split (28 -> 28 leaves, 8 th.) yielded NEGLIGIBLE change (3th in a row) (old/new=0.99519x): 0.01199s -> 0.01204s, so IGNORING this instance. +Split (28 -> 28 leaves, 37 -> 37 subms) took 0.04393s (of which: 5.007e-06s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. +3 iterations (8 th.) took 0.06797s; avg 0.02266s ( +/- 47.21/ 58.91 %); best 0.01196s; worst 0.03601s; std dev. 0.009993 (taking best). +Reference operation time is 0.011961 s (0.04816 Mflops) with 8 threads. +After split step 4: tpop: 0.01196 s ~Mflops: 0.048 nsubm:28 otn:8 +Applying split (28 -> 28 leaves, 8 th.) yielded NEGLIGIBLE change (4th in a row) (old/new=1.00209x): 0.01199s -> 0.01196s, so IGNORING this instance. +Split (28 -> 28 leaves, 37 -> 37 subms) took 0.03598s (of which: 5.007e-06s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. +3 iterations (8 th.) took 0.09597s; avg 0.03199s ( +/- 36.77/ 24.33 %); best 0.02023s; worst 0.03977s; std dev. 0.008461 (taking best). +Reference operation time is 0.020226 s (0.02848 Mflops) with 8 threads. +After split step 5: tpop: 0.02023 s ~Mflops: 0.028 nsubm:28 otn:8 +Applying split (28 -> 28 leaves, 8 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.687x: 0.01199s -> 0.02023s. +Skipping further split based tests after 1 definite performance degradations in a row (and last exceeding limit). +A total of 5 split steps (of max 6) (22 -> 28 subms) took 0.512s (of which 0.1972s partitioning, 0s I/O); computing times: 9.513e-05s in par. loops, 4.053e-06s sorting, 2.503e-05s analyzing) +Total split + benchmarking process took 0.512s, equivalent to 42.7/42.7 new/old ops (0.04396s for 1 clones -- as 3.7/3.7 ops, or 3.7/3.7 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) +In 1 tuning rounds (tot. 0.89s, 0.12s for constructor, 2 clones) obtained NO speedup (best stays 0.04806 Mflops). +After 0.888002s, global autotuning found old matrix optimal, with declared speedup 1 x when using 8 threads Considering Z clone. Building a matrix with 36 nnz, 6 x 6 Duplicates check: 36 - 0 = 36 - converted COO to RSB in 1.199e-01 s (100.00 %) - analyzed arrays in 3.994e-02 s (33.30 %) - cleaned-up arrays in 0.000e+00 s (0.00 %) - deduplicated arrays in 9.537e-07 s (0.00 %) + converted COO to RSB in 1.358e-01 s (100.00 %) + analyzed arrays in 4.774e-02 s (35.17 %) + cleaned-up arrays in 9.537e-07 s (0.00 %) + deduplicated arrays in 1.192e-06 s (0.00 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 3.999e-02 s (33.34 %) - memory allocations took 6.914e-06 s (0.01 %) - leafs setup took 3.815e-06 s (0.00 %) - halfword conversion took 3.999e-02 s (33.35 %) -Built (6 x 6)[0x57575310]{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: 22, symflags:'' + shuffled partitions in 3.202e-02 s (23.59 %) + memory allocations took 7.868e-06 s (0.01 %) + leafs setup took 4.053e-06 s (0.00 %) + halfword conversion took 5.598e-02 s (41.23 %) +Built (6 x 6)[0x5817ce00]{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)[0x57575310]{Z} @ (0(0..0),0(0..0)) (36 nnz, 6 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 22, symflags:'' +(6 x 6)[0x5817ce00]{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, 29 subms, 22 lsubms, 4.6667 bpnz. +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 (8 th.) took 0.05997s; avg 0.01999s ( +/- 40.21/ 20.62 %); best 0.01195s; worst 0.02411s; std dev. 0.005683 (taking best). -Reference operation time is 0.0119522 s (0.04819 Mflops) with 8 threads. -After 0.060006s, autotuning routine did not find a better threads count configuration. +3 iterations (8 th.) took 0.05595s; avg 0.01865s ( +/- 35.68/ 50.08 %); best 0.012s; worst 0.02799s; std dev. 0.0068 (taking best). +Reference operation time is 0.011997 s (0.04801 Mflops) with 8 threads. +After 0.055990s, autotuning routine did not find a better threads count configuration. -Will autotune matrix: 6 x 6, type Z, 36 nnz, 6 nnz/r, 29 subms, 22 lsubms, 4.6667 bpnz. +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 (8 th.) took 0.04799s; avg 0.016s ( +/- 25.03/ 49.83 %); best 0.01199s; worst 0.02397s; std dev. 0.005636 (taking best). -Reference operation time is 0.011992 s (0.04803 Mflops) with 8 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, 29 subms, 22 lsubms, 4.6667 bpnz (tpop: 0.01199 Mflops: 0.048) -Merge (22 -> 16 leaves) took w.c.t. of 6.604e-05s, ~1.597e-05s of computing time (of which 2.861e-06s sorting, 4.005e-05s analysis) -3 iterations (8 th.) took 0.0719s; avg 0.02397s ( +/- 16.57/ 16.45 %); best 0.02s; worst 0.02791s; std dev. 0.00323 (taking best). -Reference operation time is 0.0199952 s (0.02881 Mflops) with 8 threads. -After merge step 1: tpop: 0.02 s ~Mflops: 0.029 nsubm:16 otn:8 -Applying merge (22 -> 16 leaves, 8 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.667x: 0.01199s -> 0.02s. +3 iterations (8 th.) took 0.07201s; avg 0.024s ( +/- 49.91/ 66.66 %); best 0.01202s; worst 0.04s; std dev. 0.01177 (taking best). +Reference operation time is 0.012023 s (0.04791 Mflops) with 8 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: 0.01202 Mflops: 0.048) +Merge (28 -> 22 leaves) took w.c.t. of 0.007979s, ~1.788e-05s of computing time (of which 3.815e-06s sorting, 4.053e-06s analysis) +3 iterations (8 th.) took 0.09595s; avg 0.03198s ( +/- 49.98/ 49.94 %); best 0.016s; worst 0.04795s; std dev. 0.01305 (taking best). +Reference operation time is 0.015996 s (0.03601 Mflops) with 8 threads. +After merge step 1: tpop: 0.016 s ~Mflops: 0.036 nsubm:22 otn:8 +Applying merge (28 -> 22 leaves, 8 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.330x: 0.01202s -> 0.016s. Skipping further merge based tests after 1 definite performance degradations in a row (and last exceeding limit). -A total of 1 merge steps (of max 6) (22 -> 16 subms) took 0.07199s (of which 7.01e-05s partitioning, 0s I/O); computing times: 1.597e-05s in par. loops, 2.861e-06s sorting, 4.005e-05s analyzing) -Total merge + benchmarking process took 0.07199s, equivalent to 6.0/6.0 new/old ops (0.06396s for 1 clones -- as 5.3/5.3 ops, or 5.3/5.3 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) +A total of 1 merge steps (of max 6) (28 -> 22 subms) took 0.104s (of which 0.007992s partitioning, 0s I/O); computing times: 1.788e-05s in par. loops, 3.815e-06s sorting, 4.053e-06s analyzing) +Total merge + benchmarking process took 0.104s, equivalent to 8.6/8.6 new/old ops (0.05996s for 1 clones -- as 5.0/5.0 ops, or 5.0/5.0 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) Merging based autotuning FAILED (=NO SPEEDUP); let's try splitting then... -3 iterations (8 th.) took 0.04797s; avg 0.01599s ( +/- 24.92/ 49.84 %); best 0.01201s; worst 0.02396s; std dev. 0.005635 (taking best). -Reference operation time is 0.012006 s (0.04798 Mflops) with 8 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, 29 subms, 22 lsubms, 4.6667 bpnz (tpop: 0.01201 Mflops: 0.048) -Split (22 -> 28 leaves, 29 -> 37 subms) took 0.01598s (of which: 4.053e-06s analysis, -3.467e+09s mem.mgmt); compute time: 0.0001409s overall, 2.861e-06s searches, 0.000138s shuffle, 6.628e-05s switch, 6.127e-05s quadrants. -3 iterations (8 th.) took 0.05597s; avg 0.01866s ( +/- 14.30/ 28.49 %); best 0.01599s; worst 0.02397s; std dev. 0.003759 (taking best). -Reference operation time is 0.0159869 s (0.03603 Mflops) with 8 threads. -After split step 1: tpop: 0.01599 s ~Mflops: 0.036 nsubm:28 otn:8 -Applying split (22 -> 28 leaves, 8 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.332x: 0.01201s -> 0.01599s. +3 iterations (8 th.) took 0.06803s; avg 0.02268s ( +/- 29.45/ 41.09 %); best 0.016s; worst 0.032s; std dev. 0.006793 (taking best). +Reference operation time is 0.0159991 s (0.036 Mflops) with 8 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: 0.016 Mflops: 0.036) +Split (28 -> 28 leaves, 37 -> 37 subms) took 0.01997s (of which: 4.053e-06s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. +3 iterations (8 th.) took 0.03997s; avg 0.01332s ( +/- 39.91/ 49.79 %); best 0.008005s; worst 0.01995s; std dev. 0.004966 (taking best). +Reference operation time is 0.0080049 s (0.07196 Mflops) with 8 threads. +After split step 1: tpop: 0.008005 s ~Mflops: 0.072 nsubm:28 otn:8 +Applying split (28 -> 28 leaves, 8 th.) yielded SPEEDUP of 1.999x: 0.016s -> 0.008005s, so taking this instance. +Split (28 -> 28 leaves, 37 -> 37 subms) took 0.01378s (of which: 5.007e-06s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. +3 iterations (8 th.) took 0.07177s; avg 0.02392s ( +/- 16.41/ 16.08 %); best 0.02s; worst 0.02777s; std dev. 0.003173 (taking best). +Reference operation time is 0.019999 s (0.0288 Mflops) with 8 threads. +After split step 2: tpop: 0.02 s ~Mflops: 0.029 nsubm:28 otn:8 +Applying split (28 -> 28 leaves, 8 th.) yielded SLOWDOWN (1th of 3 tolerable) of 2.498x: 0.008005s -> 0.02s. 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 0.07199s (of which 0.016s partitioning, 0s I/O); computing times: 0.0001409s in par. loops, 2.861e-06s sorting, 4.053e-06s analyzing) -Total split + benchmarking process took 0.07199s, equivalent to 6.0/6.0 new/old ops (0.04798s for 1 clones -- as 4.0/4.0 ops, or 4.0/4.0 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) -In 1 tuning rounds (tot. 0.35s, 0.11s for constructor, 2 clones) obtained NO speedup (best stays 0.04798 Mflops). -After 0.351982s, global autotuning found old matrix optimal, with declared speedup 1 x when using 8 threads +A total of 2 split steps (of max 6) (28 -> 28 subms) took 0.192s (of which 0.03622s partitioning, 0s I/O); computing times: 0s in par. loops, 0s sorting, 9.06e-06s analyzing) +Total split + benchmarking process took 0.192s, equivalent to 24.0/12.0 new/old ops (0.1039s for 2 clones -- as 13.0/6.5 ops, or 6.5/3.2 ops per clone), SPEEDUP of 1.999x +Applying multi-split (28 -> 28 leaves, 1 steps, 0 -> 8 th.sp.) yielded SPEEDUP of 1.999x (0.016s -> 0.008005s), will amortize in 24.0 ops by saving 0.007994s per op. +In 1 tuning rounds (tot. 0.56s, 0.16s for constructor, 3 clones) obtained a SPEEDUP of 99.9% (1.999x) (from 0.036 to 0.07196 Mflops). +After 0.556064s, global autotuning declared speedup of 1.99866 x, when using threads count of 8 and a new matrix: +(6 x 6)[0x5817f850]{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' @@ -9252,10 +9203,10 @@ 4 0 DIFF PRINT TEST END Beginning large binary search test. -Detected 3883683840 bytes of memory, comprehensive of 197623808 of free memory. +Detected 3891118080 bytes of memory, comprehensive of 1804836864 of free memory. On this system, maximal array of coordinates can have 2147483137 elements and occupy 4294965252 bytes. -Will perform the test using less memory (141 MB) than on the maximal coordinate indices array (148217856) allows. -(c)allocated 37054464 nnz (148217856 bytes) +Will perform the test using less memory (266 MB) than on the maximal coordinate indices array (279885824) allows. +(c)allocated 69971456 nnz (279885824 bytes) Succeeded retrieving array last element. Successfully performed large binary search test. BASIC SPARSE BLAS TEST: BEGIN @@ -9264,7 +9215,7 @@ got RSB_IO_WANT_IS_INITIALIZED_MARKER: 1 INIT INTERFACE TEST: END (SUCCESS) DEVEL PRINT TEST: BEGIN -(4 x 4)[0x56c9b780]{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)[0x5760d780]{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 | @@ -9273,8 +9224,8 @@ RSB_FLAG_ASSEMBLED_IN_COO_ARRAYS | RSB_FLAG_OWN_PARTITIONING_ARRAYS | RSB_FLAG_SORT_INPUT -(2 x 2)[0x56c9b850]{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)[0x56c9b920]{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)[0x5760d850]{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)[0x5760d920]{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, 416 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%) @@ -9282,9 +9233,9 @@ ( 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)[0x56c9b850]{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)[0x56c9b920]{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)[0x56c9b780]{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)[0x5760d850]{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)[0x5760d920]{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)[0x5760d780]{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 | @@ -9302,8 +9253,8 @@ 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 30.036001 s, max allowed was 30.000000. - PASSED:15413 +Terminating testing earlier due to user timeout request: test took 30.067984 s, max allowed was 30.000000. + PASSED:640 FAILED:0 ADVANCED SPARSE BLAS TEST: END (SUCCESS) gmake qtests -C librsbpp @@ -9312,50 +9263,50 @@ 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 ++ ./rsbpp Td,s G.mtx ++ wc -l ++ grep Z-sort + test 54 = 54 ++ ./rsbpp Td G.mtx -++ wc -l ++ grep Z-sort +++ wc -l + test 27 = 27 +++ ./rsbpp Td,z G.mtx ++ grep Z-sort ++ wc -l -++ ./rsbpp Td,z G.mtx + test 54 = 54 ++ ./rsbpp vTd,z G.mtx ++ grep Z-sort ++ wc -l + test 54 = 54 ++ ./rsbpp vTd,z G.mtx -++ wc -l ++ grep Z-sort +++ wc -l + test 54 = 54 ++ ./rsbpp vvvTd,z G.mtx ++ grep Zorted ++ wc -l + test 8 = 8 -++ wc -l -++ grep Z-sort ++ ./rsbpp vvTd,z G.mtx +++ grep Z-sort +++ wc -l + test 54 = 54 ++ ./rsbpp vvTd,z G.mtx -++ wc -l ++ grep Range +++ wc -l + test 0 = 0 ++ ./rsbpp vvvTd,z G.mtx -++ wc -l ++ grep Range +++ wc -l + test 258 -gt 0 ++ ./rsbpp vvvTd,z S.mtx ++ grep Range ++ wc -l + test 0 -eq 0 ++ ./rsbpp vvvTd,z G.mtx -++ wc -l ++ grep Range +++ wc -l + test 258 = 258 ++ OMP_NUM_THREADS=1 ++ ./rsbpp m10M10I1r1,4,8sFv @@ -9364,47 +9315,47 @@ + test 9 = 9 ++ OMP_NUM_THREADS=1 ++ ./rsbpp C1000m100M100I1r1,4,8sFv -++ wc -l ++ grep spmm- +++ wc -l + test 9 = 9 -++ grep spmm- ++ OMP_NUM_THREADS=1 ++ ./rsbpp C1000m100M100I1r1sFvtN,T +++ grep spmm- ++ wc -l + test 3 = 3 ++ OMP_NUM_THREADS=1 ++ ./rsbpp C1000m100M100I1r1vtN,TsF -++ wc -l ++ grep spmm- +++ wc -l + test 2 = 2 +++ grep spmm- ++ OMP_NUM_THREADS=1 ++ ./rsbpp C1000m100M100I1r0vtN,TsF -++ grep spmm- ++ wc -l + test 0 = 0 -++ wc -l -++ grep Recursing ++ OMP_NUM_THREADS=1 ++ RSB_NUM_THREADS=1 ++ ./rsbpp vvvC1000m100M100I1r1vtN,TorsF -+ test 4 = 4 ++ grep Recursing +++ wc -l ++ test 4 = 4 ++ OMP_NUM_THREADS=2 ++ RSB_NUM_THREADS=2 ++ ./rsbpp vvvC1000m100M100I1r1vtN,TorsF +++ grep Recursing ++ wc -l + test 4 = 4 -++ grep Recursing ++ OMP_NUM_THREADS=1 ++ RSB_NUM_THREADS=1 ++ ./rsbpp vvvC1000m100M100I1r1vtN,ToRsF +++ grep Recursing ++ wc -l + test 208 = 208 -++ wc -l ++ OMP_NUM_THREADS=2 ++ RSB_NUM_THREADS=2 ++ ./rsbpp vvvC1000m100M100I1r1vtN,ToRsF ++ grep Recursing +++ wc -l + test 410 = 410 echo "Skipping tests based on Google Test (not detected at configure time)" Skipping tests based on Google Test (not detected at configure time) @@ -9451,7 +9402,7 @@ 0 0 0 0 before tuning for SPMV: -(3 x 3)[0x57f1f0e0]{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)[0x581c2ae0]{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 @@ -9540,18 +9491,18 @@ BEGIN Rsb_Matrix_test_multimatrix_ms_mnrhs BEGIN -(3 x 3)[0x57f4d110]{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 1.12121: -(3 x 3)[0x57f47450]{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)[0x57f4d110]{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 1.0678: -(3 x 3)[0x57f3dab0]{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)[0x57f4d110]{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 1.15152: -(3 x 3)[0x57f47450]{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)[0x57f4d110]{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 1.37931: -(3 x 3)[0x57f47450]{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)[0x581eed90]{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 1.52: +(3 x 3)[0x581c2670]{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)[0x581eed90]{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 1.14545: +(3 x 3)[0x581f9cf0]{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)[0x581eed90]{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 1.13793: +(3 x 3)[0x581c2670]{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)[0x581eed90]{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 1.16667: +(3 x 3)[0x581f9cf0]{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 ! @@ -9568,10 +9519,10 @@ ./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 infom07-i386 +running on i-capture-the-hostname Built without the MKL. ( ! ./rsbtest --unrecognized-option-triggers-abort ) -running on infom07-i386 +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 ) @@ -9580,7 +9531,7 @@ ( ! ./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 infom07-i386 +running on i-capture-the-hostname Will not invoke autotuning routine. Benchmark will sample for at most 0.01 s Built without render support! @@ -9632,7 +9583,7 @@ 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/i386-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/i386-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/i386-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/i386-linux-gnu/librsb.so.0.0.0 libtool: install: (cd /build/reproducible-path/librsb-1.3.0.2+dfsg/debian/tmp/usr/lib/i386-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/i386-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; }; }) @@ -9642,7 +9593,7 @@ libtool: install: ranlib /build/reproducible-path/librsb-1.3.0.2+dfsg/debian/tmp/usr/lib/i386-linux-gnu/librsb.a libtool: warning: remember to run 'libtool --finish /usr/lib/i386-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/i386-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' @@ -9769,12 +9720,12 @@ dh_gencontrol dh_md5sums dh_builddeb -dpkg-deb: building package 'librsb0t64-dbgsym' in '../librsb0t64-dbgsym_1.3.0.2+dfsg-7_i386.deb'. -dpkg-deb: building package 'librsb-tools' in '../librsb-tools_1.3.0.2+dfsg-7_i386.deb'. +dpkg-deb: building package 'librsb-dev' in '../librsb-dev_1.3.0.2+dfsg-7_i386.deb'. dpkg-deb: building package 'librsb-tools-dbgsym' in '../librsb-tools-dbgsym_1.3.0.2+dfsg-7_i386.deb'. dpkg-deb: building package 'librsb0t64' in '../librsb0t64_1.3.0.2+dfsg-7_i386.deb'. dpkg-deb: building package 'librsb-doc' in '../librsb-doc_1.3.0.2+dfsg-7_all.deb'. -dpkg-deb: building package 'librsb-dev' in '../librsb-dev_1.3.0.2+dfsg-7_i386.deb'. +dpkg-deb: building package 'librsb-tools' in '../librsb-tools_1.3.0.2+dfsg-7_i386.deb'. +dpkg-deb: building package 'librsb0t64-dbgsym' in '../librsb0t64-dbgsym_1.3.0.2+dfsg-7_i386.deb'. dpkg-genbuildinfo --build=binary -O../librsb_1.3.0.2+dfsg-7_i386.buildinfo dpkg-genchanges --build=binary -O../librsb_1.3.0.2+dfsg-7_i386.changes dpkg-genchanges: info: binary-only upload (no source code included) @@ -9783,12 +9734,14 @@ 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/13472/tmp/hooks/B01_cleanup starting +I: user script /srv/workspace/pbuilder/13472/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/6877 and its subdirectories -I: Current time: Tue Dec 3 19:49:29 -12 2024 -I: pbuilder-time-stamp: 1733298569 +I: removing directory /srv/workspace/pbuilder/13472 and its subdirectories +I: Current time: Wed Jan 7 04:29:57 +14 2026 +I: pbuilder-time-stamp: 1767709797