Diff of the two buildlogs: -- --- b1/build.log 2024-01-08 12:32:58.222482590 +0000 +++ b2/build.log 2024-01-08 12:52:13.732130403 +0000 @@ -1,7 +1,6 @@ -W: cgroups are not available on the host, not using them. I: pbuilder: network access will be disabled during build -I: Current time: Sun Feb 9 06:36:02 -12 2025 -I: pbuilder-time-stamp: 1739126162 +I: Current time: Tue Jan 9 02:33:01 +14 2024 +I: pbuilder-time-stamp: 1704717181 I: Building the build Environment I: extracting base tarball [/var/cache/pbuilder/bookworm-reproducible-base.tgz] I: copying local configuration @@ -29,48 +28,81 @@ dpkg-source: info: applying auto-gitignore I: Not using root during the build. I: Installing the build-deps -I: user script /srv/workspace/pbuilder/3156444/tmp/hooks/D02_print_environment starting +I: user script /srv/workspace/pbuilder/3272415/tmp/hooks/D01_modify_environment starting +debug: Running on codethink04-arm64. +I: Changing host+domainname to test build reproducibility +I: Adding a custom variable just for the fun of it... +I: Changing /bin/sh to bash +'/bin/sh' -> '/bin/bash' +lrwxrwxrwx 1 root root 9 Jan 8 12:33 /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/3272415/tmp/hooks/D01_modify_environment finished +I: user script /srv/workspace/pbuilder/3272415/tmp/hooks/D02_print_environment starting I: set - BUILDDIR='/build/reproducible-path' - BUILDUSERGECOS='first user,first room,first work-phone,first home-phone,first other' - BUILDUSERNAME='pbuilder1' - BUILD_ARCH='arm64' - DEBIAN_FRONTEND='noninteractive' + BASH=/bin/sh + BASHOPTS=checkwinsize:cmdhist:complete_fullquote:extquote:force_fignore:globasciiranges:globskipdots:hostcomplete:interactive_comments:patsub_replacement:progcomp:promptvars:sourcepath + BASH_ALIASES=() + BASH_ARGC=() + BASH_ARGV=() + BASH_CMDS=() + BASH_LINENO=([0]="12" [1]="0") + BASH_LOADABLES_PATH=/usr/local/lib/bash:/usr/lib/bash:/opt/local/lib/bash:/usr/pkg/lib/bash:/opt/pkg/lib/bash:. + BASH_SOURCE=([0]="/tmp/hooks/D02_print_environment" [1]="/tmp/hooks/D02_print_environment") + BASH_VERSINFO=([0]="5" [1]="2" [2]="15" [3]="1" [4]="release" [5]="aarch64-unknown-linux-gnu") + BASH_VERSION='5.2.15(1)-release' + BUILDDIR=/build/reproducible-path + BUILDUSERGECOS='second user,second room,second work-phone,second home-phone,second other' + BUILDUSERNAME=pbuilder2 + BUILD_ARCH=arm64 + DEBIAN_FRONTEND=noninteractive DEB_BUILD_OPTIONS='buildinfo=+all reproducible=+all parallel=12 ' - DISTRIBUTION='bookworm' - HOME='/root' - HOST_ARCH='arm64' + DIRSTACK=() + DISTRIBUTION=bookworm + EUID=0 + FUNCNAME=([0]="Echo" [1]="main") + GROUPS=() + HOME=/root + HOSTNAME=i-capture-the-hostname + HOSTTYPE=aarch64 + HOST_ARCH=arm64 IFS=' ' - LANG='C' - LANGUAGE='en_US:en' - LC_ALL='C' - MAIL='/var/mail/root' - OPTIND='1' - PATH='/usr/sbin:/usr/bin:/sbin:/bin:/usr/games' - PBCURRENTCOMMANDLINEOPERATION='build' - PBUILDER_OPERATION='build' - PBUILDER_PKGDATADIR='/usr/share/pbuilder' - PBUILDER_PKGLIBDIR='/usr/lib/pbuilder' - PBUILDER_SYSCONFDIR='/etc' - PPID='3156444' - PS1='# ' - PS2='> ' + INVOCATION_ID=a2de6d6fd986408fb624bee435252cbc + LANG=C + LANGUAGE=nl_BE:nl + LC_ALL=C + MACHTYPE=aarch64-unknown-linux-gnu + MAIL=/var/mail/root + OPTERR=1 + OPTIND=1 + OSTYPE=linux-gnu + PATH=/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/i/capture/the/path + PBCURRENTCOMMANDLINEOPERATION=build + PBUILDER_OPERATION=build + PBUILDER_PKGDATADIR=/usr/share/pbuilder + PBUILDER_PKGLIBDIR=/usr/lib/pbuilder + PBUILDER_SYSCONFDIR=/etc + PIPESTATUS=([0]="0") + POSIXLY_CORRECT=y + PPID=3272415 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.Pr3AxzGQ/pbuilderrc_N93h --distribution bookworm --hookdir /etc/pbuilder/first-build-hooks --debbuildopts -b --basetgz /var/cache/pbuilder/bookworm-reproducible-base.tgz --buildresult /srv/reproducible-results/rbuild-debian/r-b-build.Pr3AxzGQ/b1 --logfile b1/build.log librsb_1.3.0.2+dfsg-4.dsc' - SUDO_GID='109' - SUDO_UID='104' - SUDO_USER='jenkins' - TERM='unknown' - TZ='/usr/share/zoneinfo/Etc/GMT+12' - USER='root' - _='/usr/sbin/chroot' - http_proxy='http://192.168.101.104:3128' + PWD=/ + SHELL=/bin/bash + SHELLOPTS=braceexpand:errexit:hashall:interactive-comments:posix + SHLVL=3 + SUDO_COMMAND='/usr/bin/timeout -k 24.1h 24h /usr/bin/ionice -c 3 /usr/bin/nice -n 11 /usr/bin/unshare --uts -- /usr/sbin/pbuilder --build --configfile /srv/reproducible-results/rbuild-debian/r-b-build.Pr3AxzGQ/pbuilderrc_YgvG --distribution bookworm --hookdir /etc/pbuilder/rebuild-hooks --debbuildopts -b --basetgz /var/cache/pbuilder/bookworm-reproducible-base.tgz --buildresult /srv/reproducible-results/rbuild-debian/r-b-build.Pr3AxzGQ/b2 --logfile b2/build.log librsb_1.3.0.2+dfsg-4.dsc' + SUDO_GID=109 + SUDO_UID=104 + SUDO_USER=jenkins + TERM=unknown + TZ=/usr/share/zoneinfo/Etc/GMT-14 + UID=0 + USER=root + _='I: set' + http_proxy=http://192.168.101.104:3128 I: uname -a - Linux codethink03-arm64 6.1.0-17-cloud-arm64 #1 SMP Debian 6.1.69-1 (2023-12-30) aarch64 GNU/Linux + Linux i-capture-the-hostname 6.1.0-17-cloud-arm64 #1 SMP Debian 6.1.69-1 (2023-12-30) aarch64 GNU/Linux I: ls -l /bin total 7104 -rwxr-xr-x 1 root root 1346480 Apr 23 2023 bash @@ -128,15 +160,15 @@ -rwxr-xr-x 1 root root 68456 Sep 20 2022 readlink -rwxr-xr-x 1 root root 68592 Sep 20 2022 rm -rwxr-xr-x 1 root root 68480 Sep 20 2022 rmdir - -rwxr-xr-x 1 root root 68392 Jul 28 2023 run-parts + -rwxr-xr-x 1 root root 68392 Jul 28 23:46 run-parts -rwxr-xr-x 1 root root 134536 Jan 5 2023 sed - lrwxrwxrwx 1 root root 4 Jan 5 2023 sh -> dash + lrwxrwxrwx 1 root root 9 Jan 8 12:33 sh -> /bin/bash -rwxr-xr-x 1 root root 68432 Sep 20 2022 sleep -rwxr-xr-x 1 root root 134088 Sep 20 2022 stty -rwsr-xr-x 1 root root 133312 Mar 23 2023 su -rwxr-xr-x 1 root root 68448 Sep 20 2022 sync -rwxr-xr-x 1 root root 539896 Apr 6 2023 tar - -rwxr-xr-x 1 root root 67904 Jul 28 2023 tempfile + -rwxr-xr-x 1 root root 67904 Jul 28 23:46 tempfile -rwxr-xr-x 1 root root 134160 Sep 20 2022 touch -rwxr-xr-x 1 root root 68384 Sep 20 2022 true -rwxr-xr-x 1 root root 67664 Mar 23 2023 ulockmgr_server @@ -156,7 +188,7 @@ -rwxr-xr-x 1 root root 2206 Apr 10 2022 zless -rwxr-xr-x 1 root root 1842 Apr 10 2022 zmore -rwxr-xr-x 1 root root 4577 Apr 10 2022 znew -I: user script /srv/workspace/pbuilder/3156444/tmp/hooks/D02_print_environment finished +I: user script /srv/workspace/pbuilder/3272415/tmp/hooks/D02_print_environment finished -> Attempting to satisfy build-dependencies -> Creating pbuilder-satisfydepends-dummy package Package: pbuilder-satisfydepends-dummy @@ -356,7 +388,7 @@ Get: 152 http://deb.debian.org/debian bookworm/main arm64 libltdl-dev arm64 2.4.7-5 [165 kB] Get: 153 http://deb.debian.org/debian bookworm/main arm64 libhwloc-dev arm64 2.9.0-1 [734 kB] Get: 154 http://deb.debian.org/debian bookworm/main arm64 zlib1g-dev arm64 1:1.2.13.dfsg-1 [913 kB] -Fetched 330 MB in 2s (188 MB/s) +Fetched 330 MB in 1s (251 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 ... 18171 files and directories currently installed.) @@ -1010,7 +1042,11 @@ 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-4_source.changes +I: user script /srv/workspace/pbuilder/3272415/tmp/hooks/A99_set_merged_usr starting +Not re-configuring usrmerge for bookworm +I: user script /srv/workspace/pbuilder/3272415/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-4_source.changes dpkg-buildpackage: info: source package librsb dpkg-buildpackage: info: source version 1.3.0.2+dfsg-4 dpkg-buildpackage: info: source distribution unstable @@ -1031,62 +1067,62 @@ dh binary --no-parallel dh_update_autotools_config -O--no-parallel dh_autoreconf -O--no-parallel -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: git: not found -sh: 1: 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'. @@ -1128,90 +1164,90 @@ 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' @@ -1394,7 +1430,7 @@ checking for m4... m4 checking for gmake... gmake checking for ggrep... /bin/grep -checking for bash... /bin/bash +checking for bash... /bin/sh checking for gsed... /bin/sed checking for cmp... cmp checking for basename... basename @@ -1511,7 +1547,7 @@ 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 @@ -1533,7 +1569,7 @@ config.status: executing depfiles commands config.status: executing libtool commands === configuring in librsbpp (/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp) -configure: running /bin/bash ./configure --disable-option-checking '--prefix=/usr' '--build=aarch64-linux-gnu' '--includedir=${prefix}/include' '--mandir=${prefix}/share/man' '--infodir=${prefix}/share/info' '--sysconfdir=/etc' '--localstatedir=/var' '--disable-silent-rules' '--libdir=${prefix}/lib/aarch64-linux-gnu' '--runstatedir=/run' '--disable-maintainer-mode' '--disable-dependency-tracking' '--with-memhinfo=L2:4/64/512K,L1:8/64/24K' '--with-hwloc' '--enable-matrix-types=blas' '--with-zlib=-lz' '--enable-doc-build' '--enable-fortran-module-install' '--enable-extra-patches' '--enable-pkg-config-install' '--disable-extra-patches' 'build_alias=aarch64-linux-gnu' 'CFLAGS=-g -O2 -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' '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=aarch64-linux-gnu' '--includedir=${prefix}/include' '--mandir=${prefix}/share/man' '--infodir=${prefix}/share/info' '--sysconfdir=/etc' '--localstatedir=/var' '--disable-silent-rules' '--libdir=${prefix}/lib/aarch64-linux-gnu' '--runstatedir=/run' '--disable-maintainer-mode' '--disable-dependency-tracking' '--with-memhinfo=L2:4/64/512K,L1:8/64/24K' '--with-hwloc' '--enable-matrix-types=blas' '--with-zlib=-lz' '--enable-doc-build' '--enable-fortran-module-install' '--enable-extra-patches' '--enable-pkg-config-install' '--disable-extra-patches' 'build_alias=aarch64-linux-gnu' 'CFLAGS=-g -O2 -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' '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... /bin/mkdir -p @@ -1655,7 +1691,7 @@ 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 @@ -1664,7 +1700,7 @@ config.status: executing libtool commands configure: Successfully created a Makefile. === configuring in rsblib (/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib) -configure: running /bin/bash ./configure --disable-option-checking '--prefix=/usr' '--build=aarch64-linux-gnu' '--includedir=${prefix}/include' '--mandir=${prefix}/share/man' '--infodir=${prefix}/share/info' '--sysconfdir=/etc' '--localstatedir=/var' '--disable-silent-rules' '--libdir=${prefix}/lib/aarch64-linux-gnu' '--runstatedir=/run' '--disable-maintainer-mode' '--disable-dependency-tracking' '--with-memhinfo=L2:4/64/512K,L1:8/64/24K' '--with-hwloc' '--enable-matrix-types=blas' '--with-zlib=-lz' '--enable-doc-build' '--enable-fortran-module-install' '--enable-extra-patches' '--enable-pkg-config-install' '--disable-extra-patches' 'build_alias=aarch64-linux-gnu' 'CFLAGS=-g -O2 -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' '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=aarch64-linux-gnu' '--includedir=${prefix}/include' '--mandir=${prefix}/share/man' '--infodir=${prefix}/share/info' '--sysconfdir=/etc' '--localstatedir=/var' '--disable-silent-rules' '--libdir=${prefix}/lib/aarch64-linux-gnu' '--runstatedir=/run' '--disable-maintainer-mode' '--disable-dependency-tracking' '--with-memhinfo=L2:4/64/512K,L1:8/64/24K' '--with-hwloc' '--enable-matrix-types=blas' '--with-zlib=-lz' '--enable-doc-build' '--enable-fortran-module-install' '--enable-extra-patches' '--enable-pkg-config-install' '--disable-extra-patches' 'build_alias=aarch64-linux-gnu' 'CFLAGS=-g -O2 -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' '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... /bin/mkdir -p @@ -1773,7 +1809,7 @@ 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 @@ -1783,7 +1819,7 @@ config.status: executing libtool commands configure: Created a Makefile. === configuring in rsbtest (/build/reproducible-path/librsb-1.3.0.2+dfsg/rsbtest) -configure: running /bin/bash ./configure --disable-option-checking '--prefix=/usr' '--build=aarch64-linux-gnu' '--includedir=${prefix}/include' '--mandir=${prefix}/share/man' '--infodir=${prefix}/share/info' '--sysconfdir=/etc' '--localstatedir=/var' '--disable-silent-rules' '--libdir=${prefix}/lib/aarch64-linux-gnu' '--runstatedir=/run' '--disable-maintainer-mode' '--disable-dependency-tracking' '--with-memhinfo=L2:4/64/512K,L1:8/64/24K' '--with-hwloc' '--enable-matrix-types=blas' '--with-zlib=-lz' '--enable-doc-build' '--enable-fortran-module-install' '--enable-extra-patches' '--enable-pkg-config-install' '--disable-extra-patches' 'build_alias=aarch64-linux-gnu' 'CFLAGS=-g -O2 -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' '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=aarch64-linux-gnu' '--includedir=${prefix}/include' '--mandir=${prefix}/share/man' '--infodir=${prefix}/share/info' '--sysconfdir=/etc' '--localstatedir=/var' '--disable-silent-rules' '--libdir=${prefix}/lib/aarch64-linux-gnu' '--runstatedir=/run' '--disable-maintainer-mode' '--disable-dependency-tracking' '--with-memhinfo=L2:4/64/512K,L1:8/64/24K' '--with-hwloc' '--enable-matrix-types=blas' '--with-zlib=-lz' '--enable-doc-build' '--enable-fortran-module-install' '--enable-extra-patches' '--enable-pkg-config-install' '--disable-extra-patches' 'build_alias=aarch64-linux-gnu' 'CFLAGS=-g -O2 -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' '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... /bin/mkdir -p @@ -1894,7 +1930,7 @@ 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 @@ -1926,7 +1962,7 @@ ARFLAGS : cru M4 : m4 MAKE : gmake - BASH : /bin/bash + BASH : /bin/sh OCTAVE : false DOXYGEN : doxygen HELP2MAN : help2man @@ -1977,23 +2013,23 @@ Making all in librsbpp gmake[4]: Entering directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp' g++ -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -DRSBPP_HAS_RSB_H=1 -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -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/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 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 -/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_csr.lo rsbpp_csr.cpp 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_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/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 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 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 -/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/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 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 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 -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 -/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 +/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 rsbct rsbct.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' @@ -2058,255 +2094,255 @@ gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+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 -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 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 -g -O2 -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=link gcc -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 -g -O2 -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/aarch64-linux-gnu/12 -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/12/../../.. -lgfortran -lm +/bin/sh ./libtool --tag=CC --mode=link gcc -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 -g -O2 -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/aarch64-linux-gnu/12 -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/12/../../.. -lgfortran -lm libtool: warning: '-version-info' is ignored for programs libtool: link: gcc -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 -g -O2 -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/aarch64-linux-gnu/12 -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/12/../../.. -lgfortran -lm -fopenmp if test -f ./rsb_types.h -a ! -f ./rsb_types.h ; then cp -pv ./rsb_types.h ./rsb_types.h ; fi # out-of-dir behaviour varies between installations -if test -f ch2icfb ; then if SED=/bin/sed GREP=/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 -fopenmp -c -o rsb.lo rsb.F90 +if test -f ch2icfb ; then if SED=/bin/sed GREP=/bin/grep /bin/sh ./scripts/rsb_h_to_rsb_fi.sh . /build/reproducible-path/librsb-1.3.0.2+dfsg > rsb.F90 ; then true; else rm "rsb.F90"; echo "Failure generating rsb.F90!" ; exit ; fi ; else echo "Warning: Your system did not build ch2icfb for some reason --- skipping rebuild of "rsb.F90 ;true ; fi +/bin/sh ./libtool --tag=FC --mode=compile gfortran -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -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 -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 -fopenmp -c rsb.F90 -o 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 -fno-unroll-loops -fopenmp -g -O2 -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/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -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 -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 -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 -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 -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 -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 -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/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -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 -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 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -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 -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 -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 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -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 -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 -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 -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 -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 -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 -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/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -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/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -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 -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 -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 -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 -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 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -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 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -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 -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 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -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 -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 -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 -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 -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 -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 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -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 -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 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -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 -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 -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 -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 -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 -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 -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/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -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 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -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 -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 -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 -o librsb_nounroll_la-rsb_krnl_bcss_spsv_u.o >/dev/null 2>&1 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -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 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -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 -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 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -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 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -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 -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 -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 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -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/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -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 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -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 -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 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -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=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -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 -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 -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 -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 -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 -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 -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 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -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/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -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 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -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 -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 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -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/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -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 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -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 -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 -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 -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 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -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 -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 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -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/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fno-unroll-loops -fopenmp -g -O2 -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 -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 -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 -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 -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 -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 -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 -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 -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 -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 -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 -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=link gcc -g -O2 -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/aarch64-linux-gnu/12 -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/12/../../.. -lgfortran -lm +/bin/sh ./libtool --tag=CC --mode=link gcc -g -O2 -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/aarch64-linux-gnu/12 -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/12/../../.. -lgfortran -lm libtool: warning: '-version-info/-version-number' is ignored for convenience libraries libtool: link: ar cr .libs/librsb_nounroll.a .libs/librsb_nounroll_la-rsb_stropts.o .libs/librsb_nounroll_la-rsb_strmif.o .libs/librsb_nounroll_la-rsb_unroll.o .libs/librsb_nounroll_la-rsb_krnl_vb.o .libs/librsb_nounroll_la-rsb_krnl_lb.o .libs/librsb_nounroll_la-rsb_krnl.o .libs/librsb_nounroll_la-rsb_bench.o .libs/librsb_nounroll_la-rsb_mergesort.o .libs/librsb_nounroll_la-rsb_permute.o .libs/librsb_nounroll_la-rsb_krnl_bcss_l.o .libs/librsb_nounroll_la-rsb_krnl_bcss_u.o .libs/librsb_nounroll_la-rsb_krnl_bcss_spsv_u.o .libs/librsb_nounroll_la-rsb_krnl_bcss_spmv_u.o .libs/librsb_nounroll_la-rsb_krnl_bcss_misc_u.o .libs/librsb_nounroll_la-rsb_krnl_bcoo_spmv_u.o .libs/librsb_nounroll_la-rsb_krnl_bcss.o .libs/librsb_nounroll_la-rsb_spmv.o .libs/librsb_nounroll_la-rsb_merge.o .libs/librsb_nounroll_la-rsb_ompio.o .libs/librsb_nounroll_la-rsb_util.o .libs/librsb_nounroll_la-rsb_spgemm_csr.o .libs/librsb_nounroll_la-rsb_spsum_misc.o .libs/librsb_nounroll_la-rsb_prec.o libtool: link: ranlib .libs/librsb_nounroll.a libtool: link: ( cd ".libs" && rm -f "librsb_nounroll.la" && ln -s "../librsb_nounroll.la" "librsb_nounroll.la" ) -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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 -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 -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 -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 -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 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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 -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 -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 -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 -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 -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 -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 -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 -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 -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 -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 -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 -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 -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 -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 -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 -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 -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 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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 -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 -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 -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 -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 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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 -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 -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/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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 -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 -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 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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 -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 -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 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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 -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 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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 -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 -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 -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 -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 -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 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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 -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 -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 -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 -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 -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 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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 -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 -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 -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 -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 -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 -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 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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 -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 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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 -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 -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 -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 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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 -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 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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 -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 -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 -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 -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 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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 -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 -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 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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 -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 -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 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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 -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 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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 -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 -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 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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 -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 -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 -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 -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 -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 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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 -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 -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 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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 -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 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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 -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 -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 -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 -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 -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 -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 -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 -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 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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 -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 -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 -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 -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 -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 -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 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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 -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 -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 -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 -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 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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 -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 -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 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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 -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 -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 -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 -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 -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 -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 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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 -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/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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 -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 -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/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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 -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 -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 -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 -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 -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 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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 -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 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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 -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 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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 -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 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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 -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 -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 -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 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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 -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 -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/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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 -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 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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 -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 -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 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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 -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 libtool: compile: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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 -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 -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 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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 +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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 -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 -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 -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/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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 -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: gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -fopenmp -g -O2 -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=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 -fopenmp -c -o rsb_blas_sparse.lo rsb_blas_sparse.F90 +/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 -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 -fopenmp -c rsb_blas_sparse.F90 -fPIC -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 -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 -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/aarch64-linux-gnu/12 -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/12/../../.. -lgfortran -lm +/bin/sh ./libtool --tag=CC --mode=link gcc -g -O2 -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/aarch64-linux-gnu/12 -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/12/../../.. -lgfortran -lm libtool: warning: '-version-info/-version-number' is ignored for convenience libraries libtool: link: ar cr .libs/librsb_base.a .libs/librsb_base_la-rsb_is.o .libs/librsb_base_la-rsb_mio.o .libs/librsb_base_la-rsb_op.o .libs/librsb_base_la-rsb_bio.o .libs/librsb_base_la-rsb_get.o .libs/librsb_base_la-rsb_set.o .libs/librsb_base_la-rsb_coo.o .libs/librsb_base_la-rsb_csr.o .libs/librsb_base_la-rsb_coo_check.o .libs/librsb_base_la-rsb_coo_symm.o .libs/librsb_base_la-rsb_idx.o .libs/librsb_base_la-rsb_srt.o .libs/librsb_base_la-rsb_srtp.o .libs/librsb_base_la-rsb_src.o .libs/librsb_base_la-rsb_test_accuracy.o .libs/librsb_base_la-rsb_clone.o .libs/librsb_base_la-rsb_rec.o .libs/librsb_base_la-rsb_render.o .libs/librsb_base_la-rsb_eps.o .libs/librsb_base_la-rsb_msort_up.o .libs/librsb_base_la-rsb_sys.o .libs/librsb_base_la-rsb_blas_stuff.o .libs/librsb_base_la-rsb_gen.o .libs/librsb_base_la-rsb_perf.o .libs/librsb_base_la-rsb_rsb.o .libs/librsb_base_la-rsb_err.o .libs/librsb_base_la-rsb_tune.o .libs/librsb_base_la-rsb_do.o .libs/librsb_base_la-rsb_internals.o .libs/librsb_base_la-rsb_garbage.o .libs/librsb_base_la-rsb_mmio.o .libs/librsb_base_la-rsb_partition.o .libs/librsb_base_la-rsb_mbw.o .libs/librsb_base_la-rsb_limiter.o .libs/librsb_base_la-rsb_fpb.o .libs/librsb_base_la-rsb_spgemm.o .libs/librsb_base_la-rsb_spsum.o .libs/librsb_base_la-rsb_spsv.o .libs/librsb_base_la-rsb_lock.o .libs/librsb_base_la-rsb_swt.o .libs/librsb_base_la-rsb_init.o .libs/librsb_base_la-rsb_dump.o .libs/librsb_base_la-rsb_cpmv.o .libs/librsb_base_la-rsb_asm.o .libs/librsb_base_la-rsb_user.o .libs/librsb_base_la-rsb_coo2rec.o .libs/librsb_base_la-rsb_rec2coo.o .libs/librsb_base_la-rsb_rec2csr.o .libs/librsb_base_la-rsb_csr2coo.o .libs/rsb_blas_sparse.o libtool: link: ranlib .libs/librsb_base.a libtool: link: ( cd ".libs" && rm -f "librsb_base.la" && ln -s "../librsb_base.la" "librsb_base.la" ) -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+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 -O3 -std=c99 -c -o rsb_libspblas_handle.lo rsb_libspblas_handle.c +/bin/sh ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+dfsg -I/build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp -I/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib -g -O2 -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 -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 -g -O2 -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 -/bin/bash ./libtool --tag=CC --mode=compile gcc -DHAVE_CONFIG_H -I. -Wdate-time -D_FORTIFY_SOURCE=2 -I/build/reproducible-path/librsb-1.3.0.2+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 -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 -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 -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 -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/bash ./libtool --tag=CC --mode=link gcc -g -O2 -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/aarch64-linux-gnu/12 -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/12/../../.. -lgfortran -lm +/bin/sh ./libtool --tag=CC --mode=link gcc -g -O2 -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/aarch64-linux-gnu/12 -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/12/../../.. -lgfortran -lm libtool: warning: '-version-info/-version-number' is ignored for convenience libraries libtool: link: ar cr .libs/librsb_spblas.a .libs/rsb_libspblas_handle.o .libs/rsb_libspblas.o libtool: link: ranlib .libs/librsb_spblas.a libtool: link: ( cd ".libs" && rm -f "librsb_spblas.la" && ln -s "../librsb_spblas.la" "librsb_spblas.la" ) -/bin/bash ./libtool --tag=CC --mode=link gcc -g -O2 -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/aarch64-linux-gnu rsb.lo librsb_nounroll.la librsb_base.la librsb_spblas.la /build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp/librsbpp.la -lstdc++ -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/aarch64-linux-gnu/12 -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/12/../../.. -lgfortran -lm +/bin/sh ./libtool --tag=CC --mode=link gcc -g -O2 -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/aarch64-linux-gnu rsb.lo librsb_nounroll.la librsb_base.la librsb_spblas.la /build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp/librsbpp.la -lstdc++ -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/aarch64-linux-gnu/12 -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/12/../../.. -lgfortran -lm libtool: link: gcc -shared -fPIC -DPIC .libs/rsb.o -Wl,--whole-archive ./.libs/librsb_nounroll.a ./.libs/librsb_base.a ./.libs/librsb_spblas.a /build/reproducible-path/librsb-1.3.0.2+dfsg/librsbpp/.libs/librsbpp.a -Wl,--no-whole-archive -L/usr/lib/gcc/aarch64-linux-gnu/12 -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/12/../../.. -lpthread -lstdc++fs -lstdc++ -lhwloc -lz -lgfortran -lm -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") @@ -2318,44 +2354,44 @@ 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/aarch64-linux-gnu/12 -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/12/../../.. -lgfortran -lm +/bin/sh ./libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -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/aarch64-linux-gnu/12 -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/12/../../.. -lgfortran -lm libtool: warning: '-version-info' is ignored for programs libtool: link: g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -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/aarch64-linux-gnu/12 -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/12/../../.. -lgfortran -lm -fopenmp gmake[4]: Leaving directory '/build/reproducible-path/librsb-1.3.0.2+dfsg' Making all in examples gmake[4]: Entering directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/examples' gcc -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 -Wformat -Werror=format-security -O3 -std=c99 -c -o hello.o hello.c -/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/aarch64-linux-gnu/12 -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/12/../../.. -lgfortran -lm +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -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/aarch64-linux-gnu/12 -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/12/../../.. -lgfortran -lm 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/aarch64-linux-gnu/12 -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/12/../../.. -lgfortran -lm -fopenmp gcc -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 -Wformat -Werror=format-security -O3 -std=c99 -c -o snippets.o snippets.c -/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/aarch64-linux-gnu/12 -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/12/../../.. -lgfortran -lm +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -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/aarch64-linux-gnu/12 -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/12/../../.. -lgfortran -lm 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/aarch64-linux-gnu/12 -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/12/../../.. -lgfortran -lm -fopenmp gcc -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 -Wformat -Werror=format-security -O3 -std=c99 -c -o transpose.o transpose.c -/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/aarch64-linux-gnu/12 -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/12/../../.. -lgfortran -lm +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -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/aarch64-linux-gnu/12 -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/12/../../.. -lgfortran -lm 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/aarch64-linux-gnu/12 -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/12/../../.. -lgfortran -lm -fopenmp gcc -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 -Wformat -Werror=format-security -O3 -std=c99 -c -o power.o power.c -/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/aarch64-linux-gnu/12 -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/12/../../.. -lgfortran -lm +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -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/aarch64-linux-gnu/12 -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/12/../../.. -lgfortran -lm 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/aarch64-linux-gnu/12 -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/12/../../.. -lgfortran -lm -fopenmp gcc -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 -Wformat -Werror=format-security -O3 -std=c99 -c -o autotune.o autotune.c -/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/aarch64-linux-gnu/12 -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/12/../../.. -lgfortran -lm +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -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/aarch64-linux-gnu/12 -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/12/../../.. -lgfortran -lm 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/aarch64-linux-gnu/12 -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/12/../../.. -lgfortran -lm -fopenmp gcc -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 -Wformat -Werror=format-security -O3 -std=c99 -c -o backsolve.o backsolve.c -/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/aarch64-linux-gnu/12 -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/12/../../.. -lgfortran -lm +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -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/aarch64-linux-gnu/12 -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/12/../../.. -lgfortran -lm 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/aarch64-linux-gnu/12 -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/12/../../.. -lgfortran -lm -fopenmp gcc -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 -Wformat -Werror=format-security -O3 -std=c99 -c -o hello-spblas.o hello-spblas.c -/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/aarch64-linux-gnu/12 -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/12/../../.. -lgfortran -lm +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -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/aarch64-linux-gnu/12 -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/12/../../.. -lgfortran -lm 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/aarch64-linux-gnu/12 -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/12/../../.. -lgfortran -lm -fopenmp gcc -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 -Wformat -Werror=format-security -O3 -std=c99 -c -o io-spblas.o io-spblas.c -/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/aarch64-linux-gnu/12 -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/12/../../.. -lgfortran -lm +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -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/aarch64-linux-gnu/12 -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/12/../../.. -lgfortran -lm 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/aarch64-linux-gnu/12 -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/12/../../.. -lgfortran -lm -fopenmp 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 -fopenmp -c -o fortran.o fortran.F90 -/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/aarch64-linux-gnu/12 -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/12/../../.. -lgfortran -lm +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -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/aarch64-linux-gnu/12 -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/12/../../.. -lgfortran -lm 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/aarch64-linux-gnu/12 -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/12/../../.. -lgfortran -lm -fopenmp 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 -fopenmp -c -o fortran_rsb_fi.o fortran_rsb_fi.F90 -/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/aarch64-linux-gnu/12 -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/12/../../.. -lgfortran -lm +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -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/aarch64-linux-gnu/12 -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/12/../../.. -lgfortran -lm 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/aarch64-linux-gnu/12 -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/12/../../.. -lgfortran -lm -fopenmp 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 cplusplus cplusplus.o -L.. /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la -lhwloc -lm -lhwloc -lz -fopenmp -L/usr/lib/gcc/aarch64-linux-gnu/12 -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/12/../../.. -lgfortran -lm +/bin/sh ../libtool --tag=CXX --mode=link g++ -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -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/aarch64-linux-gnu/12 -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/12/../../.. -lgfortran -lm 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/aarch64-linux-gnu/12 -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../aarch64-linux-gnu -L/usr/lib/gcc/aarch64-linux-gnu/12/../../../../lib -L/lib/aarch64-linux-gnu -L/lib/../lib -L/usr/lib/aarch64-linux-gnu -L/usr/lib/../lib -L/usr/lib/gcc/aarch64-linux-gnu/12/../../.. -lgfortran -lm -fopenmp gmake[4]: Leaving directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/examples' Making all in scripts @@ -2373,10 +2409,10 @@ Making all in doc gmake[4]: Entering directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/doc' /bin/mkdir -p man -SOURCE_DATE_EPOCH=1735693261 \ +SOURCE_DATE_EPOCH=1704070861 \ help2man --name="benchmark and test for librsb" --no-info ../rsbench | /bin/sed 's/January //g' > man/rsbench.1 /bin/mkdir -p man -SOURCE_DATE_EPOCH=1735693261 \ +SOURCE_DATE_EPOCH=1704070861 \ help2man --name="provide configuration information for librsb" --no-info /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb-config | /bin/sed 's/January //g' > man/librsb-config.1 gmake makedox gmake[5]: Entering directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/doc' @@ -3017,49 +3053,49 @@ Making all in . gmake[6]: Entering directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib' 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 rsb.o rsb.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 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 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 -/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/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 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 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 -/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/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 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 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++ -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++ -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++ -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 gmake[6]: Leaving directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib' Making all in examples gmake[6]: Entering directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib/examples' 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 assemble.o assemble.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/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 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 autotune.o autotune.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 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 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 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 bench.o bench.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 bench bench.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la +/bin/sh ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -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/bench bench.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp 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 build.o build.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 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 build build.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la libtool: link: g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -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 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 misc.o misc.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 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 misc misc.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la libtool: link: g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -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 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 twonnz.o twonnz.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 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 twonnz twonnz.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la libtool: link: g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -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 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 example.o example.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 example example.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/librsb.la +/bin/sh ../libtool --tag=CXX --mode=link g++ -I.. -fopenmp -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -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/example example.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp 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 -/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/mtx2bin mtx2bin.o -lstdc++fs -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp 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 -/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 +/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 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 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 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 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/span span.o -lpthread /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/librsb.so -fopenmp gmake[6]: Leaving directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib/examples' gmake[5]: Leaving directory '/build/reproducible-path/librsb-1.3.0.2+dfsg/rsblib' @@ -3069,7 +3105,7 @@ 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' @@ -3145,7 +3181,7 @@ 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 @@ -3155,15 +3191,15 @@ 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 1739127198 +# beginning run at 1704718224 # /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 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 -# average timer granularity: 3e-08 s -# Will write a final performance record to file rsbench_pr__1739127198_gcc-12.2-1,4th.rpr and periodic checkpoints to rsbench_pr__1739127198_gcc-12.2-1,4th.rpr.tmp +# average timer granularity: 7.64e-08 s +# Will write a final performance record to file rsbench_pr__1704718224_gcc-12.2-1,4th.rpr and periodic checkpoints to rsbench_pr__1704718224_gcc-12.2-1,4th.rpr.tmp # will NOT perform ancillary tests. # will flush cache memory: between each operation measurement series, and NOT between each operation. # will keep any zero encountered in the matrix. -# env: export PATH=/usr/sbin:/usr/bin:/sbin:/bin:/usr/games +# env: export PATH=/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/i/capture/the/path # env: export LD_LIBRARY_PATH=/build/reproducible-path/librsb-1.3.0.2+dfsg/.libs # env: HOSTNAME is not set # env: KMP_AFFINITY is not set @@ -3202,61 +3238,61 @@ # 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: codethink03-arm64 +# detected hostname: i-capture-the-hostname # user specified a verbosity level of 1 (each --verbose occurrence counts +1) # This test will measure times in scanning arrays sized and aligned to fit in caches. # 2 cache levels detected Will fill struct with 40 samples... -# Memory benchmark took 5.229s +# Memory benchmark took 5.256s # auto-tuning oriented output implies times==0 iterations and sort-after-load. #pr: allocated a performance record for 8 samples (2240 bytes). # Cache block size total 524288 bytes, per-thread 43690 bytes -# so far, program took 5.231s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.000s/0.000s . +# so far, program took 5.260s 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, 81180 nnz/s ) (2.49 MB/s ) -#pre-sorting (6 elements) took 0.0197349 s -#weeding duplicates (to 6 elements) took 1.90735e-06 s (and check, 1.19209e-06 s ) +# file input of A.mtx took 0.00 s (6 nnz, 84449 nnz/s ) (2.59 MB/s ) +#pre-sorting (6 elements) took 0.012449 s +#weeding duplicates (to 6 elements) took 9.53674e-07 s (and check, 1.90735e-06 s ) # multi-nrhs benchmarking (1,2) -- now using nrhs 1. # Using alpha=1 beta=1 order=rows for rsb_spmv/rsb_spsv/rsb_spmm/rsb_spsm. # multi-transpose benchmarking -- now using transA = N. # will use input matrix flags: RSB_FLAG_USE_HALFWORD_INDICES, RSB_FLAG_SORTED_INPUT, RSB_FLAG_QUAD_PARTITIONING, RSB_FLAG_SYMMETRIC, RSB_FLAG_OWN_PARTITIONING_ARRAYS # Using 1 threads -# Constructed matrix (took 0.045s): (3 x 3)[0xaaab0e90cf10]{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 0.007s): (3 x 3)[0xaaaade0afd70]{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 0.0221s; avg 0.007367s ( +/- 14.43/ 25.00 %); best 0.006304s; worst 0.009209s; std dev. 0.001307 (taking best). -Reference operation time is 0.00630403 s (0.01523 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: 0.006304 Mflops: 0.015) -Merge (3 -> 1 leaves) took w.c.t. of 1.884e-05s, ~7.868e-06s of computing time (of which 9.537e-07s sorting, 5.007e-06s analysis) -3 iterations (1 th.) took 0.0002739s; avg 9.131e-05s ( +/- 99.97/200.00 %); best 3.035e-08s; worst 0.0002739s; std dev. 0.0001291 (taking best). -Reference operation time is 3.03507e-08 s (3163 Mflops) with 1 threads. -After merge step 1: tpop: 3.035e-08 s ~Mflops: 3163.026 nsubm:1 otn:1 -Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 207706.206x: 0.006304s -> 3.035e-08s, so taking this instance. +3 iterations (1 th.) took 0.003686s; avg 0.001229s ( +/- 0.96/ 0.60 %); best 0.001217s; worst 0.001236s; std dev. 8.399e-06 (taking best). +Reference operation time is 0.00121689 s (0.07889 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: 0.001217 Mflops: 0.079) +Merge (3 -> 1 leaves) took w.c.t. of 2.313e-05s, ~9.06e-06s of computing time (of which 1.192e-06s sorting, 3.099e-06s analysis) +3 iterations (1 th.) took 0.0002909s; avg 9.696e-05s ( +/- 99.02/198.03 %); best 9.537e-07s; worst 0.000289s; std dev. 0.0001358 (taking best). +Reference operation time is 9.53674e-07 s (100.7 Mflops) with 1 threads. +After merge step 1: tpop: 9.537e-07 s ~Mflops: 100.663 nsubm:1 otn:1 +Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 1276.000x: 0.001217s -> 9.537e-07s, so taking this instance. Merged all the matrix leaves: no reason to continue merging. -A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.01184s (of which 2.217e-05s partitioning, 0s I/O); computing times: 7.868e-06s in par. loops, 9.537e-07s sorting, 5.007e-06s analyzing) -Total merge + benchmarking process took 0.01184s, equivalent to 390212.1/1.9 new/old ops (0.03119s for 2 clones -- as 1027619.8/4.9 ops, or 513809.9/2.5 ops per clone), SPEEDUP of 207706.206x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 207706.206x (0.006304s -> 3.035e-08s), will amortize in 1.9 ops by saving 0.006304s per op. -In 1 tuning rounds (tot. 0.054s, 0.031s for constructor, 2 clones) obtained a SPEEDUP of 20770520.6% (2.077e+05x) (from 0.01523 to 3163 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.004263s (of which 2.789e-05s partitioning, 0s I/O); computing times: 9.06e-06s in par. loops, 1.192e-06s sorting, 3.099e-06s analyzing) +Total merge + benchmarking process took 0.004263s, equivalent to 4470.0/3.5 new/old ops (0.007438s for 2 clones -- as 7799.2/6.1 ops, or 3899.6/3.1 ops per clone), SPEEDUP of 1276.000x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 1276.000x (0.001217s -> 9.537e-07s), will amortize in 3.5 ops by saving 0.001216s per op. +In 1 tuning rounds (tot. 0.012s, 0.0074s for constructor, 2 clones) obtained a SPEEDUP of 127500.0% (1276x) (from 0.07889 to 100.7 Mflops). #pr: updating sample at index 1 (0^th of 8), 0^th touch for (0,0,0,0,0,0,0). -First run of RSB Autotuner took 0.0537579 s (6.304e-03 s -> 3.035e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.0116649 s (1.217e-03 s -> 9.537e-07 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). RSB Sparse Blocks Autotuner invoked requesting max 0 splits and max 0 merges in 1 rounds, auto threads spec. -Second run of RSB Autotuner took 0.262369 s and estimated a speedup of 1.000000 x (3.035e-08 s -> 3.035e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.0582101 s and estimated a speedup of 1.000000 x (8.070e-08 s -> 8.070e-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 0.015803 0.012216 0.028019 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 1 3 3 6 0.028019 -%:RSB_SUBDIVISION_TIME:A.mtx S N 1 3 3 6 0.015803 -%:RSB_SHUFFLE_TIME:A.mtx S N 1 3 3 6 0.012216 +%:CONSTRUCTOR_TIMES:A.mtx S N 1 3 3 6 0.000000 0.001742 0.002460 0.004202 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 1 3 3 6 0.004202 +%:RSB_SUBDIVISION_TIME:A.mtx S N 1 3 3 6 0.001742 +%:RSB_SHUFFLE_TIME:A.mtx S N 1 3 3 6 0.002460 %: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 0.028019 +%:SORTEDCOO2RSB_TIME:A.mtx S N 1 3 3 6 0.004202 %: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 @@ -3271,47 +3307,47 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 1 3 3 6 6 6 6 # # Using 4 threads -# Constructed matrix (took 0.039s): (3 x 3)[0xaaab0e911c60]{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 0.006s): (3 x 3)[0xaaaade0b4400]{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 0.02753s; avg 0.009176s ( +/- 14.98/ 26.16 %); best 0.007801s; worst 0.01158s; std dev. 0.001703 (taking best). -Reference operation time is 0.00780082 s (0.01231 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: 0.007801 Mflops: 0.012) -Merge (3 -> 1 leaves) took w.c.t. of 1.383e-05s, ~5.007e-06s of computing time (of which 0s sorting, 3.815e-06s analysis) -3 iterations (4 th.) took 4.053e-06s; avg 1.351e-06s ( +/- 97.75/200.00 %); best 3.035e-08s; worst 4.053e-06s; std dev. 1.911e-06 (taking best). -Reference operation time is 3.03507e-08 s (3163 Mflops) with 4 threads. -After merge step 1: tpop: 3.035e-08 s ~Mflops: 3163.026 nsubm:1 otn:1 -Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 257022.781x: 0.007801s -> 3.035e-08s, so taking this instance. +3 iterations (4 th.) took 0.006251s; avg 0.002084s ( +/- 54.45/108.76 %); best 0.0009491s; worst 0.00435s; std dev. 0.001602 (taking best). +Reference operation time is 0.000949144 s (0.1011 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: 0.0009491 Mflops: 0.101) +Merge (3 -> 1 leaves) took w.c.t. of 1.407e-05s, ~5.007e-06s of computing time (of which 9.537e-07s sorting, 3.099e-06s analysis) +3 iterations (4 th.) took 4.053e-06s; avg 1.351e-06s ( +/- 94.03/129.41 %); best 8.07e-08s; worst 3.099e-06s; std dev. 1.296e-06 (taking best). +Reference operation time is 8.07047e-08 s (1190 Mflops) with 4 threads. +After merge step 1: tpop: 8.07e-08 s ~Mflops: 1189.522 nsubm:1 otn:1 +Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 11760.709x: 0.0009491s -> 8.07e-08s, so taking this instance. Merged all the matrix leaves: no reason to continue merging. -A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.02399s (of which 1.693e-05s partitioning, 0s I/O); computing times: 5.007e-06s in par. loops, 0s sorting, 3.815e-06s analyzing) -Total merge + benchmarking process took 0.02399s, equivalent to 790322.1/3.1 new/old ops (0.04438s for 2 clones -- as 1462340.9/5.7 ops, or 731170.5/2.8 ops per clone), SPEEDUP of 257022.781x -Applying multi-merge (3 -> 1 leaves, 1 steps, 1 -> 1 th.sp.) yielded SPEEDUP of 257022.781x (0.007801s -> 3.035e-08s), will amortize in 3.1 ops by saving 0.007801s per op. -In 1 tuning rounds (tot. 0.072s, 0.044s for constructor, 2 clones) obtained a SPEEDUP of 25702178.1% (2.57e+05x) (from 0.01231 to 3163 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.003493s (of which 1.907e-05s partitioning, 0s I/O); computing times: 5.007e-06s in par. loops, 9.537e-07s sorting, 3.099e-06s analyzing) +Total merge + benchmarking process took 0.003493s, equivalent to 43282.1/3.7 new/old ops (0.006333s for 2 clones -- as 78469.7/6.7 ops, or 39234.9/3.3 ops per clone), SPEEDUP of 11760.709x +Applying multi-merge (3 -> 1 leaves, 1 steps, 1 -> 1 th.sp.) yielded SPEEDUP of 11760.709x (0.0009491s -> 8.07e-08s), will amortize in 3.7 ops by saving 0.0009491s per op. +In 1 tuning rounds (tot. 0.013s, 0.0063s for constructor, 2 clones) obtained a SPEEDUP of 1175970.9% (1.176e+04x) (from 0.1011 to 1190 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 0.0720041 s (7.801e-03 s -> 3.035e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.0126948 s (9.491e-04 s -> 8.070e-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 0.404207 s and estimated a speedup of 1.000000 x (3.035e-08 s -> 3.035e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.0526719 s and estimated a speedup of 1.000000 x (8.070e-08 s -> 8.070e-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 0.004399 0.018763 0.023162 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 4 3 3 6 0.023162 -%:RSB_SUBDIVISION_TIME:A.mtx S N 4 3 3 6 0.004399 -%:RSB_SHUFFLE_TIME:A.mtx S N 4 3 3 6 0.018763 +%:CONSTRUCTOR_TIMES:A.mtx S N 4 3 3 6 0.000000 0.001618 0.002302 0.003920 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 4 3 3 6 0.003920 +%:RSB_SUBDIVISION_TIME:A.mtx S N 4 3 3 6 0.001618 +%:RSB_SHUFFLE_TIME:A.mtx S N 4 3 3 6 0.002302 %: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 0.023162 +%:SORTEDCOO2RSB_TIME:A.mtx S N 4 3 3 6 0.003920 %:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 4 3 3 6 0.000 -%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 4 3 3 6 1.21 -%:SORTEDCOO2RSB_SCALING:A.mtx S N 4 3 3 6 1.21 -%:RSB_SUBDIVISION_SCALING:A.mtx S N 4 3 3 6 3.59 -%:RSB_SHUFFLE_SCALING:A.mtx S N 4 3 3 6 0.65 -%:CONSTRUCTOR_SCALING:A.mtx S N 4 3 3 6 nan 3.59 0.65 1.21 +%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 4 3 3 6 1.07 +%:SORTEDCOO2RSB_SCALING:A.mtx S N 4 3 3 6 1.07 +%:RSB_SUBDIVISION_SCALING:A.mtx S N 4 3 3 6 1.08 +%:RSB_SHUFFLE_SCALING:A.mtx S N 4 3 3 6 1.07 +%:CONSTRUCTOR_SCALING:A.mtx S N 4 3 3 6 nan 1.08 1.07 1.07 #%: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 @@ -3320,50 +3356,50 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 4 3 3 6 6 6 6 # %operation:matrix CONSTRUCTOR[1] SPMV[1] SPMV[4] -%operation:A.mtx 0.0446332 1e+09 1e+09 +%operation:A.mtx 0.00672817 1e+09 1e+09 %constructor:matrix SORT[1] SCAN[1] SHUFFLE[1] INSERT[1] -%constructor:A.mtx 0 0.0158029 0 0.0122159 +%constructor:A.mtx 0 0.00174189 0 0.00246 # symmetric matrix --- skipping transposed benchmarking # multi-nrhs benchmarking (1,2) -- now using nrhs 2. # Using alpha=1 beta=1 order=rows for rsb_spmv/rsb_spsv/rsb_spmm/rsb_spsm. # multi-transpose benchmarking -- now using transA = N. # will use input matrix flags: RSB_FLAG_USE_HALFWORD_INDICES, RSB_FLAG_SORTED_INPUT, RSB_FLAG_QUAD_PARTITIONING, RSB_FLAG_SYMMETRIC, RSB_FLAG_OWN_PARTITIONING_ARRAYS # Using 1 threads -# Constructed matrix (took 0.044s): (3 x 3)[0xaaab0e9163f0]{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 0.003s): (3 x 3)[0xaaaade0b4400]{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 0.02382s; avg 0.007941s ( +/- 4.66/ 3.81 %); best 0.007571s; worst 0.008243s; std dev. 0.0002785 (taking best). -Reference operation time is 0.00757098 s (0.02536 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: 0.007571 Mflops: 0.025) -Merge (3 -> 1 leaves) took w.c.t. of 1.407e-05s, ~5.007e-06s of computing time (of which 9.537e-07s sorting, 2.861e-06s analysis) -3 iterations (1 th.) took 6.199e-06s; avg 2.066e-06s ( +/- 98.53/142.31 %); best 3.035e-08s; worst 5.007e-06s; std dev. 2.135e-06 (taking best). -Reference operation time is 3.03507e-08 s (6326 Mflops) with 1 threads. -After merge step 1: tpop: 3.035e-08 s ~Mflops: 6326.052 nsubm:1 otn:1 -Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 249450.118x: 0.007571s -> 3.035e-08s, so taking this instance. +3 iterations (1 th.) took 0.002264s; avg 0.0007547s ( +/- 13.47/ 25.61 %); best 0.000653s; worst 0.000948s; std dev. 0.0001367 (taking best). +Reference operation time is 0.000653028 s (0.294 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: 0.000653 Mflops: 0.294) +Merge (3 -> 1 leaves) took w.c.t. of 1.001e-05s, ~3.815e-06s of computing time (of which 9.537e-07s sorting, 1.907e-06s analysis) +3 iterations (1 th.) took 5.007e-06s; avg 1.669e-06s ( +/- 95.16/142.86 %); best 8.07e-08s; worst 4.053e-06s; std dev. 1.73e-06 (taking best). +Reference operation time is 8.07047e-08 s (2379 Mflops) with 1 threads. +After merge step 1: tpop: 8.07e-08 s ~Mflops: 2379.044 nsubm:1 otn:1 +Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 8091.581x: 0.000653s -> 8.07e-08s, so taking this instance. Merged all the matrix leaves: no reason to continue merging. -A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.02441s (of which 1.693e-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 0.02441s, equivalent to 804296.9/3.2 new/old ops (0.04476s for 2 clones -- as 1474823.3/5.9 ops, or 737411.6/3.0 ops per clone), SPEEDUP of 249450.118x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 249450.118x (0.007571s -> 3.035e-08s), will amortize in 3.2 ops by saving 0.007571s per op. -In 1 tuning rounds (tot. 0.069s, 0.045s for constructor, 2 clones) obtained a SPEEDUP of 24944911.8% (2.495e+05x) (from 0.02536 to 6326 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.00166s (of which 1.407e-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 0.00166s, equivalent to 20567.2/2.5 new/old ops (0.003584s for 2 clones -- as 44407.7/5.5 ops, or 22203.8/2.7 ops per clone), SPEEDUP of 8091.581x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 8091.581x (0.000653s -> 8.07e-08s), will amortize in 2.5 ops by saving 0.0006529s per op. +In 1 tuning rounds (tot. 0.0059s, 0.0036s for constructor, 2 clones) obtained a SPEEDUP of 809058.1% (8092x) (from 0.294 to 2379 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 0.068681 s (7.571e-03 s -> 3.035e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.00592494 s (6.530e-04 s -> 8.070e-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 0.239758 s and estimated a speedup of 1.000000 x (3.035e-08 s -> 3.035e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.0461211 s and estimated a speedup of 1.000000 x (8.070e-08 s -> 8.070e-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 0.008785 0.018914 0.027699 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 1 3 3 6 0.027699 -%:RSB_SUBDIVISION_TIME:A.mtx S N 1 3 3 6 0.008785 -%:RSB_SHUFFLE_TIME:A.mtx S N 1 3 3 6 0.018914 +%:CONSTRUCTOR_TIMES:A.mtx S N 1 3 3 6 0.000000 0.000705 0.001314 0.002019 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 1 3 3 6 0.002019 +%:RSB_SUBDIVISION_TIME:A.mtx S N 1 3 3 6 0.000705 +%:RSB_SHUFFLE_TIME:A.mtx S N 1 3 3 6 0.001314 %: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 0.027699 +%:SORTEDCOO2RSB_TIME:A.mtx S N 1 3 3 6 0.002019 %: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 @@ -3378,47 +3414,47 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 1 3 3 6 6 6 6 # # Using 4 threads -# Constructed matrix (took 0.055s): (3 x 3)[0xaaab0e9163f0]{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 0.005s): (3 x 3)[0xaaaade0b9230]{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 0.02043s; avg 0.00681s ( +/- 34.94/ 17.52 %); best 0.00443s; worst 0.008003s; std dev. 0.001683 (taking best). -Reference operation time is 0.00443006 s (0.04334 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: 0.00443 Mflops: 0.043) -Merge (3 -> 1 leaves) took w.c.t. of 1.383e-05s, ~4.053e-06s of computing time (of which 1.192e-06s sorting, 3.815e-06s analysis) -3 iterations (4 th.) took 5.007e-06s; avg 1.669e-06s ( +/- 98.18/200.00 %); best 3.035e-08s; worst 5.007e-06s; std dev. 2.36e-06 (taking best). -Reference operation time is 3.03507e-08 s (6326 Mflops) with 4 threads. -After merge step 1: tpop: 3.035e-08 s ~Mflops: 6326.052 nsubm:1 otn:1 -Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 145962.294x: 0.00443s -> 3.035e-08s, so taking this instance. +3 iterations (4 th.) took 0.00251s; avg 0.0008367s ( +/- 0.44/ 0.76 %); best 0.000833s; worst 0.000843s; std dev. 4.512e-06 (taking best). +Reference operation time is 0.000833035 s (0.2305 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: 0.000833 Mflops: 0.230) +Merge (3 -> 1 leaves) took w.c.t. of 1.001e-05s, ~4.053e-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 ( +/- 94.03/129.41 %); best 8.07e-08s; worst 3.099e-06s; std dev. 1.296e-06 (taking best). +Reference operation time is 8.07047e-08 s (2379 Mflops) with 4 threads. +After merge step 1: tpop: 8.07e-08 s ~Mflops: 2379.044 nsubm:1 otn:1 +Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 10322.009x: 0.000833s -> 8.07e-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 0.03156s (of which 1.717e-05s partitioning, 0s I/O); computing times: 4.053e-06s in par. loops, 1.192e-06s sorting, 3.815e-06s analyzing) -Total merge + benchmarking process took 0.03156s, equivalent to 1039780.0/7.1 new/old ops (0.06325s for 2 clones -- as 2084006.3/14.3 ops, or 1042003.1/7.1 ops per clone), SPEEDUP of 145962.294x -Applying multi-merge (3 -> 1 leaves, 1 steps, 1 -> 1 th.sp.) yielded SPEEDUP of 145962.294x (0.00443s -> 3.035e-08s), will amortize in 7.1 ops by saving 0.00443s per op. -In 1 tuning rounds (tot. 0.084s, 0.063s for constructor, 2 clones) obtained a SPEEDUP of 14596129.4% (1.46e+05x) (from 0.04334 to 6326 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.002689s (of which 1.192e-05s partitioning, 0s I/O); computing times: 4.053e-06s in par. loops, 9.537e-07s sorting, 1.907e-06s analyzing) +Total merge + benchmarking process took 0.002689s, equivalent to 33317.6/3.2 new/old ops (0.005132s for 2 clones -- as 63589.4/6.2 ops, or 31794.7/3.1 ops per clone), SPEEDUP of 10322.009x +Applying multi-merge (3 -> 1 leaves, 1 steps, 1 -> 1 th.sp.) yielded SPEEDUP of 10322.009x (0.000833s -> 8.07e-08s), will amortize in 3.2 ops by saving 0.000833s per op. +In 1 tuning rounds (tot. 0.0077s, 0.0051s for constructor, 2 clones) obtained a SPEEDUP of 1032100.9% (1.032e+04x) (from 0.2305 to 2379 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 0.0837729 s (4.430e-03 s -> 3.035e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.00771117 s (8.330e-04 s -> 8.070e-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 0.32821 s and estimated a speedup of 1.000000 x (3.035e-08 s -> 3.035e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.0414109 s and estimated a speedup of 1.000000 x (8.070e-08 s -> 8.070e-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 0.012274 0.027226 0.039500 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 4 3 3 6 0.039500 -%:RSB_SUBDIVISION_TIME:A.mtx S N 4 3 3 6 0.012274 -%:RSB_SHUFFLE_TIME:A.mtx S N 4 3 3 6 0.027226 +%:CONSTRUCTOR_TIMES:A.mtx S N 4 3 3 6 0.000000 0.001540 0.001904 0.003444 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 4 3 3 6 0.003444 +%:RSB_SUBDIVISION_TIME:A.mtx S N 4 3 3 6 0.001540 +%:RSB_SHUFFLE_TIME:A.mtx S N 4 3 3 6 0.001904 %: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 0.039500 +%:SORTEDCOO2RSB_TIME:A.mtx S N 4 3 3 6 0.003444 %:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 4 3 3 6 0.000 -%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 4 3 3 6 0.70 -%:SORTEDCOO2RSB_SCALING:A.mtx S N 4 3 3 6 0.70 -%:RSB_SUBDIVISION_SCALING:A.mtx S N 4 3 3 6 0.72 +%:UNSORTEDCOO2RSB_SCALING:A.mtx S N 4 3 3 6 0.59 +%:SORTEDCOO2RSB_SCALING:A.mtx S N 4 3 3 6 0.59 +%:RSB_SUBDIVISION_SCALING:A.mtx S N 4 3 3 6 0.46 %:RSB_SHUFFLE_SCALING:A.mtx S N 4 3 3 6 0.69 -%:CONSTRUCTOR_SCALING:A.mtx S N 4 3 3 6 nan 0.72 0.69 0.70 +%:CONSTRUCTOR_SCALING:A.mtx S N 4 3 3 6 nan 0.46 0.69 0.59 #%: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 @@ -3427,185 +3463,185 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 4 3 3 6 6 6 6 # %operation:matrix CONSTRUCTOR[1] SPMV[1] SPMV[4] -%operation:A.mtx 0.0437169 1e+09 1e+09 +%operation:A.mtx 0.003335 1e+09 1e+09 %constructor:matrix SORT[1] SCAN[1] SHUFFLE[1] INSERT[1] -%constructor:A.mtx 0 0.00878501 0 0.018914 +%constructor:A.mtx 0 0.000705004 0 0.00131392 # symmetric matrix --- skipping transposed benchmarking -# so far, program took 7.028s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 1.513s/0.000s . +# so far, program took 5.553s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.236s/0.000s . getrusage() stats: -ru_maxrss: 8 (maximum resident set size -- MB) -ru_stime : 0.05257s (system CPU time used) -ru_utime : 6.418s (user CPU time used) +ru_maxrss: 6 (maximum resident set size -- MB) +ru_stime : 0.07981s (system CPU time used) +ru_utime : 7.294s (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 3163.03 6.304e-03 0.000e+00 3.035e-08 0.000e+00 5.376e-02 8.83e+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 3163.03 7.801e-03 0.000e+00 3.035e-08 0.000e+00 7.200e-02 8.83e+00 2.29e+00 1 9.60e-05 +pr: 1:R_R A 3 3 6 1 Z S N 1 1 0 4.0000 4.6667 3 1 100.66 1.217e-03 0.000e+00 9.537e-07 0.000e+00 1.166e-02 2.81e-01 2.29e+00 1 9.60e-05 +pr: 5:R_R A 3 3 6 1 Z S N 4 1 0 4.0000 4.6667 3 1 1189.52 9.491e-04 0.000e+00 8.070e-08 0.000e+00 1.269e-02 3.32e+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. 23236349.3 % faster, avg. sp. ratio 232364.493x, max sp. ratio 257022.781x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 2071814.6/1771225.5/2372403.8/4143629.2 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 8.9/ 8.5/ 9.2/ 17.8 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 8.9, min. 8.5, max. 9.2 ops) +#pr: (in succ. cases rsb autotuning gave avg. 651735.5 % faster, avg. sp. ratio 6518.355x, max sp. ratio 11760.709x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 84765.7/12231.5/157299.9/169531.4 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 11.5/ 9.6/ 13.4/ 23.0 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 11.5, min. 9.6, max. 13.4 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 32/ 32/ 32) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 96/ 96/ 96) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 7.249/ 7.249/ 7.249,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 17.660/ 8.830/ 8.830,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 1.478/ 0.231/ 2.726,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 3.602/ 0.281/ 3.321,GBps) #pr: (avg/min/max code balance (bytes read at least once per flop) 2.292/ 2.292/ 2.292) #pr: (avg/min/max (avg) bytes per nnz after successful tuning were 4.667/ 4.667/ 4.667) #pr: (matrix has been subdivided more/less/same in resp. 0 / 2 /0 cases) #pr: (matrix has used more/less/same threads in resp. 0 / 1 /1 cases) #pr: no unsuccessful rsb autotuning attempt (according to 1.01x threshold) -#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.06 s, min 0.05 s, max 0.07 s, tot 0.13 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.06 s, min 0.05 s, max 0.07 s, tot 0.13 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 3.163e+03, min 3.163e+03, max 3.163e+03 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 1.377e-02, min 1.231e-02, max 1.523e-02 (2 samples) -#pr: best tun. rsb operation time was: on avg. 3.035e-08s, min 3.035e-08s, max 3.035e-08s, tot 6.070e-08s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 7.052e-03s, min 6.304e-03s, max 7.801e-03s, tot 1.410e-02s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 6.540e+00 6.540e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.008e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.01 s, min 0.01 s, max 0.01 s, tot 0.02 s (2 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.01 s, min 0.01 s, max 0.01 s, tot 0.02 s (2 samples) +#pr: best tun. rsb canon. mflops were: on avg. 6.451e+02, min 1.007e+02, max 1.190e+03 (2 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 9.002e-02, min 7.889e-02, max 1.011e-01 (2 samples) +#pr: best tun. rsb operation time was: on avg. 5.172e-07s, min 8.070e-08s, max 9.537e-07s, tot 1.034e-06s (2 samples) +#pr: ref. unt. rsb operation time was: on avg. 1.083e-03s, min 9.491e-04s, max 1.217e-03s, tot 2.166e-03s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.754e+01 2.073e+02 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 9.992e-01 #pr: ======== Limiting to nrhs=2: #pr: 2 samples (out of 4) matched the dump limiting criteria. #pr: Dump from a base of 4 samples (of max 8) ordered by (1,2,1,1,2,1,2) = (filename x cores x incX x incY x nrhs x typecode x transA). pr: BESTCODE MTX NR NC NNZ NRHS TYPE SYM TRANS NT AT-NT AT-MKL-NT BPNZ AT-BPNZ NSUBM AT-SUBM RSBBEST-MFLOPS OPTIME MKL-OPTIME AT-OPTIME AT-MKL-OPTIME AT-TIME RWminBW-GBps CB-bpf AT-MS CMFLOPS -pr: 3:R_R A 3 3 6 2 Z S N 1 1 0 4.0000 4.6667 3 1 6326.05 7.571e-03 0.000e+00 3.035e-08 0.000e+00 6.868e-02 1.36e+01 1.65e+00 1 1.92e-04 -pr: 7:R_R A 3 3 6 2 Z S N 4 1 0 4.0000 4.6667 3 1 6326.05 4.430e-03 0.000e+00 3.035e-08 0.000e+00 8.377e-02 1.36e+01 1.65e+00 1 1.92e-04 +pr: 3:R_R A 3 3 6 2 Z S N 1 1 0 4.0000 4.6667 3 1 2379.04 6.530e-04 0.000e+00 8.070e-08 0.000e+00 5.925e-03 5.11e+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 2379.04 8.330e-04 0.000e+00 8.070e-08 0.000e+00 7.711e-03 5.11e+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. 19770520.6 % faster, avg. sp. ratio 197706.206x, max sp. ratio 249450.118x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 2511539.7/2262914.4/2760165.0/5023079.3 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 14.0/ 9.1/ 18.9/ 28.0 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 14.0, min. 9.1, max. 18.9 ops) +#pr: (in succ. cases rsb autotuning gave avg. 920579.5 % faster, avg. sp. ratio 9206.795x, max sp. ratio 10322.009x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 84481.5/73415.1/95548.0/168963.1 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 9.2/ 9.1/ 9.3/ 18.3 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 9.2, min. 9.1, max. 9.3 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 32/ 32/ 32) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 96/ 96/ 96) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 10.412/ 10.412/ 10.412,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 27.149/ 13.575/ 13.575,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 3.916/ 3.916/ 3.916,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 10.210/ 5.105/ 5.105,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.: 0.08 s, min 0.07 s, max 0.08 s, tot 0.15 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.08 s, min 0.07 s, max 0.08 s, tot 0.15 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 6.326e+03, min 6.326e+03, max 6.326e+03 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 3.435e-02, min 2.536e-02, max 4.334e-02 (2 samples) -#pr: best tun. rsb operation time was: on avg. 3.035e-08s, min 3.035e-08s, max 3.035e-08s, tot 6.070e-08s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 6.001e-03s, min 4.430e-03s, max 7.571e-03s, tot 1.200e-02s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 4.553e+00 4.553e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.008e+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: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.01 s, min 0.01 s, max 0.01 s, tot 0.01 s (2 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.01 s, min 0.01 s, max 0.01 s, tot 0.01 s (2 samples) +#pr: best tun. rsb canon. mflops were: on avg. 2.379e+03, min 2.379e+03, max 2.379e+03 (2 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 2.622e-01, min 2.305e-01, max 2.940e-01 (2 samples) +#pr: best tun. rsb operation time was: on avg. 8.070e-08s, min 8.070e-08s, max 8.070e-08s, tot 1.614e-07s (2 samples) +#pr: ref. unt. rsb operation time was: on avg. 7.430e-04s, min 6.530e-04s, max 8.330e-04s, tot 1.486e-03s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.221e+01 1.221e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 9.992e-01 +#pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 1.282e+01 x, min 2.000e+00 x, max 2.363e+01 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 3163.03 6.304e-03 0.000e+00 3.035e-08 0.000e+00 5.376e-02 8.83e+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 6326.05 7.571e-03 0.000e+00 3.035e-08 0.000e+00 6.868e-02 1.36e+01 1.65e+00 1 1.92e-04 -pr: 5:R_R A 3 3 6 1 Z S N 4 1 0 4.0000 4.6667 3 1 3163.03 7.801e-03 0.000e+00 3.035e-08 0.000e+00 7.200e-02 8.83e+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 6326.05 4.430e-03 0.000e+00 3.035e-08 0.000e+00 8.377e-02 1.36e+01 1.65e+00 1 1.92e-04 +pr: 1:R_R A 3 3 6 1 Z S N 1 1 0 4.0000 4.6667 3 1 100.66 1.217e-03 0.000e+00 9.537e-07 0.000e+00 1.166e-02 2.81e-01 2.29e+00 1 9.60e-05 +pr: 3:R_R A 3 3 6 2 Z S N 1 1 0 4.0000 4.6667 3 1 2379.04 6.530e-04 0.000e+00 8.070e-08 0.000e+00 5.925e-03 5.11e+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 1189.52 9.491e-04 0.000e+00 8.070e-08 0.000e+00 1.269e-02 3.32e+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 2379.04 8.330e-04 0.000e+00 8.070e-08 0.000e+00 7.711e-03 5.11e+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. 21503435.0 % faster, avg. sp. ratio 215035.350x, max sp. ratio 257022.781x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 2291677.1/1771225.5/2760165.0/9166708.6 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 11.4/ 8.5/ 18.9/ 45.7 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 11.4, min. 8.5, max. 18.9 ops) +#pr: (in succ. cases rsb autotuning gave avg. 786157.5 % faster, avg. sp. ratio 7862.575x, max sp. ratio 11760.709x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 84623.6/12231.5/157299.9/338494.4 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 10.3/ 9.1/ 13.4/ 41.3 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 10.3, min. 9.1, max. 13.4 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 32/ 32/ 32) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 96/ 96/ 96) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 8.830/ 7.249/ 10.412,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 44.810/ 8.830/ 13.575,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 2.697/ 0.231/ 3.916,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 13.812/ 0.281/ 5.105,GBps) #pr: (avg/min/max code balance (bytes read at least once per flop) 1.969/ 1.646/ 2.292) #pr: (avg/min/max (avg) bytes per nnz after successful tuning were 4.667/ 4.667/ 4.667) #pr: (matrix has been subdivided more/less/same in resp. 0 / 4 /0 cases) #pr: (matrix has used more/less/same threads in resp. 0 / 2 /2 cases) #pr: no unsuccessful rsb autotuning attempt (according to 1.01x threshold) -#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.07 s, min 0.05 s, max 0.08 s, tot 0.28 s (4 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.07 s, min 0.05 s, max 0.08 s, tot 0.28 s (4 samples) -#pr: best tun. rsb canon. mflops were: on avg. 4.745e+03, min 3.163e+03, max 6.326e+03 (4 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 2.406e-02, min 1.231e-02, max 4.334e-02 (4 samples) -#pr: best tun. rsb operation time was: on avg. 3.035e-08s, min 3.035e-08s, max 3.035e-08s, tot 1.214e-07s (4 samples) -#pr: ref. unt. rsb operation time was: on avg. 6.526e-03s, min 4.430e-03s, max 7.801e-03s, tot 2.611e-02s (4 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 4.553e+00 6.540e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.008e+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: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.01 s, min 0.01 s, max 0.01 s, tot 0.04 s (4 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.01 s, min 0.01 s, max 0.01 s, tot 0.04 s (4 samples) +#pr: best tun. rsb canon. mflops were: on avg. 1.512e+03, min 1.007e+02, max 2.379e+03 (4 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 1.761e-01, min 7.889e-02, max 2.940e-01 (4 samples) +#pr: best tun. rsb operation time was: on avg. 2.989e-07s, min 8.070e-08s, max 9.537e-07s, tot 1.196e-06s (4 samples) +#pr: ref. unt. rsb operation time was: on avg. 9.130e-04s, min 6.530e-04s, max 1.217e-03s, tot 3.652e-03s (4 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.221e+01 2.073e+02 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 9.992e-01 +#pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 1.282e+01 x, min 2.000e+00 x, max 2.363e+01 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 3163.03 6.304e-03 0.000e+00 3.035e-08 0.000e+00 5.376e-02 8.83e+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 3163.03 7.801e-03 0.000e+00 3.035e-08 0.000e+00 7.200e-02 8.83e+00 2.29e+00 1 9.60e-05 +pr: 1:R_R A 3 3 6 1 Z S N 1 1 0 4.0000 4.6667 3 1 100.66 1.217e-03 0.000e+00 9.537e-07 0.000e+00 1.166e-02 2.81e-01 2.29e+00 1 9.60e-05 +pr: 5:R_R A 3 3 6 1 Z S N 4 1 0 4.0000 4.6667 3 1 1189.52 9.491e-04 0.000e+00 8.070e-08 0.000e+00 1.269e-02 3.32e+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. 23236349.3 % faster, avg. sp. ratio 232364.493x, max sp. ratio 257022.781x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 2071814.6/1771225.5/2372403.8/4143629.2 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 8.9/ 8.5/ 9.2/ 17.8 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 8.9, min. 8.5, max. 9.2 ops) +#pr: (in succ. cases rsb autotuning gave avg. 651735.5 % faster, avg. sp. ratio 6518.355x, max sp. ratio 11760.709x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 84765.7/12231.5/157299.9/169531.4 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 11.5/ 9.6/ 13.4/ 23.0 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 11.5, min. 9.6, max. 13.4 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 32/ 32/ 32) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 96/ 96/ 96) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 7.249/ 7.249/ 7.249,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 17.660/ 8.830/ 8.830,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 1.478/ 0.231/ 2.726,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 3.602/ 0.281/ 3.321,GBps) #pr: (avg/min/max code balance (bytes read at least once per flop) 2.292/ 2.292/ 2.292) #pr: (avg/min/max (avg) bytes per nnz after successful tuning were 4.667/ 4.667/ 4.667) #pr: (matrix has been subdivided more/less/same in resp. 0 / 2 /0 cases) #pr: (matrix has used more/less/same threads in resp. 0 / 1 /1 cases) #pr: no unsuccessful rsb autotuning attempt (according to 1.01x threshold) -#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.06 s, min 0.05 s, max 0.07 s, tot 0.13 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.06 s, min 0.05 s, max 0.07 s, tot 0.13 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 3.163e+03, min 3.163e+03, max 3.163e+03 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 1.377e-02, min 1.231e-02, max 1.523e-02 (2 samples) -#pr: best tun. rsb operation time was: on avg. 3.035e-08s, min 3.035e-08s, max 3.035e-08s, tot 6.070e-08s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 7.052e-03s, min 6.304e-03s, max 7.801e-03s, tot 1.410e-02s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 6.540e+00 6.540e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.008e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.01 s, min 0.01 s, max 0.01 s, tot 0.02 s (2 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.01 s, min 0.01 s, max 0.01 s, tot 0.02 s (2 samples) +#pr: best tun. rsb canon. mflops were: on avg. 6.451e+02, min 1.007e+02, max 1.190e+03 (2 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 9.002e-02, min 7.889e-02, max 1.011e-01 (2 samples) +#pr: best tun. rsb operation time was: on avg. 5.172e-07s, min 8.070e-08s, max 9.537e-07s, tot 1.034e-06s (2 samples) +#pr: ref. unt. rsb operation time was: on avg. 1.083e-03s, min 9.491e-04s, max 1.217e-03s, tot 2.166e-03s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.754e+01 2.073e+02 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 9.992e-01 #pr: ======== Limiting to both transA=N and nrhs=2: #pr: 2 samples (out of 4) matched the dump limiting criteria. #pr: Dump from a base of 4 samples (of max 8) ordered by (1,2,1,1,2,1,2) = (filename x cores x incX x incY x nrhs x typecode x transA). pr: BESTCODE MTX NR NC NNZ NRHS TYPE SYM TRANS NT AT-NT AT-MKL-NT BPNZ AT-BPNZ NSUBM AT-SUBM RSBBEST-MFLOPS OPTIME MKL-OPTIME AT-OPTIME AT-MKL-OPTIME AT-TIME RWminBW-GBps CB-bpf AT-MS CMFLOPS -pr: 3:R_R A 3 3 6 2 Z S N 1 1 0 4.0000 4.6667 3 1 6326.05 7.571e-03 0.000e+00 3.035e-08 0.000e+00 6.868e-02 1.36e+01 1.65e+00 1 1.92e-04 -pr: 7:R_R A 3 3 6 2 Z S N 4 1 0 4.0000 4.6667 3 1 6326.05 4.430e-03 0.000e+00 3.035e-08 0.000e+00 8.377e-02 1.36e+01 1.65e+00 1 1.92e-04 +pr: 3:R_R A 3 3 6 2 Z S N 1 1 0 4.0000 4.6667 3 1 2379.04 6.530e-04 0.000e+00 8.070e-08 0.000e+00 5.925e-03 5.11e+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 2379.04 8.330e-04 0.000e+00 8.070e-08 0.000e+00 7.711e-03 5.11e+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. 19770520.6 % faster, avg. sp. ratio 197706.206x, max sp. ratio 249450.118x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 2511539.7/2262914.4/2760165.0/5023079.3 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 14.0/ 9.1/ 18.9/ 28.0 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 14.0, min. 9.1, max. 18.9 ops) +#pr: (in succ. cases rsb autotuning gave avg. 920579.5 % faster, avg. sp. ratio 9206.795x, max sp. ratio 10322.009x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 84481.5/73415.1/95548.0/168963.1 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 9.2/ 9.1/ 9.3/ 18.3 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 9.2, min. 9.1, max. 9.3 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 32/ 32/ 32) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 96/ 96/ 96) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 10.412/ 10.412/ 10.412,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 27.149/ 13.575/ 13.575,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 3.916/ 3.916/ 3.916,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 10.210/ 5.105/ 5.105,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.: 0.08 s, min 0.07 s, max 0.08 s, tot 0.15 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.08 s, min 0.07 s, max 0.08 s, tot 0.15 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 6.326e+03, min 6.326e+03, max 6.326e+03 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 3.435e-02, min 2.536e-02, max 4.334e-02 (2 samples) -#pr: best tun. rsb operation time was: on avg. 3.035e-08s, min 3.035e-08s, max 3.035e-08s, tot 6.070e-08s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 6.001e-03s, min 4.430e-03s, max 7.571e-03s, tot 1.200e-02s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 4.553e+00 4.553e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.008e+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: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.01 s, min 0.01 s, max 0.01 s, tot 0.01 s (2 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.01 s, min 0.01 s, max 0.01 s, tot 0.01 s (2 samples) +#pr: best tun. rsb canon. mflops were: on avg. 2.379e+03, min 2.379e+03, max 2.379e+03 (2 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 2.622e-01, min 2.305e-01, max 2.940e-01 (2 samples) +#pr: best tun. rsb operation time was: on avg. 8.070e-08s, min 8.070e-08s, max 8.070e-08s, tot 1.614e-07s (2 samples) +#pr: ref. unt. rsb operation time was: on avg. 7.430e-04s, min 6.530e-04s, max 8.330e-04s, tot 1.486e-03s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.221e+01 1.221e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 9.992e-01 +#pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 1.282e+01 x, min 2.000e+00 x, max 2.363e+01 x (2 samples, the non-min-nrhs ones) #pr: ======== Limiting to transA=T: #pr: No sample (out of 4) matched the dump criteria -- skipping dump round. #pr: ======== Limiting to both transA=T and nrhs=1: @@ -3615,44 +3651,44 @@ #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 3163.03 6.304e-03 0.000e+00 3.035e-08 0.000e+00 5.376e-02 8.83e+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 6326.05 7.571e-03 0.000e+00 3.035e-08 0.000e+00 6.868e-02 1.36e+01 1.65e+00 1 1.92e-04 -pr: 5:R_R A 3 3 6 1 Z S N 4 1 0 4.0000 4.6667 3 1 3163.03 7.801e-03 0.000e+00 3.035e-08 0.000e+00 7.200e-02 8.83e+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 6326.05 4.430e-03 0.000e+00 3.035e-08 0.000e+00 8.377e-02 1.36e+01 1.65e+00 1 1.92e-04 +pr: 1:R_R A 3 3 6 1 Z S N 1 1 0 4.0000 4.6667 3 1 100.66 1.217e-03 0.000e+00 9.537e-07 0.000e+00 1.166e-02 2.81e-01 2.29e+00 1 9.60e-05 +pr: 3:R_R A 3 3 6 2 Z S N 1 1 0 4.0000 4.6667 3 1 2379.04 6.530e-04 0.000e+00 8.070e-08 0.000e+00 5.925e-03 5.11e+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 1189.52 9.491e-04 0.000e+00 8.070e-08 0.000e+00 1.269e-02 3.32e+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 2379.04 8.330e-04 0.000e+00 8.070e-08 0.000e+00 7.711e-03 5.11e+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. 21503435.0 % faster, avg. sp. ratio 215035.350x, max sp. ratio 257022.781x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 2291677.1/1771225.5/2760165.0/9166708.6 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 11.4/ 8.5/ 18.9/ 45.7 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 11.4, min. 8.5, max. 18.9 ops) +#pr: (in succ. cases rsb autotuning gave avg. 786157.5 % faster, avg. sp. ratio 7862.575x, max sp. ratio 11760.709x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 84623.6/12231.5/157299.9/338494.4 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 10.3/ 9.1/ 13.4/ 41.3 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 10.3, min. 9.1, max. 13.4 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 32/ 32/ 32) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 96/ 96/ 96) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 8.830/ 7.249/ 10.412,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 44.810/ 8.830/ 13.575,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 2.697/ 0.231/ 3.916,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 13.812/ 0.281/ 5.105,GBps) #pr: (avg/min/max code balance (bytes read at least once per flop) 1.969/ 1.646/ 2.292) #pr: (avg/min/max (avg) bytes per nnz after successful tuning were 4.667/ 4.667/ 4.667) #pr: (matrix has been subdivided more/less/same in resp. 0 / 4 /0 cases) #pr: (matrix has used more/less/same threads in resp. 0 / 2 /2 cases) #pr: no unsuccessful rsb autotuning attempt (according to 1.01x threshold) -#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.07 s, min 0.05 s, max 0.08 s, tot 0.28 s (4 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.07 s, min 0.05 s, max 0.08 s, tot 0.28 s (4 samples) -#pr: best tun. rsb canon. mflops were: on avg. 4.745e+03, min 3.163e+03, max 6.326e+03 (4 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 2.406e-02, min 1.231e-02, max 4.334e-02 (4 samples) -#pr: best tun. rsb operation time was: on avg. 3.035e-08s, min 3.035e-08s, max 3.035e-08s, tot 1.214e-07s (4 samples) -#pr: ref. unt. rsb operation time was: on avg. 6.526e-03s, min 4.430e-03s, max 7.801e-03s, tot 2.611e-02s (4 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 4.553e+00 6.540e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.008e+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 1.46 s. +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.01 s, min 0.01 s, max 0.01 s, tot 0.04 s (4 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.01 s, min 0.01 s, max 0.01 s, tot 0.04 s (4 samples) +#pr: best tun. rsb canon. mflops were: on avg. 1.512e+03, min 1.007e+02, max 2.379e+03 (4 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 1.761e-01, min 7.889e-02, max 2.940e-01 (4 samples) +#pr: best tun. rsb operation time was: on avg. 2.989e-07s, min 8.070e-08s, max 9.537e-07s, tot 1.196e-06s (4 samples) +#pr: ref. unt. rsb operation time was: on avg. 9.130e-04s, min 6.530e-04s, max 1.217e-03s, tot 3.652e-03s (4 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.221e+01 2.073e+02 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 9.992e-01 +#pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 1.282e+01 x, min 2.000e+00 x, max 2.363e+01 x (2 samples, the non-min-nrhs ones) +#pr: Record collection took 0.25 s. #pr: Record comprises 40 memory benchmark samples (prepend RSB_PR_MBW=1 to dump this). -#pr: Record comprises 89 environment variables in 3761 bytes (prepend RSB_PR_ENV=1 to dump this). +#pr: Record comprises 90 environment variables in 3861 bytes (prepend RSB_PR_ENV=1 to dump this). # ====== END Total summary record. -#pr: ======== Saved a performance record of 8 samples to rsbench_pr__1739127198_gcc-12.2-1,4th.rpr -# Removing the temporary record file rsbench_pr__1739127198_gcc-12.2-1,4th.rpr.tmp. -# terminating run at 1739127205 (after 7.0s of w.c.t.) +#pr: ======== Saved a performance record of 8 samples to rsbench_pr__1704718224_gcc-12.2-1,4th.rpr +# Removing the temporary record file rsbench_pr__1704718224_gcc-12.2-1,4th.rpr.tmp. +# terminating run at 1704718230 (after 5.5s of w.c.t.) + ./rsbench -oa -Ob --help /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/rsbench is a swiss army knife for testing the library functionality and performance. You can use it to perform sparse matrix - unitary vector multiplication, specifying the blocking parameters, the times to perform multiplication. @@ -3926,8 +3962,8 @@ sysconf() : 4096 bytes per pagesize sysconf() : 8203997 physical pages sysconf() : 33603571712 bytes (32046 MB) of physical memory -sysconf() : 1737369 available (free) physical pages -sysconf() : 7116263424 available (free) physical memory +sysconf() : 4253156 available (free) physical pages +sysconf() : 17420926976 available (free) physical memory sysconf() , processors : 12 sysconf() , processors online : 12 sysconf() : no level 1 cache @@ -3952,30 +3988,30 @@ RSB_SUBM_IDX_MARKER : 2147483647 RSB_MAX_ALLOCATABLE_MEMORY_CHUNK: 18446744073709551615 timing min delta (if negative, don't complain with us) : 0 s -timing granularity : 2.8646e-08 s +timing granularity : 7.76529e-08 s CFLAGS : -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 CXXFLAGS : -g -O2 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -fopenmp CC : gcc memhinfo : L2:4/64/512K,L1:8/64/24K -detected free memory : 7115747328 +detected free memory : 17420926976 detected total memory : 33603571712 -for array sized 524288 elems, took 0.000349998 s for linear search and 0 s for binary search for element 524287, in 165 tries, for a total of 0.100263 s (ignore this:173014710) -for array sized 524288 elems, took 0.000174999 s for linear search and 0 s for binary search for element 262143, in 340 tries, for a total of 0.100161 s (ignore this:351271950) -for array sized 524288 elems, took 8.67844e-05 s for linear search and 0 s for binary search for element 131071, in 1135 tries, for a total of 0.100001 s (ignore this:648803120) -for array sized 524288 elems, took 4.29153e-05 s for linear search and 0 s for binary search for element 65535, in 2275 tries, for a total of 0.100029 s (ignore this:946987370) -for array sized 524288 elems, took 2.09808e-05 s for linear search and 0 s for binary search for element 32767, in 4536 tries, for a total of 0.100010 s (ignore this:1244249594) -for array sized 524288 elems, took 1.09673e-05 s for linear search and 0 s for binary search for element 16383, in 9005 tries, for a total of 0.100011 s (ignore this:1539307424) -for array sized 524288 elems, took 4.76837e-06 s for linear search and 0 s for binary search for element 8191, in 17927 tries, for a total of 0.100004 s (ignore this:1832987538) -for array sized 524288 elems, took 1.90735e-06 s for linear search and 0 s for binary search for element 4095, in 35230 tries, for a total of 0.100001 s (ignore this:2121521238) -for array sized 524288 elems, took 9.53674e-07 s for linear search and 0 s for binary search for element 2047, in 67968 tries, for a total of 0.100002 s (ignore this:-1895185066) -for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 1023, in 127209 tries, for a total of 0.100000 s (ignore this:-1634915452) -for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 511, in 225311 tries, for a total of 0.100001 s (ignore this:-1404647610) -for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 255, in 378506 tries, for a total of 0.100000 s (ignore this:-1211609550) -for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 127, in 561050 tries, for a total of 0.100000 s (ignore this:-1069102850) -for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 63, in 748687 tries, for a total of 0.100000 s (ignore this:-974768288) -for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 31, in 901227 tries, for a total of 0.100000 s (ignore this:-918892214) -for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 15, in 998477 tries, for a total of 0.100001 s (ignore this:-888937904) -for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 7, in 1054982 tries, for a total of 0.100001 s (ignore this:-874168156) +for array sized 524288 elems, took 0.000399828 s for linear search and 0 s for binary search for element 524287, in 153 tries, for a total of 0.100287 s (ignore this:160431822) +for array sized 524288 elems, took 0.000174999 s for linear search and 0 s for binary search for element 262143, in 557 tries, for a total of 0.100174 s (ignore this:452459124) +for array sized 524288 elems, took 8.67844e-05 s for linear search and 0 s for binary search for element 131071, in 1135 tries, for a total of 0.100059 s (ignore this:749990294) +for array sized 524288 elems, took 4.29153e-05 s for linear search and 0 s for binary search for element 65535, in 2275 tries, for a total of 0.100030 s (ignore this:1048174544) +for array sized 524288 elems, took 2.09808e-05 s for linear search and 0 s for binary search for element 32767, in 4536 tries, for a total of 0.100021 s (ignore this:1345436768) +for array sized 524288 elems, took 1.09673e-05 s for linear search and 0 s for binary search for element 16383, in 8996 tries, for a total of 0.100004 s (ignore this:1640199704) +for array sized 524288 elems, took 4.76837e-06 s for linear search and 0 s for binary search for element 8191, in 17903 tries, for a total of 0.100002 s (ignore this:1933486650) +for array sized 524288 elems, took 1.90735e-06 s for linear search and 0 s for binary search for element 4095, in 35190 tries, for a total of 0.100001 s (ignore this:-2073274546) +for array sized 524288 elems, took 9.53674e-07 s for linear search and 0 s for binary search for element 2047, in 67940 tries, for a total of 0.100000 s (ignore this:-1795128186) +for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 1023, in 125489 tries, for a total of 0.100000 s (ignore this:-1538377692) +for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 511, in 225250 tries, for a total of 0.100000 s (ignore this:-1308172192) +for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 255, in 378530 tries, for a total of 0.100000 s (ignore this:-1115121892) +for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 127, in 561303 tries, for a total of 0.100001 s (ignore this:-972550930) +for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 63, in 685614 tries, for a total of 0.100000 s (ignore this:-886163566) +for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 31, in 807746 tries, for a total of 0.100000 s (ignore this:-836083314) +for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 15, in 884572 tries, for a total of 0.100001 s (ignore this:-809546154) +for array sized 524288 elems, took 0 s for linear search and 0 s for binary search for element 7, in 923170 tries, for a total of 0.100000 s (ignore this:-796621774) + ./rsbench -C /build/reproducible-path/librsb-1.3.0.2+dfsg/.libs/rsbench version: 1.3.0 format switches:br @@ -4022,17 +4058,17 @@ 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 1739127207 +# beginning run at 1704718232 # /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 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 # User did not specify threads; assuming 1. Environment provides max 12 threads; this build supports max 128. # User did not specify threads; assuming 1. Environment provides max 12 threads; this build supports max 128. -# average timer granularity: 3.18e-08 s -# Will write a final performance record to file rsbench_pr__1739127207_gcc-12.2.rpr and periodic checkpoints to rsbench_pr__1739127207_gcc-12.2.rpr.tmp +# average timer granularity: 7.76e-08 s +# Will write a final performance record to file rsbench_pr__1704718232_gcc-12.2.rpr and periodic checkpoints to rsbench_pr__1704718232_gcc-12.2.rpr.tmp # will NOT perform ancillary tests. # will flush cache memory: between each operation measurement series, and NOT between each operation. # will keep any zero encountered in the matrix. -# env: export PATH=/usr/sbin:/usr/bin:/sbin:/bin:/usr/games +# env: export PATH=/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/i/capture/the/path # env: export LD_LIBRARY_PATH=/build/reproducible-path/librsb-1.3.0.2+dfsg/.libs # env: HOSTNAME is not set # env: KMP_AFFINITY is not set @@ -4071,61 +4107,61 @@ # 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: codethink03-arm64 +# detected hostname: i-capture-the-hostname # user specified a verbosity level of 1 (each --verbose occurrence counts +1) # This test will measure times in scanning arrays sized and aligned to fit in caches. # 2 cache levels detected Will fill struct with 40 samples... -# Memory benchmark took 5.231s +# Memory benchmark took 5.287s # auto-tuning oriented output implies times==0 iterations and sort-after-load. #pr: allocated a performance record for 16 samples (4480 bytes). # multi-type benchmarking (DSCZ) -- now using typecode D (last was D). # Cache block size total 524288 bytes, per-thread 43690 bytes -# so far, program took 5.233s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.000s/0.000s . +# so far, program took 5.290s 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, 81180 nnz/s ) (2.49 MB/s ) -#pre-sorting (6 elements) took 0.00559211 s -#weeding duplicates (to 6 elements) took 1.90735e-06 s (and check, 9.53674e-07 s ) +# file input of A.mtx took 0.00 s (6 nnz, 85890 nnz/s ) (2.63 MB/s ) +#pre-sorting (6 elements) took 0.00142789 s +#weeding duplicates (to 6 elements) took 9.53674e-07 s (and check, 1.90735e-06 s ) # multi-nrhs benchmarking (1,4) -- now using nrhs 1. # Using alpha=1 beta=1 order=rows for rsb_spmv/rsb_spsv/rsb_spmm/rsb_spsm. # multi-transpose benchmarking -- now using transA = N. # will use input matrix flags: RSB_FLAG_USE_HALFWORD_INDICES, RSB_FLAG_SORTED_INPUT, RSB_FLAG_QUAD_PARTITIONING, RSB_FLAG_SYMMETRIC, RSB_FLAG_OWN_PARTITIONING_ARRAYS # Using 12 threads -# Constructed matrix (took 0.048s): (3 x 3)[0xaaaae89a5800]{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 0.008s): (3 x 3)[0xaaaab77025a0]{D} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x2442186 (coo:1, csr:0, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'S' # matrix consistency check took 0.000s (ok) RSB Sparse Blocks Autotuner invoked requesting max 6 splits and max 6 merges in 1 rounds, threads spec.0 (specify negative values to enable threads tuning). Will autotune matrix: 3 x 3, type D, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:3 -3 iterations (12 th.) took 0.02068s; avg 0.006894s ( +/- 34.95/ 18.91 %); best 0.004485s; worst 0.008198s; std dev. 0.001705 (taking best). -Reference operation time is 0.00448489 s (0.005351 Mflops) with 12 threads. -Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=rows) (max 6 steps, inclusive 3 grace steps) on: 3 x 3, type D, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz (tpop: 0.004485 Mflops: 0.005) -Merge (3 -> 1 leaves) took w.c.t. of 2.217e-05s, ~7.868e-06s of computing time (of which 9.537e-07s sorting, 5.007e-06s analysis) -3 iterations (12 th.) took 0.000108s; avg 3.6e-05s ( +/- 99.92/197.35 %); best 2.995e-08s; worst 0.000107s; std dev. 5.024e-05 (taking best). -Reference operation time is 2.99454e-08 s (801.5 Mflops) with 12 threads. -After merge step 1: tpop: 2.995e-08 s ~Mflops: 801.459 nsubm:1 otn:12 -Applying merge (3 -> 1 leaves, 12 th.) yielded SPEEDUP of 149769.108x: 0.004485s -> 2.995e-08s, so taking this instance. +3 iterations (12 th.) took 0.004388s; avg 0.001463s ( +/- 57.28/ 73.59 %); best 0.0006249s; worst 0.002539s; std dev. 0.0007994 (taking best). +Reference operation time is 0.000624895 s (0.03841 Mflops) with 12 threads. +Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=rows) (max 6 steps, inclusive 3 grace steps) on: 3 x 3, type D, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz (tpop: 0.0006249 Mflops: 0.038) +Merge (3 -> 1 leaves) took w.c.t. of 1.407e-05s, ~5.007e-06s of computing time (of which 0s sorting, 3.099e-06s analysis) +3 iterations (12 th.) took 0.0001652s; avg 5.507e-05s ( +/- 99.84/197.84 %); best 8.775e-08s; worst 0.000164s; std dev. 7.705e-05 (taking best). +Reference operation time is 8.775e-08 s (273.5 Mflops) with 12 threads. +After merge step 1: tpop: 8.775e-08 s ~Mflops: 273.504 nsubm:1 otn:12 +Applying merge (3 -> 1 leaves, 12 th.) yielded SPEEDUP of 7121.315x: 0.0006249s -> 8.775e-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 0.01295s (of which 2.408e-05s partitioning, 0s I/O); computing times: 7.868e-06s in par. loops, 9.537e-07s sorting, 5.007e-06s analyzing) -Total merge + benchmarking process took 0.01295s, equivalent to 432420.4/2.9 new/old ops (0.03674s for 2 clones -- as 1226942.7/8.2 ops, or 613471.3/4.1 ops per clone), SPEEDUP of 149769.108x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 149769.108x (0.004485s -> 2.995e-08s), will amortize in 2.9 ops by saving 0.004485s per op. -In 1 tuning rounds (tot. 0.058s, 0.037s for constructor, 2 clones) obtained a SPEEDUP of 14976810.8% (1.498e+05x) (from 0.005351 to 801.5 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.003571s (of which 1.693e-05s partitioning, 0s I/O); computing times: 5.007e-06s in par. loops, 0s sorting, 3.099e-06s analyzing) +Total merge + benchmarking process took 0.003571s, equivalent to 40695.6/5.7 new/old ops (0.006832s for 2 clones -- as 77856.3/10.9 ops, or 38928.1/5.5 ops per clone), SPEEDUP of 7121.315x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 7121.315x (0.0006249s -> 8.775e-08s), will amortize in 5.7 ops by saving 0.0006248s per op. +In 1 tuning rounds (tot. 0.011s, 0.0068s for constructor, 2 clones) obtained a SPEEDUP of 712031.5% (7121x) (from 0.03841 to 273.5 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 0.057631 s (4.485e-03 s -> 2.995e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.0114591 s (6.249e-04 s -> 8.775e-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 0.180115 s and estimated a speedup of 1.000000 x (2.995e-08 s -> 2.995e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.044524 s and estimated a speedup of 1.000000 x (8.775e-08 s -> 8.775e-08 s per op) in same matrix (1 -> 1 lsubm) #min:1 #max:1 #sum:3 #norm:1.7320508075688772 #used index storage compared to COO:28 vs 48 bytes (58.33%) ; compared to CSR:28 vs 40 bytes (77.78%) #%:CONSTRUCTOR_*:SORT SCAN INSERT SCAN+INSERT -%:CONSTRUCTOR_TIMES:A.mtx S N 12 3 3 6 0.000000 0.017095 0.014986 0.032081 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.032081 -%:RSB_SUBDIVISION_TIME:A.mtx S N 12 3 3 6 0.017095 -%:RSB_SHUFFLE_TIME:A.mtx S N 12 3 3 6 0.014986 +%:CONSTRUCTOR_TIMES:A.mtx S N 12 3 3 6 0.000000 0.003364 0.002514 0.005878 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.005878 +%:RSB_SUBDIVISION_TIME:A.mtx S N 12 3 3 6 0.003364 +%:RSB_SHUFFLE_TIME:A.mtx S N 12 3 3 6 0.002514 %:ROW_MAJOR_SORT_TIME:A.mtx S N 12 3 3 6 0.000000 %:ROW_MAJOR_SORT_SCALING:A.mtx S N 12 3 3 6 nan -%:SORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.032081 +%:SORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.005878 %:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 12 3 3 6 0.000 %:UNSORTEDCOO2RSB_SCALING:A.mtx S N 12 3 3 6 1.00 %:SORTEDCOO2RSB_SCALING:A.mtx S N 12 3 3 6 1.00 @@ -4140,50 +4176,50 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 12 3 3 6 6 6 6 # %operation:matrix CONSTRUCTOR[12] SPMV[12] SPMV[12] -%operation:A.mtx 0.048084 1e+09 1e+09 +%operation:A.mtx 0.00836802 1e+09 1e+09 %constructor:matrix SORT[12] SCAN[12] SHUFFLE[12] INSERT[12] -%constructor:A.mtx 0 0.0170951 0 0.014986 +%constructor:A.mtx 0 0.00336385 0 0.00251389 # symmetric matrix --- skipping transposed benchmarking # multi-nrhs benchmarking (1,4) -- now using nrhs 4. # Using alpha=1 beta=1 order=rows for rsb_spmv/rsb_spsv/rsb_spmm/rsb_spsm. # multi-transpose benchmarking -- now using transA = N. # will use input matrix flags: RSB_FLAG_USE_HALFWORD_INDICES, RSB_FLAG_SORTED_INPUT, RSB_FLAG_QUAD_PARTITIONING, RSB_FLAG_SYMMETRIC, RSB_FLAG_OWN_PARTITIONING_ARRAYS # Using 12 threads -# Constructed matrix (took 0.023s): (3 x 3)[0xaaaae89a8cc0]{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 0.007s): (3 x 3)[0xaaaab7705a60]{D} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x2442186 (coo:1, csr:0, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'S' # matrix consistency check took 0.000s (ok) RSB Sparse Blocks Autotuner invoked requesting max 6 splits and max 6 merges in 1 rounds, threads spec.0 (specify negative values to enable threads tuning). Will autotune matrix: 3 x 3, type D, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:3 -3 iterations (12 th.) took 0.01335s; avg 0.004451s ( +/- 0.12/ 0.21 %); best 0.004446s; worst 0.004461s; std dev. 6.755e-06 (taking best). -Reference operation time is 0.00444603 s (0.02159 Mflops) with 12 threads. -Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=4, order=rows) (max 6 steps, inclusive 3 grace steps) on: 3 x 3, type D, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz (tpop: 0.004446 Mflops: 0.022) -Merge (3 -> 1 leaves) took w.c.t. of 1.001e-05s, ~3.099e-06s of computing time (of which 0s sorting, 1.907e-06s analysis) -3 iterations (12 th.) took 3.099e-06s; avg 1.033e-06s ( +/- 97.10/ 84.62 %); best 2.995e-08s; worst 1.907e-06s; std dev. 7.867e-07 (taking best). -Reference operation time is 2.99454e-08 s (3206 Mflops) with 12 threads. -After merge step 1: tpop: 2.995e-08 s ~Mflops: 3205.837 nsubm:1 otn:12 -Applying merge (3 -> 1 leaves, 12 th.) yielded SPEEDUP of 148471.338x: 0.004446s -> 2.995e-08s, so taking this instance. +3 iterations (12 th.) took 0.00337s; avg 0.001123s ( +/- 6.25/ 6.46 %); best 0.001053s; worst 0.001196s; std dev. 5.833e-05 (taking best). +Reference operation time is 0.00105309 s (0.09116 Mflops) with 12 threads. +Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=4, order=rows) (max 6 steps, inclusive 3 grace steps) on: 3 x 3, type D, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz (tpop: 0.001053 Mflops: 0.091) +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 (12 th.) took 3.099e-06s; avg 1.033e-06s ( +/- 91.51/ 84.62 %); best 8.775e-08s; worst 1.907e-06s; std dev. 7.867e-07 (taking best). +Reference operation time is 8.775e-08 s (1094 Mflops) with 12 threads. +After merge step 1: tpop: 8.775e-08 s ~Mflops: 1094.018 nsubm:1 otn:12 +Applying merge (3 -> 1 leaves, 12 th.) yielded SPEEDUP of 12001.087x: 0.001053s -> 8.775e-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 0.01356s (of which 1.311e-05s partitioning, 0s I/O); computing times: 3.099e-06s in par. loops, 0s sorting, 1.907e-06s analyzing) -Total merge + benchmarking process took 0.01356s, equivalent to 452659.2/3.0 new/old ops (0.03199s for 2 clones -- as 1068312.1/7.2 ops, or 534156.1/3.6 ops per clone), SPEEDUP of 148471.338x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 148471.338x (0.004446s -> 2.995e-08s), will amortize in 3.0 ops by saving 0.004446s per op. -In 1 tuning rounds (tot. 0.045s, 0.032s for constructor, 2 clones) obtained a SPEEDUP of 14847033.8% (1.485e+05x) (from 0.02159 to 3206 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.002815s (of which 2.003e-05s partitioning, 0s I/O); computing times: 5.007e-06s in par. loops, 9.537e-07s sorting, 3.099e-06s analyzing) +Total merge + benchmarking process took 0.002815s, equivalent to 32079.9/2.7 new/old ops (0.005994s for 2 clones -- as 68308.7/5.7 ops, or 34154.3/2.8 ops per clone), SPEEDUP of 12001.087x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 12001.087x (0.001053s -> 8.775e-08s), will amortize in 2.7 ops by saving 0.001053s per op. +In 1 tuning rounds (tot. 0.0095s, 0.006s for constructor, 2 clones) obtained a SPEEDUP of 1200008.7% (1.2e+04x) (from 0.09116 to 1094 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 0.045408 s (4.446e-03 s -> 2.995e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.0094769 s (1.053e-03 s -> 8.775e-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 0.214568 s and estimated a speedup of 1.000000 x (2.995e-08 s -> 2.995e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.0444379 s and estimated a speedup of 1.000000 x (8.775e-08 s -> 8.775e-08 s per op) in same matrix (1 -> 1 lsubm) #min:1 #max:1 #sum:3 #norm:1.7320508075688772 #used index storage compared to COO:28 vs 48 bytes (58.33%) ; compared to CSR:28 vs 40 bytes (77.78%) #%:CONSTRUCTOR_*:SORT SCAN INSERT SCAN+INSERT -%:CONSTRUCTOR_TIMES:A.mtx S N 12 3 3 6 0.000000 0.007640 0.008409 0.016049 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.016049 -%:RSB_SUBDIVISION_TIME:A.mtx S N 12 3 3 6 0.007640 -%:RSB_SHUFFLE_TIME:A.mtx S N 12 3 3 6 0.008409 +%:CONSTRUCTOR_TIMES:A.mtx S N 12 3 3 6 0.000000 0.002271 0.002639 0.004910 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.004910 +%:RSB_SUBDIVISION_TIME:A.mtx S N 12 3 3 6 0.002271 +%:RSB_SHUFFLE_TIME:A.mtx S N 12 3 3 6 0.002639 %:ROW_MAJOR_SORT_TIME:A.mtx S N 12 3 3 6 0.000000 %:ROW_MAJOR_SORT_SCALING:A.mtx S N 12 3 3 6 nan -%:SORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.016049 +%:SORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.004910 %:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 12 3 3 6 0.000 %:UNSORTEDCOO2RSB_SCALING:A.mtx S N 12 3 3 6 1.00 %:SORTEDCOO2RSB_SCALING:A.mtx S N 12 3 3 6 1.00 @@ -4198,59 +4234,59 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 12 3 3 6 6 6 6 # %operation:matrix CONSTRUCTOR[12] SPMV[12] SPMV[12] -%operation:A.mtx 0.0228221 1e+09 1e+09 +%operation:A.mtx 0.00653887 1e+09 1e+09 %constructor:matrix SORT[12] SCAN[12] SHUFFLE[12] INSERT[12] -%constructor:A.mtx 0 0.00764012 0 0.00840902 +%constructor:A.mtx 0 0.00227094 0 0.00263906 # symmetric matrix --- skipping transposed benchmarking -# so far, program took 5.875s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.498s/0.000s . +# so far, program took 5.428s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.110s/0.000s . getrusage() stats: ru_maxrss: 6 (maximum resident set size -- MB) -ru_stime : 0.03276s (system CPU time used) -ru_utime : 5.836s (user CPU time used) +ru_stime : 0.03204s (system CPU time used) +ru_utime : 6.53s (user CPU time used) # multi-type benchmarking (DSCZ) -- now using typecode S (last was D). # Cache block size total 524288 bytes, per-thread 43690 bytes -# so far, program took 5.875s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.498s/0.000s . +# so far, program took 5.428s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.110s/0.000s . # Reusing type converted (D->S) arrays from last iteration instead of reloading matrix file. # multi-nrhs benchmarking (1,4) -- now using nrhs 1. # Using alpha=1 beta=1 order=rows for rsb_spmv/rsb_spsv/rsb_spmm/rsb_spsm. # multi-transpose benchmarking -- now using transA = N. # will use input matrix flags: RSB_FLAG_USE_HALFWORD_INDICES, RSB_FLAG_SORTED_INPUT, RSB_FLAG_QUAD_PARTITIONING, RSB_FLAG_SYMMETRIC, RSB_FLAG_OWN_PARTITIONING_ARRAYS # Using 12 threads -# Constructed matrix (took 0.052s): (3 x 3)[0xaaaae89aba00]{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 0.005s): (3 x 3)[0xaaaab77087a0]{S} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x2442186 (coo:1, csr:0, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'S' # matrix consistency check took 0.000s (ok) RSB Sparse Blocks Autotuner invoked requesting max 6 splits and max 6 merges in 1 rounds, threads spec.0 (specify negative values to enable threads tuning). Will autotune matrix: 3 x 3, type S, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:3 -3 iterations (12 th.) took 0.0274s; avg 0.009132s ( +/- 30.13/ 40.31 %); best 0.00638s; worst 0.01281s; std dev. 0.002707 (taking best). -Reference operation time is 0.00637984 s (0.003762 Mflops) with 12 threads. -Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=rows) (max 6 steps, inclusive 3 grace steps) on: 3 x 3, type S, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz (tpop: 0.00638 Mflops: 0.004) -Merge (3 -> 1 leaves) took w.c.t. of 1.407e-05s, ~5.007e-06s of computing time (of which 1.192e-06s sorting, 2.861e-06s analysis) -3 iterations (12 th.) took 0.0001049s; avg 3.497e-05s ( +/- 99.91/197.27 %); best 2.995e-08s; worst 0.000104s; std dev. 4.878e-05 (taking best). -Reference operation time is 2.99454e-08 s (801.5 Mflops) with 12 threads. -After merge step 1: tpop: 2.995e-08 s ~Mflops: 801.459 nsubm:1 otn:12 -Applying merge (3 -> 1 leaves, 12 th.) yielded SPEEDUP of 213049.363x: 0.00638s -> 2.995e-08s, so taking this instance. +3 iterations (12 th.) took 0.003115s; avg 0.001038s ( +/- 20.53/ 17.68 %); best 0.0008252s; worst 0.001222s; std dev. 0.0001633 (taking best). +Reference operation time is 0.000825167 s (0.02909 Mflops) with 12 threads. +Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=rows) (max 6 steps, inclusive 3 grace steps) on: 3 x 3, type S, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz (tpop: 0.0008252 Mflops: 0.029) +Merge (3 -> 1 leaves) took w.c.t. of 1.001e-05s, ~4.053e-06s of computing time (of which 9.537e-07s sorting, 2.146e-06s analysis) +3 iterations (12 th.) took 0.000103s; avg 3.433e-05s ( +/- 99.74/197.22 %); best 8.775e-08s; worst 0.000102s; std dev. 4.788e-05 (taking best). +Reference operation time is 8.775e-08 s (273.5 Mflops) with 12 threads. +After merge step 1: tpop: 8.775e-08 s ~Mflops: 273.504 nsubm:1 otn:12 +Applying merge (3 -> 1 leaves, 12 th.) yielded SPEEDUP of 9403.614x: 0.0008252s -> 8.775e-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 0.025s (of which 1.597e-05s partitioning, 0s I/O); computing times: 5.007e-06s in par. loops, 1.192e-06s sorting, 2.861e-06s analyzing) -Total merge + benchmarking process took 0.025s, equivalent to 834856.7/3.9 new/old ops (0.04504s for 2 clones -- as 1504036.6/7.1 ops, or 752018.3/3.5 ops per clone), SPEEDUP of 213049.363x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 213049.363x (0.00638s -> 2.995e-08s), will amortize in 3.9 ops by saving 0.00638s per op. -In 1 tuning rounds (tot. 0.073s, 0.045s for constructor, 2 clones) obtained a SPEEDUP of 21304836.3% (2.13e+05x) (from 0.003762 to 801.5 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.002355s (of which 1.407e-05s partitioning, 0s I/O); computing times: 4.053e-06s in par. loops, 9.537e-07s sorting, 2.146e-06s analyzing) +Total merge + benchmarking process took 0.002355s, equivalent to 26838.7/2.9 new/old ops (0.004335s for 2 clones -- as 49400.9/5.3 ops, or 24700.4/2.6 ops per clone), SPEEDUP of 9403.614x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 9403.614x (0.0008252s -> 8.775e-08s), will amortize in 2.9 ops by saving 0.0008251s per op. +In 1 tuning rounds (tot. 0.0078s, 0.0043s for constructor, 2 clones) obtained a SPEEDUP of 940261.4% (9404x) (from 0.02909 to 273.5 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 0.072643 s (6.380e-03 s -> 2.995e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.0078361 s (8.252e-04 s -> 8.775e-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 0.159768 s and estimated a speedup of 1.000000 x (2.995e-08 s -> 2.995e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.0401881 s and estimated a speedup of 1.000000 x (8.775e-08 s -> 8.775e-08 s per op) in same matrix (1 -> 1 lsubm) #min:1 #max:1 #sum:3 #norm:1.73205078 #used index storage compared to COO:28 vs 48 bytes (58.33%) ; compared to CSR:28 vs 40 bytes (77.78%) #%:CONSTRUCTOR_*:SORT SCAN INSERT SCAN+INSERT -%:CONSTRUCTOR_TIMES:A.mtx S N 12 3 3 6 0.000000 0.025430 0.009438 0.034868 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.034868 -%:RSB_SUBDIVISION_TIME:A.mtx S N 12 3 3 6 0.025430 -%:RSB_SHUFFLE_TIME:A.mtx S N 12 3 3 6 0.009438 +%:CONSTRUCTOR_TIMES:A.mtx S N 12 3 3 6 0.000000 0.001536 0.001735 0.003271 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.003271 +%:RSB_SUBDIVISION_TIME:A.mtx S N 12 3 3 6 0.001536 +%:RSB_SHUFFLE_TIME:A.mtx S N 12 3 3 6 0.001735 %:ROW_MAJOR_SORT_TIME:A.mtx S N 12 3 3 6 0.000000 %:ROW_MAJOR_SORT_SCALING:A.mtx S N 12 3 3 6 nan -%:SORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.034868 +%:SORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.003271 %:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 12 3 3 6 0.000 %:UNSORTEDCOO2RSB_SCALING:A.mtx S N 12 3 3 6 1.00 %:SORTEDCOO2RSB_SCALING:A.mtx S N 12 3 3 6 1.00 @@ -4265,50 +4301,50 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 12 3 3 6 6 6 6 # %operation:matrix CONSTRUCTOR[12] SPMV[12] SPMV[12] -%operation:A.mtx 0.0522969 1e+09 1e+09 +%operation:A.mtx 0.00472498 1e+09 1e+09 %constructor:matrix SORT[12] SCAN[12] SHUFFLE[12] INSERT[12] -%constructor:A.mtx 0 0.02543 0 0.0094378 +%constructor:A.mtx 0 0.00153589 0 0.00173497 # symmetric matrix --- skipping transposed benchmarking # multi-nrhs benchmarking (1,4) -- now using nrhs 4. # Using alpha=1 beta=1 order=rows for rsb_spmv/rsb_spsv/rsb_spmm/rsb_spsm. # multi-transpose benchmarking -- now using transA = N. # will use input matrix flags: RSB_FLAG_USE_HALFWORD_INDICES, RSB_FLAG_SORTED_INPUT, RSB_FLAG_QUAD_PARTITIONING, RSB_FLAG_SYMMETRIC, RSB_FLAG_OWN_PARTITIONING_ARRAYS # Using 12 threads -# Constructed matrix (took 0.023s): (3 x 3)[0xaaaae89aba00]{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 0.006s): (3 x 3)[0xaaaab77087a0]{S} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x2442186 (coo:1, csr:0, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'S' # matrix consistency check took 0.000s (ok) RSB Sparse Blocks Autotuner invoked requesting max 6 splits and max 6 merges in 1 rounds, threads spec.0 (specify negative values to enable threads tuning). Will autotune matrix: 3 x 3, type S, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:3 -3 iterations (12 th.) took 0.0134s; avg 0.004467s ( +/- 44.73/ 27.44 %); best 0.002469s; worst 0.005693s; std dev. 0.001425 (taking best). -Reference operation time is 0.00246906 s (0.03888 Mflops) with 12 threads. -Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=4, order=rows) (max 6 steps, inclusive 3 grace steps) on: 3 x 3, type S, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz (tpop: 0.002469 Mflops: 0.039) -Merge (3 -> 1 leaves) took w.c.t. of 1.311e-05s, ~5.96e-06s of computing time (of which 9.537e-07s sorting, 3.099e-06s analysis) -3 iterations (12 th.) took 1.717e-05s; avg 5.722e-06s ( +/- 99.48/200.00 %); best 2.995e-08s; worst 1.717e-05s; std dev. 8.092e-06 (taking best). -Reference operation time is 2.99454e-08 s (3206 Mflops) with 12 threads. -After merge step 1: tpop: 2.995e-08 s ~Mflops: 3205.837 nsubm:1 otn:12 -Applying merge (3 -> 1 leaves, 12 th.) yielded SPEEDUP of 82452.229x: 0.002469s -> 2.995e-08s, so taking this instance. +3 iterations (12 th.) took 0.00269s; avg 0.0008967s ( +/- 9.78/ 17.89 %); best 0.000809s; worst 0.001057s; std dev. 0.0001136 (taking best). +Reference operation time is 0.000808954 s (0.1187 Mflops) with 12 threads. +Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=4, order=rows) (max 6 steps, inclusive 3 grace steps) on: 3 x 3, type S, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz (tpop: 0.000809 Mflops: 0.119) +Merge (3 -> 1 leaves) took w.c.t. of 8.106e-06s, ~2.861e-06s of computing time (of which 0s sorting, 1.907e-06s analysis) +3 iterations (12 th.) took 1.907e-05s; avg 6.358e-06s ( +/- 98.62/185.00 %); best 8.775e-08s; worst 1.812e-05s; std dev. 8.326e-06 (taking best). +Reference operation time is 8.775e-08 s (1094 Mflops) with 12 threads. +After merge step 1: tpop: 8.775e-08 s ~Mflops: 1094.018 nsubm:1 otn:12 +Applying merge (3 -> 1 leaves, 12 th.) yielded SPEEDUP of 9218.856x: 0.000809s -> 8.775e-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 0.0164s (of which 1.597e-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 0.0164s, equivalent to 547595.5/6.6 new/old ops (0.0268s for 2 clones -- as 895095.5/10.9 ops, or 447547.8/5.4 ops per clone), SPEEDUP of 82452.229x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 82452.229x (0.002469s -> 2.995e-08s), will amortize in 6.6 ops by saving 0.002469s per op. -In 1 tuning rounds (tot. 0.04s, 0.027s for constructor, 2 clones) obtained a SPEEDUP of 8245122.9% (8.245e+04x) (from 0.03888 to 3206 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.003115s (of which 1.097e-05s partitioning, 0s I/O); computing times: 2.861e-06s in par. loops, 0s sorting, 1.907e-06s analyzing) +Total merge + benchmarking process took 0.003115s, equivalent to 35497.9/3.9 new/old ops (0.006005s for 2 clones -- as 68430.9/7.4 ops, or 34215.5/3.7 ops per clone), SPEEDUP of 9218.856x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 9218.856x (0.000809s -> 8.775e-08s), will amortize in 3.9 ops by saving 0.0008089s per op. +In 1 tuning rounds (tot. 0.0089s, 0.006s for constructor, 2 clones) obtained a SPEEDUP of 921785.6% (9219x) (from 0.1187 to 1094 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 0.040323 s (2.469e-03 s -> 2.995e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.00887799 s (8.090e-04 s -> 8.775e-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 0.236279 s and estimated a speedup of 1.000000 x (2.995e-08 s -> 2.995e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.031291 s and estimated a speedup of 1.000000 x (8.775e-08 s -> 8.775e-08 s per op) in same matrix (1 -> 1 lsubm) #min:1 #max:1 #sum:3 #norm:1.73205078 #used index storage compared to COO:28 vs 48 bytes (58.33%) ; compared to CSR:28 vs 40 bytes (77.78%) #%:CONSTRUCTOR_*:SORT SCAN INSERT SCAN+INSERT -%:CONSTRUCTOR_TIMES:A.mtx S N 12 3 3 6 0.000000 0.009488 0.006743 0.016231 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.016231 -%:RSB_SUBDIVISION_TIME:A.mtx S N 12 3 3 6 0.009488 -%:RSB_SHUFFLE_TIME:A.mtx S N 12 3 3 6 0.006743 +%:CONSTRUCTOR_TIMES:A.mtx S N 12 3 3 6 0.000000 0.002050 0.001733 0.003783 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.003783 +%:RSB_SUBDIVISION_TIME:A.mtx S N 12 3 3 6 0.002050 +%:RSB_SHUFFLE_TIME:A.mtx S N 12 3 3 6 0.001733 %:ROW_MAJOR_SORT_TIME:A.mtx S N 12 3 3 6 0.000000 %:ROW_MAJOR_SORT_SCALING:A.mtx S N 12 3 3 6 nan -%:SORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.016231 +%:SORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.003783 %:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 12 3 3 6 0.000 %:UNSORTEDCOO2RSB_SCALING:A.mtx S N 12 3 3 6 1.00 %:SORTEDCOO2RSB_SCALING:A.mtx S N 12 3 3 6 1.00 @@ -4323,59 +4359,59 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 12 3 3 6 6 6 6 # %operation:matrix CONSTRUCTOR[12] SPMV[12] SPMV[12] -%operation:A.mtx 0.0232072 1e+09 1e+09 +%operation:A.mtx 0.00553012 1e+09 1e+09 %constructor:matrix SORT[12] SCAN[12] SHUFFLE[12] INSERT[12] -%constructor:A.mtx 0 0.00948811 0 0.00674295 +%constructor:A.mtx 0 0.00205016 0 0.00173283 # symmetric matrix --- skipping transposed benchmarking -# so far, program took 6.515s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 1.007s/0.000s . +# so far, program took 5.536s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.198s/0.000s . getrusage() stats: ru_maxrss: 6 (maximum resident set size -- MB) -ru_stime : 0.03448s (system CPU time used) -ru_utime : 6.422s (user CPU time used) +ru_stime : 0.04423s (system CPU time used) +ru_utime : 7.429s (user CPU time used) # multi-type benchmarking (DSCZ) -- now using typecode C (last was S). # Cache block size total 524288 bytes, per-thread 43690 bytes -# so far, program took 6.515s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 1.007s/0.000s . +# so far, program took 5.536s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.198s/0.000s . # Reusing type converted (S->C) arrays from last iteration instead of reloading matrix file. # multi-nrhs benchmarking (1,4) -- now using nrhs 1. # Using alpha=1 beta=1 order=rows for rsb_spmv/rsb_spsv/rsb_spmm/rsb_spsm. # multi-transpose benchmarking -- now using transA = N. # will use input matrix flags: RSB_FLAG_USE_HALFWORD_INDICES, RSB_FLAG_SORTED_INPUT, RSB_FLAG_QUAD_PARTITIONING, RSB_FLAG_SYMMETRIC, RSB_FLAG_OWN_PARTITIONING_ARRAYS # Using 12 threads -# Constructed matrix (took 0.024s): (3 x 3)[0xaaaae89aba00]{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 0.004s): (3 x 3)[0xaaaab77087a0]{C} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x2442186 (coo:1, csr:0, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'S' # matrix consistency check took 0.000s (ok) RSB Sparse Blocks Autotuner invoked requesting max 6 splits and max 6 merges in 1 rounds, threads spec.0 (specify negative values to enable threads tuning). Will autotune matrix: 3 x 3, type C, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:3 -3 iterations (12 th.) took 0.01807s; avg 0.006023s ( +/- 78.82/ 60.23 %); best 0.001276s; worst 0.009651s; std dev. 0.00351 (taking best). -Reference operation time is 0.00127602 s (0.07523 Mflops) with 12 threads. -Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=rows) (max 6 steps, inclusive 3 grace steps) on: 3 x 3, type C, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz (tpop: 0.001276 Mflops: 0.075) -Merge (3 -> 1 leaves) took w.c.t. of 1.597e-05s, ~5.007e-06s of computing time (of which 1.192e-06s sorting, 2.861e-06s analysis) -3 iterations (12 th.) took 0.0001011s; avg 3.37e-05s ( +/- 99.91/197.17 %); best 2.995e-08s; worst 0.0001001s; std dev. 4.698e-05 (taking best). -Reference operation time is 2.99454e-08 s (3206 Mflops) with 12 threads. -After merge step 1: tpop: 2.995e-08 s ~Mflops: 3205.837 nsubm:1 otn:12 -Applying merge (3 -> 1 leaves, 12 th.) yielded SPEEDUP of 42611.465x: 0.001276s -> 2.995e-08s, so taking this instance. +3 iterations (12 th.) took 0.001792s; avg 0.0005974s ( +/- 11.28/ 17.53 %); best 0.00053s; worst 0.0007021s; std dev. 7.507e-05 (taking best). +Reference operation time is 0.000530005 s (0.1811 Mflops) with 12 threads. +Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=rows) (max 6 steps, inclusive 3 grace steps) on: 3 x 3, type C, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz (tpop: 0.00053 Mflops: 0.181) +Merge (3 -> 1 leaves) took w.c.t. of 1.001e-05s, ~4.053e-06s of computing time (of which 9.537e-07s sorting, 2.146e-06s analysis) +3 iterations (12 th.) took 9.394e-05s; avg 3.131e-05s ( +/- 99.72/200.00 %); best 8.775e-08s; worst 9.394e-05s; std dev. 4.428e-05 (taking best). +Reference operation time is 8.775e-08 s (1094 Mflops) with 12 threads. +After merge step 1: tpop: 8.775e-08 s ~Mflops: 1094.018 nsubm:1 otn:12 +Applying merge (3 -> 1 leaves, 12 th.) yielded SPEEDUP of 6039.940x: 0.00053s -> 8.775e-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 0.006543s (of which 1.693e-05s partitioning, 0s I/O); computing times: 5.007e-06s in par. loops, 1.192e-06s sorting, 2.861e-06s analyzing) -Total merge + benchmarking process took 0.006543s, equivalent to 218495.2/5.1 new/old ops (0.019s for 2 clones -- as 634617.8/14.9 ops, or 317308.9/7.4 ops per clone), SPEEDUP of 42611.465x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 42611.465x (0.001276s -> 2.995e-08s), will amortize in 5.1 ops by saving 0.001276s per op. -In 1 tuning rounds (tot. 0.037s, 0.019s for constructor, 2 clones) obtained a SPEEDUP of 4261046.5% (4.261e+04x) (from 0.07523 to 3206 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.001684s (of which 1.216e-05s partitioning, 0s I/O); computing times: 4.053e-06s in par. loops, 9.537e-07s sorting, 2.146e-06s analyzing) +Total merge + benchmarking process took 0.001684s, equivalent to 19193.0/3.2 new/old ops (0.003181s for 2 clones -- as 36250.5/6.0 ops, or 18125.3/3.0 ops per clone), SPEEDUP of 6039.940x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 6039.940x (0.00053s -> 8.775e-08s), will amortize in 3.2 ops by saving 0.0005299s per op. +In 1 tuning rounds (tot. 0.0051s, 0.0032s for constructor, 2 clones) obtained a SPEEDUP of 603894.0% (6040x) (from 0.1811 to 1094 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 0.037261 s (1.276e-03 s -> 2.995e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.00512815 s (5.300e-04 s -> 8.775e-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 0.107543 s and estimated a speedup of 1.000000 x (2.995e-08 s -> 2.995e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.0280099 s and estimated a speedup of 1.000000 x (8.775e-08 s -> 8.775e-08 s per op) in same matrix (1 -> 1 lsubm) #min:1 0 #max:1 0 #sum:3 0 #norm:1.73205078 0 #used index storage compared to COO:28 vs 48 bytes (58.33%) ; compared to CSR:28 vs 40 bytes (77.78%) #%:CONSTRUCTOR_*:SORT SCAN INSERT SCAN+INSERT -%:CONSTRUCTOR_TIMES:A.mtx S N 12 3 3 6 0.000000 0.012013 0.008018 0.020031 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.020031 -%:RSB_SUBDIVISION_TIME:A.mtx S N 12 3 3 6 0.012013 -%:RSB_SHUFFLE_TIME:A.mtx S N 12 3 3 6 0.008018 +%:CONSTRUCTOR_TIMES:A.mtx S N 12 3 3 6 0.000000 0.001544 0.001445 0.002989 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.002989 +%:RSB_SUBDIVISION_TIME:A.mtx S N 12 3 3 6 0.001544 +%:RSB_SHUFFLE_TIME:A.mtx S N 12 3 3 6 0.001445 %:ROW_MAJOR_SORT_TIME:A.mtx S N 12 3 3 6 0.000000 %:ROW_MAJOR_SORT_SCALING:A.mtx S N 12 3 3 6 nan -%:SORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.020031 +%:SORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.002989 %:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 12 3 3 6 0.000 %:UNSORTEDCOO2RSB_SCALING:A.mtx S N 12 3 3 6 1.00 %:SORTEDCOO2RSB_SCALING:A.mtx S N 12 3 3 6 1.00 @@ -4390,50 +4426,50 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 12 3 3 6 6 6 6 # %operation:matrix CONSTRUCTOR[12] SPMV[12] SPMV[12] -%operation:A.mtx 0.0238149 1e+09 1e+09 +%operation:A.mtx 0.00411201 1e+09 1e+09 %constructor:matrix SORT[12] SCAN[12] SHUFFLE[12] INSERT[12] -%constructor:A.mtx 0 0.012013 0 0.00801802 +%constructor:A.mtx 0 0.001544 0 0.00144482 # symmetric matrix --- skipping transposed benchmarking # multi-nrhs benchmarking (1,4) -- now using nrhs 4. # Using alpha=1 beta=1 order=rows for rsb_spmv/rsb_spsv/rsb_spmm/rsb_spsm. # multi-transpose benchmarking -- now using transA = N. # will use input matrix flags: RSB_FLAG_USE_HALFWORD_INDICES, RSB_FLAG_SORTED_INPUT, RSB_FLAG_QUAD_PARTITIONING, RSB_FLAG_SYMMETRIC, RSB_FLAG_OWN_PARTITIONING_ARRAYS # Using 12 threads -# Constructed matrix (took 0.014s): (3 x 3)[0xaaaae89aba00]{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 0.003s): (3 x 3)[0xaaaab77087a0]{C} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x2442186 (coo:1, csr:0, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'S' # matrix consistency check took 0.000s (ok) RSB Sparse Blocks Autotuner invoked requesting max 6 splits and max 6 merges in 1 rounds, threads spec.0 (specify negative values to enable threads tuning). Will autotune matrix: 3 x 3, type C, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:3 -3 iterations (12 th.) took 0.01629s; avg 0.005432s ( +/- 28.35/ 47.27 %); best 0.003892s; worst 0.007999s; std dev. 0.001827 (taking best). -Reference operation time is 0.00389194 s (0.09867 Mflops) with 12 threads. -Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=4, order=rows) (max 6 steps, inclusive 3 grace steps) on: 3 x 3, type C, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz (tpop: 0.003892 Mflops: 0.099) -Merge (3 -> 1 leaves) took w.c.t. of 1.311e-05s, ~3.815e-06s of computing time (of which 9.537e-07s sorting, 3.099e-06s analysis) -3 iterations (12 th.) took 5.007e-06s; avg 1.669e-06s ( +/- 98.21/142.86 %); best 2.995e-08s; worst 4.053e-06s; std dev. 1.73e-06 (taking best). -Reference operation time is 2.99454e-08 s (1.282e+04 Mflops) with 12 threads. -After merge step 1: tpop: 2.995e-08 s ~Mflops: 12823.350 nsubm:1 otn:12 -Applying merge (3 -> 1 leaves, 12 th.) yielded SPEEDUP of 129968.153x: 0.003892s -> 2.995e-08s, so taking this instance. +3 iterations (12 th.) took 0.002039s; avg 0.0006797s ( +/- 30.41/ 57.56 %); best 0.000473s; worst 0.001071s; std dev. 0.0002768 (taking best). +Reference operation time is 0.000473022 s (0.8118 Mflops) with 12 threads. +Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=4, order=rows) (max 6 steps, inclusive 3 grace steps) on: 3 x 3, type C, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz (tpop: 0.000473 Mflops: 0.812) +Merge (3 -> 1 leaves) took w.c.t. of 7.868e-06s, ~3.099e-06s of computing time (of which 9.537e-07s sorting, 1.907e-06s analysis) +3 iterations (12 th.) took 2.861e-06s; avg 9.537e-07s ( +/- 90.80/100.00 %); best 8.775e-08s; worst 1.907e-06s; std dev. 7.787e-07 (taking best). +Reference operation time is 8.775e-08 s (4376 Mflops) with 12 threads. +After merge step 1: tpop: 8.775e-08 s ~Mflops: 4376.070 nsubm:1 otn:12 +Applying merge (3 -> 1 leaves, 12 th.) yielded SPEEDUP of 5390.572x: 0.000473s -> 8.775e-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 0.02031s (of which 1.502e-05s partitioning, 0s I/O); computing times: 3.815e-06s in par. loops, 9.537e-07s sorting, 3.099e-06s analyzing) -Total merge + benchmarking process took 0.02031s, equivalent to 678240.4/5.2 new/old ops (0.03784s for 2 clones -- as 1263535.0/9.7 ops, or 631767.5/4.9 ops per clone), SPEEDUP of 129968.153x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 129968.153x (0.003892s -> 2.995e-08s), will amortize in 5.2 ops by saving 0.003892s per op. -In 1 tuning rounds (tot. 0.054s, 0.038s for constructor, 2 clones) obtained a SPEEDUP of 12996715.3% (1.3e+05x) (from 0.09867 to 1.282e+04 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.001324s (of which 1.001e-05s partitioning, 0s I/O); computing times: 3.099e-06s in par. loops, 9.537e-07s sorting, 1.907e-06s analyzing) +Total merge + benchmarking process took 0.001324s, equivalent to 15087.6/2.8 new/old ops (0.002783s for 2 clones -- as 31713.1/5.9 ops, or 15856.5/2.9 ops per clone), SPEEDUP of 5390.572x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 5390.572x (0.000473s -> 8.775e-08s), will amortize in 2.8 ops by saving 0.0004729s per op. +In 1 tuning rounds (tot. 0.0049s, 0.0028s for constructor, 2 clones) obtained a SPEEDUP of 538957.2% (5391x) (from 0.8118 to 4376 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 0.0542209 s (3.892e-03 s -> 2.995e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.00487399 s (4.730e-04 s -> 8.775e-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 0.223762 s and estimated a speedup of 1.000000 x (2.995e-08 s -> 2.995e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.02159 s and estimated a speedup of 1.000000 x (8.775e-08 s -> 8.775e-08 s per op) in same matrix (1 -> 1 lsubm) #min:1 0 #max:1 0 #sum:3 0 #norm:1.73205078 0 #used index storage compared to COO:28 vs 48 bytes (58.33%) ; compared to CSR:28 vs 40 bytes (77.78%) #%:CONSTRUCTOR_*:SORT SCAN INSERT SCAN+INSERT -%:CONSTRUCTOR_TIMES:A.mtx S N 12 3 3 6 0.000000 0.005732 0.003683 0.009415 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.009415 -%:RSB_SUBDIVISION_TIME:A.mtx S N 12 3 3 6 0.005732 -%:RSB_SHUFFLE_TIME:A.mtx S N 12 3 3 6 0.003683 +%:CONSTRUCTOR_TIMES:A.mtx S N 12 3 3 6 0.000000 0.001115 0.001025 0.002140 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.002140 +%:RSB_SUBDIVISION_TIME:A.mtx S N 12 3 3 6 0.001115 +%:RSB_SHUFFLE_TIME:A.mtx S N 12 3 3 6 0.001025 %:ROW_MAJOR_SORT_TIME:A.mtx S N 12 3 3 6 0.000000 %:ROW_MAJOR_SORT_SCALING:A.mtx S N 12 3 3 6 nan -%:SORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.009415 +%:SORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.002140 %:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 12 3 3 6 0.000 %:UNSORTEDCOO2RSB_SCALING:A.mtx S N 12 3 3 6 1.00 %:SORTEDCOO2RSB_SCALING:A.mtx S N 12 3 3 6 1.00 @@ -4448,59 +4484,59 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 12 3 3 6 6 6 6 # %operation:matrix CONSTRUCTOR[12] SPMV[12] SPMV[12] -%operation:A.mtx 0.014308 1e+09 1e+09 +%operation:A.mtx 0.00314808 1e+09 1e+09 %constructor:matrix SORT[12] SCAN[12] SHUFFLE[12] INSERT[12] -%constructor:A.mtx 0 0.00573206 0 0.00368309 +%constructor:A.mtx 0 0.00111508 0 0.00102496 # symmetric matrix --- skipping transposed benchmarking -# so far, program took 7.008s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 1.430s/0.000s . +# so far, program took 5.608s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.258s/0.000s . getrusage() stats: ru_maxrss: 6 (maximum resident set size -- MB) -ru_stime : 0.04425s (system CPU time used) -ru_utime : 7.054s (user CPU time used) +ru_stime : 0.05223s (system CPU time used) +ru_utime : 8.088s (user CPU time used) # multi-type benchmarking (DSCZ) -- now using typecode Z (last was C). # Cache block size total 524288 bytes, per-thread 43690 bytes -# so far, program took 7.008s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 1.430s/0.000s . +# so far, program took 5.608s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.258s/0.000s . # Reusing type converted (C->Z) arrays from last iteration instead of reloading matrix file. # multi-nrhs benchmarking (1,4) -- now using nrhs 1. # Using alpha=1 beta=1 order=rows for rsb_spmv/rsb_spsv/rsb_spmm/rsb_spsm. # multi-transpose benchmarking -- now using transA = N. # will use input matrix flags: RSB_FLAG_USE_HALFWORD_INDICES, RSB_FLAG_SORTED_INPUT, RSB_FLAG_QUAD_PARTITIONING, RSB_FLAG_SYMMETRIC, RSB_FLAG_OWN_PARTITIONING_ARRAYS # Using 12 threads -# Constructed matrix (took 0.032s): (3 x 3)[0xaaaae89aba00]{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 0.003s): (3 x 3)[0xaaaab77087a0]{Z} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x2442186 (coo:1, csr:0, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'S' # matrix consistency check took 0.000s (ok) RSB Sparse Blocks Autotuner invoked requesting max 6 splits and max 6 merges in 1 rounds, threads spec.0 (specify negative values to enable threads tuning). Will autotune matrix: 3 x 3, type Z, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:3 -3 iterations (12 th.) took 0.01554s; avg 0.005182s ( +/- 59.88/ 34.14 %); best 0.002079s; worst 0.006951s; std dev. 0.002201 (taking best). -Reference operation time is 0.00207901 s (0.04618 Mflops) with 12 threads. -Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=rows) (max 6 steps, inclusive 3 grace steps) on: 3 x 3, type Z, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz (tpop: 0.002079 Mflops: 0.046) -Merge (3 -> 1 leaves) took w.c.t. of 1.407e-05s, ~5.007e-06s of computing time (of which 9.537e-07s sorting, 4.053e-06s analysis) -3 iterations (12 th.) took 1.884e-05s; avg 6.278e-06s ( +/- 99.52/200.00 %); best 2.995e-08s; worst 1.884e-05s; std dev. 8.879e-06 (taking best). -Reference operation time is 2.99454e-08 s (3206 Mflops) with 12 threads. -After merge step 1: tpop: 2.995e-08 s ~Mflops: 3205.837 nsubm:1 otn:12 -Applying merge (3 -> 1 leaves, 12 th.) yielded SPEEDUP of 69426.752x: 0.002079s -> 2.995e-08s, so taking this instance. +3 iterations (12 th.) took 0.00219s; avg 0.00073s ( +/- 39.75/ 23.58 %); best 0.0004399s; worst 0.0009022s; std dev. 0.0002064 (taking best). +Reference operation time is 0.000439882 s (0.2182 Mflops) with 12 threads. +Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=rows) (max 6 steps, inclusive 3 grace steps) on: 3 x 3, type Z, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz (tpop: 0.0004399 Mflops: 0.218) +Merge (3 -> 1 leaves) took w.c.t. of 5.007e-06s, ~1.907e-06s of computing time (of which 0s sorting, 1.192e-06s analysis) +3 iterations (12 th.) took 1.001e-05s; avg 3.338e-06s ( +/- 97.37/164.29 %); best 8.775e-08s; worst 8.821e-06s; std dev. 3.908e-06 (taking best). +Reference operation time is 8.775e-08 s (1094 Mflops) with 12 threads. +After merge step 1: tpop: 8.775e-08 s ~Mflops: 1094.018 nsubm:1 otn:12 +Applying merge (3 -> 1 leaves, 12 th.) yielded SPEEDUP of 5012.906x: 0.0004399s -> 8.775e-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 0.009038s (of which 1.597e-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 0.009038s, equivalent to 301815.3/4.3 new/old ops (0.01783s for 2 clones -- as 595286.6/8.6 ops, or 297643.3/4.3 ops per clone), SPEEDUP of 69426.752x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 69426.752x (0.002079s -> 2.995e-08s), will amortize in 4.3 ops by saving 0.002079s per op. -In 1 tuning rounds (tot. 0.033s, 0.018s for constructor, 2 clones) obtained a SPEEDUP of 6942575.2% (6.943e+04x) (from 0.04618 to 3206 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.001233s (of which 7.153e-06s partitioning, 0s I/O); computing times: 1.907e-06s in par. loops, 0s sorting, 1.192e-06s analyzing) +Total merge + benchmarking process took 0.001233s, equivalent to 14052.4/2.8 new/old ops (0.002428s for 2 clones -- as 27670.2/5.5 ops, or 13835.1/2.8 ops per clone), SPEEDUP of 5012.906x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 5012.906x (0.0004399s -> 8.775e-08s), will amortize in 2.8 ops by saving 0.0004398s per op. +In 1 tuning rounds (tot. 0.0047s, 0.0024s for constructor, 2 clones) obtained a SPEEDUP of 501190.6% (5013x) (from 0.2182 to 1094 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 0.0334718 s (2.079e-03 s -> 2.995e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.00466299 s (4.399e-04 s -> 8.775e-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 0.237029 s and estimated a speedup of 1.000000 x (2.995e-08 s -> 2.995e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.0213809 s and estimated a speedup of 1.000000 x (8.775e-08 s -> 8.775e-08 s per op) in same matrix (1 -> 1 lsubm) #min:1 0 #max:1 0 #sum:3 0 #norm:1.7320508075688772 0 #used index storage compared to COO:28 vs 48 bytes (58.33%) ; compared to CSR:28 vs 40 bytes (77.78%) #%:CONSTRUCTOR_*:SORT SCAN INSERT SCAN+INSERT -%:CONSTRUCTOR_TIMES:A.mtx S N 12 3 3 6 0.000000 0.009157 0.013944 0.023101 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.023101 -%:RSB_SUBDIVISION_TIME:A.mtx S N 12 3 3 6 0.009157 -%:RSB_SHUFFLE_TIME:A.mtx S N 12 3 3 6 0.013944 +%:CONSTRUCTOR_TIMES:A.mtx S N 12 3 3 6 0.000000 0.000873 0.000853 0.001726 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.001726 +%:RSB_SUBDIVISION_TIME:A.mtx S N 12 3 3 6 0.000873 +%:RSB_SHUFFLE_TIME:A.mtx S N 12 3 3 6 0.000853 %:ROW_MAJOR_SORT_TIME:A.mtx S N 12 3 3 6 0.000000 %:ROW_MAJOR_SORT_SCALING:A.mtx S N 12 3 3 6 nan -%:SORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.023101 +%:SORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.001726 %:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 12 3 3 6 0.000 %:UNSORTEDCOO2RSB_SCALING:A.mtx S N 12 3 3 6 1.00 %:SORTEDCOO2RSB_SCALING:A.mtx S N 12 3 3 6 1.00 @@ -4515,50 +4551,50 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 12 3 3 6 6 6 6 # %operation:matrix CONSTRUCTOR[12] SPMV[12] SPMV[12] -%operation:A.mtx 0.031925 1e+09 1e+09 +%operation:A.mtx 0.00255704 1e+09 1e+09 %constructor:matrix SORT[12] SCAN[12] SHUFFLE[12] INSERT[12] -%constructor:A.mtx 0 0.00915718 0 0.0139439 +%constructor:A.mtx 0 0.000873089 0 0.000853062 # symmetric matrix --- skipping transposed benchmarking # multi-nrhs benchmarking (1,4) -- now using nrhs 4. # Using alpha=1 beta=1 order=rows for rsb_spmv/rsb_spsv/rsb_spmm/rsb_spsm. # multi-transpose benchmarking -- now using transA = N. # will use input matrix flags: RSB_FLAG_USE_HALFWORD_INDICES, RSB_FLAG_SORTED_INPUT, RSB_FLAG_QUAD_PARTITIONING, RSB_FLAG_SYMMETRIC, RSB_FLAG_OWN_PARTITIONING_ARRAYS # Using 12 threads -# Constructed matrix (took 0.006s): (3 x 3)[0xaaaae89ad520]{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 0.004s): (3 x 3)[0xaaaab7709500]{Z} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x2442186 (coo:1, csr:0, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'S' # matrix consistency check took 0.000s (ok) RSB Sparse Blocks Autotuner invoked requesting max 6 splits and max 6 merges in 1 rounds, threads spec.0 (specify negative values to enable threads tuning). Will autotune matrix: 3 x 3, type Z, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:3 -3 iterations (12 th.) took 0.02442s; avg 0.008141s ( +/- 1.71/ 3.35 %); best 0.008002s; worst 0.008414s; std dev. 0.0001927 (taking best). -Reference operation time is 0.00800204 s (0.04799 Mflops) with 12 threads. -Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=4, order=rows) (max 6 steps, inclusive 3 grace steps) on: 3 x 3, type Z, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz (tpop: 0.008002 Mflops: 0.048) -Merge (3 -> 1 leaves) took w.c.t. of 1.407e-05s, ~4.053e-06s of computing time (of which 9.537e-07s sorting, 4.053e-06s analysis) -3 iterations (12 th.) took 5.007e-06s; avg 1.669e-06s ( +/- 98.21/200.00 %); best 2.995e-08s; worst 5.007e-06s; std dev. 2.36e-06 (taking best). -Reference operation time is 2.99454e-08 s (1.282e+04 Mflops) with 12 threads. -After merge step 1: tpop: 2.995e-08 s ~Mflops: 12823.350 nsubm:1 otn:12 -Applying merge (3 -> 1 leaves, 12 th.) yielded SPEEDUP of 267221.338x: 0.008002s -> 2.995e-08s, so taking this instance. +3 iterations (12 th.) took 0.001272s; avg 0.000424s ( +/- 5.19/ 3.30 %); best 0.000402s; worst 0.000438s; std dev. 1.576e-05 (taking best). +Reference operation time is 0.000401974 s (0.9553 Mflops) with 12 threads. +Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=4, order=rows) (max 6 steps, inclusive 3 grace steps) on: 3 x 3, type Z, 6 nnz, 2 nnz/r, 4 subms, 3 lsubms, 4.0000 bpnz (tpop: 0.000402 Mflops: 0.955) +Merge (3 -> 1 leaves) took w.c.t. of 5.007e-06s, ~1.907e-06s of computing time (of which 0s sorting, 9.537e-07s analysis) +3 iterations (12 th.) took 4.053e-06s; avg 1.351e-06s ( +/- 93.50/129.41 %); best 8.775e-08s; worst 3.099e-06s; std dev. 1.296e-06 (taking best). +Reference operation time is 8.775e-08 s (4376 Mflops) with 12 threads. +After merge step 1: tpop: 8.775e-08 s ~Mflops: 4376.070 nsubm:1 otn:12 +Applying merge (3 -> 1 leaves, 12 th.) yielded SPEEDUP of 4580.899x: 0.000402s -> 8.775e-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 0.02395s (of which 1.502e-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 0.02395s, equivalent to 799888.5/3.0 new/old ops (0.04024s for 2 clones -- as 1343686.3/5.0 ops, or 671843.2/2.5 ops per clone), SPEEDUP of 267221.338x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 267221.338x (0.008002s -> 2.995e-08s), will amortize in 3.0 ops by saving 0.008002s per op. -In 1 tuning rounds (tot. 0.065s, 0.04s for constructor, 2 clones) obtained a SPEEDUP of 26722033.8% (2.672e+05x) (from 0.04799 to 1.282e+04 Mflops). +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.001281s (of which 8.106e-06s partitioning, 0s I/O); computing times: 1.907e-06s in par. loops, 0s sorting, 9.537e-07s analyzing) +Total merge + benchmarking process took 0.001281s, equivalent to 14598.6/3.2 new/old ops (0.002532s for 2 clones -- as 28854.8/6.3 ops, or 14427.4/3.1 ops per clone), SPEEDUP of 4580.899x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 4580.899x (0.000402s -> 8.775e-08s), will amortize in 3.2 ops by saving 0.0004019s per op. +In 1 tuning rounds (tot. 0.0038s, 0.0025s for constructor, 2 clones) obtained a SPEEDUP of 457989.9% (4581x) (from 0.9553 to 4376 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 0.064764 s (8.002e-03 s -> 2.995e-08 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.00392103 s (4.020e-04 s -> 8.775e-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 0.24799 s and estimated a speedup of 1.000000 x (2.995e-08 s -> 2.995e-08 s per op) in same matrix (1 -> 1 lsubm) +Second run of RSB Autotuner took 0.021116 s and estimated a speedup of 1.000000 x (8.775e-08 s -> 8.775e-08 s per op) in same matrix (1 -> 1 lsubm) #min:1 0 #max:1 0 #sum:3 0 #norm:1.7320508075688772 0 #used index storage compared to COO:28 vs 48 bytes (58.33%) ; compared to CSR:28 vs 40 bytes (77.78%) #%:CONSTRUCTOR_*:SORT SCAN INSERT SCAN+INSERT -%:CONSTRUCTOR_TIMES:A.mtx S N 12 3 3 6 0.000000 0.000886 0.000842 0.001728 -%:UNSORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.001728 -%:RSB_SUBDIVISION_TIME:A.mtx S N 12 3 3 6 0.000886 -%:RSB_SHUFFLE_TIME:A.mtx S N 12 3 3 6 0.000842 +%:CONSTRUCTOR_TIMES:A.mtx S N 12 3 3 6 0.000000 0.001003 0.000862 0.001865 +%:UNSORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.001865 +%:RSB_SUBDIVISION_TIME:A.mtx S N 12 3 3 6 0.001003 +%:RSB_SHUFFLE_TIME:A.mtx S N 12 3 3 6 0.000862 %:ROW_MAJOR_SORT_TIME:A.mtx S N 12 3 3 6 0.000000 %:ROW_MAJOR_SORT_SCALING:A.mtx S N 12 3 3 6 nan -%:SORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.001728 +%:SORTEDCOO2RSB_TIME:A.mtx S N 12 3 3 6 0.001865 %:ROW_MAJOR_SORT_TO_MOP:A.mtx S N 12 3 3 6 0.000 %:UNSORTEDCOO2RSB_SCALING:A.mtx S N 12 3 3 6 1.00 %:SORTEDCOO2RSB_SCALING:A.mtx S N 12 3 3 6 1.00 @@ -4573,332 +4609,332 @@ %:SM_MINMAXAVGNNZ:A.mtx S N 12 3 3 6 6 6 6 # %operation:matrix CONSTRUCTOR[12] SPMV[12] SPMV[12] -%operation:A.mtx 0.00623298 1e+09 1e+09 +%operation:A.mtx 0.00352383 1e+09 1e+09 %constructor:matrix SORT[12] SCAN[12] SHUFFLE[12] INSERT[12] -%constructor:A.mtx 0 0.000885963 0 0.000842094 +%constructor:A.mtx 0 0.00100303 0 0.000861883 # symmetric matrix --- skipping transposed benchmarking -# so far, program took 7.676s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 2.013s/0.000s . +# so far, program took 5.671s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.309s/0.000s . getrusage() stats: ru_maxrss: 6 (maximum resident set size -- MB) -ru_stime : 0.04772s (system CPU time used) -ru_utime : 7.655s (user CPU time used) +ru_stime : 0.05638s (system CPU time used) +ru_utime : 8.681s (user CPU time used) # benchmarking terminated --- finalizing run. # ====== BEGIN Total summary record. #pr: ======== Limiting to type D: #pr: 2 samples (out of 8) matched the dump limiting criteria. #pr: Dump from a base of 8 samples (of max 16) ordered by (1,1,1,1,2,4,2) = (filename x cores x incX x incY x nrhs x typecode x transA). pr: BESTCODE MTX NR NC NNZ NRHS TYPE SYM TRANS NT AT-NT AT-MKL-NT BPNZ AT-BPNZ NSUBM AT-SUBM RSBBEST-MFLOPS OPTIME MKL-OPTIME AT-OPTIME AT-MKL-OPTIME AT-TIME RWminBW-GBps CB-bpf AT-MS CMFLOPS -pr: 1:R_R A 3 3 6 1 D S N 12 12 0 4.0000 4.6667 3 1 801.46 4.485e-03 0.000e+00 2.995e-08 0.000e+00 5.763e-02 4.94e+00 5.17e+00 1 2.40e-05 -pr: 9:R_R A 3 3 6 4 D S N 12 12 0 4.0000 4.6667 3 1 3205.84 4.446e-03 0.000e+00 2.995e-08 0.000e+00 4.541e-02 1.22e+01 2.79e+00 1 9.60e-05 +pr: 1:R_R A 3 3 6 1 D S N 12 12 0 4.0000 4.6667 3 1 273.50 6.249e-04 0.000e+00 8.775e-08 0.000e+00 1.146e-02 1.69e+00 5.17e+00 1 2.40e-05 +pr: 9:R_R A 3 3 6 4 D S N 12 12 0 4.0000 4.6667 3 1 1094.02 1.053e-03 0.000e+00 8.775e-08 0.000e+00 9.477e-03 4.15e+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. 14911922.3 % faster, avg. sp. ratio 149120.223x, max sp. ratio 149769.108x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 1720449.8/1516361.5/1924538.2/3440899.7 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 11.5/ 10.2/ 12.9/ 23.1 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 11.5, min. 10.2, max. 12.9 ops) +#pr: (in succ. cases rsb autotuning gave avg. 956020.1 % faster, avg. sp. ratio 9561.201x, max sp. ratio 12001.087x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 119293.6/107998.9/130588.2/238587.1 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 13.7/ 9.0/ 18.3/ 27.3 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 13.7, min. 9.0, max. 18.3 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 16/ 16/ 16) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 48/ 48/ 48) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 6.545/ 4.141/ 8.950,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 17.098/ 4.942/ 12.155,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 2.234/ 1.413/ 3.054,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 5.835/ 1.687/ 4.148,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.: 0.05 s, min 0.05 s, max 0.06 s, tot 0.10 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.05 s, min 0.05 s, max 0.06 s, tot 0.10 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 2.004e+03, min 8.015e+02, max 3.206e+03 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 1.347e-02, min 5.351e-03, max 2.159e-02 (2 samples) -#pr: best tun. rsb operation time was: on avg. 2.995e-08s, min 2.995e-08s, max 2.995e-08s, tot 5.989e-08s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 4.465e-03s, min 4.446e-03s, max 4.485e-03s, tot 8.931e-03s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 5.317e+00 1.149e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.004e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.01 s, min 0.01 s, max 0.01 s, tot 0.02 s (2 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.01 s, min 0.01 s, max 0.01 s, tot 0.02 s (2 samples) +#pr: best tun. rsb canon. mflops were: on avg. 6.838e+02, min 2.735e+02, max 1.094e+03 (2 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 6.478e-02, min 3.841e-02, max 9.116e-02 (2 samples) +#pr: best tun. rsb operation time was: on avg. 8.775e-08s, min 8.775e-08s, max 8.775e-08s, tot 1.755e-07s (2 samples) +#pr: ref. unt. rsb operation time was: on avg. 8.390e-04s, min 6.249e-04s, max 1.053e-03s, tot 1.678e-03s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.567e+01 3.386e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 9.983e-01 #pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 4.000e+00 x, min 4.000e+00 x, max 4.000e+00 x (1 samples, the non-min-nrhs ones) #pr: ======== Limiting to type S: #pr: 2 samples (out of 8) matched the dump limiting criteria. #pr: Dump from a base of 8 samples (of max 16) ordered by (1,1,1,1,2,4,2) = (filename x cores x incX x incY x nrhs x typecode x transA). pr: BESTCODE MTX NR NC NNZ NRHS TYPE SYM TRANS NT AT-NT AT-MKL-NT BPNZ AT-BPNZ NSUBM AT-SUBM RSBBEST-MFLOPS OPTIME MKL-OPTIME AT-OPTIME AT-MKL-OPTIME AT-TIME RWminBW-GBps CB-bpf AT-MS CMFLOPS -pr: 3:R_R A 3 3 6 1 S S N 12 12 0 4.0000 4.6667 3 1 801.46 6.380e-03 0.000e+00 2.995e-08 0.000e+00 7.264e-02 2.94e+00 3.17e+00 1 2.40e-05 -pr: 11:R_R A 3 3 6 4 S S N 12 12 0 4.0000 4.6667 3 1 3205.84 2.469e-03 0.000e+00 2.995e-08 0.000e+00 4.032e-02 6.55e+00 1.54e+00 1 9.60e-05 +pr: 3:R_R A 3 3 6 1 S S N 12 12 0 4.0000 4.6667 3 1 273.50 8.252e-04 0.000e+00 8.775e-08 0.000e+00 7.836e-03 1.00e+00 3.17e+00 1 2.40e-05 +pr: 11:R_R A 3 3 6 4 S S N 12 12 0 4.0000 4.6667 3 1 1094.02 8.090e-04 0.000e+00 8.775e-08 0.000e+00 8.878e-03 2.23e+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. 14774979.6 % faster, avg. sp. ratio 147750.796x, max sp. ratio 213049.363x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 1886202.2/1346552.5/2425851.9/3772404.5 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 13.9/ 11.4/ 16.3/ 27.7 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 13.9, min. 11.4, max. 16.3 ops) +#pr: (in succ. cases rsb autotuning gave avg. 931023.5 % faster, avg. sp. ratio 9311.235x, max sp. ratio 9403.614x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 95237.1/89300.4/101173.8/190474.1 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 10.2/ 9.5/ 11.0/ 20.5 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 10.2, min. 9.5, max. 11.0 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 8/ 8/ 8) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 24/ 24/ 24) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 3.740/ 2.538/ 4.942,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 9.484/ 2.939/ 6.545,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 1.276/ 0.866/ 1.687,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 3.236/ 1.003/ 2.234,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.: 0.06 s, min 0.04 s, max 0.07 s, tot 0.11 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.06 s, min 0.04 s, max 0.07 s, tot 0.11 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 2.004e+03, min 8.015e+02, max 3.206e+03 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 2.132e-02, min 3.762e-03, max 3.888e-02 (2 samples) -#pr: best tun. rsb operation time was: on avg. 2.995e-08s, min 2.995e-08s, max 2.995e-08s, tot 5.989e-08s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 4.424e-03s, min 2.469e-03s, max 6.380e-03s, tot 8.849e-03s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 9.629e+00 1.875e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.004e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.01 s, min 0.01 s, max 0.01 s, tot 0.02 s (2 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.01 s, min 0.01 s, max 0.01 s, tot 0.02 s (2 samples) +#pr: best tun. rsb canon. mflops were: on avg. 6.838e+02, min 2.735e+02, max 1.094e+03 (2 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 7.388e-02, min 2.909e-02, max 1.187e-01 (2 samples) +#pr: best tun. rsb operation time was: on avg. 8.775e-08s, min 8.775e-08s, max 8.775e-08s, tot 1.755e-07s (2 samples) +#pr: ref. unt. rsb operation time was: on avg. 8.171e-04s, min 8.090e-04s, max 8.252e-04s, tot 1.634e-03s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 2.837e+01 5.525e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 9.983e-01 #pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 4.000e+00 x, min 4.000e+00 x, max 4.000e+00 x (1 samples, the non-min-nrhs ones) #pr: ======== Limiting to type C: #pr: 2 samples (out of 8) matched the dump limiting criteria. #pr: Dump from a base of 8 samples (of max 16) ordered by (1,1,1,1,2,4,2) = (filename x cores x incX x incY x nrhs x typecode x transA). pr: BESTCODE MTX NR NC NNZ NRHS TYPE SYM TRANS NT AT-NT AT-MKL-NT BPNZ AT-BPNZ NSUBM AT-SUBM RSBBEST-MFLOPS OPTIME MKL-OPTIME AT-OPTIME AT-MKL-OPTIME AT-TIME RWminBW-GBps CB-bpf AT-MS CMFLOPS -pr: 5:R_R A 3 3 6 1 C S N 12 12 0 4.0000 4.6667 3 1 3205.84 1.276e-03 0.000e+00 2.995e-08 0.000e+00 3.726e-02 4.94e+00 1.29e+00 1 9.60e-05 -pr: 13:R_R A 3 3 6 4 C S N 12 12 0 4.0000 4.6667 3 1 12823.35 3.892e-03 0.000e+00 2.995e-08 0.000e+00 5.422e-02 1.22e+01 6.98e-01 1 3.84e-04 +pr: 5:R_R A 3 3 6 1 C S N 12 12 0 4.0000 4.6667 3 1 1094.02 5.300e-04 0.000e+00 8.775e-08 0.000e+00 5.128e-03 1.69e+00 1.29e+00 1 9.60e-05 +pr: 13:R_R A 3 3 6 4 C S N 12 12 0 4.0000 4.6667 3 1 4376.07 4.730e-04 0.000e+00 8.775e-08 0.000e+00 4.874e-03 4.15e+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. 8628880.9 % faster, avg. sp. ratio 86289.809x, max sp. ratio 129968.153x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 1527480.1/1244299.4/1810660.8/3054960.2 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 21.6/ 13.9/ 29.2/ 43.1 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 21.6, min. 13.9, max. 29.2 ops) +#pr: (in succ. cases rsb autotuning gave avg. 571425.6 % faster, avg. sp. ratio 5715.256x, max sp. ratio 6039.940x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 56992.3/55544.1/58440.4/113984.5 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 10.0/ 9.7/ 10.3/ 20.0 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 10.0, min. 9.7, max. 10.3 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 16/ 16/ 16) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 48/ 48/ 48) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 6.545/ 4.141/ 8.950,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 17.098/ 4.942/ 12.155,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 2.234/ 1.413/ 3.054,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 5.835/ 1.687/ 4.148,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.: 0.05 s, min 0.04 s, max 0.05 s, tot 0.09 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.05 s, min 0.04 s, max 0.05 s, tot 0.09 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 8.015e+03, min 3.206e+03, max 1.282e+04 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 8.695e-02, min 7.523e-02, max 9.867e-02 (2 samples) -#pr: best tun. rsb operation time was: on avg. 2.995e-08s, min 2.995e-08s, max 2.995e-08s, tot 5.989e-08s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 2.584e-03s, min 1.276e-03s, max 3.892e-03s, tot 5.168e-03s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 5.317e+00 1.149e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.004e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.01 s, min 0.00 s, max 0.01 s, tot 0.01 s (2 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.01 s, min 0.00 s, max 0.01 s, tot 0.01 s (2 samples) +#pr: best tun. rsb canon. mflops were: on avg. 2.735e+03, min 1.094e+03, max 4.376e+03 (2 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 4.965e-01, min 1.811e-01, max 8.118e-01 (2 samples) +#pr: best tun. rsb operation time was: on avg. 8.775e-08s, min 8.775e-08s, max 8.775e-08s, tot 1.755e-07s (2 samples) +#pr: ref. unt. rsb operation time was: on avg. 5.015e-04s, min 4.730e-04s, max 5.300e-04s, tot 1.003e-03s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.567e+01 3.386e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 9.983e-01 #pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 4.000e+00 x, min 4.000e+00 x, max 4.000e+00 x (1 samples, the non-min-nrhs ones) #pr: ======== Limiting to type Z: #pr: 2 samples (out of 8) matched the dump limiting criteria. #pr: Dump from a base of 8 samples (of max 16) ordered by (1,1,1,1,2,4,2) = (filename x cores x incX x incY x nrhs x typecode x transA). pr: BESTCODE MTX NR NC NNZ NRHS TYPE SYM TRANS NT AT-NT AT-MKL-NT BPNZ AT-BPNZ NSUBM AT-SUBM RSBBEST-MFLOPS OPTIME MKL-OPTIME AT-OPTIME AT-MKL-OPTIME AT-TIME RWminBW-GBps CB-bpf AT-MS CMFLOPS -pr: 7:R_R A 3 3 6 1 Z S N 12 12 0 4.0000 4.6667 3 1 3205.84 2.079e-03 0.000e+00 2.995e-08 0.000e+00 3.347e-02 8.95e+00 2.29e+00 1 9.60e-05 -pr: 15:R_R A 3 3 6 4 Z S N 12 12 0 4.0000 4.6667 3 1 12823.35 8.002e-03 0.000e+00 2.995e-08 0.000e+00 6.476e-02 2.34e+01 1.32e+00 1 3.84e-04 +pr: 7:R_R A 3 3 6 1 Z S N 12 12 0 4.0000 4.6667 3 1 1094.02 4.399e-04 0.000e+00 8.775e-08 0.000e+00 4.663e-03 3.05e+00 2.29e+00 1 9.60e-05 +pr: 15:R_R A 3 3 6 4 Z S N 12 12 0 4.0000 4.6667 3 1 4376.07 4.020e-04 0.000e+00 8.775e-08 0.000e+00 3.921e-03 7.98e+00 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. 16832304.5 % faster, avg. sp. ratio 168324.045x, max sp. ratio 267221.338x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 1640250.8/1117762.7/2162738.9/3280501.6 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 12.1/ 8.1/ 16.1/ 24.2 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 12.1, min. 8.1, max. 16.1 ops) +#pr: (in succ. cases rsb autotuning gave avg. 479590.3 % faster, avg. sp. ratio 4796.903x, max sp. ratio 5012.906x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 48911.8/44684.1/53139.5/97823.7 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 10.2/ 9.8/ 10.6/ 20.4 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 10.2, min. 9.8, max. 10.6 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 12.155/ 7.347/ 16.964,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 32.326/ 8.950/ 23.376,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 4.148/ 2.507/ 5.789,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 11.031/ 3.054/ 7.977,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.: 0.05 s, min 0.03 s, max 0.06 s, tot 0.10 s (2 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.05 s, min 0.03 s, max 0.06 s, tot 0.10 s (2 samples) -#pr: best tun. rsb canon. mflops were: on avg. 8.015e+03, min 3.206e+03, max 1.282e+04 (2 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 4.708e-02, min 4.618e-02, max 4.799e-02 (2 samples) -#pr: best tun. rsb operation time was: on avg. 2.995e-08s, min 2.995e-08s, max 2.995e-08s, tot 5.989e-08s (2 samples) -#pr: ref. unt. rsb operation time was: on avg. 5.041e-03s, min 2.079e-03s, max 8.002e-03s, tot 1.008e-02s (2 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 2.805e+00 6.478e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.004e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.00 s, min 0.00 s, max 0.00 s, tot 0.01 s (2 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.00 s, min 0.00 s, max 0.00 s, tot 0.01 s (2 samples) +#pr: best tun. rsb canon. mflops were: on avg. 2.735e+03, min 1.094e+03, max 4.376e+03 (2 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 5.868e-01, min 2.182e-01, max 9.553e-01 (2 samples) +#pr: best tun. rsb operation time was: on avg. 8.775e-08s, min 8.775e-08s, max 8.775e-08s, tot 1.755e-07s (2 samples) +#pr: ref. unt. rsb operation time was: on avg. 4.209e-04s, min 4.020e-04s, max 4.399e-04s, tot 8.419e-04s (2 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 8.266e+00 1.909e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 9.983e-01 #pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 4.000e+00 x, min 4.000e+00 x, max 4.000e+00 x (1 samples, the non-min-nrhs ones) #pr: ======== Limiting to nrhs=1: #pr: 4 samples (out of 8) matched the dump limiting criteria. #pr: Dump from a base of 8 samples (of max 16) ordered by (1,1,1,1,2,4,2) = (filename x cores x incX x incY x nrhs x typecode x transA). pr: BESTCODE MTX NR NC NNZ NRHS TYPE SYM TRANS NT AT-NT AT-MKL-NT BPNZ AT-BPNZ NSUBM AT-SUBM RSBBEST-MFLOPS OPTIME MKL-OPTIME AT-OPTIME AT-MKL-OPTIME AT-TIME RWminBW-GBps CB-bpf AT-MS CMFLOPS -pr: 1:R_R A 3 3 6 1 D S N 12 12 0 4.0000 4.6667 3 1 801.46 4.485e-03 0.000e+00 2.995e-08 0.000e+00 5.763e-02 4.94e+00 5.17e+00 1 2.40e-05 -pr: 3:R_R A 3 3 6 1 S S N 12 12 0 4.0000 4.6667 3 1 801.46 6.380e-03 0.000e+00 2.995e-08 0.000e+00 7.264e-02 2.94e+00 3.17e+00 1 2.40e-05 -pr: 5:R_R A 3 3 6 1 C S N 12 12 0 4.0000 4.6667 3 1 3205.84 1.276e-03 0.000e+00 2.995e-08 0.000e+00 3.726e-02 4.94e+00 1.29e+00 1 9.60e-05 -pr: 7:R_R A 3 3 6 1 Z S N 12 12 0 4.0000 4.6667 3 1 3205.84 2.079e-03 0.000e+00 2.995e-08 0.000e+00 3.347e-02 8.95e+00 2.29e+00 1 9.60e-05 +pr: 1:R_R A 3 3 6 1 D S N 12 12 0 4.0000 4.6667 3 1 273.50 6.249e-04 0.000e+00 8.775e-08 0.000e+00 1.146e-02 1.69e+00 5.17e+00 1 2.40e-05 +pr: 3:R_R A 3 3 6 1 S S N 12 12 0 4.0000 4.6667 3 1 273.50 8.252e-04 0.000e+00 8.775e-08 0.000e+00 7.836e-03 1.00e+00 3.17e+00 1 2.40e-05 +pr: 5:R_R A 3 3 6 1 C S N 12 12 0 4.0000 4.6667 3 1 1094.02 5.300e-04 0.000e+00 8.775e-08 0.000e+00 5.128e-03 1.69e+00 1.29e+00 1 9.60e-05 +pr: 7:R_R A 3 3 6 1 Z S N 12 12 0 4.0000 4.6667 3 1 1094.02 4.399e-04 0.000e+00 8.775e-08 0.000e+00 4.663e-03 3.05e+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. 11871317.2 % faster, avg. sp. ratio 118714.172x, max sp. ratio 213049.363x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 1678113.1/1117762.7/2425851.9/6712452.2 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 17.4/ 11.4/ 29.2/ 69.5 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 17.4, min. 11.4, max. 29.2 ops) +#pr: (in succ. cases rsb autotuning gave avg. 689344.4 % faster, avg. sp. ratio 6894.444x, max sp. ratio 9403.614x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 82867.1/53139.5/130588.2/331468.6 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 12.0/ 9.5/ 18.3/ 48.1 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 12.0, min. 9.5, max. 18.3 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 18/ 8/ 32) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 54/ 24/ 96) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 4.542/ 2.538/ 7.347,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 21.773/ 2.939/ 8.950,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 1.550/ 0.866/ 2.507,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 7.430/ 1.003/ 3.054,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.: 0.05 s, min 0.03 s, max 0.07 s, tot 0.20 s (4 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.05 s, min 0.03 s, max 0.07 s, tot 0.20 s (4 samples) -#pr: best tun. rsb canon. mflops were: on avg. 2.004e+03, min 8.015e+02, max 3.206e+03 (4 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 3.263e-02, min 3.762e-03, max 7.523e-02 (4 samples) -#pr: best tun. rsb operation time was: on avg. 2.995e-08s, min 2.995e-08s, max 2.995e-08s, tot 1.198e-07s (4 samples) -#pr: ref. unt. rsb operation time was: on avg. 3.555e-03s, min 1.276e-03s, max 6.380e-03s, tot 1.422e-02s (4 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 6.478e+00 1.875e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.004e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.01 s, min 0.00 s, max 0.01 s, tot 0.03 s (4 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.01 s, min 0.00 s, max 0.01 s, tot 0.03 s (4 samples) +#pr: best tun. rsb canon. mflops were: on avg. 6.838e+02, min 2.735e+02, max 1.094e+03 (4 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 1.167e-01, min 2.909e-02, max 2.182e-01 (4 samples) +#pr: best tun. rsb operation time was: on avg. 8.775e-08s, min 8.775e-08s, max 8.775e-08s, tot 3.510e-07s (4 samples) +#pr: ref. unt. rsb operation time was: on avg. 6.050e-04s, min 4.399e-04s, max 8.252e-04s, tot 2.420e-03s (4 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.909e+01 5.525e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 9.983e-01 #pr: ======== Limiting to nrhs=4: #pr: 4 samples (out of 8) matched the dump limiting criteria. #pr: Dump from a base of 8 samples (of max 16) ordered by (1,1,1,1,2,4,2) = (filename x cores x incX x incY x nrhs x typecode x transA). pr: BESTCODE MTX NR NC NNZ NRHS TYPE SYM TRANS NT AT-NT AT-MKL-NT BPNZ AT-BPNZ NSUBM AT-SUBM RSBBEST-MFLOPS OPTIME MKL-OPTIME AT-OPTIME AT-MKL-OPTIME AT-TIME RWminBW-GBps CB-bpf AT-MS CMFLOPS -pr: 9:R_R A 3 3 6 4 D S N 12 12 0 4.0000 4.6667 3 1 3205.84 4.446e-03 0.000e+00 2.995e-08 0.000e+00 4.541e-02 1.22e+01 2.79e+00 1 9.60e-05 -pr: 11:R_R A 3 3 6 4 S S N 12 12 0 4.0000 4.6667 3 1 3205.84 2.469e-03 0.000e+00 2.995e-08 0.000e+00 4.032e-02 6.55e+00 1.54e+00 1 9.60e-05 -pr: 13:R_R A 3 3 6 4 C S N 12 12 0 4.0000 4.6667 3 1 12823.35 3.892e-03 0.000e+00 2.995e-08 0.000e+00 5.422e-02 1.22e+01 6.98e-01 1 3.84e-04 -pr: 15:R_R A 3 3 6 4 Z S N 12 12 0 4.0000 4.6667 3 1 12823.35 8.002e-03 0.000e+00 2.995e-08 0.000e+00 6.476e-02 2.34e+01 1.32e+00 1 3.84e-04 +pr: 9:R_R A 3 3 6 4 D S N 12 12 0 4.0000 4.6667 3 1 1094.02 1.053e-03 0.000e+00 8.775e-08 0.000e+00 9.477e-03 4.15e+00 2.79e+00 1 9.60e-05 +pr: 11:R_R A 3 3 6 4 S S N 12 12 0 4.0000 4.6667 3 1 1094.02 8.090e-04 0.000e+00 8.775e-08 0.000e+00 8.878e-03 2.23e+00 1.54e+00 1 9.60e-05 +pr: 13:R_R A 3 3 6 4 C S N 12 12 0 4.0000 4.6667 3 1 4376.07 4.730e-04 0.000e+00 8.775e-08 0.000e+00 4.874e-03 4.15e+00 6.98e-01 1 3.84e-04 +pr: 15:R_R A 3 3 6 4 Z S N 12 12 0 4.0000 4.6667 3 1 4376.07 4.020e-04 0.000e+00 8.775e-08 0.000e+00 3.921e-03 7.98e+00 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. 15702726.4 % faster, avg. sp. ratio 157028.264x, max sp. ratio 267221.338x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 1709078.4/1346552.5/2162738.9/6836313.7 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 12.1/ 8.1/ 16.3/ 48.6 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 12.1, min. 8.1, max. 16.3 ops) +#pr: (in succ. cases rsb autotuning gave avg. 779685.4 % faster, avg. sp. ratio 7797.854x, max sp. ratio 12001.087x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 77350.2/44684.1/107998.9/309400.9 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 10.0/ 9.0/ 11.0/ 40.0 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 10.0, min. 9.0, max. 11.0 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 9.951/ 4.942/ 16.964,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 54.232/ 6.545/ 23.376,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 3.396/ 1.687/ 5.789,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 18.507/ 2.234/ 7.977,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.: 0.05 s, min 0.04 s, max 0.06 s, tot 0.20 s (4 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.05 s, min 0.04 s, max 0.06 s, tot 0.20 s (4 samples) -#pr: best tun. rsb canon. mflops were: on avg. 8.015e+03, min 3.206e+03, max 1.282e+04 (4 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 5.178e-02, min 2.159e-02, max 9.867e-02 (4 samples) -#pr: best tun. rsb operation time was: on avg. 2.995e-08s, min 2.995e-08s, max 2.995e-08s, tot 1.198e-07s (4 samples) -#pr: ref. unt. rsb operation time was: on avg. 4.702e-03s, min 2.469e-03s, max 8.002e-03s, tot 1.881e-02s (4 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 2.805e+00 9.629e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.004e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.01 s, min 0.00 s, max 0.01 s, tot 0.03 s (4 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.01 s, min 0.00 s, max 0.01 s, tot 0.03 s (4 samples) +#pr: best tun. rsb canon. mflops were: on avg. 2.735e+03, min 1.094e+03, max 4.376e+03 (4 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 4.942e-01, min 9.116e-02, max 9.553e-01 (4 samples) +#pr: best tun. rsb operation time was: on avg. 8.775e-08s, min 8.775e-08s, max 8.775e-08s, tot 3.510e-07s (4 samples) +#pr: ref. unt. rsb operation time was: on avg. 6.843e-04s, min 4.020e-04s, max 1.053e-03s, tot 2.737e-03s (4 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 8.266e+00 2.837e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 9.983e-01 #pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 4.000e+00 x, min 4.000e+00 x, max 4.000e+00 x (4 samples, the non-min-nrhs ones) #pr: ======== Limiting to transA=N: #pr: Dump from a base of 8 samples (of max 16) ordered by (1,1,1,1,2,4,2) = (filename x cores x incX x incY x nrhs x typecode x transA). pr: BESTCODE MTX NR NC NNZ NRHS TYPE SYM TRANS NT AT-NT AT-MKL-NT BPNZ AT-BPNZ NSUBM AT-SUBM RSBBEST-MFLOPS OPTIME MKL-OPTIME AT-OPTIME AT-MKL-OPTIME AT-TIME RWminBW-GBps CB-bpf AT-MS CMFLOPS -pr: 1:R_R A 3 3 6 1 D S N 12 12 0 4.0000 4.6667 3 1 801.46 4.485e-03 0.000e+00 2.995e-08 0.000e+00 5.763e-02 4.94e+00 5.17e+00 1 2.40e-05 -pr: 3:R_R A 3 3 6 1 S S N 12 12 0 4.0000 4.6667 3 1 801.46 6.380e-03 0.000e+00 2.995e-08 0.000e+00 7.264e-02 2.94e+00 3.17e+00 1 2.40e-05 -pr: 5:R_R A 3 3 6 1 C S N 12 12 0 4.0000 4.6667 3 1 3205.84 1.276e-03 0.000e+00 2.995e-08 0.000e+00 3.726e-02 4.94e+00 1.29e+00 1 9.60e-05 -pr: 7:R_R A 3 3 6 1 Z S N 12 12 0 4.0000 4.6667 3 1 3205.84 2.079e-03 0.000e+00 2.995e-08 0.000e+00 3.347e-02 8.95e+00 2.29e+00 1 9.60e-05 -pr: 9:R_R A 3 3 6 4 D S N 12 12 0 4.0000 4.6667 3 1 3205.84 4.446e-03 0.000e+00 2.995e-08 0.000e+00 4.541e-02 1.22e+01 2.79e+00 1 9.60e-05 -pr: 11:R_R A 3 3 6 4 S S N 12 12 0 4.0000 4.6667 3 1 3205.84 2.469e-03 0.000e+00 2.995e-08 0.000e+00 4.032e-02 6.55e+00 1.54e+00 1 9.60e-05 -pr: 13:R_R A 3 3 6 4 C S N 12 12 0 4.0000 4.6667 3 1 12823.35 3.892e-03 0.000e+00 2.995e-08 0.000e+00 5.422e-02 1.22e+01 6.98e-01 1 3.84e-04 -pr: 15:R_R A 3 3 6 4 Z S N 12 12 0 4.0000 4.6667 3 1 12823.35 8.002e-03 0.000e+00 2.995e-08 0.000e+00 6.476e-02 2.34e+01 1.32e+00 1 3.84e-04 +pr: 1:R_R A 3 3 6 1 D S N 12 12 0 4.0000 4.6667 3 1 273.50 6.249e-04 0.000e+00 8.775e-08 0.000e+00 1.146e-02 1.69e+00 5.17e+00 1 2.40e-05 +pr: 3:R_R A 3 3 6 1 S S N 12 12 0 4.0000 4.6667 3 1 273.50 8.252e-04 0.000e+00 8.775e-08 0.000e+00 7.836e-03 1.00e+00 3.17e+00 1 2.40e-05 +pr: 5:R_R A 3 3 6 1 C S N 12 12 0 4.0000 4.6667 3 1 1094.02 5.300e-04 0.000e+00 8.775e-08 0.000e+00 5.128e-03 1.69e+00 1.29e+00 1 9.60e-05 +pr: 7:R_R A 3 3 6 1 Z S N 12 12 0 4.0000 4.6667 3 1 1094.02 4.399e-04 0.000e+00 8.775e-08 0.000e+00 4.663e-03 3.05e+00 2.29e+00 1 9.60e-05 +pr: 9:R_R A 3 3 6 4 D S N 12 12 0 4.0000 4.6667 3 1 1094.02 1.053e-03 0.000e+00 8.775e-08 0.000e+00 9.477e-03 4.15e+00 2.79e+00 1 9.60e-05 +pr: 11:R_R A 3 3 6 4 S S N 12 12 0 4.0000 4.6667 3 1 1094.02 8.090e-04 0.000e+00 8.775e-08 0.000e+00 8.878e-03 2.23e+00 1.54e+00 1 9.60e-05 +pr: 13:R_R A 3 3 6 4 C S N 12 12 0 4.0000 4.6667 3 1 4376.07 4.730e-04 0.000e+00 8.775e-08 0.000e+00 4.874e-03 4.15e+00 6.98e-01 1 3.84e-04 +pr: 15:R_R A 3 3 6 4 Z S N 12 12 0 4.0000 4.6667 3 1 4376.07 4.020e-04 0.000e+00 8.775e-08 0.000e+00 3.921e-03 7.98e+00 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. 13787021.8 % faster, avg. sp. ratio 137871.218x, max sp. ratio 267221.338x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 1693595.7/1117762.7/2425851.9/13548765.9 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 14.8/ 8.1/ 29.2/118.1 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 14.8, min. 8.1, max. 29.2 ops) +#pr: (in succ. cases rsb autotuning gave avg. 734514.9 % faster, avg. sp. ratio 7346.149x, max sp. ratio 12001.087x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 80108.7/44684.1/130588.2/640869.4 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 11.0/ 9.0/ 18.3/ 88.1 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 11.0, min. 9.0, max. 18.3 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 18/ 8/ 32) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 54/ 24/ 96) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 7.247/ 2.538/ 16.964,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 76.005/ 2.939/ 23.376,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 2.473/ 0.866/ 5.789,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 25.937/ 1.003/ 7.977,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.: 0.05 s, min 0.03 s, max 0.07 s, tot 0.41 s (8 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.05 s, min 0.03 s, max 0.07 s, tot 0.41 s (8 samples) -#pr: best tun. rsb canon. mflops were: on avg. 5.009e+03, min 8.015e+02, max 1.282e+04 (8 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 4.221e-02, min 3.762e-03, max 9.867e-02 (8 samples) -#pr: best tun. rsb operation time was: on avg. 2.995e-08s, min 2.995e-08s, max 2.995e-08s, tot 2.396e-07s (8 samples) -#pr: ref. unt. rsb operation time was: on avg. 4.129e-03s, min 1.276e-03s, max 8.002e-03s, tot 3.303e-02s (8 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 2.805e+00 1.875e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.004e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.01 s, min 0.00 s, max 0.01 s, tot 0.06 s (8 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.01 s, min 0.00 s, max 0.01 s, tot 0.06 s (8 samples) +#pr: best tun. rsb canon. mflops were: on avg. 1.709e+03, min 2.735e+02, max 4.376e+03 (8 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 3.055e-01, min 2.909e-02, max 9.553e-01 (8 samples) +#pr: best tun. rsb operation time was: on avg. 8.775e-08s, min 8.775e-08s, max 8.775e-08s, tot 7.020e-07s (8 samples) +#pr: ref. unt. rsb operation time was: on avg. 6.446e-04s, min 4.020e-04s, max 1.053e-03s, tot 5.157e-03s (8 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 8.266e+00 5.525e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 9.983e-01 #pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 4.000e+00 x, min 4.000e+00 x, max 4.000e+00 x (4 samples, the non-min-nrhs ones) #pr: ======== Limiting to both transA=N and nrhs=1: #pr: 4 samples (out of 8) matched the dump limiting criteria. #pr: Dump from a base of 8 samples (of max 16) ordered by (1,1,1,1,2,4,2) = (filename x cores x incX x incY x nrhs x typecode x transA). pr: BESTCODE MTX NR NC NNZ NRHS TYPE SYM TRANS NT AT-NT AT-MKL-NT BPNZ AT-BPNZ NSUBM AT-SUBM RSBBEST-MFLOPS OPTIME MKL-OPTIME AT-OPTIME AT-MKL-OPTIME AT-TIME RWminBW-GBps CB-bpf AT-MS CMFLOPS -pr: 1:R_R A 3 3 6 1 D S N 12 12 0 4.0000 4.6667 3 1 801.46 4.485e-03 0.000e+00 2.995e-08 0.000e+00 5.763e-02 4.94e+00 5.17e+00 1 2.40e-05 -pr: 3:R_R A 3 3 6 1 S S N 12 12 0 4.0000 4.6667 3 1 801.46 6.380e-03 0.000e+00 2.995e-08 0.000e+00 7.264e-02 2.94e+00 3.17e+00 1 2.40e-05 -pr: 5:R_R A 3 3 6 1 C S N 12 12 0 4.0000 4.6667 3 1 3205.84 1.276e-03 0.000e+00 2.995e-08 0.000e+00 3.726e-02 4.94e+00 1.29e+00 1 9.60e-05 -pr: 7:R_R A 3 3 6 1 Z S N 12 12 0 4.0000 4.6667 3 1 3205.84 2.079e-03 0.000e+00 2.995e-08 0.000e+00 3.347e-02 8.95e+00 2.29e+00 1 9.60e-05 +pr: 1:R_R A 3 3 6 1 D S N 12 12 0 4.0000 4.6667 3 1 273.50 6.249e-04 0.000e+00 8.775e-08 0.000e+00 1.146e-02 1.69e+00 5.17e+00 1 2.40e-05 +pr: 3:R_R A 3 3 6 1 S S N 12 12 0 4.0000 4.6667 3 1 273.50 8.252e-04 0.000e+00 8.775e-08 0.000e+00 7.836e-03 1.00e+00 3.17e+00 1 2.40e-05 +pr: 5:R_R A 3 3 6 1 C S N 12 12 0 4.0000 4.6667 3 1 1094.02 5.300e-04 0.000e+00 8.775e-08 0.000e+00 5.128e-03 1.69e+00 1.29e+00 1 9.60e-05 +pr: 7:R_R A 3 3 6 1 Z S N 12 12 0 4.0000 4.6667 3 1 1094.02 4.399e-04 0.000e+00 8.775e-08 0.000e+00 4.663e-03 3.05e+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. 11871317.2 % faster, avg. sp. ratio 118714.172x, max sp. ratio 213049.363x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 1678113.1/1117762.7/2425851.9/6712452.2 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 17.4/ 11.4/ 29.2/ 69.5 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 17.4, min. 11.4, max. 29.2 ops) +#pr: (in succ. cases rsb autotuning gave avg. 689344.4 % faster, avg. sp. ratio 6894.444x, max sp. ratio 9403.614x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 82867.1/53139.5/130588.2/331468.6 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 12.0/ 9.5/ 18.3/ 48.1 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 12.0, min. 9.5, max. 18.3 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 18/ 8/ 32) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 54/ 24/ 96) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 4.542/ 2.538/ 7.347,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 21.773/ 2.939/ 8.950,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 1.550/ 0.866/ 2.507,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 7.430/ 1.003/ 3.054,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.: 0.05 s, min 0.03 s, max 0.07 s, tot 0.20 s (4 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.05 s, min 0.03 s, max 0.07 s, tot 0.20 s (4 samples) -#pr: best tun. rsb canon. mflops were: on avg. 2.004e+03, min 8.015e+02, max 3.206e+03 (4 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 3.263e-02, min 3.762e-03, max 7.523e-02 (4 samples) -#pr: best tun. rsb operation time was: on avg. 2.995e-08s, min 2.995e-08s, max 2.995e-08s, tot 1.198e-07s (4 samples) -#pr: ref. unt. rsb operation time was: on avg. 3.555e-03s, min 1.276e-03s, max 6.380e-03s, tot 1.422e-02s (4 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 6.478e+00 1.875e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.004e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.01 s, min 0.00 s, max 0.01 s, tot 0.03 s (4 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.01 s, min 0.00 s, max 0.01 s, tot 0.03 s (4 samples) +#pr: best tun. rsb canon. mflops were: on avg. 6.838e+02, min 2.735e+02, max 1.094e+03 (4 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 1.167e-01, min 2.909e-02, max 2.182e-01 (4 samples) +#pr: best tun. rsb operation time was: on avg. 8.775e-08s, min 8.775e-08s, max 8.775e-08s, tot 3.510e-07s (4 samples) +#pr: ref. unt. rsb operation time was: on avg. 6.050e-04s, min 4.399e-04s, max 8.252e-04s, tot 2.420e-03s (4 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.909e+01 5.525e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 9.983e-01 #pr: ======== Limiting to both transA=N and nrhs=4: #pr: 4 samples (out of 8) matched the dump limiting criteria. #pr: Dump from a base of 8 samples (of max 16) ordered by (1,1,1,1,2,4,2) = (filename x cores x incX x incY x nrhs x typecode x transA). pr: BESTCODE MTX NR NC NNZ NRHS TYPE SYM TRANS NT AT-NT AT-MKL-NT BPNZ AT-BPNZ NSUBM AT-SUBM RSBBEST-MFLOPS OPTIME MKL-OPTIME AT-OPTIME AT-MKL-OPTIME AT-TIME RWminBW-GBps CB-bpf AT-MS CMFLOPS -pr: 9:R_R A 3 3 6 4 D S N 12 12 0 4.0000 4.6667 3 1 3205.84 4.446e-03 0.000e+00 2.995e-08 0.000e+00 4.541e-02 1.22e+01 2.79e+00 1 9.60e-05 -pr: 11:R_R A 3 3 6 4 S S N 12 12 0 4.0000 4.6667 3 1 3205.84 2.469e-03 0.000e+00 2.995e-08 0.000e+00 4.032e-02 6.55e+00 1.54e+00 1 9.60e-05 -pr: 13:R_R A 3 3 6 4 C S N 12 12 0 4.0000 4.6667 3 1 12823.35 3.892e-03 0.000e+00 2.995e-08 0.000e+00 5.422e-02 1.22e+01 6.98e-01 1 3.84e-04 -pr: 15:R_R A 3 3 6 4 Z S N 12 12 0 4.0000 4.6667 3 1 12823.35 8.002e-03 0.000e+00 2.995e-08 0.000e+00 6.476e-02 2.34e+01 1.32e+00 1 3.84e-04 +pr: 9:R_R A 3 3 6 4 D S N 12 12 0 4.0000 4.6667 3 1 1094.02 1.053e-03 0.000e+00 8.775e-08 0.000e+00 9.477e-03 4.15e+00 2.79e+00 1 9.60e-05 +pr: 11:R_R A 3 3 6 4 S S N 12 12 0 4.0000 4.6667 3 1 1094.02 8.090e-04 0.000e+00 8.775e-08 0.000e+00 8.878e-03 2.23e+00 1.54e+00 1 9.60e-05 +pr: 13:R_R A 3 3 6 4 C S N 12 12 0 4.0000 4.6667 3 1 4376.07 4.730e-04 0.000e+00 8.775e-08 0.000e+00 4.874e-03 4.15e+00 6.98e-01 1 3.84e-04 +pr: 15:R_R A 3 3 6 4 Z S N 12 12 0 4.0000 4.6667 3 1 4376.07 4.020e-04 0.000e+00 8.775e-08 0.000e+00 3.921e-03 7.98e+00 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. 15702726.4 % faster, avg. sp. ratio 157028.264x, max sp. ratio 267221.338x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 1709078.4/1346552.5/2162738.9/6836313.7 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 12.1/ 8.1/ 16.3/ 48.6 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 12.1, min. 8.1, max. 16.3 ops) +#pr: (in succ. cases rsb autotuning gave avg. 779685.4 % faster, avg. sp. ratio 7797.854x, max sp. ratio 12001.087x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 77350.2/44684.1/107998.9/309400.9 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 10.0/ 9.0/ 11.0/ 40.0 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 10.0, min. 9.0, max. 11.0 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 9.951/ 4.942/ 16.964,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 54.232/ 6.545/ 23.376,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 3.396/ 1.687/ 5.789,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 18.507/ 2.234/ 7.977,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.: 0.05 s, min 0.04 s, max 0.06 s, tot 0.20 s (4 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.05 s, min 0.04 s, max 0.06 s, tot 0.20 s (4 samples) -#pr: best tun. rsb canon. mflops were: on avg. 8.015e+03, min 3.206e+03, max 1.282e+04 (4 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 5.178e-02, min 2.159e-02, max 9.867e-02 (4 samples) -#pr: best tun. rsb operation time was: on avg. 2.995e-08s, min 2.995e-08s, max 2.995e-08s, tot 1.198e-07s (4 samples) -#pr: ref. unt. rsb operation time was: on avg. 4.702e-03s, min 2.469e-03s, max 8.002e-03s, tot 1.881e-02s (4 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 2.805e+00 9.629e+00 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.004e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.01 s, min 0.00 s, max 0.01 s, tot 0.03 s (4 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.01 s, min 0.00 s, max 0.01 s, tot 0.03 s (4 samples) +#pr: best tun. rsb canon. mflops were: on avg. 2.735e+03, min 1.094e+03, max 4.376e+03 (4 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 4.942e-01, min 9.116e-02, max 9.553e-01 (4 samples) +#pr: best tun. rsb operation time was: on avg. 8.775e-08s, min 8.775e-08s, max 8.775e-08s, tot 3.510e-07s (4 samples) +#pr: ref. unt. rsb operation time was: on avg. 6.843e-04s, min 4.020e-04s, max 1.053e-03s, tot 2.737e-03s (4 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 8.266e+00 2.837e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 9.983e-01 #pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 4.000e+00 x, min 4.000e+00 x, max 4.000e+00 x (4 samples, the non-min-nrhs ones) #pr: ======== Limiting to transA=T: #pr: No sample (out of 8) matched the dump criteria -- skipping dump round. @@ -4909,53 +4945,53 @@ #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 12 12 0 4.0000 4.6667 3 1 801.46 4.485e-03 0.000e+00 2.995e-08 0.000e+00 5.763e-02 4.94e+00 5.17e+00 1 2.40e-05 -pr: 3:R_R A 3 3 6 1 S S N 12 12 0 4.0000 4.6667 3 1 801.46 6.380e-03 0.000e+00 2.995e-08 0.000e+00 7.264e-02 2.94e+00 3.17e+00 1 2.40e-05 -pr: 5:R_R A 3 3 6 1 C S N 12 12 0 4.0000 4.6667 3 1 3205.84 1.276e-03 0.000e+00 2.995e-08 0.000e+00 3.726e-02 4.94e+00 1.29e+00 1 9.60e-05 -pr: 7:R_R A 3 3 6 1 Z S N 12 12 0 4.0000 4.6667 3 1 3205.84 2.079e-03 0.000e+00 2.995e-08 0.000e+00 3.347e-02 8.95e+00 2.29e+00 1 9.60e-05 -pr: 9:R_R A 3 3 6 4 D S N 12 12 0 4.0000 4.6667 3 1 3205.84 4.446e-03 0.000e+00 2.995e-08 0.000e+00 4.541e-02 1.22e+01 2.79e+00 1 9.60e-05 -pr: 11:R_R A 3 3 6 4 S S N 12 12 0 4.0000 4.6667 3 1 3205.84 2.469e-03 0.000e+00 2.995e-08 0.000e+00 4.032e-02 6.55e+00 1.54e+00 1 9.60e-05 -pr: 13:R_R A 3 3 6 4 C S N 12 12 0 4.0000 4.6667 3 1 12823.35 3.892e-03 0.000e+00 2.995e-08 0.000e+00 5.422e-02 1.22e+01 6.98e-01 1 3.84e-04 -pr: 15:R_R A 3 3 6 4 Z S N 12 12 0 4.0000 4.6667 3 1 12823.35 8.002e-03 0.000e+00 2.995e-08 0.000e+00 6.476e-02 2.34e+01 1.32e+00 1 3.84e-04 +pr: 1:R_R A 3 3 6 1 D S N 12 12 0 4.0000 4.6667 3 1 273.50 6.249e-04 0.000e+00 8.775e-08 0.000e+00 1.146e-02 1.69e+00 5.17e+00 1 2.40e-05 +pr: 3:R_R A 3 3 6 1 S S N 12 12 0 4.0000 4.6667 3 1 273.50 8.252e-04 0.000e+00 8.775e-08 0.000e+00 7.836e-03 1.00e+00 3.17e+00 1 2.40e-05 +pr: 5:R_R A 3 3 6 1 C S N 12 12 0 4.0000 4.6667 3 1 1094.02 5.300e-04 0.000e+00 8.775e-08 0.000e+00 5.128e-03 1.69e+00 1.29e+00 1 9.60e-05 +pr: 7:R_R A 3 3 6 1 Z S N 12 12 0 4.0000 4.6667 3 1 1094.02 4.399e-04 0.000e+00 8.775e-08 0.000e+00 4.663e-03 3.05e+00 2.29e+00 1 9.60e-05 +pr: 9:R_R A 3 3 6 4 D S N 12 12 0 4.0000 4.6667 3 1 1094.02 1.053e-03 0.000e+00 8.775e-08 0.000e+00 9.477e-03 4.15e+00 2.79e+00 1 9.60e-05 +pr: 11:R_R A 3 3 6 4 S S N 12 12 0 4.0000 4.6667 3 1 1094.02 8.090e-04 0.000e+00 8.775e-08 0.000e+00 8.878e-03 2.23e+00 1.54e+00 1 9.60e-05 +pr: 13:R_R A 3 3 6 4 C S N 12 12 0 4.0000 4.6667 3 1 4376.07 4.730e-04 0.000e+00 8.775e-08 0.000e+00 4.874e-03 4.15e+00 6.98e-01 1 3.84e-04 +pr: 15:R_R A 3 3 6 4 Z S N 12 12 0 4.0000 4.6667 3 1 4376.07 4.020e-04 0.000e+00 8.775e-08 0.000e+00 3.921e-03 7.98e+00 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. 13787021.8 % faster, avg. sp. ratio 137871.218x, max sp. ratio 267221.338x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 1693595.7/1117762.7/2425851.9/13548765.9 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 14.8/ 8.1/ 29.2/118.1 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 14.8, min. 8.1, max. 29.2 ops) +#pr: (in succ. cases rsb autotuning gave avg. 734514.9 % faster, avg. sp. ratio 7346.149x, max sp. ratio 12001.087x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 80108.7/44684.1/130588.2/640869.4 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 11.0/ 9.0/ 18.3/ 88.1 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 11.0, min. 9.0, max. 18.3 ops) #pr: (avg/min/max (avg) nnz per subm before successful tuning were 2/ 2/ 2) #pr: (avg/min/max (avg) nnz per subm after successful tuning were 6/ 6/ 6) #pr: (avg/min/max (avg) bytes per subm before successful tuning were 18/ 8/ 32) #pr: (avg/min/max (avg) bytes per subm after successful tuning were 54/ 24/ 96) #pr: (avg/min/max (avg) bytes per nnz before successful tuning were 4.000/ 4.000/ 4.000) -#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 7.247/ 2.538/ 16.964,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 76.005/ 2.939/ 23.376,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 2.473/ 0.866/ 5.789,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 25.937/ 1.003/ 7.977,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.: 0.05 s, min 0.03 s, max 0.07 s, tot 0.41 s (8 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.05 s, min 0.03 s, max 0.07 s, tot 0.41 s (8 samples) -#pr: best tun. rsb canon. mflops were: on avg. 5.009e+03, min 8.015e+02, max 1.282e+04 (8 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 4.221e-02, min 3.762e-03, max 9.867e-02 (8 samples) -#pr: best tun. rsb operation time was: on avg. 2.995e-08s, min 2.995e-08s, max 2.995e-08s, tot 2.396e-07s (8 samples) -#pr: ref. unt. rsb operation time was: on avg. 4.129e-03s, min 1.276e-03s, max 8.002e-03s, tot 3.303e-02s (8 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 2.805e+00 1.875e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.004e+00 +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.01 s, min 0.00 s, max 0.01 s, tot 0.06 s (8 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.01 s, min 0.00 s, max 0.01 s, tot 0.06 s (8 samples) +#pr: best tun. rsb canon. mflops were: on avg. 1.709e+03, min 2.735e+02, max 4.376e+03 (8 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 3.055e-01, min 2.909e-02, max 9.553e-01 (8 samples) +#pr: best tun. rsb operation time was: on avg. 8.775e-08s, min 8.775e-08s, max 8.775e-08s, tot 7.020e-07s (8 samples) +#pr: ref. unt. rsb operation time was: on avg. 6.446e-04s, min 4.020e-04s, max 1.053e-03s, tot 5.157e-03s (8 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 8.266e+00 5.525e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 9.983e-01 #pr: rsb nrhs-to-overall-min-rhs speed ratio was: on avg. 4.000e+00 x, min 4.000e+00 x, max 4.000e+00 x (4 samples, the non-min-nrhs ones) -#pr: Record collection took 2.17 s. +#pr: Record collection took 0.36 s. #pr: Record comprises 40 memory benchmark samples (prepend RSB_PR_MBW=1 to dump this). -#pr: Record comprises 89 environment variables in 3761 bytes (prepend RSB_PR_ENV=1 to dump this). +#pr: Record comprises 90 environment variables in 3861 bytes (prepend RSB_PR_ENV=1 to dump this). # ====== END Total summary record. -#pr: ======== Saved a performance record of 16 samples to rsbench_pr__1739127207_gcc-12.2.rpr -# Removing the temporary record file rsbench_pr__1739127207_gcc-12.2.rpr.tmp. -# terminating run at 1739127215 (after 7.7s 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__1704718232_gcc-12.2.rpr +# Removing the temporary record file rsbench_pr__1704718232_gcc-12.2.rpr.tmp. +# terminating run at 1704718237 (after 5.7s 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,\}' @@ -4963,14 +4999,14 @@ ++ wc -l ++ /build/reproducible-path/librsb-1.3.0.2+dfsg/rsbench -h + test 63 -ge 61 -++ wc -c ++ /build/reproducible-path/librsb-1.3.0.2+dfsg/rsbench -h +++ wc -c + test 2014 -ge 1966 -++ wc -l ++ /build/reproducible-path/librsb-1.3.0.2+dfsg/rsbench -oa -Ob -h +++ wc -l + test 182 -ge 157 -++ wc -c ++ /build/reproducible-path/librsb-1.3.0.2+dfsg/rsbench -oa -Ob -h +++ wc -c + test 5369 -ge 4600 + exit 0 if ! ./librsb-config --help ; then echo "Problem executing the librsb-config script!"; false; fi; @@ -5005,7 +5041,7 @@ 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 @@ -5015,15 +5051,15 @@ 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 1739127215 +# beginning run at 1704718238 # /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 -ffile-prefix-map=/build/reproducible-path/librsb-1.3.0.2+dfsg=. -fstack-protector-strong -Wformat -Werror=format-security -O3 -std=c99 -# average timer granularity: 2.96e-08 s +# average timer granularity: 7.9e-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 # env: HOSTNAME is not set # env: KMP_AFFINITY is not set @@ -5062,7 +5098,7 @@ # 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: codethink03-arm64 +# detected hostname: i-capture-the-hostname # user specified a verbosity level of 2 (each --verbose occurrence counts +1) # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 43690 bytes @@ -5082,29 +5118,29 @@ # This test will measure times in scanning arrays sized and aligned to fit in caches. # 2 cache levels detected Will fill struct with 40 samples... -# Memory benchmark took 5.243s +# Memory benchmark took 5.276s # auto-tuning oriented output implies times==0 iterations and sort-after-load. #pr: allocated a performance record for 4 samples (1120 bytes). # multi-type benchmarking (DSCZ) -- now using typecode D (last was D). # Cache block size total 524288 bytes, per-thread 43690 bytes -# so far, program took 5.245s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.000s/0.000s . +# so far, program took 5.279s 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 9.048e-02 s (100.00 %) - analyzed arrays in 1.387e-02 s (15.33 %) - cleaned-up arrays in 1.121e-05 s (0.01 %) - deduplicated arrays in 7.868e-06 s (0.01 %) + converted COO to RSB in 6.845e-03 s (100.00 %) + analyzed arrays in 1.951e-03 s (28.51 %) + cleaned-up arrays in 1.001e-05 s (0.15 %) + deduplicated arrays in 8.106e-06 s (0.12 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 6.021e-02 s (66.55 %) - memory allocations took 8.821e-06 s (0.01 %) - leafs setup took 5.960e-06 s (0.01 %) - halfword conversion took 1.636e-02 s (18.08 %) -Built (100 x 100)[0xaaaaf9247a60]{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 0.091s): (100 x 100)[0xaaaaf9247a60]{D} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x2446196 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LS' + shuffled partitions in 3.241e-03 s (47.35 %) + memory allocations took 1.192e-05 s (0.17 %) + leafs setup took 5.007e-06 s (0.07 %) + halfword conversion took 1.616e-03 s (23.61 %) +Built (100 x 100)[0xaaab0bd4adb0]{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 0.007s): (100 x 100)[0xaaab0bd4adb0]{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. @@ -5155,10 +5191,10 @@ # 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 0.01563s; avg 0.005211s ( +/- 6.64/ 9.48 %); best 0.004865s; worst 0.005705s; std dev. 0.0003586 (taking best). -Reference operation time is 0.00486517 s (4.152 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: 0.004865 Mflops: 4.152) -Merge (3 -> 1 leaves) took w.c.t. of 4.196e-05s, ~3.099e-05s of computing time (of which 1.311e-05s sorting, 2.861e-06s analysis) +3 iterations (1 th.) took 0.003714s; avg 0.001238s ( +/- 3.15/ 3.72 %); best 0.001199s; worst 0.001284s; std dev. 3.511e-05 (taking best). +Reference operation time is 0.00119901 s (16.85 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: 0.001199 Mflops: 16.847) +Merge (3 -> 1 leaves) took w.c.t. of 0.000109s, ~9.203e-05s of computing time (of which 4.601e-05s sorting, 5.007e-06s analysis) # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -5189,8 +5225,8 @@ # 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 1.788e-05s; avg 5.96e-06s ( +/- 16.00/ 16.00 %); best 5.007e-06s; worst 6.914e-06s; std dev. 7.787e-07 (taking best). -Reference operation time is 5.00679e-06 s (4035 Mflops) with 1 threads. +3 iterations (1 th.) took 5.388e-05s; avg 1.796e-05s ( +/- 11.06/ 22.12 %); best 1.597e-05s; worst 2.193e-05s; std dev. 2.81e-06 (taking best). +Reference operation time is 1.5974e-05 s (1265 Mflops) with 1 threads. # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -5206,16 +5242,16 @@ # 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: 5.007e-06 s ~Mflops: 4034.521 nsubm:1 otn:1 -Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 971.714x: 0.004865s -> 5.007e-06s, so taking this instance. +After merge step 1: tpop: 1.597e-05 s ~Mflops: 1264.551 nsubm:1 otn:1 +Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 75.060x: 0.001199s -> 1.597e-05s, so taking this instance. Saved plot to test-tuning-lower-100x100-5050nz--D-N-1--mv-tuned_merge1_1x1th.eps Merged all the matrix leaves: no reason to continue merging. -A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.03888s (of which 4.411e-05s partitioning, 0.02663s I/O); computing times: 3.099e-05s in par. loops, 1.311e-05s sorting, 2.861e-06s analyzing) -Total merge + benchmarking process took 0.03888s, equivalent to 7765.1/8.0 new/old ops (0.02551s for 2 clones -- as 5096.0/5.2 ops, or 2548.0/2.6 ops per clone), SPEEDUP of 971.714x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 971.714x (0.004865s -> 5.007e-06s), will amortize in 8.0 ops by saving 0.00486s per op. -In 1 tuning rounds (tot. 0.068s, 0.026s for constructor, 2 clones) obtained a SPEEDUP of 97071.4% (971.7x) (from 4.152 to 4035 Mflops). Employed 0.034s for I/O of matrix plots. +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.01439s (of which 0.0001149s partitioning, 0.01071s I/O); computing times: 9.203e-05s in par. loops, 4.601e-05s sorting, 5.007e-06s analyzing) +Total merge + benchmarking process took 0.01439s, equivalent to 901.1/12.0 new/old ops (0.006584s for 2 clones -- as 412.2/5.5 ops, or 206.1/2.7 ops per clone), SPEEDUP of 75.060x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 75.060x (0.001199s -> 1.597e-05s), will amortize in 12.2 ops by saving 0.001183s per op. +In 1 tuning rounds (tot. 0.022s, 0.0066s for constructor, 2 clones) obtained a SPEEDUP of 7406.0% (75.06x) (from 16.85 to 1265 Mflops). Employed 0.0087s 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 0.102068 s (4.865e-03 s -> 5.007e-06 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.0304718 s (1.199e-03 s -> 1.597e-05 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). RSB Sparse Blocks Autotuner invoked requesting max 0 splits and max 0 merges in 1 rounds, auto threads spec. Will autotune matrix: 100 x 100, type D, 5050 nnz, 50 nnz/r, 1 subms, 1 lsubms, 2.0800 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:10 @@ -5281,20 +5317,20 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 2.503e-05s; avg 8.345e-06s ( +/- 40.00/ 68.57 %); best 5.007e-06s; worst 1.407e-05s; std dev. 4.065e-06 (taking best). -Reference operation time is 5.00679e-06 s (4035 Mflops) with 1 threads. +3 iterations (1 th.) took 5.507e-05s; avg 1.836e-05s ( +/- 12.99/ 25.97 %); best 1.597e-05s; worst 2.313e-05s; std dev. 3.372e-06 (taking best). +Reference operation time is 1.5974e-05 s (1265 Mflops) with 1 threads. Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 2.096e-02 s (100.00 %) - analyzed arrays in 1.202e-02 s (57.35 %) - cleaned-up arrays in 8.821e-06 s (0.04 %) - deduplicated arrays in 8.106e-06 s (0.04 %) + converted COO to RSB in 2.504e-03 s (100.00 %) + analyzed arrays in 8.299e-04 s (33.14 %) + cleaned-up arrays in 2.480e-05 s (0.99 %) + deduplicated arrays in 2.217e-05 s (0.89 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 8.910e-03 s (42.52 %) - memory allocations took 3.099e-06 s (0.01 %) - leafs setup took 1.907e-06 s (0.01 %) - halfword conversion took 5.007e-06 s (0.02 %) -Built (100 x 100)[0xaaaaf924cc90]{D} @ (0(0..100),0(0..100)) (5050 nnz, 50 nnz/r) flags 0x42644094 (coo:0, csr:1, hw:0, ic:1, fi:0), storage: 1, subm: 1, symflags:'LS' + shuffled partitions in 1.617e-03 s (64.58 %) + memory allocations took 3.099e-06 s (0.12 %) + leafs setup took 9.537e-07 s (0.04 %) + halfword conversion took 5.007e-06 s (0.20 %) +Built (100 x 100)[0xaaab0bd642c0]{D} @ (0(0..100),0(0..100)) (5050 nnz, 50 nnz/r) flags 0x42644094 (coo:0, csr:1, hw:0, ic:1, fi:0), storage: 1, subm: 1, symflags:'LS' Starting autotuning stage, with subdivision of 1 (current threads=1, requested threads=0, max threads = 12). # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes @@ -5328,16 +5364,16 @@ # 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 2.391e-02 s (100.00 %) - analyzed arrays in 4.476e-03 s (18.72 %) - cleaned-up arrays in 7.868e-06 s (0.03 %) - deduplicated arrays in 8.106e-06 s (0.03 %) + converted COO to RSB in 4.388e-03 s (100.00 %) + analyzed arrays in 1.121e-03 s (25.55 %) + cleaned-up arrays in 2.480e-05 s (0.57 %) + deduplicated arrays in 2.122e-05 s (0.48 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 8.912e-03 s (37.27 %) - memory allocations took 2.146e-06 s (0.01 %) - leafs setup took 1.192e-06 s (0.00 %) - halfword conversion took 1.050e-02 s (43.93 %) -Built (100 x 100)[0xaaaaf9248100]{D} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 3, symflags:'LS' + shuffled partitions in 1.603e-03 s (36.53 %) + memory allocations took 4.053e-06 s (0.09 %) + leafs setup took 9.537e-07 s (0.02 %) + halfword conversion took 1.613e-03 s (36.76 %) +Built (100 x 100)[0xaaab0bd4ae00]{D} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 3, symflags:'LS' # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -5383,9 +5419,9 @@ # 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 0.01237s; avg 0.004123s ( +/- 40.75/ 22.91 %); best 0.002443s; worst 0.005068s; std dev. 0.001191 (taking best). -Reference operation time is 0.00244308 s (8.268 Mflops) with 1 threads. -Challenging best inner round reference (5.00679e-06 s/1 threads) with: subdivision 0.25, 3 leaves, 2.121 bytes/nz, 0.00244308 s/0 threads (speedup 0.00204938 x), same?n. +3 iterations (1 th.) took 0.002313s; avg 0.000771s ( +/- 10.24/ 5.57 %); best 0.0006921s; worst 0.000814s; std dev. 5.587e-05 (taking best). +Reference operation time is 0.000692129 s (29.19 Mflops) with 1 threads. +Challenging best inner round reference (1.5974e-05 s/1 threads) with: subdivision 0.25, 3 leaves, 2.121 bytes/nz, 0.000692129 s/0 threads (speedup 0.0230796 x), same?n. New candidate clone performs slowly; discarding it: 100 x 100, type D, 5050 nnz, 50 nnz/r, 4 subms, 3 lsubms, 2.1212 bpnz # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes @@ -5419,16 +5455,16 @@ # 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 2.544e-02 s (100.00 %) - analyzed arrays in 8.017e-03 s (31.51 %) - cleaned-up arrays in 7.868e-06 s (0.03 %) - deduplicated arrays in 8.106e-06 s (0.03 %) + converted COO to RSB in 5.204e-03 s (100.00 %) + analyzed arrays in 1.904e-03 s (36.59 %) + cleaned-up arrays in 2.480e-05 s (0.48 %) + deduplicated arrays in 2.217e-05 s (0.43 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 9.509e-03 s (37.37 %) - memory allocations took 3.099e-06 s (0.01 %) - leafs setup took 5.007e-06 s (0.02 %) - halfword conversion took 7.894e-03 s (31.02 %) -Built (100 x 100)[0xaaaaf92753a0]{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 1.633e-03 s (31.38 %) + memory allocations took 3.099e-06 s (0.06 %) + leafs setup took 3.099e-06 s (0.06 %) + halfword conversion took 1.613e-03 s (30.99 %) +Built (100 x 100)[0xaaab0bd4be40]{D} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 10, symflags:'LS' # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -5474,9 +5510,9 @@ # 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 0.01671s; avg 0.005568s ( +/- 49.59/ 58.43 %); best 0.002807s; worst 0.008822s; std dev. 0.00248 (taking best). -Reference operation time is 0.0028069 s (7.197 Mflops) with 1 threads. -Challenging best inner round reference (5.00679e-06 s/1 threads) with: subdivision 0.5, 10 leaves, 2.206 bytes/nz, 0.0028069 s/0 threads (speedup 0.00178374 x), same?n. +3 iterations (1 th.) took 0.002318s; avg 0.0007726s ( +/- 9.56/ 5.10 %); best 0.0006988s; worst 0.0008121s; std dev. 5.225e-05 (taking best). +Reference operation time is 0.000698805 s (28.91 Mflops) with 1 threads. +Challenging best inner round reference (1.5974e-05 s/1 threads) with: subdivision 0.5, 10 leaves, 2.206 bytes/nz, 0.000698805 s/0 threads (speedup 0.0228591 x), same?n. New candidate clone performs slowly; discarding it: 100 x 100, type D, 5050 nnz, 50 nnz/r, 14 subms, 10 lsubms, 2.2059 bpnz # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes @@ -5510,16 +5546,16 @@ # 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 3.302e-02 s (100.00 %) - analyzed arrays in 1.396e-02 s (42.29 %) - cleaned-up arrays in 9.060e-06 s (0.03 %) - deduplicated arrays in 7.868e-06 s (0.02 %) + converted COO to RSB in 6.546e-03 s (100.00 %) + analyzed arrays in 1.976e-03 s (30.19 %) + cleaned-up arrays in 2.289e-05 s (0.35 %) + deduplicated arrays in 2.003e-05 s (0.31 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 9.004e-03 s (27.27 %) - memory allocations took 6.914e-06 s (0.02 %) - leafs setup took 3.099e-06 s (0.01 %) - halfword conversion took 1.003e-02 s (30.36 %) -Built (100 x 100)[0xaaaaf92753a0]{D} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 25, symflags:'LS' + shuffled partitions in 2.478e-03 s (37.86 %) + memory allocations took 4.053e-06 s (0.06 %) + leafs setup took 2.861e-06 s (0.04 %) + halfword conversion took 2.042e-03 s (31.20 %) +Built (100 x 100)[0xaaab0bd784f0]{D} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 24, symflags:'LS' # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -5565,10 +5601,10 @@ # 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 0.01396s; avg 0.004653s ( +/- 9.69/ 4.99 %); best 0.004202s; worst 0.004885s; std dev. 0.0003188 (taking best). -Reference operation time is 0.00420189 s (4.807 Mflops) with 1 threads. -Challenging best inner round reference (5.00679e-06 s/1 threads) with: subdivision 1, 25 leaves, 2.317 bytes/nz, 0.00420189 s/0 threads (speedup 0.00119156 x), same?n. -New candidate clone performs slowly; discarding it: 100 x 100, type D, 5050 nnz, 50 nnz/r, 34 subms, 25 lsubms, 2.3168 bpnz +3 iterations (1 th.) took 0.003133s; avg 0.001044s ( +/- 51.26/ 51.08 %); best 0.000509s; worst 0.001578s; std dev. 0.0004364 (taking best). +Reference operation time is 0.000509024 s (39.68 Mflops) with 1 threads. +Challenging best inner round reference (1.5974e-05 s/1 threads) with: subdivision 1, 24 leaves, 2.306 bytes/nz, 0.000509024 s/0 threads (speedup 0.0313817 x), same?n. +New candidate clone performs slowly; discarding it: 100 x 100, type D, 5050 nnz, 50 nnz/r, 33 subms, 24 lsubms, 2.3057 bpnz # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -5601,16 +5637,16 @@ # 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 3.399e-02 s (100.00 %) - analyzed arrays in 1.040e-02 s (30.59 %) - cleaned-up arrays in 9.060e-06 s (0.03 %) - deduplicated arrays in 8.106e-06 s (0.02 %) + converted COO to RSB in 1.320e-02 s (100.00 %) + analyzed arrays in 1.402e-03 s (10.62 %) + cleaned-up arrays in 2.193e-05 s (0.17 %) + deduplicated arrays in 1.717e-05 s (0.13 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.403e-02 s (41.27 %) - memory allocations took 2.861e-06 s (0.01 %) - leafs setup took 5.007e-06 s (0.01 %) - halfword conversion took 9.537e-03 s (28.06 %) -Built (100 x 100)[0xaaaaf92753a0]{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 1.014e-02 s (76.80 %) + memory allocations took 4.768e-06 s (0.04 %) + leafs setup took 5.007e-06 s (0.04 %) + halfword conversion took 1.610e-03 s (12.20 %) +Built (100 x 100)[0xaaab0bd784f0]{D} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 36, symflags:'LS' # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -5656,9 +5692,9 @@ # 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 0.01392s; avg 0.00464s ( +/- 31.85/ 26.96 %); best 0.003162s; worst 0.005891s; std dev. 0.001125 (taking best). -Reference operation time is 0.00316215 s (6.388 Mflops) with 1 threads. -Challenging best inner round reference (5.00679e-06 s/1 threads) with: subdivision 2, 36 leaves, 2.383 bytes/nz, 0.00316215 s/0 threads (speedup 0.00158335 x), same?n. +3 iterations (1 th.) took 0.01194s; avg 0.003981s ( +/- 89.60/172.97 %); best 0.0004141s; worst 0.01087s; std dev. 0.00487 (taking best). +Reference operation time is 0.000414133 s (48.78 Mflops) with 1 threads. +Challenging best inner round reference (1.5974e-05 s/1 threads) with: subdivision 2, 36 leaves, 2.383 bytes/nz, 0.000414133 s/0 threads (speedup 0.0385723 x), same?n. New candidate clone performs slowly; discarding it: 100 x 100, type D, 5050 nnz, 50 nnz/r, 50 subms, 36 lsubms, 2.3834 bpnz # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes @@ -5692,16 +5728,16 @@ # 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 2.399e-02 s (100.00 %) - analyzed arrays in 6.874e-03 s (28.65 %) - cleaned-up arrays in 9.060e-06 s (0.04 %) - deduplicated arrays in 6.914e-06 s (0.03 %) + converted COO to RSB in 5.276e-03 s (100.00 %) + analyzed arrays in 1.943e-03 s (36.82 %) + cleaned-up arrays in 2.098e-05 s (0.40 %) + deduplicated arrays in 1.884e-05 s (0.36 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 9.185e-03 s (38.28 %) - memory allocations took 4.053e-06 s (0.02 %) - leafs setup took 2.861e-06 s (0.01 %) - halfword conversion took 7.909e-03 s (32.97 %) -Built (100 x 100)[0xaaaaf92753a0]{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 1.657e-03 s (31.41 %) + memory allocations took 6.199e-06 s (0.12 %) + leafs setup took 4.053e-06 s (0.08 %) + halfword conversion took 1.625e-03 s (30.80 %) +Built (100 x 100)[0xaaab0bd784f0]{D} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 36, symflags:'LS' # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -5747,11 +5783,11 @@ # 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 0.0157s; avg 0.005232s ( +/- 7.00/ 13.92 %); best 0.004866s; worst 0.00596s; std dev. 0.0005148 (taking best). -Reference operation time is 0.00486588 s (4.151 Mflops) with 1 threads. -Challenging best inner round reference (5.00679e-06 s/1 threads) with: subdivision 4, 36 leaves, 2.383 bytes/nz, 0.00486588 s/0 threads (speedup 0.00102896 x), same?n. +3 iterations (1 th.) took 0.001475s; avg 0.0004917s ( +/- 17.86/ 34.46 %); best 0.0004039s; worst 0.0006611s; std dev. 0.0001198 (taking best). +Reference operation time is 0.000403881 s (50.01 Mflops) with 1 threads. +Challenging best inner round reference (1.5974e-05 s/1 threads) with: subdivision 4, 36 leaves, 2.383 bytes/nz, 0.000403881 s/0 threads (speedup 0.0395514 x), same?n. New candidate clone performs slowly; discarding it: 100 x 100, type D, 5050 nnz, 50 nnz/r, 50 subms, 36 lsubms, 2.3834 bpnz -Best sparse multiply performance with subdivision multiplier of 1: 4034.52 Mflops. +Best sparse multiply performance with subdivision multiplier of 1: 1264.55 Mflops. # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -5767,23 +5803,23 @@ # 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 0.234482 s (eq. to 5e+04/ 5e+04 old/new op.times), gained local/global speedup 1 x (5.00679e-06 : 5.00679e-06) / 1 x (5.00679e-06 : 5.00679e-06). This is not amortizable ! +Last tuner inner round (1 of 1) took 0.059665 s (eq. to 4e+03/ 4e+03 old/new op.times), gained local/global speedup 1 x (1.5974e-05 : 1.5974e-05) / 1 x (1.5974e-05 : 1.5974e-05). This is not amortizable ! Auto tuning inner round 1 did not find a configuration better than the original. -In 1 tuning rounds (tot. 0.23s, 0.16s for constructor, 0 clones) obtained NO speedup (best stays 4035 Mflops). -Second run of RSB Autotuner took 0.234503 s and estimated a speedup of 1.000000 x (5.007e-06 s -> 5.007e-06 s per op) in same matrix (1 -> 1 lsubm) +In 1 tuning rounds (tot. 0.06s, 0.038s for constructor, 0 clones) obtained NO speedup (best stays 1265 Mflops). +Second run of RSB Autotuner took 0.0597029 s and estimated a speedup of 1.000000 x (1.597e-05 s -> 1.597e-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 0.013868 0.060212 0.074080 -%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.074080 -%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.013868 -%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.060212 +%:CONSTRUCTOR_TIMES:lower-100x100-5050nz S N 1 100 100 5050 0.000000 0.001951 0.003241 0.005192 +%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.005192 +%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.001951 +%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.003241 %: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 0.074080 +%:SORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.005192 %: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 @@ -5798,34 +5834,34 @@ %: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 0.090477 1e+09 1e+09 +%operation:lower-100x100-5050nz 0.006845 1e+09 1e+09 %constructor:matrix SORT[1] SCAN[1] SHUFFLE[1] INSERT[1] -%constructor:lower-100x100-5050nz 0 0.0138679 0 0.0602121 -# so far, program took 5.698s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.337s/0.000s . +%constructor:lower-100x100-5050nz 0 0.00195122 0 0.00324082 +# so far, program took 5.380s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.090s/0.000s . getrusage() stats: ru_maxrss: 6 (maximum resident set size -- MB) -ru_stime : 0.02426s (system CPU time used) -ru_utime : 5.592s (user CPU time used) +ru_stime : 0.03182s (system CPU time used) +ru_utime : 5.988s (user CPU time used) # multi-type benchmarking (DSCZ) -- now using typecode S (last was D). # Cache block size total 524288 bytes, per-thread 524288 bytes -# so far, program took 5.698s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.337s/0.000s . +# so far, program took 5.380s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.090s/0.000s . # Using 1 threads # Using alpha=1 beta=1 order=cols for rsb_spmv/rsb_spsv/rsb_spmm/rsb_spsm. # will use input matrix flags: RSB_FLAG_USE_HALFWORD_INDICES, RSB_FLAG_SORTED_INPUT, RSB_FLAG_LOWER, RSB_FLAG_QUAD_PARTITIONING, RSB_FLAG_SYMMETRIC, RSB_FLAG_OWN_PARTITIONING_ARRAYS # Using 1 threads Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 3.160e-02 s (100.00 %) - analyzed arrays in 7.020e-03 s (22.21 %) - cleaned-up arrays in 9.060e-06 s (0.03 %) - deduplicated arrays in 7.868e-06 s (0.02 %) - sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.725e-02 s (54.59 %) - memory allocations took 2.217e-05 s (0.07 %) - leafs setup took 9.537e-07 s (0.00 %) - halfword conversion took 7.289e-03 s (23.07 %) -Built (100 x 100)[0xaaaaf926b5c0]{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 0.032s): (100 x 100)[0xaaaaf926b5c0]{S} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x2446196 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LS' + converted COO to RSB in 3.579e-03 s (100.00 %) + analyzed arrays in 4.280e-04 s (11.96 %) + cleaned-up arrays in 1.693e-05 s (0.47 %) + deduplicated arrays in 1.502e-05 s (0.42 %) + sorted arrays in 9.537e-07 s (0.03 %) + shuffled partitions in 1.610e-03 s (44.98 %) + memory allocations took 5.245e-06 s (0.15 %) + leafs setup took 1.192e-06 s (0.03 %) + halfword conversion took 1.502e-03 s (41.96 %) +Built (100 x 100)[0xaaab0bd2d410]{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 0.004s): (100 x 100)[0xaaab0bd2d410]{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. @@ -5876,10 +5912,10 @@ # 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 0.01342s; avg 0.004473s ( +/- 0.26/ 0.39 %); best 0.004461s; worst 0.00449s; std dev. 1.258e-05 (taking best). -Reference operation time is 0.00446105 s (4.528 Mflops) with 1 threads. -Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=cols) (max 6 steps, inclusive 3 grace steps) on: 100 x 100, type S, 5050 nnz, 50 nnz/r, 4 subms, 3 lsubms, 2.1212 bpnz (tpop: 0.004461 Mflops: 4.528) -Merge (3 -> 1 leaves) took w.c.t. of 3.719e-05s, ~3.099e-05s of computing time (of which 1.287e-05s sorting, 2.146e-06s analysis) +3 iterations (1 th.) took 0.003649s; avg 0.001216s ( +/- 0.44/ 0.71 %); best 0.001211s; worst 0.001225s; std dev. 6.188e-06 (taking best). +Reference operation time is 0.00121093 s (16.68 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: 0.001211 Mflops: 16.681) +Merge (3 -> 1 leaves) took w.c.t. of 8.011e-05s, ~6.7e-05s of computing time (of which 2.694e-05s sorting, 3.815e-06s analysis) # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -5910,8 +5946,8 @@ # 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 1.788e-05s; avg 5.96e-06s ( +/- 16.00/ 16.00 %); best 5.007e-06s; worst 6.914e-06s; std dev. 7.787e-07 (taking best). -Reference operation time is 5.00679e-06 s (4035 Mflops) with 1 threads. +3 iterations (1 th.) took 4.411e-05s; avg 1.47e-05s ( +/- 4.32/ 2.16 %); best 1.407e-05s; worst 1.502e-05s; std dev. 4.496e-07 (taking best). +Reference operation time is 1.40667e-05 s (1436 Mflops) with 1 threads. # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -5927,16 +5963,16 @@ # 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: 5.007e-06 s ~Mflops: 4034.521 nsubm:1 otn:1 -Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 891.000x: 0.004461s -> 5.007e-06s, so taking this instance. +After merge step 1: tpop: 1.407e-05 s ~Mflops: 1436.016 nsubm:1 otn:1 +Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 86.085x: 0.001211s -> 1.407e-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 0.0478s (of which 3.815e-05s partitioning, 0.03234s I/O); computing times: 3.099e-05s in par. loops, 1.287e-05s sorting, 2.146e-06s analyzing) -Total merge + benchmarking process took 0.0478s, equivalent to 9547.7/10.7 new/old ops (0.02898s for 2 clones -- as 5788.3/6.5 ops, or 2894.2/3.2 ops per clone), SPEEDUP of 891.000x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 891.000x (0.004461s -> 5.007e-06s), will amortize in 10.7 ops by saving 0.004456s per op. -In 1 tuning rounds (tot. 0.075s, 0.029s for constructor, 2 clones) obtained a SPEEDUP of 89000.0% (891x) (from 4.528 to 4035 Mflops). Employed 0.028s for I/O of matrix plots. +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.01422s (of which 8.416e-05s partitioning, 0.01075s I/O); computing times: 6.7e-05s in par. loops, 2.694e-05s sorting, 3.815e-06s analyzing) +Total merge + benchmarking process took 0.01422s, equivalent to 1011.0/11.7 new/old ops (0.006093s for 2 clones -- as 433.2/5.0 ops, or 216.6/2.5 ops per clone), SPEEDUP of 86.085x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 86.085x (0.001211s -> 1.407e-05s), will amortize in 11.9 ops by saving 0.001197s per op. +In 1 tuning rounds (tot. 0.021s, 0.0061s for constructor, 2 clones) obtained a SPEEDUP of 8508.5% (86.08x) (from 16.68 to 1436 Mflops). Employed 0.0098s 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 0.103128 s (4.461e-03 s -> 5.007e-06 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.0306602 s (1.211e-03 s -> 1.407e-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 @@ -6002,20 +6038,20 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 2.313e-05s; avg 7.709e-06s ( +/- 35.05/ 54.64 %); best 5.007e-06s; worst 1.192e-05s; std dev. 3.018e-06 (taking best). -Reference operation time is 5.00679e-06 s (4035 Mflops) with 1 threads. +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. Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 7.673e-03 s (100.00 %) - analyzed arrays in 2.717e-03 s (35.41 %) - cleaned-up arrays in 9.060e-06 s (0.12 %) - deduplicated arrays in 7.868e-06 s (0.10 %) + converted COO to RSB in 3.771e-03 s (100.00 %) + analyzed arrays in 1.656e-03 s (43.91 %) + cleaned-up arrays in 2.098e-05 s (0.56 %) + deduplicated arrays in 1.812e-05 s (0.48 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 4.932e-03 s (64.28 %) - memory allocations took 3.099e-06 s (0.04 %) - leafs setup took 9.537e-07 s (0.01 %) - halfword conversion took 2.146e-06 s (0.03 %) -Built (100 x 100)[0xaaaaf924cc90]{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 2.064e-03 s (54.73 %) + memory allocations took 3.815e-06 s (0.10 %) + leafs setup took 3.099e-06 s (0.08 %) + halfword conversion took 4.053e-06 s (0.11 %) +Built (100 x 100)[0xaaab0bd642c0]{S} @ (0(0..100),0(0..100)) (5050 nnz, 50 nnz/r) flags 0x42644094 (coo:0, csr:1, hw:0, ic:1, fi:0), storage: 1, subm: 1, symflags:'LS' Starting autotuning stage, with subdivision of 1 (current threads=1, requested threads=0, max threads = 12). # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes @@ -6049,16 +6085,16 @@ # 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 7.548e-03 s (100.00 %) - analyzed arrays in 5.059e-03 s (67.03 %) - cleaned-up arrays in 9.060e-06 s (0.12 %) - deduplicated arrays in 7.868e-06 s (0.10 %) + converted COO to RSB in 2.429e-03 s (100.00 %) + analyzed arrays in 1.441e-03 s (59.32 %) + cleaned-up arrays in 2.003e-05 s (0.82 %) + deduplicated arrays in 1.717e-05 s (0.71 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 2.464e-03 s (32.64 %) - memory allocations took 3.099e-06 s (0.04 %) - leafs setup took 1.192e-06 s (0.02 %) - halfword conversion took 2.861e-06 s (0.04 %) -Built (100 x 100)[0xaaaaf926bc60]{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 9.429e-04 s (38.82 %) + memory allocations took 2.861e-06 s (0.12 %) + leafs setup took 1.192e-06 s (0.05 %) + halfword conversion took 2.861e-06 s (0.12 %) +Built (100 x 100)[0xaaab0bd2dab0]{S} @ (0(0..100),0(0..100)) (5050 nnz, 50 nnz/r) flags 0x42644096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 1, symflags:'LS' # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -6104,10 +6140,9 @@ # 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 2.122e-05s; avg 7.073e-06s ( +/- 29.21/ 41.57 %); best 5.007e-06s; worst 1.001e-05s; std dev. 2.135e-06 (taking best). -Reference operation time is 5.00679e-06 s (4035 Mflops) with 1 threads. -Challenging best inner round reference (5.00679e-06 s/1 threads) with: subdivision 0.25, 1 leaves, 2.08 bytes/nz, 5.00679e-06 s/0 threads (speedup 1 x), same?n. -New candidate clone performs slowly; discarding it: 100 x 100, type S, 5050 nnz, 50 nnz/r, 1 subms, 1 lsubms, 2.0800 bpnz +3 iterations (1 th.) took 4.387e-05s; avg 1.462e-05s ( +/- 16.85/ 28.80 %); best 1.216e-05s; worst 1.884e-05s; std dev. 2.993e-06 (taking best). +Reference operation time is 1.21593e-05 s (1661 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, 1.21593e-05 s/0 threads (speedup 1.05882 x), same?n. # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -6140,16 +6175,16 @@ # 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 1.183e-02 s (100.00 %) - analyzed arrays in 5.119e-03 s (43.28 %) - cleaned-up arrays in 9.060e-06 s (0.08 %) - deduplicated arrays in 7.868e-06 s (0.07 %) + converted COO to RSB in 7.150e-03 s (100.00 %) + analyzed arrays in 2.317e-03 s (32.40 %) + cleaned-up arrays in 2.003e-05 s (0.28 %) + deduplicated arrays in 1.693e-05 s (0.24 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 3.600e-03 s (30.43 %) - memory allocations took 3.099e-06 s (0.03 %) - leafs setup took 4.053e-06 s (0.03 %) - halfword conversion took 3.086e-03 s (26.09 %) -Built (100 x 100)[0xaaaaf927cdf0]{S} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 8, symflags:'LS' + shuffled partitions in 2.349e-03 s (32.85 %) + memory allocations took 4.292e-06 s (0.06 %) + leafs setup took 5.007e-06 s (0.07 %) + halfword conversion took 2.438e-03 s (34.10 %) +Built (100 x 100)[0xaaab0bd48a20]{S} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 8, symflags:'LS' # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -6195,9 +6230,9 @@ # 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 0.0111s; avg 0.0037s ( +/- 63.79/ 54.04 %); best 0.00134s; worst 0.0057s; std dev. 0.001798 (taking best). -Reference operation time is 0.00133991 s (15.08 Mflops) with 1 threads. -Challenging best inner round reference (5.00679e-06 s/1 threads) with: subdivision 0.5, 8 leaves, 2.185 bytes/nz, 0.00133991 s/0 threads (speedup 0.00373665 x), same?n. +3 iterations (1 th.) took 0.00356s; avg 0.001187s ( +/- 2.83/ 5.34 %); best 0.001153s; worst 0.00125s; std dev. 4.487e-05 (taking best). +Reference operation time is 0.00115299 s (17.52 Mflops) with 1 threads. +Challenging best inner round reference (1.21593e-05 s/0 threads) with: subdivision 0.5, 8 leaves, 2.185 bytes/nz, 0.00115299 s/0 threads (speedup 0.0105459 x), same?n. New candidate clone performs slowly; discarding it: 100 x 100, type S, 5050 nnz, 50 nnz/r, 11 subms, 8 lsubms, 2.1846 bpnz # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes @@ -6231,16 +6266,16 @@ # 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 2.328e-02 s (100.00 %) - analyzed arrays in 8.522e-03 s (36.60 %) - cleaned-up arrays in 9.060e-06 s (0.04 %) - deduplicated arrays in 7.868e-06 s (0.03 %) + converted COO to RSB in 7.844e-03 s (100.00 %) + analyzed arrays in 2.814e-03 s (35.88 %) + cleaned-up arrays in 2.313e-05 s (0.29 %) + deduplicated arrays in 2.098e-05 s (0.27 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 9.091e-03 s (39.05 %) - memory allocations took 7.153e-06 s (0.03 %) - leafs setup took 4.053e-06 s (0.02 %) - halfword conversion took 5.639e-03 s (24.22 %) -Built (100 x 100)[0xaaaaf927cdf0]{S} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 19, symflags:'LS' + shuffled partitions in 2.782e-03 s (35.47 %) + memory allocations took 6.676e-06 s (0.09 %) + leafs setup took 4.053e-06 s (0.05 %) + halfword conversion took 2.192e-03 s (27.95 %) +Built (100 x 100)[0xaaab0bd48a20]{S} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 19, symflags:'LS' # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -6286,9 +6321,9 @@ # 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 0.02442s; avg 0.008141s ( +/- 91.03/102.16 %); best 0.00073s; worst 0.01646s; std dev. 0.006453 (taking best). -Reference operation time is 0.000730038 s (27.67 Mflops) with 1 threads. -Challenging best inner round reference (5.00679e-06 s/1 threads) with: subdivision 1, 19 leaves, 2.272 bytes/nz, 0.000730038 s/0 threads (speedup 0.00685826 x), same?n. +3 iterations (1 th.) took 0.002736s; avg 0.000912s ( +/- 33.99/ 18.98 %); best 0.000602s; worst 0.001085s; std dev. 0.0002197 (taking best). +Reference operation time is 0.000602007 s (33.55 Mflops) with 1 threads. +Challenging best inner round reference (1.21593e-05 s/0 threads) with: subdivision 1, 19 leaves, 2.272 bytes/nz, 0.000602007 s/0 threads (speedup 0.020198 x), same?n. New candidate clone performs slowly; discarding it: 100 x 100, type S, 5050 nnz, 50 nnz/r, 26 subms, 19 lsubms, 2.2725 bpnz # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes @@ -6322,16 +6357,16 @@ # 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 3.924e-02 s (100.00 %) - analyzed arrays in 1.566e-02 s (39.91 %) - cleaned-up arrays in 9.060e-06 s (0.02 %) - deduplicated arrays in 7.868e-06 s (0.02 %) + converted COO to RSB in 6.057e-03 s (100.00 %) + analyzed arrays in 2.298e-03 s (37.94 %) + cleaned-up arrays in 2.289e-05 s (0.38 %) + deduplicated arrays in 2.003e-05 s (0.33 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 8.462e-03 s (21.57 %) - memory allocations took 6.914e-06 s (0.02 %) - leafs setup took 5.007e-06 s (0.01 %) - halfword conversion took 1.509e-02 s (38.45 %) -Built (100 x 100)[0xaaaaf922efb0]{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 1.958e-03 s (32.32 %) + memory allocations took 5.960e-06 s (0.10 %) + leafs setup took 4.053e-06 s (0.07 %) + halfword conversion took 1.748e-03 s (28.86 %) +Built (100 x 100)[0xaaab0bd784f0]{S} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 36, symflags:'LS' # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -6377,9 +6412,9 @@ # 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 0.008905s; avg 0.002968s ( +/- 77.29/ 55.48 %); best 0.000674s; worst 0.004615s; std dev. 0.001673 (taking best). -Reference operation time is 0.000674009 s (29.97 Mflops) with 1 threads. -Challenging best inner round reference (5.00679e-06 s/1 threads) with: subdivision 2, 36 leaves, 2.383 bytes/nz, 0.000674009 s/0 threads (speedup 0.00742837 x), same?n. +3 iterations (1 th.) took 0.002695s; avg 0.0008983s ( +/- 7.61/ 5.32 %); best 0.0008299s; worst 0.000946s; std dev. 4.959e-05 (taking best). +Reference operation time is 0.000829935 s (24.34 Mflops) with 1 threads. +Challenging best inner round reference (1.21593e-05 s/0 threads) with: subdivision 2, 36 leaves, 2.383 bytes/nz, 0.000829935 s/0 threads (speedup 0.014651 x), same?n. New candidate clone performs slowly; discarding it: 100 x 100, type S, 5050 nnz, 50 nnz/r, 50 subms, 36 lsubms, 2.3834 bpnz # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes @@ -6413,16 +6448,16 @@ # 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 3.525e-02 s (100.00 %) - analyzed arrays in 1.520e-02 s (43.12 %) - cleaned-up arrays in 9.060e-06 s (0.03 %) - deduplicated arrays in 7.868e-06 s (0.02 %) + converted COO to RSB in 5.957e-03 s (100.00 %) + analyzed arrays in 2.122e-03 s (35.62 %) + cleaned-up arrays in 2.003e-05 s (0.34 %) + deduplicated arrays in 1.693e-05 s (0.28 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 8.246e-03 s (23.39 %) - memory allocations took 1.001e-05 s (0.03 %) - leafs setup took 6.199e-06 s (0.02 %) - halfword conversion took 1.177e-02 s (33.39 %) -Built (100 x 100)[0xaaaaf922efb0]{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 2.146e-03 s (36.02 %) + memory allocations took 5.960e-06 s (0.10 %) + leafs setup took 5.960e-06 s (0.10 %) + halfword conversion took 1.640e-03 s (27.53 %) +Built (100 x 100)[0xaaab0bd784f0]{S} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 36, symflags:'LS' # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -6468,11 +6503,11 @@ # 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 0.01174s; avg 0.003915s ( +/- 4.19/ 7.17 %); best 0.003751s; worst 0.004195s; std dev. 0.0001993 (taking best). -Reference operation time is 0.0037508 s (5.386 Mflops) with 1 threads. -Challenging best inner round reference (5.00679e-06 s/1 threads) with: subdivision 4, 36 leaves, 2.383 bytes/nz, 0.0037508 s/0 threads (speedup 0.00133486 x), same?n. +3 iterations (1 th.) took 0.002604s; avg 0.000868s ( +/- 7.02/ 3.91 %); best 0.000807s; worst 0.0009019s; std dev. 4.319e-05 (taking best). +Reference operation time is 0.000807047 s (25.03 Mflops) with 1 threads. +Challenging best inner round reference (1.21593e-05 s/0 threads) with: subdivision 4, 36 leaves, 2.383 bytes/nz, 0.000807047 s/0 threads (speedup 0.0150665 x), same?n. New candidate clone performs slowly; discarding it: 100 x 100, type S, 5050 nnz, 50 nnz/r, 50 subms, 36 lsubms, 2.3834 bpnz -Best sparse multiply performance with subdivision multiplier of 1: 4034.52 Mflops. +Best sparse multiply performance with subdivision multiplier of 0.25: 1661.27 Mflops. # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -6488,29 +6523,29 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success -Last tuner inner round (1 of 1) took 0.181573 s (eq. to 4e+04/ 4e+04 old/new op.times), gained local/global speedup 1 x (5.00679e-06 : 5.00679e-06) / 1 x (5.00679e-06 : 5.00679e-06). This is not amortizable ! -Auto tuning inner round 1 did not find a configuration better than the original. -In 1 tuning rounds (tot. 0.18s, 0.13s for constructor, 0 clones) obtained NO speedup (best stays 4035 Mflops). -Second run of RSB Autotuner took 0.181596 s and estimated a speedup of 1.000000 x (5.007e-06 s -> 5.007e-06 s per op) in same matrix (1 -> 1 lsubm) +Last tuner inner round (1 of 1) took 0.045908 s (eq. to 4e+03/ 4e+03 old/new op.times), gained local/global speedup 1.05882 x (1.28746e-05 : 1.21593e-05) / 1.05882 x (1.28746e-05 : 1.21593e-05). This is amortizable in 64184 op.times. +In 1 tuning rounds (tot. 0.046s, 0.034s for constructor, 0 clones) obtained a SPEEDUP of 5.9% (1.059x) (from 1569 to 1661 Mflops). +Second run of RSB Autotuner took 0.0459461 s and estimated a speedup of 1.058824 x (1.287e-05 s -> 1.216e-05 s per op) in new matrix (1 -> 1 lsubm) +RSB Autotuner suggested a new matrix: freeing the old one. #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 0.007020 0.017252 0.024272 -%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.024272 -%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.007020 -%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.017252 -%: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 0.024272 +%:CONSTRUCTOR_TIMES:lower-100x100-5050nz S N 1 100 100 5050 0.000001 0.000428 0.001610 0.002038 +%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.002039 +%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.000428 +%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.001610 +%:ROW_MAJOR_SORT_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.000001 +%:ROW_MAJOR_SORT_SCALING:lower-100x100-5050nz S N 1 100 100 5050 1.000 +%:SORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.002038 %:ROW_MAJOR_SORT_TO_MOP:lower-100x100-5050nz S N 1 100 100 5050 0.000 %:UNSORTEDCOO2RSB_SCALING:lower-100x100-5050nz S N 1 100 100 5050 1.00 %:SORTEDCOO2RSB_SCALING:lower-100x100-5050nz S N 1 100 100 5050 1.00 %:RSB_SUBDIVISION_SCALING:lower-100x100-5050nz S N 1 100 100 5050 1.00 %:RSB_SHUFFLE_SCALING:lower-100x100-5050nz S N 1 100 100 5050 1.00 -%:CONSTRUCTOR_SCALING:lower-100x100-5050nz S N 1 100 100 5050 nan 1.00 1.00 1.00 +%:CONSTRUCTOR_SCALING:lower-100x100-5050nz S N 1 100 100 5050 1.00 1.00 1.00 1.00 #%:SM_COUNTS: Tot HalfwordCsr FullwordCsr HalfwordCoo FullwordCoo %:SM_COUNTS:lower-100x100-5050nz S N 1 100 100 5050 1 1 0 0 0 %:SM_IDXOCCUPATIONRSBVSCOOANDCSR:lower-100x100-5050nz S N 1 100 100 5050 10504 40400 20600 @@ -6519,34 +6554,34 @@ %: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 0.031601 1e+09 1e+09 +%operation:lower-100x100-5050nz 0.0035789 1e+09 1e+09 %constructor:matrix SORT[1] SCAN[1] SHUFFLE[1] INSERT[1] -%constructor:lower-100x100-5050nz 0 0.00702 0 0.017252 -# so far, program took 6.035s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.621s/0.000s . +%constructor:lower-100x100-5050nz 9.53674e-07 0.000427961 0 0.0016098 +# so far, program took 5.465s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.167s/0.000s . getrusage() stats: ru_maxrss: 6 (maximum resident set size -- MB) -ru_stime : 0.02486s (system CPU time used) -ru_utime : 5.941s (user CPU time used) +ru_stime : 0.04377s (system CPU time used) +ru_utime : 6.708s (user CPU time used) # multi-type benchmarking (DSCZ) -- now using typecode C (last was D). # Cache block size total 524288 bytes, per-thread 524288 bytes -# so far, program took 6.035s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.621s/0.000s . +# so far, program took 5.465s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.167s/0.000s . # Using 1 threads # Using alpha=1 beta=1 order=cols for rsb_spmv/rsb_spsv/rsb_spmm/rsb_spsm. # will use input matrix flags: RSB_FLAG_USE_HALFWORD_INDICES, RSB_FLAG_SORTED_INPUT, RSB_FLAG_LOWER, RSB_FLAG_QUAD_PARTITIONING, RSB_FLAG_SYMMETRIC, RSB_FLAG_OWN_PARTITIONING_ARRAYS # Using 1 threads Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 3.537e-02 s (100.00 %) - analyzed arrays in 7.373e-03 s (20.84 %) - cleaned-up arrays in 9.060e-06 s (0.03 %) - deduplicated arrays in 7.868e-06 s (0.02 %) + converted COO to RSB in 6.238e-03 s (100.00 %) + analyzed arrays in 1.112e-03 s (17.83 %) + cleaned-up arrays in 2.003e-05 s (0.32 %) + deduplicated arrays in 1.597e-05 s (0.26 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.997e-02 s (56.46 %) - memory allocations took 4.053e-06 s (0.01 %) - leafs setup took 4.053e-06 s (0.01 %) - halfword conversion took 8.005e-03 s (22.63 %) -Built (100 x 100)[0xaaaaf927cdf0]{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 0.035s): (100 x 100)[0xaaaaf927cdf0]{C} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x2446196 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LS' + shuffled partitions in 3.409e-03 s (54.65 %) + memory allocations took 3.815e-06 s (0.06 %) + leafs setup took 2.146e-06 s (0.03 %) + halfword conversion took 1.674e-03 s (26.83 %) +Built (100 x 100)[0xaaab0bd55170]{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 0.006s): (100 x 100)[0xaaab0bd55170]{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. @@ -6597,10 +6632,10 @@ # 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 0.01602s; avg 0.005339s ( +/- 25.42/ 49.07 %); best 0.003982s; worst 0.007959s; std dev. 0.001853 (taking best). -Reference operation time is 0.00398207 s (20.29 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: 0.003982 Mflops: 20.291) -Merge (3 -> 1 leaves) took w.c.t. of 4.601e-05s, ~3.6e-05s of computing time (of which 1.502e-05s sorting, 3.099e-06s analysis) +3 iterations (1 th.) took 0.002631s; avg 0.000877s ( +/- 3.65/ 3.77 %); best 0.000845s; worst 0.00091s; std dev. 2.658e-05 (taking best). +Reference operation time is 0.000844955 s (95.63 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: 0.000845 Mflops: 95.626) +Merge (3 -> 1 leaves) took w.c.t. of 7.296e-05s, ~6.294e-05s of computing time (of which 2.909e-05s sorting, 2.861e-06s analysis) # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -6631,8 +6666,8 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 6.104e-05s; avg 2.035e-05s ( +/- 1.56/ 3.13 %); best 2.003e-05s; worst 2.098e-05s; std dev. 4.496e-07 (taking best). -Reference operation time is 2.00272e-05 s (4035 Mflops) with 1 threads. +3 iterations (1 th.) took 0.0001361s; avg 4.538e-05s ( +/- 2.80/ 4.03 %); best 4.411e-05s; worst 4.721e-05s; std dev. 1.325e-06 (taking best). +Reference operation time is 4.41074e-05 s (1832 Mflops) with 1 threads. # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -6648,16 +6683,16 @@ # 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: 2.003e-05 s ~Mflops: 4034.521 nsubm:1 otn:1 -Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 198.833x: 0.003982s -> 2.003e-05s, so taking this instance. +After merge step 1: tpop: 4.411e-05 s ~Mflops: 1831.891 nsubm:1 otn:1 +Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 19.157x: 0.000845s -> 4.411e-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 0.04356s (of which 4.888e-05s partitioning, 0.03161s I/O); computing times: 3.6e-05s in par. loops, 1.502e-05s sorting, 3.099e-06s analyzing) -Total merge + benchmarking process took 0.04356s, equivalent to 2174.9/10.9 new/old ops (0.02981s for 2 clones -- as 1488.4/7.5 ops, or 744.2/3.7 ops per clone), SPEEDUP of 198.833x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 198.833x (0.003982s -> 2.003e-05s), will amortize in 11.0 ops by saving 0.003962s per op. -In 1 tuning rounds (tot. 0.078s, 0.03s for constructor, 2 clones) obtained a SPEEDUP of 19783.3% (198.8x) (from 20.29 to 4035 Mflops). Employed 0.022s for I/O of matrix plots. +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.01026s (of which 7.701e-05s partitioning, 0.007665s I/O); computing times: 6.294e-05s in par. loops, 2.909e-05s sorting, 2.861e-06s analyzing) +Total merge + benchmarking process took 0.01026s, equivalent to 232.5/12.1 new/old ops (0.004195s for 2 clones -- as 95.1/5.0 ops, or 47.6/2.5 ops per clone), SPEEDUP of 19.157x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 19.157x (0.000845s -> 4.411e-05s), will amortize in 12.8 ops by saving 0.0008008s per op. +In 1 tuning rounds (tot. 0.015s, 0.0042s for constructor, 2 clones) obtained a SPEEDUP of 1815.7% (19.16x) (from 95.63 to 1832 Mflops). Employed 0.0071s 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 0.100027 s (3.982e-03 s -> 2.003e-05 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.02213 s (8.450e-04 s -> 4.411e-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 @@ -6723,20 +6758,20 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 6.58e-05s; avg 2.193e-05s ( +/- 9.78/ 18.48 %); best 1.979e-05s; worst 2.599e-05s; std dev. 2.868e-06 (taking best). -Reference operation time is 1.97887e-05 s (4083 Mflops) with 1 threads. +3 iterations (1 th.) took 7.2e-05s; avg 2.4e-05s ( +/- 20.53/ 37.09 %); best 1.907e-05s; worst 3.29e-05s; std dev. 6.306e-06 (taking best). +Reference operation time is 1.90735e-05 s (4236 Mflops) with 1 threads. Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 2.818e-02 s (100.00 %) - analyzed arrays in 1.218e-02 s (43.23 %) - cleaned-up arrays in 1.001e-05 s (0.04 %) - deduplicated arrays in 7.868e-06 s (0.03 %) + converted COO to RSB in 2.785e-03 s (100.00 %) + analyzed arrays in 1.113e-03 s (39.97 %) + cleaned-up arrays in 8.106e-06 s (0.29 %) + deduplicated arrays in 7.868e-06 s (0.28 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.597e-02 s (56.67 %) - memory allocations took 1.907e-06 s (0.01 %) - leafs setup took 4.053e-06 s (0.01 %) - halfword conversion took 5.007e-06 s (0.02 %) -Built (100 x 100)[0xaaaaf924cc90]{C} @ (0(0..100),0(0..100)) (5050 nnz, 50 nnz/r) flags 0x42644094 (coo:0, csr:1, hw:0, ic:1, fi:0), storage: 1, subm: 1, symflags:'LS' + shuffled partitions in 1.651e-03 s (59.28 %) + memory allocations took 2.861e-06 s (0.10 %) + leafs setup took 0.000e+00 s (0.00 %) + halfword conversion took 1.907e-06 s (0.07 %) +Built (100 x 100)[0xaaab0bd642c0]{C} @ (0(0..100),0(0..100)) (5050 nnz, 50 nnz/r) flags 0x42644094 (coo:0, csr:1, hw:0, ic:1, fi:0), storage: 1, subm: 1, symflags:'LS' Starting autotuning stage, with subdivision of 1 (current threads=1, requested threads=0, max threads = 12). # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes @@ -6770,16 +6805,16 @@ # 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 3.153e-02 s (100.00 %) - analyzed arrays in 1.175e-02 s (37.26 %) - cleaned-up arrays in 9.060e-06 s (0.03 %) - deduplicated arrays in 7.153e-06 s (0.02 %) + converted COO to RSB in 3.406e-03 s (100.00 %) + analyzed arrays in 6.690e-04 s (19.64 %) + cleaned-up arrays in 9.060e-06 s (0.27 %) + deduplicated arrays in 7.868e-06 s (0.23 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 7.979e-03 s (25.31 %) - memory allocations took 5.722e-06 s (0.02 %) - leafs setup took 4.053e-06 s (0.01 %) - halfword conversion took 1.177e-02 s (37.34 %) -Built (100 x 100)[0xaaaaf927cdf0]{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 8.402e-04 s (24.67 %) + memory allocations took 9.537e-07 s (0.03 %) + leafs setup took 9.537e-07 s (0.03 %) + halfword conversion took 1.878e-03 s (55.14 %) +Built (100 x 100)[0xaaab0bd2dab0]{C} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 3, symflags:'LS' # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -6825,9 +6860,9 @@ # 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 0.01637s; avg 0.005457s ( +/- 27.32/ 43.24 %); best 0.003966s; worst 0.007816s; std dev. 0.001688 (taking best). -Reference operation time is 0.00396585 s (20.37 Mflops) with 1 threads. -Challenging best inner round reference (1.97887e-05 s/1 threads) with: subdivision 0.25, 3 leaves, 2.121 bytes/nz, 0.00396585 s/0 threads (speedup 0.00498978 x), same?n. +3 iterations (1 th.) took 0.002354s; avg 0.0007847s ( +/- 21.10/ 37.00 %); best 0.0006192s; worst 0.001075s; std dev. 0.000206 (taking best). +Reference operation time is 0.000619173 s (130.5 Mflops) with 1 threads. +Challenging best inner round reference (1.90735e-05 s/1 threads) with: subdivision 0.25, 3 leaves, 2.121 bytes/nz, 0.000619173 s/0 threads (speedup 0.0308048 x), same?n. New candidate clone performs slowly; discarding it: 100 x 100, type C, 5050 nnz, 50 nnz/r, 4 subms, 3 lsubms, 2.1212 bpnz # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes @@ -6861,16 +6896,16 @@ # 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 3.627e-02 s (100.00 %) - analyzed arrays in 1.215e-02 s (33.50 %) - cleaned-up arrays in 9.060e-06 s (0.02 %) - deduplicated arrays in 6.914e-06 s (0.02 %) + converted COO to RSB in 5.140e-03 s (100.00 %) + analyzed arrays in 2.037e-03 s (39.63 %) + cleaned-up arrays in 8.106e-06 s (0.16 %) + deduplicated arrays in 8.106e-06 s (0.16 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.120e-02 s (30.87 %) - memory allocations took 8.821e-06 s (0.02 %) - leafs setup took 4.053e-06 s (0.01 %) - halfword conversion took 1.290e-02 s (35.55 %) -Built (100 x 100)[0xaaaaf927cdf0]{C} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 10, symflags:'LS' + shuffled partitions in 1.524e-03 s (29.65 %) + memory allocations took 3.815e-06 s (0.07 %) + leafs setup took 1.907e-06 s (0.04 %) + halfword conversion took 1.557e-03 s (30.29 %) +Built (100 x 100)[0xaaab0bd48a20]{C} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 10, symflags:'LS' # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -6916,9 +6951,9 @@ # 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 0.02341s; avg 0.007803s ( +/- 90.13/ 58.98 %); best 0.0007699s; worst 0.01241s; std dev. 0.005052 (taking best). -Reference operation time is 0.000769854 s (105 Mflops) with 1 threads. -Challenging best inner round reference (1.97887e-05 s/1 threads) with: subdivision 0.5, 10 leaves, 2.206 bytes/nz, 0.000769854 s/0 threads (speedup 0.0257046 x), same?n. +3 iterations (1 th.) took 0.002284s; avg 0.0007613s ( +/- 17.64/ 19.53 %); best 0.000627s; worst 0.00091s; std dev. 0.000116 (taking best). +Reference operation time is 0.000627041 s (128.9 Mflops) with 1 threads. +Challenging best inner round reference (1.90735e-05 s/1 threads) with: subdivision 0.5, 10 leaves, 2.206 bytes/nz, 0.000627041 s/0 threads (speedup 0.0304183 x), same?n. New candidate clone performs slowly; discarding it: 100 x 100, type C, 5050 nnz, 50 nnz/r, 14 subms, 10 lsubms, 2.2059 bpnz # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes @@ -6952,16 +6987,16 @@ # 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 3.946e-02 s (100.00 %) - analyzed arrays in 4.603e-03 s (11.67 %) - cleaned-up arrays in 9.060e-06 s (0.02 %) - deduplicated arrays in 7.868e-06 s (0.02 %) + converted COO to RSB in 5.252e-03 s (100.00 %) + analyzed arrays in 1.821e-03 s (34.67 %) + cleaned-up arrays in 8.821e-06 s (0.17 %) + deduplicated arrays in 8.106e-06 s (0.15 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.902e-02 s (48.21 %) - memory allocations took 4.768e-06 s (0.01 %) - leafs setup took 7.153e-06 s (0.02 %) - halfword conversion took 1.580e-02 s (40.05 %) -Built (100 x 100)[0xaaaaf9242b70]{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: 24, symflags:'LS' + shuffled partitions in 1.471e-03 s (28.01 %) + memory allocations took 2.146e-06 s (0.04 %) + leafs setup took 1.907e-06 s (0.04 %) + halfword conversion took 1.938e-03 s (36.90 %) +Built (100 x 100)[0xaaab0bd615a0]{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: 24, symflags:'LS' # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -7007,9 +7042,9 @@ # 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 0.02353s; avg 0.007844s ( +/- 1.36/ 1.68 %); best 0.007737s; worst 0.007975s; std dev. 9.879e-05 (taking best). -Reference operation time is 0.00773692 s (10.44 Mflops) with 1 threads. -Challenging best inner round reference (1.97887e-05 s/1 threads) with: subdivision 1, 24 leaves, 2.306 bytes/nz, 0.00773692 s/0 threads (speedup 0.0025577 x), same?n. +3 iterations (1 th.) took 0.002441s; avg 0.0008136s ( +/- 13.35/ 8.77 %); best 0.000705s; worst 0.000885s; std dev. 7.807e-05 (taking best). +Reference operation time is 0.000705004 s (114.6 Mflops) with 1 threads. +Challenging best inner round reference (1.90735e-05 s/1 threads) with: subdivision 1, 24 leaves, 2.306 bytes/nz, 0.000705004 s/0 threads (speedup 0.0270544 x), same?n. New candidate clone performs slowly; discarding it: 100 x 100, type C, 5050 nnz, 50 nnz/r, 33 subms, 24 lsubms, 2.3057 bpnz # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes @@ -7043,16 +7078,16 @@ # librsb version 1.3.0.2 - 202212201855: Initialization success Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 4.013e-02 s (100.00 %) - analyzed arrays in 1.612e-02 s (40.18 %) - cleaned-up arrays in 8.821e-06 s (0.02 %) - deduplicated arrays in 8.106e-06 s (0.02 %) + converted COO to RSB in 6.357e-03 s (100.00 %) + analyzed arrays in 2.194e-03 s (34.51 %) + cleaned-up arrays in 9.060e-06 s (0.14 %) + deduplicated arrays in 7.868e-06 s (0.12 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.600e-02 s (39.88 %) - memory allocations took 9.060e-06 s (0.02 %) - leafs setup took 5.960e-06 s (0.01 %) - halfword conversion took 7.971e-03 s (19.86 %) -Built (100 x 100)[0xaaaaf927f580]{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 2.369e-03 s (37.26 %) + memory allocations took 5.007e-06 s (0.08 %) + leafs setup took 5.007e-06 s (0.08 %) + halfword conversion took 1.766e-03 s (27.78 %) +Built (100 x 100)[0xaaab0bd822d0]{C} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 36, symflags:'LS' # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -7098,9 +7133,9 @@ # 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 0.02837s; avg 0.009456s ( +/- 48.98/ 24.58 %); best 0.004824s; worst 0.01178s; std dev. 0.003275 (taking best). -Reference operation time is 0.00482392 s (16.75 Mflops) with 1 threads. -Challenging best inner round reference (1.97887e-05 s/1 threads) with: subdivision 2, 36 leaves, 2.383 bytes/nz, 0.00482392 s/0 threads (speedup 0.00410221 x), same?n. +3 iterations (1 th.) took 0.002564s; avg 0.0008547s ( +/- 52.27/ 96.92 %); best 0.0004079s; worst 0.001683s; std dev. 0.0005863 (taking best). +Reference operation time is 0.000407934 s (198.1 Mflops) with 1 threads. +Challenging best inner round reference (1.90735e-05 s/1 threads) with: subdivision 2, 36 leaves, 2.383 bytes/nz, 0.000407934 s/0 threads (speedup 0.0467563 x), same?n. New candidate clone performs slowly; discarding it: 100 x 100, type C, 5050 nnz, 50 nnz/r, 50 subms, 36 lsubms, 2.3834 bpnz # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes @@ -7134,16 +7169,16 @@ # 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 1.544e-02 s (100.00 %) - analyzed arrays in 5.993e-03 s (38.81 %) - cleaned-up arrays in 8.821e-06 s (0.06 %) - deduplicated arrays in 8.106e-06 s (0.05 %) + converted COO to RSB in 5.708e-03 s (100.00 %) + analyzed arrays in 2.076e-03 s (36.37 %) + cleaned-up arrays in 8.821e-06 s (0.15 %) + deduplicated arrays in 7.153e-06 s (0.13 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 4.940e-03 s (31.99 %) - memory allocations took 4.053e-06 s (0.03 %) - leafs setup took 1.907e-06 s (0.01 %) - halfword conversion took 4.487e-03 s (29.06 %) -Built (100 x 100)[0xaaaaf927f580]{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: 34, symflags:'LS' + shuffled partitions in 2.077e-03 s (36.39 %) + memory allocations took 6.199e-06 s (0.11 %) + leafs setup took 3.099e-06 s (0.05 %) + halfword conversion took 1.529e-03 s (26.79 %) +Built (100 x 100)[0xaaab0bd822d0]{C} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 36, symflags:'LS' # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -7189,11 +7224,11 @@ # 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 0.008382s; avg 0.002794s ( +/- 41.23/ 32.10 %); best 0.001642s; worst 0.003691s; std dev. 0.0008557 (taking best). -Reference operation time is 0.00164199 s (49.21 Mflops) with 1 threads. -Challenging best inner round reference (1.97887e-05 s/1 threads) with: subdivision 4, 34 leaves, 2.372 bytes/nz, 0.00164199 s/0 threads (speedup 0.0120517 x), same?n. -New candidate clone performs slowly; discarding it: 100 x 100, type C, 5050 nnz, 50 nnz/r, 47 subms, 34 lsubms, 2.3723 bpnz -Best sparse multiply performance with subdivision multiplier of 1: 4083.13 Mflops. +3 iterations (1 th.) took 0.002226s; avg 0.000742s ( +/- 7.97/ 14.14 %); best 0.0006828s; worst 0.0008469s; std dev. 7.438e-05 (taking best). +Reference operation time is 0.000682831 s (118.3 Mflops) with 1 threads. +Challenging best inner round reference (1.90735e-05 s/1 threads) with: subdivision 4, 36 leaves, 2.383 bytes/nz, 0.000682831 s/0 threads (speedup 0.027933 x), same?n. +New candidate clone performs slowly; discarding it: 100 x 100, type C, 5050 nnz, 50 nnz/r, 50 subms, 36 lsubms, 2.3834 bpnz +Best sparse multiply performance with subdivision multiplier of 1: 4236.25 Mflops. # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -7209,23 +7244,23 @@ # 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 0.29222 s (eq. to 1e+04/ 1e+04 old/new op.times), gained local/global speedup 1 x (1.97887e-05 : 1.97887e-05) / 1 x (1.97887e-05 : 1.97887e-05). This is not amortizable ! +Last tuner inner round (1 of 1) took 0.0419478 s (eq. to 2e+03/ 2e+03 old/new op.times), gained local/global speedup 1 x (1.90735e-05 : 1.90735e-05) / 1 x (1.90735e-05 : 1.90735e-05). This is not amortizable ! Auto tuning inner round 1 did not find a configuration better than the original. -In 1 tuning rounds (tot. 0.29s, 0.19s for constructor, 0 clones) obtained NO speedup (best stays 4083 Mflops). -Second run of RSB Autotuner took 0.292246 s and estimated a speedup of 1.000000 x (1.979e-05 s -> 1.979e-05 s per op) in same matrix (1 -> 1 lsubm) +In 1 tuning rounds (tot. 0.042s, 0.03s for constructor, 0 clones) obtained NO speedup (best stays 4236 Mflops). +Second run of RSB Autotuner took 0.0419741 s and estimated a speedup of 1.000000 x (1.907e-05 s -> 1.907e-05 s per op) in same matrix (1 -> 1 lsubm) #min:1 0 #max:1 0 #sum:100 0 #norm:10 0 #used index storage compared to COO:10504 vs 40400 bytes (26.00%) ; compared to CSR:10504 vs 20604 bytes (50.99%) #%:CONSTRUCTOR_*:SORT SCAN INSERT SCAN+INSERT -%:CONSTRUCTOR_TIMES:lower-100x100-5050nz S N 1 100 100 5050 0.000000 0.007373 0.019971 0.027344 -%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.027344 -%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.007373 -%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.019971 +%:CONSTRUCTOR_TIMES:lower-100x100-5050nz S N 1 100 100 5050 0.000000 0.001112 0.003409 0.004521 +%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.004521 +%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.001112 +%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.003409 %: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 0.027344 +%:SORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.004521 %: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 @@ -7240,34 +7275,34 @@ %: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 0.0353749 1e+09 1e+09 +%operation:lower-100x100-5050nz 0.00623798 1e+09 1e+09 %constructor:matrix SORT[1] SCAN[1] SHUFFLE[1] INSERT[1] -%constructor:lower-100x100-5050nz 0 0.00737286 0 0.0199709 -# so far, program took 6.481s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 1.014s/0.000s . +%constructor:lower-100x100-5050nz 0 0.00111198 0 0.00340891 +# so far, program took 5.541s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.231s/0.000s . getrusage() stats: ru_maxrss: 6 (maximum resident set size -- MB) -ru_stime : 0.02613s (system CPU time used) -ru_utime : 6.312s (user CPU time used) +ru_stime : 0.05141s (system CPU time used) +ru_utime : 7.326s (user CPU time used) # multi-type benchmarking (DSCZ) -- now using typecode Z (last was D). # Cache block size total 524288 bytes, per-thread 524288 bytes -# so far, program took 6.481s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 1.014s/0.000s . +# so far, program took 5.541s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.231s/0.000s . # Using 1 threads # Using alpha=1 beta=1 order=cols for rsb_spmv/rsb_spsv/rsb_spmm/rsb_spsm. # will use input matrix flags: RSB_FLAG_USE_HALFWORD_INDICES, RSB_FLAG_SORTED_INPUT, RSB_FLAG_LOWER, RSB_FLAG_QUAD_PARTITIONING, RSB_FLAG_SYMMETRIC, RSB_FLAG_OWN_PARTITIONING_ARRAYS # Using 1 threads Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 2.256e-02 s (100.00 %) - analyzed arrays in 4.815e-03 s (21.35 %) - cleaned-up arrays in 1.001e-05 s (0.04 %) - deduplicated arrays in 8.106e-06 s (0.04 %) - sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.245e-02 s (55.17 %) - memory allocations took 4.768e-06 s (0.02 %) - leafs setup took 4.053e-06 s (0.02 %) - halfword conversion took 5.268e-03 s (23.35 %) -Built (100 x 100)[0xaaaaf9277860]{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 0.023s): (100 x 100)[0xaaaaf9277860]{Z} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x2446196 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LS' + converted COO to RSB in 5.038e-03 s (100.00 %) + analyzed arrays in 9.091e-04 s (18.04 %) + cleaned-up arrays in 1.311e-05 s (0.26 %) + deduplicated arrays in 1.097e-05 s (0.22 %) + sorted arrays in 9.537e-07 s (0.02 %) + shuffled partitions in 2.772e-03 s (55.02 %) + memory allocations took 2.861e-06 s (0.06 %) + leafs setup took 1.907e-06 s (0.04 %) + halfword conversion took 1.327e-03 s (26.34 %) +Built (100 x 100)[0xaaab0bd2ff20]{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 0.005s): (100 x 100)[0xaaab0bd2ff20]{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. @@ -7318,10 +7353,10 @@ # 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 0.0101s; avg 0.003366s ( +/- 51.24/100.64 %); best 0.001641s; worst 0.006753s; std dev. 0.002395 (taking best). -Reference operation time is 0.00164104 s (49.24 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: 0.001641 Mflops: 49.237) -Merge (3 -> 1 leaves) took w.c.t. of 4.911e-05s, ~4.22e-05s of computing time (of which 2.098e-05s sorting, 3.099e-06s analysis) +3 iterations (1 th.) took 0.00207s; avg 0.00069s ( +/- 7.53/ 7.71 %); best 0.000638s; worst 0.0007432s; std dev. 4.293e-05 (taking best). +Reference operation time is 0.000638008 s (126.6 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: 0.000638 Mflops: 126.644) +Merge (3 -> 1 leaves) took w.c.t. of 6.199e-05s, ~5.507e-05s of computing time (of which 2.718e-05s sorting, 3.099e-06s analysis) # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -7352,8 +7387,8 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 6.008e-05s; avg 2.003e-05s ( +/- 4.76/ 4.76 %); best 1.907e-05s; worst 2.098e-05s; std dev. 7.787e-07 (taking best). -Reference operation time is 1.90735e-05 s (4236 Mflops) with 1 threads. +3 iterations (1 th.) took 9.513e-05s; avg 3.171e-05s ( +/- 2.26/ 4.51 %); best 3.099e-05s; worst 3.314e-05s; std dev. 1.012e-06 (taking best). +Reference operation time is 3.09944e-05 s (2607 Mflops) with 1 threads. # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -7369,16 +7404,16 @@ # 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: 1.907e-05 s ~Mflops: 4236.247 nsubm:1 otn:1 -Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 86.037x: 0.001641s -> 1.907e-05s, so taking this instance. +After merge step 1: tpop: 3.099e-05 s ~Mflops: 2606.921 nsubm:1 otn:1 +Applying merge (3 -> 1 leaves, 1 th.) yielded SPEEDUP of 20.585x: 0.000638s -> 3.099e-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 0.04149s (of which 5.198e-05s partitioning, 0.02616s I/O); computing times: 4.22e-05s in par. loops, 2.098e-05s sorting, 3.099e-06s analyzing) -Total merge + benchmarking process took 0.04149s, equivalent to 2175.4/25.3 new/old ops (0.02879s for 2 clones -- as 1509.7/17.5 ops, or 754.8/8.8 ops per clone), SPEEDUP of 86.037x -Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 86.037x (0.001641s -> 1.907e-05s), will amortize in 25.6 ops by saving 0.001622s per op. -In 1 tuning rounds (tot. 0.065s, 0.029s for constructor, 2 clones) obtained a SPEEDUP of 8503.8% (86.04x) (from 49.24 to 4236 Mflops). Employed 0.03s for I/O of matrix plots. +A total of 1 merge steps (of max 6) (3 -> 1 subms) took 0.009296s (of which 6.413e-05s partitioning, 0.007097s I/O); computing times: 5.507e-05s in par. loops, 2.718e-05s sorting, 3.099e-06s analyzing) +Total merge + benchmarking process took 0.009296s, equivalent to 299.9/14.6 new/old ops (0.003777s for 2 clones -- as 121.9/5.9 ops, or 60.9/3.0 ops per clone), SPEEDUP of 20.585x +Applying multi-merge (3 -> 1 leaves, 1 steps, 0 -> 1 th.sp.) yielded SPEEDUP of 20.585x (0.000638s -> 3.099e-05s), will amortize in 15.3 ops by saving 0.000607s per op. +In 1 tuning rounds (tot. 0.013s, 0.0038s for constructor, 2 clones) obtained a SPEEDUP of 1958.5% (20.58x) (from 126.6 to 2607 Mflops). Employed 0.0063s 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 0.0948641 s (1.641e-03 s -> 1.907e-05 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). +First run of RSB Autotuner took 0.019726 s (6.380e-04 s -> 3.099e-05 s per spmv_sxsa) (tuned: 3 -> 1 lsubm). RSB Sparse Blocks Autotuner invoked requesting max 0 splits and max 0 merges in 1 rounds, auto threads spec. Will autotune matrix: 100 x 100, type Z, 5050 nnz, 50 nnz/r, 1 subms, 1 lsubms, 2.0800 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:10 @@ -7444,20 +7479,20 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success -3 iterations (1 th.) took 6.509e-05s; avg 2.17e-05s ( +/- 12.09/ 19.78 %); best 1.907e-05s; worst 2.599e-05s; std dev. 3.059e-06 (taking best). -Reference operation time is 1.90735e-05 s (4236 Mflops) with 1 threads. +3 iterations (1 th.) took 8.512e-05s; avg 2.837e-05s ( +/- 8.40/ 16.81 %); best 2.599e-05s; worst 3.314e-05s; std dev. 3.372e-06 (taking best). +Reference operation time is 2.59876e-05 s (3109 Mflops) with 1 threads. Building a matrix with 5050 nnz, 100 x 100 Duplicates check: 5050 - 0 = 5050 - converted COO to RSB in 1.906e-02 s (100.00 %) - analyzed arrays in 5.211e-03 s (27.34 %) - cleaned-up arrays in 9.060e-06 s (0.05 %) - deduplicated arrays in 8.106e-06 s (0.04 %) + converted COO to RSB in 1.590e-03 s (100.00 %) + analyzed arrays in 5.691e-04 s (35.79 %) + cleaned-up arrays in 1.192e-05 s (0.75 %) + deduplicated arrays in 9.060e-06 s (0.57 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.382e-02 s (72.51 %) - memory allocations took 3.099e-06 s (0.02 %) - leafs setup took 4.053e-06 s (0.02 %) - halfword conversion took 2.861e-06 s (0.02 %) -Built (100 x 100)[0xaaaaf924cc90]{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 9.930e-04 s (62.45 %) + memory allocations took 3.099e-06 s (0.19 %) + leafs setup took 9.537e-07 s (0.06 %) + halfword conversion took 1.907e-06 s (0.12 %) +Built (100 x 100)[0xaaab0bd642c0]{Z} @ (0(0..100),0(0..100)) (5050 nnz, 50 nnz/r) flags 0x42644094 (coo:0, csr:1, hw:0, ic:1, fi:0), storage: 1, subm: 1, symflags:'LS' Starting autotuning stage, with subdivision of 1 (current threads=1, requested threads=0, max threads = 12). # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes @@ -7491,16 +7526,16 @@ # 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 2.753e-02 s (100.00 %) - analyzed arrays in 1.168e-02 s (42.43 %) - cleaned-up arrays in 1.001e-05 s (0.04 %) - deduplicated arrays in 7.153e-06 s (0.03 %) + converted COO to RSB in 3.335e-03 s (100.00 %) + analyzed arrays in 1.068e-03 s (32.03 %) + cleaned-up arrays in 1.192e-05 s (0.36 %) + deduplicated arrays in 9.060e-06 s (0.27 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 8.541e-03 s (31.03 %) - memory allocations took 4.053e-06 s (0.01 %) - leafs setup took 1.907e-06 s (0.01 %) - halfword conversion took 7.284e-03 s (26.46 %) -Built (100 x 100)[0xaaaaf927cdf0]{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 1.123e-03 s (33.67 %) + memory allocations took 2.861e-06 s (0.09 %) + leafs setup took 2.146e-06 s (0.06 %) + halfword conversion took 1.117e-03 s (33.49 %) +Built (100 x 100)[0xaaab0bd3daf0]{Z} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 6, symflags:'LS' # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -7546,9 +7581,9 @@ # 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 0.0135s; avg 0.004499s ( +/- 45.28/ 36.91 %); best 0.002462s; worst 0.00616s; std dev. 0.001533 (taking best). -Reference operation time is 0.00246191 s (32.82 Mflops) with 1 threads. -Challenging best inner round reference (1.90735e-05 s/1 threads) with: subdivision 0.25, 6 leaves, 2.163 bytes/nz, 0.00246191 s/0 threads (speedup 0.00774743 x), same?n. +3 iterations (1 th.) took 0.002452s; avg 0.0008174s ( +/- 23.52/ 20.88 %); best 0.0006251s; worst 0.000988s; std dev. 0.0001489 (taking best). +Reference operation time is 0.000625134 s (129.3 Mflops) with 1 threads. +Challenging best inner round reference (2.59876e-05 s/1 threads) with: subdivision 0.25, 6 leaves, 2.163 bytes/nz, 0.000625134 s/0 threads (speedup 0.0415713 x), same?n. New candidate clone performs slowly; discarding it: 100 x 100, type Z, 5050 nnz, 50 nnz/r, 8 subms, 6 lsubms, 2.1632 bpnz # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes @@ -7582,16 +7617,16 @@ # 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 3.386e-02 s (100.00 %) - analyzed arrays in 1.317e-02 s (38.91 %) - cleaned-up arrays in 8.106e-06 s (0.02 %) - deduplicated arrays in 6.914e-06 s (0.02 %) - sorted arrays in 9.537e-07 s (0.00 %) - shuffled partitions in 8.541e-03 s (25.23 %) - memory allocations took 9.537e-07 s (0.00 %) - leafs setup took 1.907e-06 s (0.01 %) - halfword conversion took 1.212e-02 s (35.80 %) -Built (100 x 100)[0xaaaaf927cdf0]{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' + converted COO to RSB in 4.723e-03 s (100.00 %) + analyzed arrays in 1.599e-03 s (33.85 %) + cleaned-up arrays in 1.287e-05 s (0.27 %) + deduplicated arrays in 1.097e-05 s (0.23 %) + sorted arrays in 0.000e+00 s (0.00 %) + shuffled partitions in 1.549e-03 s (32.80 %) + memory allocations took 6.199e-06 s (0.13 %) + leafs setup took 1.907e-06 s (0.04 %) + halfword conversion took 1.542e-03 s (32.65 %) +Built (100 x 100)[0xaaab0bd48a40]{Z} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 16, symflags:'LS' # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -7637,9 +7672,9 @@ # 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 0.01325s; avg 0.004417s ( +/- 7.72/ 10.89 %); best 0.004076s; worst 0.004898s; std dev. 0.0003499 (taking best). -Reference operation time is 0.004076 s (19.82 Mflops) with 1 threads. -Challenging best inner round reference (1.90735e-05 s/1 threads) with: subdivision 0.5, 16 leaves, 2.25 bytes/nz, 0.004076 s/0 threads (speedup 0.00467946 x), same?n. +3 iterations (1 th.) took 0.002321s; avg 0.0007737s ( +/- 0.46/ 0.80 %); best 0.0007701s; worst 0.0007799s; std dev. 4.401e-06 (taking best). +Reference operation time is 0.000770092 s (104.9 Mflops) with 1 threads. +Challenging best inner round reference (2.59876e-05 s/1 threads) with: subdivision 0.5, 16 leaves, 2.25 bytes/nz, 0.000770092 s/0 threads (speedup 0.0337461 x), same?n. New candidate clone performs slowly; discarding it: 100 x 100, type Z, 5050 nnz, 50 nnz/r, 22 subms, 16 lsubms, 2.2503 bpnz # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes @@ -7673,16 +7708,16 @@ # 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 2.364e-02 s (100.00 %) - analyzed arrays in 7.364e-03 s (31.15 %) - cleaned-up arrays in 8.821e-06 s (0.04 %) - deduplicated arrays in 8.106e-06 s (0.03 %) + converted COO to RSB in 4.544e-03 s (100.00 %) + analyzed arrays in 1.724e-03 s (37.94 %) + cleaned-up arrays in 1.407e-05 s (0.31 %) + deduplicated arrays in 1.287e-05 s (0.28 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 4.944e-03 s (20.91 %) - memory allocations took 3.099e-06 s (0.01 %) - leafs setup took 1.907e-06 s (0.01 %) - halfword conversion took 1.131e-02 s (47.84 %) -Built (100 x 100)[0xaaaaf9277860]{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 1.527e-03 s (33.61 %) + memory allocations took 7.153e-06 s (0.16 %) + leafs setup took 3.815e-06 s (0.08 %) + halfword conversion took 1.255e-03 s (27.62 %) +Built (100 x 100)[0xaaab0bda9a20]{Z} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 36, symflags:'LS' # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -7728,9 +7763,9 @@ # 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 0.01021s; avg 0.003404s ( +/- 55.23/ 71.17 %); best 0.001524s; worst 0.005826s; std dev. 0.001798 (taking best). -Reference operation time is 0.00152397 s (53.02 Mflops) with 1 threads. -Challenging best inner round reference (1.90735e-05 s/1 threads) with: subdivision 1, 36 leaves, 2.383 bytes/nz, 0.00152397 s/0 threads (speedup 0.0125156 x), same?n. +3 iterations (1 th.) took 0.002129s; avg 0.0007097s ( +/- 9.97/ 13.31 %); best 0.000639s; worst 0.0008042s; std dev. 6.951e-05 (taking best). +Reference operation time is 0.000638962 s (126.5 Mflops) with 1 threads. +Challenging best inner round reference (2.59876e-05 s/1 threads) with: subdivision 1, 36 leaves, 2.383 bytes/nz, 0.000638962 s/0 threads (speedup 0.0406716 x), same?n. New candidate clone performs slowly; discarding it: 100 x 100, type Z, 5050 nnz, 50 nnz/r, 50 subms, 36 lsubms, 2.3834 bpnz # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes @@ -7764,16 +7799,16 @@ # 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 2.643e-02 s (100.00 %) - analyzed arrays in 6.412e-03 s (24.26 %) - cleaned-up arrays in 9.060e-06 s (0.03 %) - deduplicated arrays in 8.106e-06 s (0.03 %) + converted COO to RSB in 4.313e-03 s (100.00 %) + analyzed arrays in 1.615e-03 s (37.45 %) + cleaned-up arrays in 1.311e-05 s (0.30 %) + deduplicated arrays in 1.097e-05 s (0.25 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.508e-02 s (57.07 %) - memory allocations took 5.960e-06 s (0.02 %) - leafs setup took 5.960e-06 s (0.02 %) - halfword conversion took 4.904e-03 s (18.55 %) -Built (100 x 100)[0xaaaaf92a6ce0]{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 1.377e-03 s (31.93 %) + memory allocations took 4.768e-06 s (0.11 %) + leafs setup took 3.099e-06 s (0.07 %) + halfword conversion took 1.288e-03 s (29.86 %) +Built (100 x 100)[0xaaab0bda9a20]{Z} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 36, symflags:'LS' # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -7819,9 +7854,9 @@ # 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 0.01469s; avg 0.004896s ( +/- 65.34/ 77.72 %); best 0.001697s; worst 0.008701s; std dev. 0.002891 (taking best). -Reference operation time is 0.00169706 s (47.61 Mflops) with 1 threads. -Challenging best inner round reference (1.90735e-05 s/1 threads) with: subdivision 2, 36 leaves, 2.383 bytes/nz, 0.00169706 s/0 threads (speedup 0.0112391 x), same?n. +3 iterations (1 th.) took 0.001758s; avg 0.000586s ( +/- 25.10/ 15.54 %); best 0.0004389s; worst 0.0006771s; std dev. 0.000105 (taking best). +Reference operation time is 0.000438929 s (184.1 Mflops) with 1 threads. +Challenging best inner round reference (2.59876e-05 s/1 threads) with: subdivision 2, 36 leaves, 2.383 bytes/nz, 0.000438929 s/0 threads (speedup 0.059207 x), same?n. New candidate clone performs slowly; discarding it: 100 x 100, type Z, 5050 nnz, 50 nnz/r, 50 subms, 36 lsubms, 2.3834 bpnz # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes @@ -7855,16 +7890,16 @@ # 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 3.013e-02 s (100.00 %) - analyzed arrays in 8.062e-03 s (26.76 %) - cleaned-up arrays in 9.060e-06 s (0.03 %) - deduplicated arrays in 6.914e-06 s (0.02 %) + converted COO to RSB in 4.165e-03 s (100.00 %) + analyzed arrays in 1.470e-03 s (35.29 %) + cleaned-up arrays in 1.287e-05 s (0.31 %) + deduplicated arrays in 1.001e-05 s (0.24 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 6.090e-03 s (20.21 %) - memory allocations took 5.722e-06 s (0.02 %) - leafs setup took 5.960e-06 s (0.02 %) - halfword conversion took 1.595e-02 s (52.93 %) -Built (100 x 100)[0xaaaaf92a6ce0]{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 1.252e-03 s (30.06 %) + memory allocations took 4.053e-06 s (0.10 %) + leafs setup took 1.907e-06 s (0.05 %) + halfword conversion took 1.414e-03 s (33.95 %) +Built (100 x 100)[0xaaab0bda9a20]{Z} @ (0(0..0),0(0..0)) (5050 nnz, 50 nnz/r) flags 0x42646096 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 36, symflags:'LS' # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -7910,11 +7945,11 @@ # 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 0.004844s; avg 0.001615s ( +/- 15.03/ 14.56 %); best 0.001372s; worst 0.00185s; std dev. 0.0001951 (taking best). -Reference operation time is 0.0013721 s (58.89 Mflops) with 1 threads. -Challenging best inner round reference (1.90735e-05 s/1 threads) with: subdivision 4, 34 leaves, 2.372 bytes/nz, 0.0013721 s/0 threads (speedup 0.013901 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 -Best sparse multiply performance with subdivision multiplier of 1: 4236.25 Mflops. +3 iterations (1 th.) took 0.0017s; avg 0.0005666s ( +/- 6.13/ 3.25 %); best 0.0005319s; worst 0.0005851s; std dev. 2.457e-05 (taking best). +Reference operation time is 0.000531912 s (151.9 Mflops) with 1 threads. +Challenging best inner round reference (2.59876e-05 s/1 threads) with: subdivision 4, 36 leaves, 2.383 bytes/nz, 0.000531912 s/0 threads (speedup 0.048857 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: 3109.17 Mflops. # librsb version 1.3.0.2 - 202212201855: Initializing # Cache block size total 524288 bytes, per-thread 524288 bytes # RSB_IO_WANT_MEMORY_HIERARCHY_INFO_STRING: unset @@ -7930,29 +7965,29 @@ # RSB_IO_WANT_SORT_METHOD: 0 # RSB_IO_WANT_SUBDIVISION_MULTIPLIER: 1 # librsb version 1.3.0.2 - 202212201855: Initialization success -Last tuner inner round (1 of 1) took 0.217898 s (eq. to 1e+04/ 1e+04 old/new op.times), gained local/global speedup 1 x (1.90735e-05 : 1.90735e-05) / 1 x (1.90735e-05 : 1.90735e-05). This is not amortizable ! +Last tuner inner round (1 of 1) took 0.0351849 s (eq. to 1e+03/ 1e+03 old/new op.times), gained local/global speedup 1 x (2.59876e-05 : 2.59876e-05) / 1 x (2.59876e-05 : 2.59876e-05). This is not amortizable ! Auto tuning inner round 1 did not find a configuration better than the original. -In 1 tuning rounds (tot. 0.22s, 0.16s for constructor, 0 clones) obtained NO speedup (best stays 4236 Mflops). -Second run of RSB Autotuner took 0.217921 s and estimated a speedup of 1.000000 x (1.907e-05 s -> 1.907e-05 s per op) in same matrix (1 -> 1 lsubm) +In 1 tuning rounds (tot. 0.035s, 0.023s for constructor, 0 clones) obtained NO speedup (best stays 3109 Mflops). +Second run of RSB Autotuner took 0.0352099 s and estimated a speedup of 1.000000 x (2.599e-05 s -> 2.599e-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 0.004815 0.012446 0.017261 -%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.017261 -%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.004815 -%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.012446 -%: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 0.017261 +%:CONSTRUCTOR_TIMES:lower-100x100-5050nz S N 1 100 100 5050 0.000001 0.000909 0.002772 0.003681 +%:UNSORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.003682 +%:RSB_SUBDIVISION_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.000909 +%:RSB_SHUFFLE_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.002772 +%:ROW_MAJOR_SORT_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.000001 +%:ROW_MAJOR_SORT_SCALING:lower-100x100-5050nz S N 1 100 100 5050 1.000 +%:SORTEDCOO2RSB_TIME:lower-100x100-5050nz S N 1 100 100 5050 0.003681 %:ROW_MAJOR_SORT_TO_MOP:lower-100x100-5050nz S N 1 100 100 5050 0.000 %:UNSORTEDCOO2RSB_SCALING:lower-100x100-5050nz S N 1 100 100 5050 1.00 %:SORTEDCOO2RSB_SCALING:lower-100x100-5050nz S N 1 100 100 5050 1.00 %:RSB_SUBDIVISION_SCALING:lower-100x100-5050nz S N 1 100 100 5050 1.00 %:RSB_SHUFFLE_SCALING:lower-100x100-5050nz S N 1 100 100 5050 1.00 -%:CONSTRUCTOR_SCALING:lower-100x100-5050nz S N 1 100 100 5050 nan 1.00 1.00 1.00 +%:CONSTRUCTOR_SCALING:lower-100x100-5050nz S N 1 100 100 5050 1.00 1.00 1.00 1.00 #%:SM_COUNTS: Tot HalfwordCsr FullwordCsr HalfwordCoo FullwordCoo %:SM_COUNTS:lower-100x100-5050nz S N 1 100 100 5050 1 1 0 0 0 %:SM_IDXOCCUPATIONRSBVSCOOANDCSR:lower-100x100-5050nz S N 1 100 100 5050 10504 40400 20600 @@ -7961,68 +7996,68 @@ %: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 0.022558 1e+09 1e+09 +%operation:lower-100x100-5050nz 0.00503802 1e+09 1e+09 %constructor:matrix SORT[1] SCAN[1] SHUFFLE[1] INSERT[1] -%constructor:lower-100x100-5050nz 0 0.0048151 0 0.0124459 -# so far, program took 6.828s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 1.326s/0.000s . +%constructor:lower-100x100-5050nz 9.53674e-07 0.00090909 0 0.00277209 +# so far, program took 5.604s of wall clock time; ancillary tests 0.000s; I/O 0.000s; checks 0.000s; conversions 0.000s; rsb/mkl tuning 0.286s/0.000s . getrusage() stats: ru_maxrss: 6 (maximum resident set size -- MB) -ru_stime : 0.04411s (system CPU time used) -ru_utime : 6.683s (user CPU time used) +ru_stime : 0.06356s (system CPU time used) +ru_utime : 7.82s (user CPU time used) # benchmarking terminated --- finalizing run. # ====== BEGIN Total summary record. #pr: ======== All results (not limiting) #pr: Dump from a base of 4 samples (of max 4) ordered by (1,1,1,1,1,4,1) = (filename x cores x incX x incY x nrhs x typecode x transA). pr: BESTCODE MTX NR NC NNZ NRHS TYPE SYM TRANS NT AT-NT AT-MKL-NT BPNZ AT-BPNZ NSUBM AT-SUBM RSBBEST-MFLOPS OPTIME MKL-OPTIME AT-OPTIME AT-MKL-OPTIME AT-TIME RWminBW-GBps CB-bpf AT-MS CMFLOPS -pr: 1:R_R lower-100x100-5050nz 100 100 5050 1 D S N 1 1 0 2.1212 2.0800 3 1 4034.52 4.865e-03 0.000e+00 5.007e-06 0.000e+00 1.021e-01 1.06e+01 2.60e+00 1 2.02e-02 -pr: 2:R_R lower-100x100-5050nz 100 100 5050 1 S S N 1 1 0 2.1212 2.0800 3 1 4034.52 4.461e-03 0.000e+00 5.007e-06 0.000e+00 1.031e-01 6.37e+00 1.56e+00 1 2.02e-02 -pr: 3:R_R lower-100x100-5050nz 100 100 5050 1 C S N 1 1 0 2.1212 2.0800 3 1 4034.52 3.982e-03 0.000e+00 2.003e-05 0.000e+00 1.000e-01 2.66e+00 6.50e-01 1 8.08e-02 -pr: 4:R_R lower-100x100-5050nz 100 100 5050 1 Z S N 1 1 0 2.1212 2.0800 3 1 4236.25 1.641e-03 0.000e+00 1.907e-05 0.000e+00 9.486e-02 5.04e+00 1.17e+00 1 8.08e-02 +pr: 1:R_R lower-100x100-5050nz 100 100 5050 1 D S N 1 1 0 2.1212 2.0800 3 1 1264.55 1.199e-03 0.000e+00 1.597e-05 0.000e+00 3.047e-02 3.34e+00 2.60e+00 1 2.02e-02 +pr: 2:R_R lower-100x100-5050nz 100 100 5050 1 S S N 1 1 0 2.1212 2.0800 3 1 1436.02 1.211e-03 0.000e+00 1.407e-05 0.000e+00 3.066e-02 2.27e+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 1831.89 8.450e-04 0.000e+00 4.411e-05 0.000e+00 2.213e-02 1.21e+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 2606.92 6.380e-04 0.000e+00 3.099e-05 0.000e+00 1.973e-02 3.10e+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. 53589.6 % faster, avg. sp. ratio 536.896x, max sp. ratio 971.714x, avg. ratio 0.000x) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 12737.9/4973.6/20597.6/50951.7 tuned ops) -#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 31.8/ 21.0/ 57.8/127.0 untuned ops) -#pr: (and amortizes from untuned rsb in avg. 32.0, min. 21.0, max. 58.5 ops) +#pr: (in succ. cases rsb autotuning gave avg. 4922.1 % faster, avg. sp. ratio 50.221x, max sp. ratio 86.085x, avg. ratio 0.000x) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 1306.3/501.7/2179.6/5225.4 tuned ops) +#pr: (in succ. cases rsb autotuning took an avg/min/max/tot of: 27.0/ 25.3/ 30.9/107.8 untuned ops) +#pr: (and amortizes from untuned rsb in avg. 27.9, min. 25.6, 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 6.089/ 2.622/ 10.487,GBps) -#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 24.719/ 2.662/ 10.646,GBps) +#pr: (avg/min/max operands (mtx,lhs,rhs) read bandwidth lower bound 2.441/ 1.190/ 3.287,GBps) +#pr: (avg/min/max operands (mtx,rhs:r;lhs:rw) bandwidth lower bound 9.914/ 1.209/ 3.337,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.: 0.10 s, min 0.09 s, max 0.10 s, tot 0.40 s (4 samples) -#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.10 s, min 0.09 s, max 0.10 s, tot 0.40 s (4 samples) -#pr: best tun. rsb canon. mflops were: on avg. 4.085e+03, min 4.035e+03, max 4.236e+03 (4 samples) -#pr: ref. unt. rsb canon. mflops were: on avg. 1.955e+01, min 4.152e+00, max 4.924e+01 (4 samples) -#pr: best tun. rsb operation time was: on avg. 1.228e-05s, min 5.007e-06s, max 2.003e-05s, tot 4.911e-05s (4 samples) -#pr: ref. unt. rsb operation time was: on avg. 3.737e-03s, min 1.641e-03s, max 4.865e-03s, tot 1.495e-02s (4 samples) -#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 4.529e+00 1.811e+01 -#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.006e+00 -#pr: Record collection took 1.35 s. +#pr: rsb auto tuning (either succ. or uns.) time was: on avg.: 0.03 s, min 0.02 s, max 0.03 s, tot 0.10 s (4 samples) +#pr: rsb auto tuning ( only successful ) time was: on avg.: 0.03 s, min 0.02 s, max 0.03 s, tot 0.10 s (4 samples) +#pr: best tun. rsb canon. mflops were: on avg. 1.785e+03, min 1.265e+03, max 2.607e+03 (4 samples) +#pr: ref. unt. rsb canon. mflops were: on avg. 6.395e+01, min 1.668e+01, max 1.266e+02 (4 samples) +#pr: best tun. rsb operation time was: on avg. 2.629e-05s, min 1.407e-05s, max 4.411e-05s, tot 1.051e-04s (4 samples) +#pr: ref. unt. rsb operation time was: on avg. 9.732e-04s, min 6.380e-04s, max 1.211e-03s, tot 3.893e-03s (4 samples) +#pr: min / max ratio of in-memory MEMSET bandwidth to extrapolated read bandwidth ratio: 1.452e+01 4.010e+01 +#pr: in-cache to in-memory MEMSET bandwidth ratio: 1.000e+00 +#pr: Record collection took 0.29 s. #pr: Record comprises 40 memory benchmark samples (prepend RSB_PR_MBW=1 to dump this). -#pr: Record comprises 88 environment variables in 3807 bytes (prepend RSB_PR_ENV=1 to dump this). +#pr: Record comprises 89 environment variables in 3907 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 1739127222 (after 6.8s of w.c.t.) +# terminating run at 1704718243 (after 5.6s 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 85636 Feb 9 18:53 test-tuning-lower-100x100-5050nz--D-N-1--base.eps --rw-r--r-- 1 pbuilder1 pbuilder1 84559 Feb 9 18:53 test-tuning-lower-100x100-5050nz--D-N-1--mv-tuned_merge1_1x1th.eps --rw-r--r-- 1 pbuilder1 pbuilder1 85638 Feb 9 18:53 test-tuning-lower-100x100-5050nz--S-N-1--base.eps --rw-r--r-- 1 pbuilder1 pbuilder1 84560 Feb 9 18:53 test-tuning-lower-100x100-5050nz--S-N-1--mv-tuned_merge1_1x1th.eps --rw-r--r-- 1 pbuilder1 pbuilder1 85638 Feb 9 18:53 test-tuning-lower-100x100-5050nz--C-N-1--base.eps --rw-r--r-- 1 pbuilder1 pbuilder1 84559 Feb 9 18:53 test-tuning-lower-100x100-5050nz--C-N-1--mv-tuned_merge1_1x1th.eps --rw-r--r-- 1 pbuilder1 pbuilder1 85638 Feb 9 18:53 test-tuning-lower-100x100-5050nz--Z-N-1--base.eps --rw-r--r-- 1 pbuilder1 pbuilder1 84560 Feb 9 18:53 test-tuning-lower-100x100-5050nz--Z-N-1--mv-tuned_merge1_1x1th.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 85644 Jan 8 12:50 test-tuning-lower-100x100-5050nz--D-N-1--base.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 84565 Jan 8 12:50 test-tuning-lower-100x100-5050nz--D-N-1--mv-tuned_merge1_1x1th.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 85642 Jan 8 12:50 test-tuning-lower-100x100-5050nz--S-N-1--base.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 84564 Jan 8 12:50 test-tuning-lower-100x100-5050nz--S-N-1--mv-tuned_merge1_1x1th.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 85644 Jan 8 12:50 test-tuning-lower-100x100-5050nz--C-N-1--base.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 84566 Jan 8 12:50 test-tuning-lower-100x100-5050nz--C-N-1--mv-tuned_merge1_1x1th.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 85641 Jan 8 12:50 test-tuning-lower-100x100-5050nz--Z-N-1--base.eps +-rw-r--r-- 1 pbuilder2 pbuilder2 84566 Jan 8 12:50 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 4098 Feb 9 18:53 test.txt +-rw-r--r-- 1 pbuilder2 pbuilder2 4091 Jan 8 12:50 test.txt + RSB_PR_WLTC=2 + RSB_PR_SR=0 + rsbench --read-performance-record test.rpr @@ -8032,29 +8067,29 @@ /usr/bin/kpsepath ++ kpsepath tex ++ sed 's/!!//g;s/:/\n/g;' -+ find . /nonexistent/first-build/.texlive2022/texmf-config/tex/kpsewhich// /nonexistent/first-build/.texlive2022/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/.texlive2022/texmf-config/tex/generic// /nonexistent/first-build/.texlive2022/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/.texlive2022/texmf-config/tex/latex// /nonexistent/first-build/.texlive2022/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/.texlive2022/texmf-config/tex/// /nonexistent/first-build/.texlive2022/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/.texlive2022/texmf-config/tex/kpsewhich//': No such file or directory -find: '/nonexistent/first-build/.texlive2022/texmf-var/tex/kpsewhich//': No such file or directory -find: '/nonexistent/first-build/texmf/tex/kpsewhich//': No such file or directory ++ find . /nonexistent/second-build/.texlive2022/texmf-config/tex/kpsewhich// /nonexistent/second-build/.texlive2022/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/.texlive2022/texmf-config/tex/generic// /nonexistent/second-build/.texlive2022/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/.texlive2022/texmf-config/tex/latex// /nonexistent/second-build/.texlive2022/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/.texlive2022/texmf-config/tex/// /nonexistent/second-build/.texlive2022/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/.texlive2022/texmf-config/tex/kpsewhich//': No such file or directory +find: '/nonexistent/second-build/.texlive2022/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/.texlive2022/texmf-config/tex/generic//': No such file or directory -find: '/nonexistent/first-build/.texlive2022/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/.texlive2022/texmf-config/tex/generic//': No such file or directory +find: '/nonexistent/second-build/.texlive2022/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/.texlive2022/texmf-config/tex/latex//': No such file or directory -find: '/nonexistent/first-build/.texlive2022/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/.texlive2022/texmf-config/tex/latex//': No such file or directory +find: '/nonexistent/second-build/.texlive2022/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/.texlive2022/texmf-config/tex///': No such file or directory -find: '/nonexistent/first-build/.texlive2022/texmf-var/tex///': No such file or directory -find: '/nonexistent/first-build/texmf/tex///': No such file or directory +find: '/nonexistent/second-build/.texlive2022/texmf-config/tex///': No such file or directory +find: '/nonexistent/second-build/.texlive2022/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 @@ -8069,7 +8104,7 @@ This error may be safely ignored. Correctly allocated a matrix. Summary information of the matrix: -(3 x 3)[0xaaaadfbbd030]{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)[0xaaab09142030]{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. @@ -8084,7 +8119,7 @@ This error may be safely ignored. Correctly allocated a matrix. Summary information of the matrix: -(3 x 3)[0xaaaacdedb030]{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)[0xaaaaf8c92030]{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. @@ -8148,51 +8183,51 @@ Done. Building a matrix with 5 nnz, 5 x 5 Duplicates check: 5 - 0 = 5 - converted COO to RSB in 3.280e-02 s (100.00 %) - analyzed arrays in 1.234e-02 s (37.60 %) - cleaned-up arrays in 9.537e-07 s (0.00 %) + converted COO to RSB in 8.496e-03 s (100.00 %) + analyzed arrays in 2.999e-03 s (35.30 %) + cleaned-up arrays in 0.000e+00 s (0.00 %) deduplicated arrays in 0.000e+00 s (0.00 %) - sorted arrays in 4.669e-03 s (14.23 %) - shuffled partitions in 6.480e-03 s (19.75 %) - memory allocations took 3.099e-06 s (0.01 %) - leafs setup took 1.192e-06 s (0.00 %) - halfword conversion took 9.315e-03 s (28.39 %) -Built (5 x 5)[0xaaaacdedffc0]{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 6.571e-04 s (7.73 %) + shuffled partitions in 2.419e-03 s (28.47 %) + memory allocations took 5.960e-06 s (0.07 %) + leafs setup took 3.099e-06 s (0.04 %) + halfword conversion took 2.411e-03 s (28.38 %) +Built (5 x 5)[0xaaaaf8c96fc0]{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)[0xaaaacdedffc0]{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)[0xaaaaf8c96fc0]{D} @ (0(0..0),0(0..0)) (5 nnz, 1 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 2, symflags:'' -Before auto-tuning, 100 multiplications took 0.347126s. +Before auto-tuning, 100 multiplications took 0.090823s. Threads autotuning (may take more than 1.500000s)... Will use autotuning routine to sample matrix: 5 x 5, type D, 5 nnz, 1 nnz/r, 3 subms, 2 lsubms, 4.0000 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:0.1 -Sampling (15 x 0.1 s stages, transA=N, nrhs=2, timer gran.=3.01003e-08), 12 suggested as starting thread count(default). -3 iterations (12 th.) took 0.008499s; avg 0.002833s ( +/- 1.30/ 0.95 %); best 0.002796s; worst 0.00286s; std dev. 2.695e-05 (taking best). -Reference operation time is 0.00279617 s (0.007153 Mflops) with 12 threads. -3 iterations (12 th.) took 0.007323s; avg 0.002441s ( +/- 34.09/ 17.21 %); best 0.001609s; worst 0.002861s; std dev. 0.0005884 (taking best). -Reference operation time is 0.00160885 s (0.01243 Mflops) with 12 threads. -After 0.015895s, autotuning routine did not find a better threads count configuration. -(5 x 5)[0xaaaacdedffc0]{D} @ (0(0..0),0(0..0)) (5 nnz, 1 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 2, symflags:'' -After threads auto-tuning, 100 multiplications took 0.293335s -- effective speedup of 1.18338 x +Sampling (15 x 0.1 s stages, transA=N, nrhs=2, timer gran.=7.53522e-08), 12 suggested as starting thread count(default). +3 iterations (12 th.) took 0.001838s; avg 0.0006127s ( +/- 1.43/ 0.87 %); best 0.0006039s; worst 0.000618s; std dev. 6.23e-06 (taking best). +Reference operation time is 0.000603914 s (0.03312 Mflops) with 12 threads. +3 iterations (12 th.) took 0.001779s; avg 0.000593s ( +/- 0.01/ 0.03 %); best 0.0005929s; worst 0.0005932s; std dev. 1.124e-07 (taking best). +Reference operation time is 0.000592947 s (0.03373 Mflops) with 12 threads. +After 0.003663s, autotuning routine did not find a better threads count configuration. +(5 x 5)[0xaaaaf8c96fc0]{D} @ (0(0..0),0(0..0)) (5 nnz, 1 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 2, symflags:'' +After threads auto-tuning, 100 multiplications took 0.059045s -- effective speedup of 1.5382 x Matrix autotuning (may take more than 1.500000s; using 12 threads )... Will autotune matrix: 5 x 5, type D, 5 nnz, 1 nnz/r, 3 subms, 2 lsubms, 4.0000 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:0.1 -Starting autotuning (15 x 0.1 s stages, transA=N, nrhs=2, timer gran.=3.01003e-08), 12 suggested as starting thread count. -3 iterations (12 th.) took 0.006326s; avg 0.002109s ( +/- 12.93/ 6.51 %); best 0.001836s; worst 0.002246s; std dev. 0.0001928 (taking best). -Reference operation time is 0.00183606 s (0.01089 Mflops) with 12 threads. -Starting merge (user-supplied threads) based auto-tuning procedure (transA=N, nrhs=2, order=cols) (max 6 steps, inclusive 3 grace steps) on: 5 x 5, type D, 5 nnz, 1 nnz/r, 3 subms, 2 lsubms, 4.0000 bpnz (tpop: 0.001836 Mflops: 0.011) -Merge (2 -> 1 leaves) took w.c.t. of 1.812e-05s, ~2.861e-06s of computing time (of which 9.537e-07s sorting, 4.053e-06s analysis) -3 iterations (12 th.) took 4.053e-06s; avg 1.351e-06s ( +/- 97.77/200.00 %); best 3.01e-08s; worst 4.053e-06s; std dev. 1.911e-06 (taking best). -Reference operation time is 3.01003e-08 s (664.4 Mflops) with 12 threads. -After merge step 1: tpop: 3.01e-08 s ~Mflops: 664.444 nsubm:1 otn:12 -Applying merge (2 -> 1 leaves, 12 th.) yielded SPEEDUP of 60998.020x: 0.001836s -> 3.01e-08s, so taking this instance. +Starting autotuning (15 x 0.1 s stages, transA=N, nrhs=2, timer gran.=7.53522e-08), 12 suggested as starting thread count. +3 iterations (12 th.) took 0.001468s; avg 0.0004894s ( +/- 0.47/ 0.75 %); best 0.0004871s; worst 0.000493s; std dev. 2.614e-06 (taking best). +Reference operation time is 0.000487089 s (0.04106 Mflops) with 12 threads. +Starting merge (user-supplied threads) based auto-tuning procedure (transA=N, nrhs=2, order=cols) (max 6 steps, inclusive 3 grace steps) on: 5 x 5, type D, 5 nnz, 1 nnz/r, 3 subms, 2 lsubms, 4.0000 bpnz (tpop: 0.0004871 Mflops: 0.041) +Merge (2 -> 1 leaves) took w.c.t. of 1.097e-05s, ~1.907e-06s of computing time (of which 0s sorting, 2.146e-06s analysis) +3 iterations (12 th.) took 3.099e-06s; avg 1.033e-06s ( +/- 92.71/107.69 %); best 7.535e-08s; worst 2.146e-06s; std dev. 8.778e-07 (taking best). +Reference operation time is 7.53522e-08 s (265.4 Mflops) with 12 threads. +After merge step 1: tpop: 7.535e-08 s ~Mflops: 265.420 nsubm:1 otn:12 +Applying merge (2 -> 1 leaves, 12 th.) yielded SPEEDUP of 6464.167x: 0.0004871s -> 7.535e-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 0.006072s (of which 4.22e-05s partitioning, 0s I/O); computing times: 2.861e-06s in par. loops, 9.537e-07s sorting, 4.053e-06s analyzing) -Total merge + benchmarking process took 0.006072s, equivalent to 201726.7/3.3 new/old ops (0.0119s for 2 clones -- as 395239.6/6.5 ops, or 197619.8/3.2 ops per clone), SPEEDUP of 60998.020x -Applying multi-merge (2 -> 1 leaves, 1 steps, 12 -> 12 th.sp.) yielded SPEEDUP of 60998.020x (0.001836s -> 3.01e-08s), will amortize in 3.3 ops by saving 0.001836s per op. -In 1 tuning rounds (tot. 0.018s, 0.012s for constructor, 2 clones) obtained a SPEEDUP of 6099702.0% (6.1e+04x) (from 0.01089 to 664.4 Mflops). -After 0.018340s, autotuning routine declared speedup of 60998 x, when using threads count of 12. -(5 x 5)[0xaaaacdeddfc0]{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 0.000013s -- further speedup of 22369.7 x +A total of 1 merge steps (of max 6) (2 -> 1 subms) took 0.001471s (of which 0.0002s partitioning, 0s I/O); computing times: 1.907e-06s in par. loops, 0s sorting, 2.146e-06s analyzing) +Total merge + benchmarking process took 0.001471s, equivalent to 19522.2/3.0 new/old ops (0.002711s for 2 clones -- as 35978.5/5.6 ops, or 17989.2/2.8 ops per clone), SPEEDUP of 6464.167x +Applying multi-merge (2 -> 1 leaves, 1 steps, 12 -> 12 th.sp.) yielded SPEEDUP of 6464.167x (0.0004871s -> 7.535e-08s), will amortize in 3.0 ops by saving 0.000487s per op. +In 1 tuning rounds (tot. 0.0044s, 0.0027s for constructor, 2 clones) obtained a SPEEDUP of 646316.7% (6464x) (from 0.04106 to 265.4 Mflops). +After 0.004419s, autotuning routine declared speedup of 6464.17 x, when using threads count of 12. +(5 x 5)[0xaaaaf8c94fc0]{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 0.000010s -- further speedup of 5896.5 x 0/2 0 0 -> 0 1/2 1 0 -> 5 0/2 0 3 -> 0 @@ -8203,7 +8238,7 @@ Correctly initialized the library. Correctly allocated a matrix with 7 nonzeroes. Summary information of the matrix: -(6 x 6)[0xaaaacdedffc0]{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)[0xaaaaf8c96fc0]{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 @@ -8354,62 +8389,66 @@ 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 5.858e-02 s (100.00 %) - analyzed arrays in 9.131e-03 s (15.59 %) - cleaned-up arrays in 1.070e-04 s (0.18 %) - deduplicated arrays in 8.607e-05 s (0.15 %) - sorted arrays in 1.968e-02 s (33.59 %) - shuffled partitions in 1.977e-02 s (33.75 %) - memory allocations took 3.791e-05 s (0.06 %) - leafs setup took 6.914e-06 s (0.01 %) - halfword conversion took 9.761e-03 s (16.66 %) -Built (500 x 500)[0xaaaad277ce60]{D} @ (0(0..0),0(0..0)) (62500 nnz, 1.2e+02 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 55, symflags:'' + converted COO to RSB in 1.656e-02 s (100.00 %) + analyzed arrays in 2.606e-03 s (15.74 %) + cleaned-up arrays in 2.110e-04 s (1.27 %) + deduplicated arrays in 2.081e-04 s (1.26 %) + sorted arrays in 6.696e-03 s (40.43 %) + shuffled partitions in 4.537e-03 s (27.40 %) + memory allocations took 5.794e-05 s (0.35 %) + leafs setup took 1.097e-05 s (0.07 %) + halfword conversion took 2.228e-03 s (13.45 %) +Built (500 x 500)[0xaaaad43a8e60]{D} @ (0(0..0),0(0..0)) (62500 nnz, 1.2e+02 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 55, symflags:'' Allocated matrix of 62500 nonzeroes: -(500 x 500)[0xaaaad277ce60]{D} @ (0(0..0),0(0..0)) (62500 nnz, 1.2e+02 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 55, symflags:'' +(500 x 500)[0xaaaad43a8e60]{D} @ (0(0..0),0(0..0)) (62500 nnz, 1.2e+02 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 55, symflags:'' -Before auto-tuning, 100 multiplications took 0.455049s. +Before auto-tuning, 100 multiplications took 0.099620s. Threads autotuning (may take more than 1.500000s)... Will use autotuning routine to sample matrix: 500 x 500, type D, 62500 nnz, 1.2e+02 nnz/r, 75 subms, 55 lsubms, 2.1196 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:0.1 -Sampling (15 x 0.1 s stages, transA=N, nrhs=2, timer gran.=2.93493e-08), 12 suggested as starting thread count(default). -3 iterations (12 th.) took 0.02305s; avg 0.007683s ( +/- 62.33/ 56.34 %); best 0.002894s; worst 0.01201s; std dev. 0.003736 (taking best). -Reference operation time is 0.00289392 s (86.39 Mflops) with 12 threads. -3 iterations (12 th.) took 0.00984s; avg 0.00328s ( +/- 40.58/ 56.04 %); best 0.001949s; worst 0.005118s; std dev. 0.001343 (taking best). -Reference operation time is 0.00194883 s (128.3 Mflops) with 12 threads. -After 0.032969s, autotuning routine did not find a better threads count configuration. -(500 x 500)[0xaaaad277ce60]{D} @ (0(0..0),0(0..0)) (62500 nnz, 1.2e+02 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 55, symflags:'' -After threads auto-tuning, 100 multiplications took 0.413338s -- effective speedup of 1.10091 x +Sampling (15 x 0.1 s stages, transA=N, nrhs=2, timer gran.=5.47051e-08), 12 suggested as starting thread count(default). +3 iterations (12 th.) took 0.001924s; avg 0.0006413s ( +/- 16.73/ 14.46 %); best 0.0005341s; worst 0.0007341s; std dev. 8.231e-05 (taking best). +Reference operation time is 0.000534058 s (468.1 Mflops) with 12 threads. +3 iterations (12 th.) took 0.002045s; avg 0.0006816s ( +/- 1.26/ 0.63 %); best 0.0006731s; worst 0.0006859s; std dev. 6.069e-06 (taking best). +Reference operation time is 0.000673056 s (371.4 Mflops) with 12 threads. +After 0.004025s, autotuning routine did not find a better threads count configuration. +(500 x 500)[0xaaaad43a8e60]{D} @ (0(0..0),0(0..0)) (62500 nnz, 1.2e+02 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 55, symflags:'' +After threads auto-tuning, 100 multiplications took 0.125918s -- effective speedup of 0.791148 x Matrix autotuning (may take more than 1.500000s; using 12 threads )... Will autotune matrix: 500 x 500, type D, 62500 nnz, 1.2e+02 nnz/r, 75 subms, 55 lsubms, 2.1196 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:0.1 -Starting autotuning (15 x 0.1 s stages, transA=N, nrhs=2, timer gran.=2.93493e-08), 12 suggested as starting thread count. -3 iterations (12 th.) took 0.01952s; avg 0.006507s ( +/- 27.98/ 55.15 %); best 0.004686s; worst 0.0101s; std dev. 0.002538 (taking best). -Reference operation time is 0.00468612 s (53.35 Mflops) with 12 threads. -Starting merge (user-supplied threads) based auto-tuning procedure (transA=N, nrhs=2, order=cols) (max 6 steps, inclusive 3 grace steps) on: 500 x 500, type D, 62500 nnz, 1.2e+02 nnz/r, 75 subms, 55 lsubms, 2.1196 bpnz (tpop: 0.004686 Mflops: 53.349) -Merge (55 -> 37 leaves) took w.c.t. of 0.01351s, ~0.0004151s of computing time (of which 0.000113s sorting, 8.821e-06s analysis) -3 iterations (12 th.) took 0.05179s; avg 0.01726s ( +/- 52.49/ 84.45 %); best 0.008203s; worst 0.03184s; std dev. 0.01041 (taking best). -Reference operation time is 0.00820303 s (30.48 Mflops) with 12 threads. -After merge step 1: tpop: 0.008203 s ~Mflops: 30.477 nsubm:37 otn:12 -Applying merge (55 -> 37 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.750x: 0.004686s -> 0.008203s. +Starting autotuning (15 x 0.1 s stages, transA=N, nrhs=2, timer gran.=5.47051e-08), 12 suggested as starting thread count. +3 iterations (12 th.) took 0.004782s; avg 0.001594s ( +/- 51.94/ 46.42 %); best 0.000766s; worst 0.002334s; std dev. 0.0006431 (taking best). +Reference operation time is 0.000766039 s (326.4 Mflops) with 12 threads. +Starting merge (user-supplied threads) based auto-tuning procedure (transA=N, nrhs=2, order=cols) (max 6 steps, inclusive 3 grace steps) on: 500 x 500, type D, 62500 nnz, 1.2e+02 nnz/r, 75 subms, 55 lsubms, 2.1196 bpnz (tpop: 0.000766 Mflops: 326.354) +Merge (55 -> 37 leaves) took w.c.t. of 0.000644s, ~0.00169s of computing time (of which 0.0003071s sorting, 8.106e-06s analysis) +3 iterations (12 th.) took 0.003823s; avg 0.001274s ( +/- 38.02/ 47.76 %); best 0.0007899s; worst 0.001883s; std dev. 0.0004548 (taking best). +Reference operation time is 0.000789881 s (316.5 Mflops) with 12 threads. +After merge step 1: tpop: 0.0007899 s ~Mflops: 316.503 nsubm:37 otn:12 +Applying merge (55 -> 37 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.031x: 0.000766s -> 0.0007899s. +Merge (37 -> 28 leaves) took w.c.t. of 0.0002408s, ~0.0001197s of computing time (of which 5.126e-05s sorting, 5.007e-06s analysis) +3 iterations (12 th.) took 0.002271s; avg 0.000757s ( +/- 19.56/ 17.45 %); best 0.0006089s; worst 0.0008891s; std dev. 0.0001149 (taking best). +Reference operation time is 0.000608921 s (410.6 Mflops) with 12 threads. +After merge step 2: tpop: 0.0006089 s ~Mflops: 410.562 nsubm:28 otn:12 +Applying merge (37 -> 28 leaves, 12 th.) yielded SPEEDUP of 1.258x: 0.000766s -> 0.0006089s, so taking this instance. +Merge (28 -> 22 leaves) took w.c.t. of 0.0002658s, ~0.0001059s of computing time (of which 6.08e-05s sorting, 4.053e-06s analysis) +3 iterations (12 th.) took 0.002013s; avg 0.0006711s ( +/- 55.73/ 57.39 %); best 0.0002971s; worst 0.001056s; std dev. 0.00031 (taking best). +Reference operation time is 0.00029707 s (841.6 Mflops) with 12 threads. +After merge step 3: tpop: 0.0002971 s ~Mflops: 841.554 nsubm:22 otn:12 +Applying merge (28 -> 22 leaves, 12 th.) yielded SPEEDUP of 2.050x: 0.0006089s -> 0.0002971s, so taking this instance. +Merge (22 -> 16 leaves) took w.c.t. of 0.0002749s, ~7.391e-05s of computing time (of which 3.791e-05s sorting, 4.053e-06s analysis) +3 iterations (12 th.) took 0.009727s; avg 0.003242s ( +/- 81.25/153.71 %); best 0.000608s; worst 0.008226s; std dev. 0.003526 (taking best). +Reference operation time is 0.000607967 s (411.2 Mflops) with 12 threads. +After merge step 4: tpop: 0.000608 s ~Mflops: 411.206 nsubm:16 otn:12 +Applying merge (22 -> 16 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 2.047x: 0.0002971s -> 0.000608s. 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) (55 -> 37 subms) took 0.06534s (of which 0.01352s partitioning, 0s I/O); computing times: 0.0004151s in par. loops, 0.000113s sorting, 8.821e-06s analyzing) -Total merge + benchmarking process took 0.06534s, equivalent to 13.9/13.9 new/old ops (0.01603s for 1 clones -- as 3.4/3.4 ops, or 3.4/3.4 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) -Merging based autotuning FAILED (=NO SPEEDUP); let's try splitting then... -3 iterations (12 th.) took 0.01659s; avg 0.005529s ( +/- 40.48/ 48.17 %); best 0.003291s; worst 0.008193s; std dev. 0.002024 (taking best). -Reference operation time is 0.00329113 s (75.96 Mflops) with 12 threads. -Starting split (user-supplied threads) based auto-tuning procedure (transA=N, nrhs=2, order=cols) (max 6 steps, inclusive 3 grace steps) on: 500 x 500, type D, 62500 nnz, 1.2e+02 nnz/r, 75 subms, 55 lsubms, 2.1196 bpnz (tpop: 0.003291 Mflops: 75.962) -Split (55 -> 136 leaves, 75 -> 183 subms) took 0.01863s (of which: 6.199e-06s analysis, -4.696e+10s mem.mgmt); compute time: 0.0003238s overall, 0.0001025s searches, 0.0002213s shuffle, 0.0001009s switch, 5.722e-06s quadrants. -3 iterations (12 th.) took 0.01483s; avg 0.004945s ( +/- 4.41/ 8.45 %); best 0.004727s; worst 0.005363s; std dev. 0.0002957 (taking best). -Reference operation time is 0.00472689 s (52.89 Mflops) with 12 threads. -After split step 1: tpop: 0.004727 s ~Mflops: 52.889 nsubm:136 otn:12 -Applying split (55 -> 136 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.436x: 0.003291s -> 0.004727s. -Skipping further split based tests after 1 definite performance degradations in a row (and last exceeding limit). -A total of 1 split steps (of max 6) (55 -> 136 subms) took 0.03364s (of which 0.01878s partitioning, 0s I/O); computing times: 0.0003238s in par. loops, 0.0001025s sorting, 6.199e-06s analyzing) -Total split + benchmarking process took 0.03364s, equivalent to 10.2/10.2 new/old ops (0.01981s for 1 clones -- as 6.0/6.0 ops, or 6.0/6.0 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) -In 1 tuning rounds (tot. 0.17s, 0.036s for constructor, 2 clones) obtained NO speedup (best stays 75.96 Mflops). -After 0.171046s, autotuning routine declared speedup of 1 x, when using threads count of 12. -(500 x 500)[0xaaaad277ce60]{D} @ (0(0..0),0(0..0)) (62500 nnz, 1.2e+02 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 55, symflags:'' -After threads auto-tuning, 100 multiplications took 0.499971s -- further speedup of 0.826724 x +A total of 4 merge steps (of max 6) (55 -> 16 subms) took 0.02243s (of which 0.00145s partitioning, 0s I/O); computing times: 0.001989s in par. loops, 0.000457s sorting, 2.122e-05s analyzing) +Total merge + benchmarking process took 0.02243s, equivalent to 75.5/29.3 new/old ops (0.00443s for 3 clones -- as 14.9/5.8 ops, or 5.0/1.9 ops per clone), SPEEDUP of 2.579x +Applying multi-merge (55 -> 22 leaves, 3 steps, 12 -> 12 th.sp.) yielded SPEEDUP of 2.579x (0.000766s -> 0.0002971s), will amortize in 47.8 ops by saving 0.000469s per op. +In 1 tuning rounds (tot. 0.029s, 0.0044s for constructor, 3 clones) obtained a SPEEDUP of 157.9% (2.579x) (from 326.4 to 841.6 Mflops). +After 0.028844s, autotuning routine declared speedup of 2.57865 x, when using threads count of 12. +(500 x 500)[0xaaaad44acec0]{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 0.100889s -- further speedup of 1.24809 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! @@ -8417,19 +8456,19 @@ Correctly initialized the library. Building a matrix with 7 nnz, 6 x 6 Duplicates check: 1 - 0 = 1 - converted COO to RSB in 2.910e-02 s (100.00 %) - analyzed arrays in 2.463e-02 s (84.63 %) - cleaned-up arrays in 7.153e-06 s (0.02 %) + converted COO to RSB in 2.239e-03 s (100.00 %) + analyzed arrays in 1.688e-03 s (75.39 %) + cleaned-up arrays in 4.053e-06 s (0.18 %) deduplicated arrays in 0.000e+00 s (0.00 %) - sorted arrays in 9.537e-07 s (0.00 %) - shuffled partitions in 4.435e-03 s (15.24 %) - memory allocations took 1.597e-05 s (0.05 %) - leafs setup took 5.007e-06 s (0.02 %) - halfword conversion took 6.199e-06 s (0.02 %) -Built (6 x 6)[0xaaaaeabd3060]{D} @ (0(0..1),0(5..6)) (1 nnz, 0.17 nnz/r) flags 0x20443ee (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 1, symflags:'UT' + sorted arrays in 2.146e-06 s (0.10 %) + shuffled partitions in 5.209e-04 s (23.27 %) + memory allocations took 1.192e-05 s (0.53 %) + leafs setup took 4.053e-06 s (0.18 %) + halfword conversion took 5.960e-06 s (0.27 %) +Built (6 x 6)[0xaaaac9dfc060]{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)[0xaaaaeabd3060]{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)[0xaaaac9dfc060]{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 @@ -8455,55 +8494,55 @@ 1 1 Will autotune matrix: 6 x 6, type D, 1 nnz, 0.17 nnz/r, 1 subms, 1 lsubms, 4.0000 bpnz. -Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:3.716e-08 -3 iterations (12 th.) took 2.813e-05s; avg 9.378e-06s ( +/- 99.60/189.83 %); best 3.716e-08s; worst 2.718e-05s; std dev. 1.259e-05 (taking best). -Reference operation time is 3.71575e-08 s (53.82 Mflops) with 12 threads. -Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=cols) (max 6 steps, inclusive 3 grace steps) on: 6 x 6, type D, 1 nnz, 0.17 nnz/r, 1 subms, 1 lsubms, 4.0000 bpnz (tpop: 3.716e-08 Mflops: 53.825) +Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:3.005e-08 +3 iterations (12 th.) took 2.694e-05s; avg 8.98e-06s ( +/- 99.67/189.38 %); best 3.005e-08s; worst 2.599e-05s; std dev. 1.203e-05 (taking best). +Reference operation time is 3.00527e-08 s (66.55 Mflops) with 12 threads. +Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=cols) (max 6 steps, inclusive 3 grace steps) on: 6 x 6, type D, 1 nnz, 0.17 nnz/r, 1 subms, 1 lsubms, 4.0000 bpnz (tpop: 3.005e-08 Mflops: 66.550) Merge (1 -> 1 leaves) took w.c.t. of 0s, ~0s of computing time (of which 0s sorting, 0s analysis) -3 iterations (12 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 88.31/200.00 %); best 3.716e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). -Reference operation time is 3.71575e-08 s (53.82 Mflops) with 12 threads. -After merge step 1: tpop: 3.716e-08 s ~Mflops: 53.825 nsubm:1 otn:12 -Applying merge (1 -> 1 leaves, 12 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=1.00000x): 3.716e-08s -> 3.716e-08s, so IGNORING this instance. +3 iterations (12 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 90.55/200.00 %); best 3.005e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). +Reference operation time is 3.00527e-08 s (66.55 Mflops) with 12 threads. +After merge step 1: tpop: 3.005e-08 s ~Mflops: 66.550 nsubm:1 otn:12 +Applying merge (1 -> 1 leaves, 12 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=1.00000x): 3.005e-08s -> 3.005e-08s, so IGNORING this instance. Merged all the matrix leaves: no reason to continue merging. -A total of 1 merge steps (of max 6) (1 -> 1 subms) took 9.775e-06s (of which 2.861e-06s partitioning, 0s I/O); computing times: 0s in par. loops, 0s sorting, 0s analyzing) -Total merge + benchmarking process took 9.775e-06s, equivalent to 263.1/263.1 new/old ops (0.02787s for 1 clones -- as 749945.5/749945.5 ops, or 749945.5/749945.5 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 3.099e-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 333.2/333.2 new/old ops (0.001483s for 1 clones -- as 49345.5/49345.5 ops, or 49345.5/49345.5 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) Merging based autotuning FAILED (=NO SPEEDUP); let's try splitting then... -3 iterations (12 th.) took 9.06e-06s; avg 3.02e-06s ( +/- 98.77/200.00 %); best 3.716e-08s; worst 9.06e-06s; std dev. 4.271e-06 (taking best). -Reference operation time is 3.71575e-08 s (53.82 Mflops) with 12 threads. -Starting split (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=cols) (max 6 steps, inclusive 3 grace steps) on: 6 x 6, type D, 1 nnz, 0.17 nnz/r, 1 subms, 1 lsubms, 4.0000 bpnz (tpop: 3.716e-08 Mflops: 53.825) -Split (1 -> 1 leaves, 1 -> 1 subms) took 3.004e-05s (of which: 5.007e-06s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. -3 iterations (12 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 88.31/200.00 %); best 3.716e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). -Reference operation time is 3.71575e-08 s (53.82 Mflops) with 12 threads. -After split step 1: tpop: 3.716e-08 s ~Mflops: 53.825 nsubm:1 otn:12 -Applying split (1 -> 1 leaves, 12 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=1.00000x): 3.716e-08s -> 3.716e-08s, so IGNORING this instance. -Split (1 -> 1 leaves, 1 -> 1 subms) took 1.907e-06s (of which: 0s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. -3 iterations (12 th.) took 0s; avg 0s ( +/- -inf/ nan %); best 3.716e-08s; worst 0s; std dev. 0 (taking best). -Reference operation time is 3.71575e-08 s (53.82 Mflops) with 12 threads. -After split step 2: tpop: 3.716e-08 s ~Mflops: 53.825 nsubm:1 otn:12 -Applying split (1 -> 1 leaves, 12 th.) yielded NEGLIGIBLE change (2th in a row) (old/new=1.00000x): 3.716e-08s -> 3.716e-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 (12 th.) took 0s; avg 0s ( +/- -inf/ nan %); best 3.716e-08s; worst 0s; std dev. 0 (taking best). -Reference operation time is 3.71575e-08 s (53.82 Mflops) with 12 threads. -After split step 3: tpop: 3.716e-08 s ~Mflops: 53.825 nsubm:1 otn:12 -Applying split (1 -> 1 leaves, 12 th.) yielded NEGLIGIBLE change (3th in a row) (old/new=1.00000x): 3.716e-08s -> 3.716e-08s, so IGNORING this instance. -Split (1 -> 1 leaves, 1 -> 1 subms) took 9.537e-07s (of which: 0s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. -3 iterations (12 th.) took 0s; avg 0s ( +/- -inf/ nan %); best 3.716e-08s; worst 0s; std dev. 0 (taking best). -Reference operation time is 3.71575e-08 s (53.82 Mflops) with 12 threads. -After split step 4: tpop: 3.716e-08 s ~Mflops: 53.825 nsubm:1 otn:12 -Applying split (1 -> 1 leaves, 12 th.) yielded NEGLIGIBLE change (4th in a row) (old/new=1.00000x): 3.716e-08s -> 3.716e-08s, so IGNORING this instance. +3 iterations (12 th.) took 5.007e-06s; avg 1.669e-06s ( +/- 98.20/142.86 %); best 3.005e-08s; worst 4.053e-06s; std dev. 1.73e-06 (taking best). +Reference operation time is 3.00527e-08 s (66.55 Mflops) with 12 threads. +Starting split (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=cols) (max 6 steps, inclusive 3 grace steps) on: 6 x 6, type D, 1 nnz, 0.17 nnz/r, 1 subms, 1 lsubms, 4.0000 bpnz (tpop: 3.005e-08 Mflops: 66.550) +Split (1 -> 1 leaves, 1 -> 1 subms) took 2.003e-05s (of which: 3.099e-06s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. +3 iterations (12 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 90.55/200.00 %); best 3.005e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). +Reference operation time is 3.00527e-08 s (66.55 Mflops) with 12 threads. +After split step 1: tpop: 3.005e-08 s ~Mflops: 66.550 nsubm:1 otn:12 +Applying split (1 -> 1 leaves, 12 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=1.00000x): 3.005e-08s -> 3.005e-08s, so IGNORING this instance. +Split (1 -> 1 leaves, 1 -> 1 subms) took 1.192e-06s (of which: 0s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. +3 iterations (12 th.) took 3.099e-06s; avg 1.033e-06s ( +/- 97.09/107.69 %); best 3.005e-08s; worst 2.146e-06s; std dev. 8.778e-07 (taking best). +Reference operation time is 3.00527e-08 s (66.55 Mflops) with 12 threads. +After split step 2: tpop: 3.005e-08 s ~Mflops: 66.550 nsubm:1 otn:12 +Applying split (1 -> 1 leaves, 12 th.) yielded NEGLIGIBLE change (2th in a row) (old/new=1.00000x): 3.005e-08s -> 3.005e-08s, so IGNORING this instance. +Split (1 -> 1 leaves, 1 -> 1 subms) took 8.106e-06s (of which: 0s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. +3 iterations (12 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 90.55/200.00 %); best 3.005e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). +Reference operation time is 3.00527e-08 s (66.55 Mflops) with 12 threads. +After split step 3: tpop: 3.005e-08 s ~Mflops: 66.550 nsubm:1 otn:12 +Applying split (1 -> 1 leaves, 12 th.) yielded NEGLIGIBLE change (3th in a row) (old/new=1.00000x): 3.005e-08s -> 3.005e-08s, so IGNORING this instance. +Split (1 -> 1 leaves, 1 -> 1 subms) took 1.192e-06s (of which: 0s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. +3 iterations (12 th.) took 0s; avg 0s ( +/- -inf/ nan %); best 3.005e-08s; worst 0s; std dev. 0 (taking best). +Reference operation time is 3.00527e-08 s (66.55 Mflops) with 12 threads. +After split step 4: tpop: 3.005e-08 s ~Mflops: 66.550 nsubm:1 otn:12 +Applying split (1 -> 1 leaves, 12 th.) yielded NEGLIGIBLE change (4th in a row) (old/new=1.00000x): 3.005e-08s -> 3.005e-08s, so IGNORING this instance. Split (1 -> 1 leaves, 1 -> 1 subms) took 9.537e-07s (of which: 0s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. -3 iterations (12 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 88.31/200.00 %); best 3.716e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). -Reference operation time is 3.71575e-08 s (53.82 Mflops) with 12 threads. -After split step 5: tpop: 3.716e-08 s ~Mflops: 53.825 nsubm:1 otn:12 -Applying split (1 -> 1 leaves, 12 th.) yielded NEGLIGIBLE change (5th in a row) (old/new=1.00000x): 3.716e-08s -> 3.716e-08s, so IGNORING this instance. -Split (1 -> 1 leaves, 1 -> 1 subms) took 5.007e-06s (of which: 9.537e-07s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. -3 iterations (12 th.) took 0s; avg 0s ( +/- -inf/ nan %); best 3.716e-08s; worst 0s; std dev. 0 (taking best). -Reference operation time is 3.71575e-08 s (53.82 Mflops) with 12 threads. -After split step 6: tpop: 3.716e-08 s ~Mflops: 53.825 nsubm:1 otn:12 -Applying split (1 -> 1 leaves, 12 th.) yielded NEGLIGIBLE change (6th in a row) (old/new=1.00000x): 3.716e-08s -> 3.716e-08s, so IGNORING this instance. -A total of 6 split steps (of max 6) (1 -> 1 subms) took 0.0001068s (of which 7.796e-05s partitioning, 0s I/O); computing times: 0s in par. loops, 0s sorting, 5.96e-06s analyzing) -Total split + benchmarking process took 0.0001068s, equivalent to 2874.6/2874.6 new/old ops (0.03174s for 1 clones -- as 854173.9/854173.9 ops, or 854173.9/854173.9 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) -In 1 tuning rounds (tot. 0.06s, 0.06s for constructor, 2 clones) obtained NO speedup (best stays 53.82 Mflops). +3 iterations (12 th.) took 0s; avg 0s ( +/- -inf/ nan %); best 3.005e-08s; worst 0s; std dev. 0 (taking best). +Reference operation time is 3.00527e-08 s (66.55 Mflops) with 12 threads. +After split step 5: tpop: 3.005e-08 s ~Mflops: 66.550 nsubm:1 otn:12 +Applying split (1 -> 1 leaves, 12 th.) yielded NEGLIGIBLE change (5th in a row) (old/new=1.00000x): 3.005e-08s -> 3.005e-08s, so IGNORING this instance. +Split (1 -> 1 leaves, 1 -> 1 subms) took 2.146e-06s (of which: 0s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. +3 iterations (12 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 90.55/200.00 %); best 3.005e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). +Reference operation time is 3.00527e-08 s (66.55 Mflops) with 12 threads. +After split step 6: tpop: 3.005e-08 s ~Mflops: 66.550 nsubm:1 otn:12 +Applying split (1 -> 1 leaves, 12 th.) yielded NEGLIGIBLE change (6th in a row) (old/new=1.00000x): 3.005e-08s -> 3.005e-08s, so IGNORING this instance. +A total of 6 split steps (of max 6) (1 -> 1 subms) took 0.0002811s (of which 0.0002429s partitioning, 0s I/O); computing times: 0s in par. loops, 0s sorting, 3.099e-06s analyzing) +Total split + benchmarking process took 0.0002811s, equivalent to 9353.4/9353.4 new/old ops (0.00139s for 1 clones -- as 46251.5/46251.5 ops, or 46251.5/46251.5 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) +In 1 tuning rounds (tot. 0.0032s, 0.0029s for constructor, 2 clones) obtained NO speedup (best stays 66.55 Mflops). Backsolving we should get a unitary vector: %%MatrixMarket matrix array real general @@ -8538,135 +8577,182 @@ /build/reproducible-path/librsb-1.3.0.2+dfsg/examples/fortran Building a matrix with 210 nnz, 20 x 20 Duplicates check: 210 - 0 = 210 - converted COO to RSB in 6.920e-02 s (100.00 %) - analyzed arrays in 2.434e-02 s (35.16 %) - cleaned-up arrays in 1.907e-06 s (0.00 %) - deduplicated arrays in 1.907e-06 s (0.00 %) - sorted arrays in 1.298e-02 s (18.76 %) - shuffled partitions in 1.616e-02 s (23.35 %) - memory allocations took 3.695e-05 s (0.05 %) - leafs setup took 7.868e-06 s (0.01 %) - halfword conversion took 1.566e-02 s (22.63 %) -Built (20 x 20)[0xaaaae6bb0580]{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 8.150e-03 s (100.00 %) + analyzed arrays in 2.460e-03 s (30.18 %) + cleaned-up arrays in 2.861e-06 s (0.04 %) + deduplicated arrays in 1.907e-06 s (0.02 %) + sorted arrays in 1.872e-03 s (22.97 %) + shuffled partitions in 2.126e-03 s (26.09 %) + memory allocations took 3.910e-05 s (0.48 %) + leafs setup took 5.007e-06 s (0.06 %) + halfword conversion took 1.630e-03 s (20.00 %) +Built (20 x 20)[0xaaaae5518580]{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:3e-08 -Starting autotuning (16 x 3.0005e-08 s stages, transA=N, nrhs=1, timer gran.=3.0005e-08), 12 suggested as starting thread count(default). -3 iterations (12 th.) took 0.0238s; avg 0.007934s ( +/- 9.40/ 5.88 %); best 0.007188s; worst 0.0084s; std dev. 0.0005327 (taking best). -Reference operation time is 0.00718808 s (0.1169 Mflops) with 12 threads. -Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=cols) (max 6 steps, inclusive 3 grace steps) on: 20 x 20, type D, 210 nnz, 10 nnz/r, 30 subms, 22 lsubms, 3.7524 bpnz (tpop: 0.007188 Mflops: 0.117) -Merge (22 -> 16 leaves) took w.c.t. of 0.007144s, ~6.104e-05s of computing time (of which 1.907e-06s sorting, 7.868e-06s analysis) -3 iterations (12 th.) took 0.02718s; avg 0.009059s ( +/- 11.76/ 19.36 %); best 0.007993s; worst 0.01081s; std dev. 0.001249 (taking best). -Reference operation time is 0.00799298 s (0.1051 Mflops) with 12 threads. -After merge step 1: tpop: 0.007993 s ~Mflops: 0.105 nsubm:16 otn:12 -Applying merge (22 -> 16 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.112x: 0.007188s -> 0.007993s. -Merge (16 -> 10 leaves) took w.c.t. of 0.01184s, ~2.193e-05s of computing time (of which 2.861e-06s sorting, 6.914e-06s analysis) -3 iterations (12 th.) took 0.03317s; avg 0.01106s ( +/- 63.64/ 54.77 %); best 0.00402s; worst 0.01711s; std dev. 0.00539 (taking best). -Reference operation time is 0.00402021 s (0.2089 Mflops) with 12 threads. -After merge step 2: tpop: 0.00402 s ~Mflops: 0.209 nsubm:10 otn:12 -Applying merge (16 -> 10 leaves, 12 th.) yielded SPEEDUP of 1.788x: 0.007188s -> 0.00402s, so taking this instance. -Merge (10 -> 8 leaves) took w.c.t. of 2.003e-05s, ~5.007e-06s of computing time (of which 9.537e-07s sorting, 6.914e-06s analysis) -3 iterations (12 th.) took 0.02314s; avg 0.007715s ( +/- 12.36/ 6.60 %); best 0.006761s; worst 0.008224s; std dev. 0.000675 (taking best). -Reference operation time is 0.00676084 s (0.1242 Mflops) with 12 threads. -After merge step 3: tpop: 0.006761 s ~Mflops: 0.124 nsubm:8 otn:12 -Applying merge (10 -> 8 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.682x: 0.00402s -> 0.006761s. -Skipping further merge based tests after 1 definite performance degradations in a row (and last exceeding limit). -A total of 3 merge steps (of max 6) (22 -> 8 subms) took 0.1234s (of which 0.01903s partitioning, 0s I/O); computing times: 8.798e-05s in par. loops, 5.722e-06s sorting, 2.17e-05s analyzing) -Total merge + benchmarking process took 0.1234s, equivalent to 30.7/17.2 new/old ops (0.04508s for 2 clones -- as 11.2/6.3 ops, or 5.6/3.1 ops per clone), SPEEDUP of 1.788x -Applying multi-merge (22 -> 10 leaves, 2 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 1.788x (0.007188s -> 0.00402s), will amortize in 38.9 ops by saving 0.003168s per op. -In 1 tuning rounds (tot. 0.17s, 0.045s for constructor, 2 clones) obtained a SPEEDUP of 78.8% (1.788x) (from 0.1169 to 0.2089 Mflops). +Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:5.27e-08 +Starting autotuning (16 x 5.27024e-08 s stages, transA=N, nrhs=1, timer gran.=5.27024e-08), 12 suggested as starting thread count(default). +3 iterations (12 th.) took 0.004937s; avg 0.001646s ( +/- 9.83/ 18.99 %); best 0.001484s; worst 0.001958s; std dev. 0.000221 (taking best). +Reference operation time is 0.00148392 s (0.5661 Mflops) with 12 threads. +Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=1, order=cols) (max 6 steps, inclusive 3 grace steps) on: 20 x 20, type D, 210 nnz, 10 nnz/r, 30 subms, 22 lsubms, 3.7524 bpnz (tpop: 0.001484 Mflops: 0.566) +Merge (22 -> 16 leaves) took w.c.t. of 0.0003209s, ~0.0002198s of computing time (of which 1.907e-06s sorting, 4.053e-06s analysis) +3 iterations (12 th.) took 0.005008s; avg 0.001669s ( +/- 20.62/ 33.28 %); best 0.001325s; worst 0.002225s; std dev. 0.0003966 (taking best). +Reference operation time is 0.00132513 s (0.6339 Mflops) with 12 threads. +After merge step 1: tpop: 0.001325 s ~Mflops: 0.634 nsubm:16 otn:12 +Applying merge (22 -> 16 leaves, 12 th.) yielded SPEEDUP of 1.120x: 0.001484s -> 0.001325s, so taking this instance. +Merge (16 -> 10 leaves) took w.c.t. of 0.000427s, ~1.502e-05s of computing time (of which 1.907e-06s sorting, 3.099e-06s analysis) +3 iterations (12 th.) took 0.003878s; avg 0.001293s ( +/- 35.02/ 47.83 %); best 0.0008399s; worst 0.001911s; std dev. 0.0004526 (taking best). +Reference operation time is 0.000839949 s (1 Mflops) with 12 threads. +After merge step 2: tpop: 0.0008399 s ~Mflops: 1.000 nsubm:10 otn:12 +Applying merge (16 -> 10 leaves, 12 th.) yielded SPEEDUP of 1.578x: 0.001325s -> 0.0008399s, so taking this instance. +Merge (10 -> 8 leaves) took w.c.t. of 1.097e-05s, ~5.007e-06s of computing time (of which 9.537e-07s sorting, 2.861e-06s analysis) +3 iterations (12 th.) took 0.002097s; avg 0.000699s ( +/- 23.74/ 13.03 %); best 0.0005331s; worst 0.0007901s; std dev. 0.0001175 (taking best). +Reference operation time is 0.000533104 s (1.576 Mflops) with 12 threads. +After merge step 3: tpop: 0.0005331 s ~Mflops: 1.576 nsubm:8 otn:12 +Applying merge (10 -> 8 leaves, 12 th.) yielded SPEEDUP of 1.576x: 0.0008399s -> 0.0005331s, so taking this instance. +Merge (8 -> 6 leaves) took w.c.t. of 1.502e-05s, ~5.007e-06s of computing time (of which 9.537e-07s sorting, 4.053e-06s analysis) +3 iterations (12 th.) took 0.005747s; avg 0.001916s ( +/- 71.50/ 93.24 %); best 0.000546s; worst 0.003702s; std dev. 0.001322 (taking best). +Reference operation time is 0.000545979 s (1.539 Mflops) with 12 threads. +After merge step 4: tpop: 0.000546 s ~Mflops: 1.539 nsubm:6 otn:12 +Applying merge (8 -> 6 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.024x: 0.0005331s -> 0.000546s. +Merge (6 -> 3 leaves) took w.c.t. of 1.001e-05s, ~5.007e-06s of computing time (of which 9.537e-07s sorting, 9.537e-07s analysis) +3 iterations (12 th.) took 0.002006s; avg 0.0006687s ( +/- 24.34/ 12.31 %); best 0.0005059s; worst 0.000751s; std dev. 0.0001151 (taking best). +Reference operation time is 0.000505924 s (1.66 Mflops) with 12 threads. +After merge step 5: tpop: 0.0005059 s ~Mflops: 1.660 nsubm:3 otn:12 +Applying merge (6 -> 3 leaves, 12 th.) yielded SPEEDUP of 1.054x: 0.0005331s -> 0.0005059s, so taking this instance. +Merge (3 -> 1 leaves) took w.c.t. of 1.311e-05s, ~6.914e-06s of computing time (of which 2.146e-06s sorting, 1.907e-06s analysis) +3 iterations (12 th.) took 5.007e-06s; avg 1.669e-06s ( +/- 42.86/ 85.71 %); best 9.537e-07s; worst 3.099e-06s; std dev. 1.012e-06 (taking best). +Reference operation time is 9.53674e-07 s (880.8 Mflops) with 12 threads. +After merge step 6: tpop: 9.537e-07 s ~Mflops: 880.804 nsubm:1 otn:12 +Applying merge (3 -> 1 leaves, 12 th.) yielded SPEEDUP of 530.500x: 0.0005059s -> 9.537e-07s, so taking this instance. +Merged all the matrix leaves: no reason to continue merging. +A total of 6 merge steps (of max 6) (22 -> 1 subms) took 0.03269s (of which 0.0009131s partitioning, 0s I/O); computing times: 0.0002568s in par. loops, 8.821e-06s sorting, 1.693e-05s analyzing) +Total merge + benchmarking process took 0.03269s, equivalent to 34274.8/22.0 new/old ops (0.01497s for 6 clones -- as 15694.0/10.1 ops, or 2615.7/1.7 ops per clone), SPEEDUP of 1556.000x +Applying multi-merge (22 -> 1 leaves, 6 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 1556.000x (0.001484s -> 9.537e-07s), will amortize in 22.0 ops by saving 0.001483s per op. +In 1 tuning rounds (tot. 0.04s, 0.015s for constructor, 6 clones) obtained a SPEEDUP of 155500.0% (1556x) (from 0.5661 to 880.8 Mflops). autotuner chose 12 threads -Will autotune matrix: 20 x 20, type D, 210 nnz, 10 nnz/r, 14 subms, 10 lsubms, 3.1429 bpnz. -Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:3e-08 -Starting autotuning (16 x 3.0005e-08 s stages, transA=N, nrhs=1, timer gran.=3.0005e-08), 12 suggested as starting thread count(default). -3 iterations (12 th.) took 0.02043s; avg 0.00681s ( +/- 35.02/ 29.52 %); best 0.004425s; worst 0.008821s; std dev. 0.001814 (taking best). -~ 12 threads: 0.004425s (0.19 Mflops) (0/2 degradations so far) - -3 iterations (11 th.) took 0.02715s; avg 0.009048s ( +/- 25.17/ 34.47 %); best 0.006771s; worst 0.01217s; std dev. 0.002282 (taking best). - 11 threads: 0.006771s (0.12 Mflops) (1/2 degradations so far) - -3 iterations (10 th.) took 0.02369s; avg 0.007897s ( +/- 46.12/ 46.29 %); best 0.004255s; worst 0.01155s; std dev. 0.002979 (taking best). - 10 threads: 0.004255s (0.2 Mflops) (0/2 degradations so far) - -3 iterations (9 th.) took 0.01752s; avg 0.005839s ( +/- 71.81/ 99.25 %); best 0.001646s; worst 0.01164s; std dev. 0.004232 (taking best). - 9 threads: 0.001646s (0.51 Mflops) (0/2 degradations so far) - -3 iterations (8 th.) took 0.03031s; avg 0.0101s ( +/- 37.00/ 58.30 %); best 0.006365s; worst 0.01599s; std dev. 0.004215 (taking best). - 8 threads: 0.006365s (0.13 Mflops) (1/2 degradations so far) - -3 iterations (7 th.) took 0.01518s; avg 0.005058s ( +/- 31.74/ 49.57 %); best 0.003453s; worst 0.007566s; std dev. 0.001796 (taking best). - 7 threads: 0.003453s (0.24 Mflops) (2/2 degradations so far) - -Best threads choice is 9; starting threads were 12; max speed gap is 4.1x; search took 0.13s. -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, 14 subms, 10 lsubms, 3.1429 bpnz (tpop: 0.001646 Mflops: 0.510) -Merge (10 -> 8 leaves) took w.c.t. of 1.907e-05s, ~6.914e-06s of computing time (of which 1.192e-06s sorting, 5.007e-06s analysis) -3 iterations (12 th.) took 0.0128s; avg 0.004265s ( +/- 61.53/ 37.99 %); best 0.001641s; worst 0.005886s; std dev. 0.001873 (taking best). -~ 12 threads: 0.001641s (0.51 Mflops) (0/2 degradations so far) - -3 iterations (11 th.) took 0.01239s; avg 0.004129s ( +/- 36.01/ 18.08 %); best 0.002642s; worst 0.004875s; std dev. 0.001051 (taking best). - 11 threads: 0.002642s (0.32 Mflops) (1/2 degradations so far) - -3 iterations (10 th.) took 0.01478s; avg 0.004928s ( +/- 1.40/ 2.68 %); best 0.004859s; worst 0.00506s; std dev. 9.337e-05 (taking best). - 10 threads: 0.004859s (0.17 Mflops) (2/2 degradations so far) - -Best threads choice is 12; starting threads were 12; max speed gap is 3x; search took 0.04s. -After merge step 1: tpop: 0.001641 s ~Mflops: 0.512 nsubm:8 otn:12 -Applying merge (10 -> 8 leaves, 12 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=1.00305x): 0.001646s -> 0.001641s, so IGNORING this instance. -Merge (8 -> 6 leaves) took w.c.t. of 8.821e-06s, ~3.099e-06s of computing time (of which 0s sorting, 1.907e-06s analysis) -3 iterations (12 th.) took 0.01237s; avg 0.004125s ( +/- 36.04/ 18.21 %); best 0.002638s; worst 0.004876s; std dev. 0.001051 (taking best). -~ 12 threads: 0.002638s (0.32 Mflops) (0/2 degradations so far) - -3 iterations (11 th.) took 0.01458s; avg 0.004861s ( +/- 0.03/ 0.06 %); best 0.00486s; worst 0.004864s; std dev. 1.911e-06 (taking best). - 11 threads: 0.00486s (0.17 Mflops) (1/2 degradations so far) - -3 iterations (10 th.) took 0.02085s; avg 0.006951s ( +/- 64.88/103.25 %); best 0.002441s; worst 0.01413s; std dev. 0.005131 (taking best). - 10 threads: 0.002441s (0.34 Mflops) (0/2 degradations so far) - -3 iterations (9 th.) took 0.01486s; avg 0.004954s ( +/- 2.83/ 3.91 %); best 0.004814s; worst 0.005148s; std dev. 0.0001416 (taking best). - 9 threads: 0.004814s (0.17 Mflops) (1/2 degradations so far) - -3 iterations (8 th.) took 0.01235s; avg 0.004115s ( +/- 35.97/ 18.02 %); best 0.002635s; worst 0.004857s; std dev. 0.001047 (taking best). - 8 threads: 0.002635s (0.32 Mflops) (2/2 degradations so far) - -Best threads choice is 10; starting threads were 12; max speed gap is 2x; search took 0.075s. -After merge step 2: tpop: 0.002441 s ~Mflops: 0.344 nsubm:6 otn:10 -Applying merge (8 -> 6 leaves, 10 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.483x: 0.001646s -> 0.002441s. -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) (10 -> 6 subms) took 0.1151s (of which 3.076e-05s partitioning, 0s I/O); computing times: 1.001e-05s in par. loops, 1.192e-06s sorting, 6.914e-06s analyzing) -Total merge + benchmarking process took 0.1151s, equivalent to 69.9/69.9 new/old ops (0.02122s for 1 clones -- as 12.9/12.9 ops, or 12.9/12.9 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) +Will autotune matrix: 20 x 20, type D, 210 nnz, 10 nnz/r, 1 subms, 1 lsubms, 2.4000 bpnz. +Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:5.27e-08 +Starting autotuning (16 x 5.27024e-08 s stages, transA=N, nrhs=1, timer gran.=5.27024e-08), 12 suggested as starting thread count(default). +3 iterations (12 th.) took 4.053e-06s; avg 1.351e-06s ( +/- 29.41/ 41.18 %); best 9.537e-07s; worst 1.907e-06s; std dev. 4.052e-07 (taking best). +~ 12 threads: 9.537e-07s (8.8e+02 Mflops) (0/2 degradations so far) - +3 iterations (11 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 91.71/ 50.00 %); best 5.27e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 11 threads: 5.27e-08s (1.6e+04 Mflops) (0/2 degradations so far) - +3 iterations (10 th.) took 2.146e-06s; avg 7.153e-07s ( +/- 92.63/ 66.67 %); best 5.27e-08s; worst 1.192e-06s; std dev. 5.15e-07 (taking best). + 10 threads: 5.27e-08s (1.6e+04 Mflops) (0/2 degradations so far) - +3 iterations (9 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 91.71/ 50.00 %); best 5.27e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 9 threads: 5.27e-08s (1.6e+04 Mflops) (0/2 degradations so far) - +3 iterations (8 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 91.71/ 50.00 %); best 5.27e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 8 threads: 5.27e-08s (1.6e+04 Mflops) (0/2 degradations so far) - +3 iterations (7 th.) took 2.146e-06s; avg 7.153e-07s ( +/- 92.63/ 66.67 %); best 5.27e-08s; worst 1.192e-06s; std dev. 5.15e-07 (taking best). + 7 threads: 5.27e-08s (1.6e+04 Mflops) (0/2 degradations so far) - +3 iterations (6 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 91.71/ 50.00 %); best 5.27e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 6 threads: 5.27e-08s (1.6e+04 Mflops) (0/2 degradations so far) - +3 iterations (5 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 91.71/ 50.00 %); best 5.27e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 5 threads: 5.27e-08s (1.6e+04 Mflops) (0/2 degradations so far) - +3 iterations (4 th.) took 2.146e-06s; avg 7.153e-07s ( +/- 92.63/ 66.67 %); best 5.27e-08s; worst 1.192e-06s; std dev. 5.15e-07 (taking best). + 4 threads: 5.27e-08s (1.6e+04 Mflops) (0/2 degradations so far) - +3 iterations (3 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 91.71/ 50.00 %); best 5.27e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 3 threads: 5.27e-08s (1.6e+04 Mflops) (0/2 degradations so far) - +3 iterations (2 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 91.71/ 50.00 %); best 5.27e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 2 threads: 5.27e-08s (1.6e+04 Mflops) (0/2 degradations so far) - +3 iterations (1 th.) took 2.146e-06s; avg 7.153e-07s ( +/- 92.63/ 66.67 %); best 5.27e-08s; worst 1.192e-06s; std dev. 5.15e-07 (taking best). + 1 threads: 5.27e-08s (1.6e+04 Mflops) (0/2 degradations so far) - +Best threads choice is 11; starting threads were 12; max speed gap is 18x; search took 9.5e-05s. +Starting merge (and threads) based auto-tuning procedure (transA=N, nrhs=1, order=cols) (max 6 steps, inclusive 3 grace steps) on: 20 x 20, type D, 210 nnz, 10 nnz/r, 1 subms, 1 lsubms, 2.4000 bpnz (tpop: 5.27e-08 Mflops: 15938.545) +Merge (1 -> 1 leaves) took w.c.t. of 0s, ~0s of computing time (of which 0s sorting, 0s analysis) +3 iterations (12 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 91.71/ 50.00 %); best 5.27e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). +~ 12 threads: 5.27e-08s (1.6e+04 Mflops) (0/2 degradations so far) - +3 iterations (11 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 91.71/ 50.00 %); best 5.27e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 11 threads: 5.27e-08s (1.6e+04 Mflops) (0/2 degradations so far) - +3 iterations (10 th.) took 2.146e-06s; avg 7.153e-07s ( +/- 92.63/ 66.67 %); best 5.27e-08s; worst 1.192e-06s; std dev. 5.15e-07 (taking best). + 10 threads: 5.27e-08s (1.6e+04 Mflops) (0/2 degradations so far) - +3 iterations (9 th.) took 2.146e-06s; avg 7.153e-07s ( +/- 92.63/ 66.67 %); best 5.27e-08s; worst 1.192e-06s; std dev. 5.15e-07 (taking best). + 9 threads: 5.27e-08s (1.6e+04 Mflops) (0/2 degradations so far) - +3 iterations (8 th.) took 3.099e-06s; avg 1.033e-06s ( +/- 7.69/ 15.38 %); best 9.537e-07s; worst 1.192e-06s; std dev. 1.124e-07 (taking best). + 8 threads: 9.537e-07s (8.8e+02 Mflops) (1/2 degradations so far) - +3 iterations (7 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 91.71/ 50.00 %); best 5.27e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 7 threads: 5.27e-08s (1.6e+04 Mflops) (0/2 degradations so far) - +3 iterations (6 th.) took 2.146e-06s; avg 7.153e-07s ( +/- 92.63/ 66.67 %); best 5.27e-08s; worst 1.192e-06s; std dev. 5.15e-07 (taking best). + 6 threads: 5.27e-08s (1.6e+04 Mflops) (0/2 degradations so far) - +3 iterations (5 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 91.71/ 50.00 %); best 5.27e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 5 threads: 5.27e-08s (1.6e+04 Mflops) (0/2 degradations so far) - +3 iterations (4 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 91.71/ 50.00 %); best 5.27e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 4 threads: 5.27e-08s (1.6e+04 Mflops) (0/2 degradations so far) - +3 iterations (3 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 91.71/ 50.00 %); best 5.27e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 3 threads: 5.27e-08s (1.6e+04 Mflops) (0/2 degradations so far) - +3 iterations (2 th.) took 2.146e-06s; avg 7.153e-07s ( +/- 92.63/ 66.67 %); best 5.27e-08s; worst 1.192e-06s; std dev. 5.15e-07 (taking best). + 2 threads: 5.27e-08s (1.6e+04 Mflops) (0/2 degradations so far) - +3 iterations (1 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 91.71/ 50.00 %); best 5.27e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 1 threads: 5.27e-08s (1.6e+04 Mflops) (0/2 degradations so far) - +Best threads choice is 12; starting threads were 12; max speed gap is 18x; search took 9.5e-05s. +After merge step 1: tpop: 5.27e-08 s ~Mflops: 15938.545 nsubm:1 otn:12 +Applying merge (1 -> 1 leaves, 12 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=1.00000x): 5.27e-08s -> 5.27e-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 0.000103s (of which 1.907e-06s partitioning, 0s I/O); computing times: 0s in par. loops, 0s sorting, 0s analyzing) +Total merge + benchmarking process took 0.000103s, equivalent to 1954.3/1954.3 new/old ops (0.002411s for 1 clones -- as 45749.8/45749.8 ops, or 45749.8/45749.8 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) Merging based autotuning FAILED (=NO SPEEDUP); let's try splitting then... -3 iterations (12 th.) took 0.00861s; avg 0.00287s ( +/- 55.19/ 67.52 %); best 0.001286s; worst 0.004808s; std dev. 0.001459 (taking best). -~ 12 threads: 0.001286s (0.65 Mflops) (0/2 degradations so far) - -3 iterations (11 th.) took 0.02811s; avg 0.00937s ( +/- 52.39/ 41.60 %); best 0.004461s; worst 0.01327s; std dev. 0.003666 (taking best). - 11 threads: 0.004461s (0.19 Mflops) (1/2 degradations so far) - -3 iterations (10 th.) took 0.01548s; avg 0.005159s ( +/- 16.78/ 22.18 %); best 0.004293s; worst 0.006303s; std dev. 0.000844 (taking best). - 10 threads: 0.004293s (0.2 Mflops) (2/2 degradations so far) - -Best threads choice is 12; starting threads were 12; max speed gap is 3.5x; search took 0.052s. -Starting split (and threads) based auto-tuning procedure (transA=N, nrhs=1, order=cols) (max 6 steps, inclusive 3 grace steps) on: 20 x 20, type D, 210 nnz, 10 nnz/r, 14 subms, 10 lsubms, 3.1429 bpnz (tpop: 0.001286 Mflops: 0.653) -Split (10 -> 25 leaves, 14 -> 34 subms) took 0.002881s (of which: 4.053e-06s analysis, -8.696e+09s mem.mgmt); compute time: 1.383e-05s overall, 9.537e-07s searches, 1.287e-05s shuffle, 4.768e-06s switch, 1.907e-06s quadrants. -3 iterations (12 th.) took 0.05673s; avg 0.01891s ( +/- 52.59/ 48.10 %); best 0.008966s; worst 0.02801s; std dev. 0.007797 (taking best). -~ 12 threads: 0.008966s (0.094 Mflops) (0/2 degradations so far) - -3 iterations (11 th.) took 0.0198s; avg 0.006601s ( +/- 42.43/ 33.60 %); best 0.0038s; worst 0.008819s; std dev. 0.00209 (taking best). - 11 threads: 0.0038s (0.22 Mflops) (0/2 degradations so far) - -3 iterations (10 th.) took 0.01975s; avg 0.006582s ( +/- 31.78/ 24.73 %); best 0.00449s; worst 0.00821s; std dev. 0.001554 (taking best). - 10 threads: 0.00449s (0.19 Mflops) (1/2 degradations so far) - -3 iterations (9 th.) took 0.02046s; avg 0.00682s ( +/- 35.07/ 20.82 %); best 0.004428s; worst 0.00824s; std dev. 0.001701 (taking best). - 9 threads: 0.004428s (0.19 Mflops) (2/2 degradations so far) - -Best threads choice is 11; starting threads were 12; max speed gap is 2.4x; search took 0.12s. -After split step 1: tpop: 0.0038 s ~Mflops: 0.221 nsubm:25 otn:11 -Applying split (10 -> 25 leaves, 11 th.) yielded SLOWDOWN (1th of 3 tolerable) of 2.955x: 0.001286s -> 0.0038s. +3 iterations (12 th.) took 4.053e-06s; avg 1.351e-06s ( +/- 29.41/ 58.82 %); best 9.537e-07s; worst 2.146e-06s; std dev. 5.62e-07 (taking best). +~ 12 threads: 9.537e-07s (8.8e+02 Mflops) (0/2 degradations so far) - +3 iterations (11 th.) took 2.146e-06s; avg 7.153e-07s ( +/- 92.63/ 66.67 %); best 5.27e-08s; worst 1.192e-06s; std dev. 5.15e-07 (taking best). + 11 threads: 5.27e-08s (1.6e+04 Mflops) (0/2 degradations so far) - +3 iterations (10 th.) took 2.146e-06s; avg 7.153e-07s ( +/- 92.63/ 66.67 %); best 5.27e-08s; worst 1.192e-06s; std dev. 5.15e-07 (taking best). + 10 threads: 5.27e-08s (1.6e+04 Mflops) (0/2 degradations so far) - +3 iterations (9 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 91.71/ 50.00 %); best 5.27e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 9 threads: 5.27e-08s (1.6e+04 Mflops) (0/2 degradations so far) - +3 iterations (8 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 91.71/ 50.00 %); best 5.27e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 8 threads: 5.27e-08s (1.6e+04 Mflops) (0/2 degradations so far) - +3 iterations (7 th.) took 2.146e-06s; avg 7.153e-07s ( +/- 92.63/ 66.67 %); best 5.27e-08s; worst 1.192e-06s; std dev. 5.15e-07 (taking best). + 7 threads: 5.27e-08s (1.6e+04 Mflops) (0/2 degradations so far) - +3 iterations (6 th.) took 2.146e-06s; avg 7.153e-07s ( +/- 92.63/ 66.67 %); best 5.27e-08s; worst 1.192e-06s; std dev. 5.15e-07 (taking best). + 6 threads: 5.27e-08s (1.6e+04 Mflops) (0/2 degradations so far) - +3 iterations (5 th.) took 2.146e-06s; avg 7.153e-07s ( +/- 92.63/ 66.67 %); best 5.27e-08s; worst 1.192e-06s; std dev. 5.15e-07 (taking best). + 5 threads: 5.27e-08s (1.6e+04 Mflops) (0/2 degradations so far) - +3 iterations (4 th.) took 2.146e-06s; avg 7.153e-07s ( +/- 92.63/ 66.67 %); best 5.27e-08s; worst 1.192e-06s; std dev. 5.15e-07 (taking best). + 4 threads: 5.27e-08s (1.6e+04 Mflops) (0/2 degradations so far) - +3 iterations (3 th.) took 9.537e-07s; avg 3.179e-07s ( +/- 83.42/200.00 %); best 5.27e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 3 threads: 5.27e-08s (1.6e+04 Mflops) (0/2 degradations so far) - +3 iterations (2 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 91.71/ 50.00 %); best 5.27e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 2 threads: 5.27e-08s (1.6e+04 Mflops) (0/2 degradations so far) - +3 iterations (1 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 91.71/ 50.00 %); best 5.27e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). + 1 threads: 5.27e-08s (1.6e+04 Mflops) (0/2 degradations so far) - +Best threads choice is 11; starting threads were 12; max speed gap is 18x; search took 8.8e-05s. +Starting split (and threads) based auto-tuning procedure (transA=N, nrhs=1, order=cols) (max 6 steps, inclusive 3 grace steps) on: 20 x 20, type D, 210 nnz, 10 nnz/r, 1 subms, 1 lsubms, 2.4000 bpnz (tpop: 5.27e-08 Mflops: 15938.545) +Split (1 -> 3 leaves, 1 -> 4 subms) took 2.909e-05s (of which: 1.907e-06s analysis, -1.705e+09s mem.mgmt); compute time: 1.311e-05s overall, 1.907e-06s searches, 1.121e-05s shuffle, 3.099e-06s switch, 9.537e-07s quadrants. +3 iterations (12 th.) took 0.00185s; avg 0.0006167s ( +/- 36.60/ 19.19 %); best 0.000391s; worst 0.000735s; std dev. 0.0001597 (taking best). +~ 12 threads: 0.000391s (2.1 Mflops) (0/2 degradations so far) - +3 iterations (11 th.) took 0.002274s; avg 0.000758s ( +/- 9.51/ 18.86 %); best 0.0006859s; worst 0.000901s; std dev. 0.0001011 (taking best). + 11 threads: 0.0006859s (1.2 Mflops) (1/2 degradations so far) - +3 iterations (10 th.) took 0.002478s; avg 0.000826s ( +/- 15.02/ 29.06 %); best 0.0007019s; worst 0.001066s; std dev. 0.0001697 (taking best). + 10 threads: 0.0007019s (1.2 Mflops) (2/2 degradations so far) - +Best threads choice is 12; starting threads were 12; max speed gap is 1.8x; search took 0.0066s. +After split step 1: tpop: 0.000391 s ~Mflops: 2.148 nsubm:3 otn:12 +Applying split (1 -> 3 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 7419.136x: 5.27e-08s -> 0.000391s. 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) (10 -> 25 subms) took 0.1198s (of which 0.002929s partitioning, 0s I/O); computing times: 1.383e-05s in par. loops, 9.537e-07s sorting, 4.053e-06s analyzing) -Total split + benchmarking process took 0.1198s, equivalent to 93.1/93.1 new/old ops (0.01396s for 1 clones -- as 10.9/10.9 ops, or 10.9/10.9 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) -In 1 tuning rounds (tot. 0.46s, 0.035s for constructor, 2 clones) obtained NO speedup (best stays 0.6532 Mflops). +A total of 1 split steps (of max 6) (1 -> 3 subms) took 0.006668s (of which 4.101e-05s partitioning, 0s I/O); computing times: 1.311e-05s in par. loops, 1.907e-06s sorting, 1.907e-06s analyzing) +Total split + benchmarking process took 0.006668s, equivalent to 126523.4/126523.4 new/old ops (0.002448s for 1 clones -- as 46451.0/46451.0 ops, or 46451.0/46451.0 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) +In 1 tuning rounds (tot. 0.012s, 0.0049s for constructor, 2 clones) obtained NO speedup (best stays 1.594e+04 Mflops). check results are ok Building a matrix with 36 nnz, 6 x 6 Duplicates check: 36 - 0 = 36 - converted COO to RSB in 2.004e-02 s (100.00 %) - analyzed arrays in 7.807e-03 s (38.96 %) + converted COO to RSB in 2.112e-03 s (100.00 %) + analyzed arrays in 1.071e-03 s (50.71 %) cleaned-up arrays in 0.000e+00 s (0.00 %) - deduplicated arrays in 9.537e-07 s (0.00 %) - sorted arrays in 1.097e-02 s (54.72 %) - shuffled partitions in 1.248e-03 s (6.23 %) - memory allocations took 1.192e-05 s (0.06 %) - leafs setup took 1.192e-06 s (0.01 %) - halfword conversion took 9.537e-07 s (0.00 %) -Built (6 x 6)[0xaaaae6bb07d0]{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' + deduplicated arrays in 9.537e-07 s (0.05 %) + sorted arrays in 3.510e-04 s (16.62 %) + shuffled partitions in 6.850e-04 s (32.43 %) + memory allocations took 3.099e-06 s (0.15 %) + leafs setup took 1.192e-06 s (0.06 %) + halfword conversion took 0.000e+00 s (0.00 %) +Built (6 x 6)[0xaaaae5524330]{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 0.1860E-03 s -A single USMM took 0.9203E-04 s -USMM-to-USMV speed ratio is is 2.021 x +Repeated USMV took 0.1919E-03 s +A single USMM took 0.9394E-04 s +USMM-to-USMV speed ratio is is 2.043 x Call auto-tuning routine.. Repeat measurement. -Tuned USMM took 0.9537E-06 s -Tuned-to-untuned speed ratio is is 96.50 x +Tuned USMM took 0.4053E-05 s +Tuned-to-untuned speed ratio is is 23.18 x FAILED: 0 PASSED: 2 /build/reproducible-path/librsb-1.3.0.2+dfsg/examples/fortran_rsb_fi @@ -8715,246 +8801,240 @@ 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 8.215e-02 s (100.00 %) - analyzed arrays in 1.994e-02 s (24.27 %) - cleaned-up arrays in 9.537e-07 s (0.00 %) - deduplicated arrays in 1.907e-06 s (0.00 %) - sorted arrays in 2.925e-02 s (35.61 %) - shuffled partitions in 1.559e-02 s (18.97 %) - memory allocations took 1.597e-05 s (0.02 %) - leafs setup took 7.868e-06 s (0.01 %) - halfword conversion took 1.730e-02 s (21.06 %) -Built (6 x 6)[0xaaaae65915b0]{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 9.977e-03 s (100.00 %) + analyzed arrays in 3.106e-03 s (31.13 %) + cleaned-up arrays in 1.907e-06 s (0.02 %) + deduplicated arrays in 1.907e-06 s (0.02 %) + sorted arrays in 1.830e-03 s (18.34 %) + shuffled partitions in 2.479e-03 s (24.85 %) + memory allocations took 1.526e-05 s (0.15 %) + leafs setup took 8.106e-06 s (0.08 %) + halfword conversion took 2.521e-03 s (25.27 %) +Built (6 x 6)[0xaaaafb09a5b0]{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)[0xaaaae6595820]{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)[0xaaaafb09e820]{D} @ (0(0..0),0(0..0)) (36 nnz, 6 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 22, symflags:'' Will use autotuning routine to sample matrix: 6 x 6, type D, 36 nnz, 6 nnz/r, 29 subms, 22 lsubms, 4.6667 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:0.1 -3 iterations (12 th.) took 0.01635s; avg 0.005449s ( +/- 27.73/ 50.31 %); best 0.003938s; worst 0.00819s; std dev. 0.001942 (taking best). -Reference operation time is 0.00393796 s (0.03657 Mflops) with 12 threads. -After 0.016406s, autotuning routine did not find a better threads count configuration. +3 iterations (12 th.) took 0.004955s; avg 0.001652s ( +/- 19.83/ 10.61 %); best 0.001324s; worst 0.001827s; std dev. 0.0002318 (taking best). +Reference operation time is 0.00132418 s (0.1087 Mflops) with 12 threads. +After 0.005022s, autotuning routine did not find a better threads count configuration. Will autotune matrix: 6 x 6, type D, 36 nnz, 6 nnz/r, 29 subms, 22 lsubms, 4.6667 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:0.1 -3 iterations (12 th.) took 0.0238s; avg 0.007932s ( +/- 51.96/ 48.44 %); best 0.003811s; worst 0.01178s; std dev. 0.003257 (taking best). -Reference operation time is 0.00381088 s (0.03779 Mflops) with 12 threads. -Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=2, order=cols) (max 6 steps, inclusive 3 grace steps) on: 6 x 6, type D, 36 nnz, 6 nnz/r, 29 subms, 22 lsubms, 4.6667 bpnz (tpop: 0.003811 Mflops: 0.038) -Merge (22 -> 16 leaves) took w.c.t. of 0.002502s, ~3.695e-05s of computing time (of which 1.192e-06s sorting, 6.914e-06s analysis) -3 iterations (12 th.) took 0.02502s; avg 0.008341s ( +/- 31.99/ 38.74 %); best 0.005673s; worst 0.01157s; std dev. 0.002441 (taking best). -Reference operation time is 0.00567293 s (0.02538 Mflops) with 12 threads. -After merge step 1: tpop: 0.005673 s ~Mflops: 0.025 nsubm:16 otn:12 -Applying merge (22 -> 16 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.489x: 0.003811s -> 0.005673s. -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 0.02756s (of which 0.002511s partitioning, 0s I/O); computing times: 3.695e-05s in par. loops, 1.192e-06s sorting, 6.914e-06s analyzing) -Total merge + benchmarking process took 0.02756s, equivalent to 7.2/7.2 new/old ops (0.02416s for 1 clones -- as 6.3/6.3 ops, or 6.3/6.3 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) +3 iterations (12 th.) took 0.003708s; avg 0.001236s ( +/- 2.75/ 3.08 %); best 0.001202s; worst 0.001274s; std dev. 2.954e-05 (taking best). +Reference operation time is 0.00120211 s (0.1198 Mflops) with 12 threads. +Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=2, order=cols) (max 6 steps, inclusive 3 grace steps) on: 6 x 6, type D, 36 nnz, 6 nnz/r, 29 subms, 22 lsubms, 4.6667 bpnz (tpop: 0.001202 Mflops: 0.120) +Merge (22 -> 16 leaves) took w.c.t. of 0.0009389s, ~0.000453s of computing time (of which 1.907e-06s sorting, 5.007e-06s analysis) +3 iterations (12 th.) took 0.005456s; avg 0.001819s ( +/- 30.13/ 47.48 %); best 0.001271s; worst 0.002682s; std dev. 0.0006179 (taking best). +Reference operation time is 0.00127077 s (0.1133 Mflops) with 12 threads. +After merge step 1: tpop: 0.001271 s ~Mflops: 0.113 nsubm:16 otn:12 +Applying merge (22 -> 16 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.057x: 0.001202s -> 0.001271s. +Merge (16 -> 10 leaves) took w.c.t. of 0.0001528s, ~1.597e-05s of computing time (of which 2.861e-06s sorting, 5.007e-06s analysis) +3 iterations (12 th.) took 0.007478s; avg 0.002493s ( +/- 34.61/ 40.69 %); best 0.00163s; worst 0.003507s; std dev. 0.0007737 (taking best). +Reference operation time is 0.00163007 s (0.08834 Mflops) with 12 threads. +After merge step 2: tpop: 0.00163 s ~Mflops: 0.088 nsubm:10 otn:12 +Applying merge (16 -> 10 leaves, 12 th.) yielded SLOWDOWN (2th of 3 tolerable) of 1.356x: 0.001202s -> 0.00163s. +Skipping further merge based tests after 2 definite performance degradations in a row (and last exceeding limit). +A total of 2 merge steps (of max 6) (22 -> 10 subms) took 0.01408s (of which 0.001105s partitioning, 0s I/O); computing times: 0.000469s in par. loops, 4.768e-06s sorting, 1.001e-05s analyzing) +Total merge + benchmarking process took 0.01408s, equivalent to 11.7/11.7 new/old ops (0.003301s for 1 clones -- as 2.7/2.7 ops, or 2.7/2.7 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) Merging based autotuning FAILED (=NO SPEEDUP); let's try splitting then... -3 iterations (12 th.) took 0.02378s; avg 0.007928s ( +/- 44.28/ 68.02 %); best 0.004417s; worst 0.01332s; std dev. 0.003871 (taking best). -Reference operation time is 0.00441694 s (0.0326 Mflops) with 12 threads. -Starting split (same threads) based auto-tuning procedure (transA=N, nrhs=2, order=cols) (max 6 steps, inclusive 3 grace steps) on: 6 x 6, type D, 36 nnz, 6 nnz/r, 29 subms, 22 lsubms, 4.6667 bpnz (tpop: 0.004417 Mflops: 0.033) -Split (22 -> 28 leaves, 29 -> 37 subms) took 0.002161s (of which: 4.053e-06s analysis, -3.478e+09s mem.mgmt); compute time: 0.0001013s overall, 2.861e-06s searches, 9.847e-05s shuffle, 8.798e-05s switch, 1.907e-06s quadrants. -3 iterations (12 th.) took 0.006856s; avg 0.002285s ( +/- 19.18/ 9.66 %); best 0.001847s; worst 0.002506s; std dev. 0.0003099 (taking best). -Reference operation time is 0.00184703 s (0.07796 Mflops) with 12 threads. -After split step 1: tpop: 0.001847 s ~Mflops: 0.078 nsubm:28 otn:12 -Applying split (22 -> 28 leaves, 12 th.) yielded SPEEDUP of 2.391x: 0.004417s -> 0.001847s, so taking this instance. -Split (28 -> 28 leaves, 37 -> 37 subms) took 0.003958s (of which: 3.099e-06s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. -3 iterations (12 th.) took 0.005957s; avg 0.001986s ( +/- 37.91/ 23.33 %); best 0.001233s; worst 0.002449s; std dev. 0.000537 (taking best). -Reference operation time is 0.00123286 s (0.1168 Mflops) with 12 threads. -After split step 2: tpop: 0.001233 s ~Mflops: 0.117 nsubm:28 otn:12 -Applying split (28 -> 28 leaves, 12 th.) yielded SPEEDUP of 1.498x: 0.001847s -> 0.001233s, so taking this instance. -Split (28 -> 28 leaves, 37 -> 37 subms) took 0.006972s (of which: 5.007e-06s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. -3 iterations (12 th.) took 0.0122s; avg 0.004068s ( +/- 47.93/ 95.85 %); best 0.002118s; worst 0.007967s; std dev. 0.002757 (taking best). -Reference operation time is 0.00211811 s (0.06799 Mflops) with 12 threads. -After split step 3: tpop: 0.002118 s ~Mflops: 0.068 nsubm:28 otn:12 -Applying split (28 -> 28 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.718x: 0.001233s -> 0.002118s. +3 iterations (12 th.) took 0.009407s; avg 0.003136s ( +/- 46.81/ 79.04 %); best 0.001668s; worst 0.005614s; std dev. 0.001762 (taking best). +Reference operation time is 0.00166798 s (0.08633 Mflops) with 12 threads. +Starting split (same threads) based auto-tuning procedure (transA=N, nrhs=2, order=cols) (max 6 steps, inclusive 3 grace steps) on: 6 x 6, type D, 36 nnz, 6 nnz/r, 29 subms, 22 lsubms, 4.6667 bpnz (tpop: 0.001668 Mflops: 0.086) +Split (22 -> 28 leaves, 29 -> 37 subms) took 0.001493s (of which: 5.007e-06s analysis, -3.409e+09s mem.mgmt); compute time: 0.0001678s overall, 2.861e-06s searches, 0.000165s shuffle, 7.892e-05s switch, 2.146e-06s quadrants. +3 iterations (12 th.) took 0.004342s; avg 0.001447s ( +/- 27.86/ 27.34 %); best 0.001044s; worst 0.001843s; std dev. 0.0003262 (taking best). +Reference operation time is 0.00104403 s (0.1379 Mflops) with 12 threads. +After split step 1: tpop: 0.001044 s ~Mflops: 0.138 nsubm:28 otn:12 +Applying split (22 -> 28 leaves, 12 th.) yielded SPEEDUP of 1.598x: 0.001668s -> 0.001044s, so taking this instance. +Split (28 -> 28 leaves, 37 -> 37 subms) took 0.000998s (of which: 5.96e-06s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. +3 iterations (12 th.) took 0.004114s; avg 0.001371s ( +/- 15.62/ 10.98 %); best 0.001157s; worst 0.001522s; std dev. 0.0001556 (taking best). +Reference operation time is 0.00115705 s (0.1245 Mflops) with 12 threads. +After split step 2: tpop: 0.001157 s ~Mflops: 0.124 nsubm:28 otn:12 +Applying split (28 -> 28 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.108x: 0.001044s -> 0.001157s. +Split (28 -> 28 leaves, 37 -> 37 subms) took 0.001997s (of which: 5.007e-06s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. +3 iterations (12 th.) took 0.00383s; avg 0.001277s ( +/- 21.21/ 13.27 %); best 0.001006s; worst 0.001446s; std dev. 0.0001935 (taking best). +Reference operation time is 0.00100589 s (0.1432 Mflops) with 12 threads. +After split step 3: tpop: 0.001006 s ~Mflops: 0.143 nsubm:28 otn:12 +Applying split (28 -> 28 leaves, 12 th.) yielded SPEEDUP of 1.038x: 0.001044s -> 0.001006s, so taking this instance. +Split (28 -> 28 leaves, 37 -> 37 subms) took 0.001051s (of which: 5.007e-06s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. +3 iterations (12 th.) took 0.004264s; avg 0.001421s ( +/- 3.19/ 4.49 %); best 0.001376s; worst 0.001485s; std dev. 4.645e-05 (taking best). +Reference operation time is 0.00137591 s (0.1047 Mflops) with 12 threads. +After split step 4: tpop: 0.001376 s ~Mflops: 0.105 nsubm:28 otn:12 +Applying split (28 -> 28 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.368x: 0.001006s -> 0.001376s. Skipping further split based tests after 1 definite performance degradations in a row (and last exceeding limit). -A total of 3 split steps (of max 6) (22 -> 28 subms) took 0.05595s (of which 0.01321s partitioning, 0s I/O); computing times: 0.0001013s in par. loops, 2.861e-06s sorting, 1.216e-05s analyzing) -Total split + benchmarking process took 0.05595s, equivalent to 45.4/12.7 new/old ops (0.03838s for 3 clones -- as 31.1/8.7 ops, or 10.4/2.9 ops per clone), SPEEDUP of 3.583x -Applying multi-split (22 -> 28 leaves, 2 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 3.583x (0.004417s -> 0.001233s), will amortize in 17.6 ops by saving 0.003184s per op. -In 1 tuning rounds (tot. 0.18s, 0.063s for constructor, 4 clones) obtained a SPEEDUP of 258.3% (3.583x) (from 0.0326 to 0.1168 Mflops). -After 0.176077s, global autotuning declared speedup of 3.58267 x, when using threads count of 12 and a new matrix: -(6 x 6)[0xaaaae65a6020]{D} @ (0(0..0),0(0..0)) (36 nnz, 6 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 28, symflags:'' +A total of 4 split steps (of max 6) (22 -> 28 subms) took 0.02782s (of which 0.005955s partitioning, 0s I/O); computing times: 0.0001678s in par. loops, 2.861e-06s sorting, 2.098e-05s analyzing) +Total split + benchmarking process took 0.02782s, equivalent to 27.7/16.7 new/old ops (0.008758s for 3 clones -- as 8.7/5.3 ops, or 2.9/1.8 ops per clone), SPEEDUP of 1.658x +Applying multi-split (22 -> 28 leaves, 3 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 1.658x (0.001668s -> 0.001006s), will amortize in 42.0 ops by saving 0.0006621s per op. +In 1 tuning rounds (tot. 0.062s, 0.012s for constructor, 4 clones) obtained a SPEEDUP of 65.8% (1.658x) (from 0.08633 to 0.1432 Mflops). +After 0.061941s, global autotuning declared speedup of 1.65821 x, when using threads count of 12 and a new matrix: +(6 x 6)[0xaaaafb0af020]{D} @ (0(0..0),0(0..0)) (36 nnz, 6 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 28, symflags:'' Considering S clone. Building a matrix with 36 nnz, 6 x 6 Duplicates check: 36 - 0 = 36 - converted COO to RSB in 2.697e-02 s (100.00 %) - analyzed arrays in 8.514e-03 s (31.56 %) - cleaned-up arrays in 9.537e-07 s (0.00 %) - deduplicated arrays in 0.000e+00 s (0.00 %) + converted COO to RSB in 5.121e-03 s (100.00 %) + analyzed arrays in 2.456e-03 s (47.96 %) + cleaned-up arrays in 9.537e-07 s (0.02 %) + deduplicated arrays in 9.537e-07 s (0.02 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 4.280e-03 s (15.87 %) - memory allocations took 7.868e-06 s (0.03 %) - leafs setup took 1.907e-06 s (0.01 %) - halfword conversion took 1.417e-02 s (52.53 %) -Built (6 x 6)[0xaaaae6595820]{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 1.197e-03 s (23.37 %) + memory allocations took 4.292e-06 s (0.08 %) + leafs setup took 1.907e-06 s (0.04 %) + halfword conversion took 1.459e-03 s (28.49 %) +Built (6 x 6)[0xaaaafb09e820]{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)[0xaaaae6595820]{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)[0xaaaafb09e820]{S} @ (0(0..0),0(0..0)) (36 nnz, 6 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 16, symflags:'' -Will use autotuning routine to sample matrix: 6 x 6, type S, 36 nnz, 6 nnz/r, 21 subms, 16 lsubms, 4.8889 bpnz. +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 (12 th.) took 0.009061s; avg 0.00302s ( +/- 18.02/ 10.02 %); best 0.002476s; worst 0.003323s; std dev. 0.0003857 (taking best). -Reference operation time is 0.00247598 s (0.05816 Mflops) with 12 threads. -After 0.009082s, autotuning routine did not find a better threads count configuration. +3 iterations (12 th.) took 0.003886s; avg 0.001295s ( +/- 25.27/ 41.51 %); best 0.000968s; worst 0.001833s; std dev. 0.0003832 (taking best). +Reference operation time is 0.000967979 s (0.1488 Mflops) with 12 threads. +After 0.003914s, autotuning routine did not find a better threads count configuration. -Will autotune matrix: 6 x 6, type S, 36 nnz, 6 nnz/r, 21 subms, 16 lsubms, 4.8889 bpnz. +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 (12 th.) took 0.008201s; avg 0.002734s ( +/- 39.68/ 20.53 %); best 0.001649s; worst 0.003295s; std dev. 0.0007672 (taking best). -Reference operation time is 0.0016489 s (0.08733 Mflops) with 12 threads. -Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=2, order=cols) (max 6 steps, inclusive 3 grace steps) on: 6 x 6, type S, 36 nnz, 6 nnz/r, 21 subms, 16 lsubms, 4.8889 bpnz (tpop: 0.001649 Mflops: 0.087) -Merge (16 -> 10 leaves) took w.c.t. of 0.0007901s, ~5.96e-06s of computing time (of which 9.537e-07s sorting, 4.053e-06s analysis) -3 iterations (12 th.) took 0.01372s; avg 0.004573s ( +/- 37.11/ 39.18 %); best 0.002876s; worst 0.006365s; std dev. 0.001426 (taking best). -Reference operation time is 0.00287604 s (0.05007 Mflops) with 12 threads. -After merge step 1: tpop: 0.002876 s ~Mflops: 0.050 nsubm:10 otn:12 -Applying merge (16 -> 10 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.744x: 0.001649s -> 0.002876s. -Skipping further merge based tests after 1 definite performance degradations in a row (and last exceeding limit). -A total of 1 merge steps (of max 6) (16 -> 10 subms) took 0.01454s (of which 0.0007961s partitioning, 0s I/O); computing times: 5.96e-06s in par. loops, 9.537e-07s sorting, 4.053e-06s analyzing) -Total merge + benchmarking process took 0.01454s, equivalent to 8.8/8.8 new/old ops (0.008566s for 1 clones -- as 5.2/5.2 ops, or 5.2/5.2 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) -Merging based autotuning FAILED (=NO SPEEDUP); let's try splitting then... -3 iterations (12 th.) took 0.01651s; avg 0.005503s ( +/- 73.72/125.56 %); best 0.001446s; worst 0.01241s; std dev. 0.00491 (taking best). -Reference operation time is 0.00144601 s (0.09958 Mflops) with 12 threads. -Starting split (same threads) based auto-tuning procedure (transA=N, nrhs=2, order=cols) (max 6 steps, inclusive 3 grace steps) on: 6 x 6, type S, 36 nnz, 6 nnz/r, 21 subms, 16 lsubms, 4.8889 bpnz (tpop: 0.001446 Mflops: 0.100) -Split (16 -> 28 leaves, 21 -> 37 subms) took 0.005456s (of which: 4.053e-06s analysis, -6.957e+09s mem.mgmt); compute time: 1.097e-05s overall, 9.537e-07s searches, 1.001e-05s shuffle, 3.099e-06s switch, 9.537e-07s quadrants. -3 iterations (12 th.) took 0.01222s; avg 0.004072s ( +/- 44.35/ 65.85 %); best 0.002266s; worst 0.006754s; std dev. 0.001934 (taking best). -Reference operation time is 0.00226617 s (0.06354 Mflops) with 12 threads. -After split step 1: tpop: 0.002266 s ~Mflops: 0.064 nsubm:28 otn:12 -Applying split (16 -> 28 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.567x: 0.001446s -> 0.002266s. -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 -> 28 subms) took 0.01772s (of which 0.005479s partitioning, 0s I/O); computing times: 1.097e-05s in par. loops, 9.537e-07s sorting, 4.053e-06s analyzing) -Total split + benchmarking process took 0.01772s, equivalent to 12.3/12.3 new/old ops (0.007285s for 1 clones -- as 5.0/5.0 ops, or 5.0/5.0 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) -In 1 tuning rounds (tot. 0.073s, 0.016s for constructor, 2 clones) obtained NO speedup (best stays 0.09958 Mflops). -After 0.072890s, global autotuning found old matrix optimal, with declared speedup 1 x when using 12 threads +3 iterations (12 th.) took 0.002749s; avg 0.0009163s ( +/- 0.14/ 0.17 %); best 0.0009151s; worst 0.0009179s; std dev. 1.189e-06 (taking best). +Reference operation time is 0.000915051 s (0.1574 Mflops) with 12 threads. +Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=2, order=cols) (max 6 steps, inclusive 3 grace steps) on: 6 x 6, type S, 36 nnz, 6 nnz/r, 21 subms, 16 lsubms, 4.5000 bpnz (tpop: 0.0009151 Mflops: 0.157) +Merge (16 -> 13 leaves) took w.c.t. of 1.311e-05s, ~4.053e-06s of computing time (of which 9.537e-07s sorting, 4.053e-06s analysis) +3 iterations (12 th.) took 0.004187s; avg 0.001396s ( +/- 29.86/ 41.45 %); best 0.0009789s; worst 0.001974s; std dev. 0.0004221 (taking best). +Reference operation time is 0.000978947 s (0.1471 Mflops) with 12 threads. +After merge step 1: tpop: 0.0009789 s ~Mflops: 0.147 nsubm:13 otn:12 +Applying merge (16 -> 13 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.070x: 0.0009151s -> 0.0009789s. +Merge (13 -> 10 leaves) took w.c.t. of 1.597e-05s, ~4.053e-06s of computing time (of which 9.537e-07s sorting, 5.007e-06s analysis) +3 iterations (12 th.) took 0.002497s; avg 0.0008324s ( +/- 4.25/ 8.01 %); best 0.000797s; worst 0.0008991s; std dev. 4.718e-05 (taking best). +Reference operation time is 0.000797033 s (0.1807 Mflops) with 12 threads. +After merge step 2: tpop: 0.000797 s ~Mflops: 0.181 nsubm:10 otn:12 +Applying merge (13 -> 10 leaves, 12 th.) yielded SPEEDUP of 1.148x: 0.0009151s -> 0.000797s, so taking this instance. +Merge (10 -> 7 leaves) took w.c.t. of 6.914e-06s, ~2.146e-06s of computing time (of which 9.537e-07s sorting, 1.907e-06s analysis) +3 iterations (12 th.) took 0.002381s; avg 0.0007936s ( +/- 0.47/ 0.31 %); best 0.0007899s; worst 0.0007961s; std dev. 2.686e-06 (taking best). +Reference operation time is 0.000789881 s (0.1823 Mflops) with 12 threads. +After merge step 3: tpop: 0.0007899 s ~Mflops: 0.182 nsubm:7 otn:12 +Applying merge (10 -> 7 leaves, 12 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=1.00906x): 0.000797s -> 0.0007899s, so IGNORING this instance. +Merge (7 -> 4 leaves) took w.c.t. of 5.96e-06s, ~1.907e-06s of computing time (of which 0s sorting, 9.537e-07s analysis) +3 iterations (12 th.) took 0.002387s; avg 0.0007956s ( +/- 0.96/ 0.54 %); best 0.000788s; worst 0.0007999s; std dev. 5.409e-06 (taking best). +Reference operation time is 0.000787973 s (0.1827 Mflops) with 12 threads. +After merge step 4: tpop: 0.000788 s ~Mflops: 0.183 nsubm:4 otn:12 +Applying merge (7 -> 4 leaves, 12 th.) yielded SPEEDUP of 1.011x: 0.000797s -> 0.000788s, so taking this instance. +Merge (4 -> 1 leaves) took w.c.t. of 5.96e-06s, ~3.099e-06s of computing time (of which 9.537e-07s sorting, 9.537e-07s analysis) +3 iterations (12 th.) took 1.907e-06s; avg 6.358e-07s ( +/- 87.79/ 50.00 %); best 7.764e-08s; worst 9.537e-07s; std dev. 4.496e-07 (taking best). +Reference operation time is 7.7641e-08 s (1855 Mflops) with 12 threads. +After merge step 5: tpop: 7.764e-08 s ~Mflops: 1854.690 nsubm:1 otn:12 +Applying merge (4 -> 1 leaves, 12 th.) yielded SPEEDUP of 10148.933x: 0.000788s -> 7.764e-08s, so taking this instance. +Merged all the matrix leaves: no reason to continue merging. +A total of 5 merge steps (of max 6) (16 -> 1 subms) took 0.01869s (of which 6.437e-05s partitioning, 0s I/O); computing times: 1.526e-05s in par. loops, 3.815e-06s sorting, 1.287e-05s analyzing) +Total merge + benchmarking process took 0.01869s, equivalent to 240749.3/20.4 new/old ops (0.009723s for 4 clones -- as 125232.6/10.6 ops, or 31308.2/2.7 ops per clone), SPEEDUP of 11785.659x +Applying multi-merge (16 -> 1 leaves, 5 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 11785.659x (0.0009151s -> 7.764e-08s), will amortize in 20.4 ops by saving 0.000915s per op. +In 1 tuning rounds (tot. 0.024s, 0.0097s for constructor, 4 clones) obtained a SPEEDUP of 1178465.9% (1.179e+04x) (from 0.1574 to 1855 Mflops). +After 0.024215s, global autotuning declared speedup of 11785.7 x, when using threads count of 12 and a new matrix: +(6 x 6)[0xaaaafb0a3ef0]{S} @ (0(0..6),0(0..6)) (36 nnz, 6 nnz/r) flags 0x2244086 (coo:0, csr:1, hw:1, ic:1, fi:0), storage: 1, subm: 1, symflags:'' Considering C clone. Building a matrix with 36 nnz, 6 x 6 Duplicates check: 36 - 0 = 36 - converted COO to RSB in 1.347e-02 s (100.00 %) - analyzed arrays in 4.908e-03 s (36.44 %) + converted COO to RSB in 4.855e-03 s (100.00 %) + analyzed arrays in 2.151e-03 s (44.31 %) cleaned-up arrays in 0.000e+00 s (0.00 %) - deduplicated arrays in 9.537e-07 s (0.01 %) + deduplicated arrays in 1.192e-06 s (0.02 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 3.674e-03 s (27.28 %) - memory allocations took 2.861e-06 s (0.02 %) - leafs setup took 2.146e-06 s (0.02 %) - halfword conversion took 4.880e-03 s (36.23 %) -Built (6 x 6)[0xaaaae659dc60]{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 1.346e-03 s (27.73 %) + memory allocations took 2.861e-06 s (0.06 %) + leafs setup took 1.907e-06 s (0.04 %) + halfword conversion took 1.351e-03 s (27.82 %) +Built (6 x 6)[0xaaaafb0a5600]{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)[0xaaaae659dc60]{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)[0xaaaafb0a5600]{C} @ (0(0..0),0(0..0)) (36 nnz, 6 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 22, symflags:'' Will use autotuning routine to sample matrix: 6 x 6, type C, 36 nnz, 6 nnz/r, 29 subms, 22 lsubms, 4.6667 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:0.1 -3 iterations (12 th.) took 0.006209s; avg 0.00207s ( +/- 36.03/ 18.09 %); best 0.001324s; worst 0.002444s; std dev. 0.0005273 (taking best). -Reference operation time is 0.00132394 s (0.4351 Mflops) with 12 threads. -After 0.006233s, autotuning routine did not find a better threads count configuration. +3 iterations (12 th.) took 0.003222s; avg 0.001074s ( +/- 8.36/ 14.61 %); best 0.0009842s; worst 0.001231s; std dev. 0.0001114 (taking best). +Reference operation time is 0.000984192 s (0.5853 Mflops) with 12 threads. +After 0.003242s, autotuning routine did not find a better threads count configuration. Will autotune matrix: 6 x 6, type C, 36 nnz, 6 nnz/r, 29 subms, 22 lsubms, 4.6667 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:0.1 -3 iterations (12 th.) took 0.01478s; avg 0.004927s ( +/- 17.65/ 26.92 %); best 0.004057s; worst 0.006253s; std dev. 0.0009529 (taking best). -Reference operation time is 0.00405693 s (0.142 Mflops) with 12 threads. -Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=2, order=cols) (max 6 steps, inclusive 3 grace steps) on: 6 x 6, type C, 36 nnz, 6 nnz/r, 29 subms, 22 lsubms, 4.6667 bpnz (tpop: 0.004057 Mflops: 0.142) -Merge (22 -> 16 leaves) took w.c.t. of 0.0009558s, ~5.96e-06s of computing time (of which 1.192e-06s sorting, 3.815e-06s analysis) -3 iterations (12 th.) took 0.05077s; avg 0.01692s ( +/- 52.73/ 40.56 %); best 0.008001s; worst 0.02379s; std dev. 0.006608 (taking best). -Reference operation time is 0.00800109 s (0.07199 Mflops) with 12 threads. -After merge step 1: tpop: 0.008001 s ~Mflops: 0.072 nsubm:16 otn:12 -Applying merge (22 -> 16 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.972x: 0.004057s -> 0.008001s. -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 0.05175s (of which 0.0009589s partitioning, 0s I/O); computing times: 5.96e-06s in par. loops, 1.192e-06s sorting, 3.815e-06s analyzing) -Total merge + benchmarking process took 0.05175s, equivalent to 12.8/12.8 new/old ops (0.01997s for 1 clones -- as 4.9/4.9 ops, or 4.9/4.9 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) -Merging based autotuning FAILED (=NO SPEEDUP); let's try splitting then... -3 iterations (12 th.) took 0.02441s; avg 0.008137s ( +/- 1.83/ 3.50 %); best 0.007988s; worst 0.008422s; std dev. 0.0002015 (taking best). -Reference operation time is 0.00798798 s (0.07211 Mflops) with 12 threads. -Starting split (same threads) based auto-tuning procedure (transA=N, nrhs=2, order=cols) (max 6 steps, inclusive 3 grace steps) on: 6 x 6, type C, 36 nnz, 6 nnz/r, 29 subms, 22 lsubms, 4.6667 bpnz (tpop: 0.007988 Mflops: 0.072) -Split (22 -> 28 leaves, 29 -> 37 subms) took 0.0119s (of which: 4.053e-06s analysis, -3.478e+09s mem.mgmt); compute time: 1.693e-05s overall, 9.537e-07s searches, 1.597e-05s shuffle, 7.868e-06s switch, 1.907e-06s quadrants. -3 iterations (12 th.) took 0.02364s; avg 0.00788s ( +/- 6.14/ 4.06 %); best 0.007396s; worst 0.0082s; std dev. 0.000348 (taking best). -Reference operation time is 0.00739598 s (0.07788 Mflops) with 12 threads. -After split step 1: tpop: 0.007396 s ~Mflops: 0.078 nsubm:28 otn:12 -Applying split (22 -> 28 leaves, 12 th.) yielded SPEEDUP of 1.080x: 0.007988s -> 0.007396s, so taking this instance. -Split (28 -> 28 leaves, 37 -> 37 subms) took 0.007776s (of which: 5.007e-06s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. -3 iterations (12 th.) took 0.01226s; avg 0.004085s ( +/- 5.98/ 9.15 %); best 0.003841s; worst 0.004459s; std dev. 0.0002683 (taking best). -Reference operation time is 0.00384092 s (0.15 Mflops) with 12 threads. -After split step 2: tpop: 0.003841 s ~Mflops: 0.150 nsubm:28 otn:12 -Applying split (28 -> 28 leaves, 12 th.) yielded SPEEDUP of 1.926x: 0.007396s -> 0.003841s, so taking this instance. -Split (28 -> 28 leaves, 37 -> 37 subms) took 0.01081s (of which: 4.053e-06s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. -3 iterations (12 th.) took 0.01379s; avg 0.004598s ( +/- 3.07/ 5.74 %); best 0.004457s; worst 0.004862s; std dev. 0.0001869 (taking best). -Reference operation time is 0.004457 s (0.1292 Mflops) with 12 threads. -After split step 3: tpop: 0.004457 s ~Mflops: 0.129 nsubm:28 otn:12 -Applying split (28 -> 28 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.160x: 0.003841s -> 0.004457s. -Split (28 -> 28 leaves, 37 -> 37 subms) took 0.01139s (of which: 4.053e-06s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. -3 iterations (12 th.) took 0.01939s; avg 0.006463s ( +/- 39.36/ 64.14 %); best 0.003919s; worst 0.01061s; std dev. 0.002957 (taking best). -Reference operation time is 0.00391912 s (0.147 Mflops) with 12 threads. -After split step 4: tpop: 0.003919 s ~Mflops: 0.147 nsubm:28 otn:12 -Applying split (28 -> 28 leaves, 12 th.) yielded SLOWDOWN (2th of 3 tolerable) of 1.020x: 0.003841s -> 0.003919s. -Split (28 -> 28 leaves, 37 -> 37 subms) took 0.005481s (of which: 5.007e-06s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. -3 iterations (12 th.) took 0.01257s; avg 0.004189s ( +/- 41.75/ 25.85 %); best 0.00244s; worst 0.005272s; std dev. 0.001248 (taking best). -Reference operation time is 0.00243998 s (0.2361 Mflops) with 12 threads. -After split step 5: tpop: 0.00244 s ~Mflops: 0.236 nsubm:28 otn:12 -Applying split (28 -> 28 leaves, 12 th.) yielded SPEEDUP of 1.574x: 0.003841s -> 0.00244s, so taking this instance. -Split (28 -> 28 leaves, 37 -> 37 subms) took 0.005208s (of which: 4.053e-06s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. -3 iterations (12 th.) took 0.0183s; avg 0.006099s ( +/- 78.29/ 47.77 %); best 0.001324s; worst 0.009012s; std dev. 0.003403 (taking best). -Reference operation time is 0.00132394 s (0.4351 Mflops) with 12 threads. -After split step 6: tpop: 0.001324 s ~Mflops: 0.435 nsubm:28 otn:12 -Applying split (28 -> 28 leaves, 12 th.) yielded SPEEDUP of 1.843x: 0.00244s -> 0.001324s, so taking this instance. -A total of 6 split steps (of max 6) (22 -> 28 subms) took 0.2177s (of which 0.05278s partitioning, 0s I/O); computing times: 1.693e-05s in par. loops, 9.537e-07s sorting, 2.623e-05s analyzing) -Total split + benchmarking process took 0.2177s, equivalent to 164.4/27.2 new/old ops (0.08122s for 5 clones -- as 61.3/10.2 ops, or 12.3/2.0 ops per clone), SPEEDUP of 6.033x -Applying multi-split (22 -> 28 leaves, 6 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 6.033x (0.007988s -> 0.001324s), will amortize in 32.7 ops by saving 0.006664s per op. -In 1 tuning rounds (tot. 0.35s, 0.1s for constructor, 6 clones) obtained a SPEEDUP of 503.3% (6.033x) (from 0.07211 to 0.4351 Mflops). -After 0.345070s, global autotuning declared speedup of 6.0335 x, when using threads count of 12 and a new matrix: -(6 x 6)[0xaaaae65a6020]{C} @ (0(0..0),0(0..0)) (36 nnz, 6 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 28, symflags:'' +3 iterations (12 th.) took 0.002872s; avg 0.0009573s ( +/- 26.16/ 20.44 %); best 0.0007069s; worst 0.001153s; std dev. 0.0001862 (taking best). +Reference operation time is 0.000706911 s (0.8148 Mflops) with 12 threads. +Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=2, order=cols) (max 6 steps, inclusive 3 grace steps) on: 6 x 6, type C, 36 nnz, 6 nnz/r, 29 subms, 22 lsubms, 4.6667 bpnz (tpop: 0.0007069 Mflops: 0.815) +Merge (22 -> 16 leaves) took w.c.t. of 0.0002291s, ~7.868e-06s of computing time (of which 0s sorting, 4.053e-06s analysis) +3 iterations (12 th.) took 0.003517s; avg 0.001172s ( +/- 34.68/ 25.83 %); best 0.0007658s; worst 0.001475s; std dev. 0.0002987 (taking best). +Reference operation time is 0.0007658 s (0.7522 Mflops) with 12 threads. +After merge step 1: tpop: 0.0007658 s ~Mflops: 0.752 nsubm:16 otn:12 +Applying merge (22 -> 16 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.083x: 0.0007069s -> 0.0007658s. +Merge (16 -> 10 leaves) took w.c.t. of 0.0002859s, ~1.001e-05s of computing time (of which 2.384e-06s sorting, 3.099e-06s analysis) +3 iterations (12 th.) took 0.002451s; avg 0.000817s ( +/- 16.51/ 29.37 %); best 0.0006821s; worst 0.001057s; std dev. 0.0001701 (taking best). +Reference operation time is 0.000682116 s (0.8444 Mflops) with 12 threads. +After merge step 2: tpop: 0.0006821 s ~Mflops: 0.844 nsubm:10 otn:12 +Applying merge (16 -> 10 leaves, 12 th.) yielded SPEEDUP of 1.036x: 0.0007069s -> 0.0006821s, so taking this instance. +Merge (10 -> 7 leaves) took w.c.t. of 8.821e-06s, ~3.099e-06s of computing time (of which 9.537e-07s sorting, 1.907e-06s analysis) +3 iterations (12 th.) took 0.002351s; avg 0.0007837s ( +/- 12.72/ 24.28 %); best 0.000684s; worst 0.0009739s; std dev. 0.0001346 (taking best). +Reference operation time is 0.000684023 s (0.8421 Mflops) with 12 threads. +After merge step 3: tpop: 0.000684 s ~Mflops: 0.842 nsubm:7 otn:12 +Applying merge (10 -> 7 leaves, 12 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=0.99721x): 0.0006821s -> 0.000684s, so IGNORING this instance. +Merge (7 -> 4 leaves) took w.c.t. of 1.001e-05s, ~2.861e-06s of computing time (of which 0s sorting, 1.907e-06s analysis) +3 iterations (12 th.) took 0.001787s; avg 0.0005956s ( +/- 31.51/ 49.26 %); best 0.0004079s; worst 0.0008891s; std dev. 0.0002102 (taking best). +Reference operation time is 0.000407934 s (1.412 Mflops) with 12 threads. +After merge step 4: tpop: 0.0004079 s ~Mflops: 1.412 nsubm:4 otn:12 +Applying merge (7 -> 4 leaves, 12 th.) yielded SPEEDUP of 1.672x: 0.0006821s -> 0.0004079s, so taking this instance. +Merge (4 -> 1 leaves) took w.c.t. of 8.106e-06s, ~2.861e-06s of computing time (of which 9.537e-07s sorting, 1.192e-06s analysis) +3 iterations (12 th.) took 3.099e-06s; avg 1.033e-06s ( +/- 92.48/107.69 %); best 7.764e-08s; worst 2.146e-06s; std dev. 8.778e-07 (taking best). +Reference operation time is 7.7641e-08 s (7419 Mflops) with 12 threads. +After merge step 5: tpop: 7.764e-08 s ~Mflops: 7418.760 nsubm:1 otn:12 +Applying merge (4 -> 1 leaves, 12 th.) yielded SPEEDUP of 5254.107x: 0.0004079s -> 7.764e-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 0.01687s (of which 0.000555s partitioning, 0s I/O); computing times: 2.67e-05s in par. loops, 4.292e-06s sorting, 1.216e-05s analyzing) +Total merge + benchmarking process took 0.01687s, equivalent to 217242.4/23.9 new/old ops (0.008004s for 4 clones -- as 103092.3/11.3 ops, or 25773.1/2.8 ops per clone), SPEEDUP of 9104.867x +Applying multi-merge (22 -> 1 leaves, 5 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 9104.867x (0.0007069s -> 7.764e-08s), will amortize in 23.9 ops by saving 0.0007068s per op. +In 1 tuning rounds (tot. 0.022s, 0.008s for constructor, 4 clones) obtained a SPEEDUP of 910386.7% (9105x) (from 0.8148 to 7419 Mflops). +After 0.021814s, global autotuning declared speedup of 9104.87 x, when using threads count of 12 and a new matrix: +(6 x 6)[0xaaaafb0a3ef0]{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:'' Considering Z clone. Building a matrix with 36 nnz, 6 x 6 Duplicates check: 36 - 0 = 36 - converted COO to RSB in 5.466e-02 s (100.00 %) - analyzed arrays in 2.539e-02 s (46.45 %) - cleaned-up arrays in 1.192e-06 s (0.00 %) - deduplicated arrays in 0.000e+00 s (0.00 %) + converted COO to RSB in 3.499e-03 s (100.00 %) + analyzed arrays in 1.287e-03 s (36.78 %) + cleaned-up arrays in 0.000e+00 s (0.00 %) + deduplicated arrays in 9.537e-07 s (0.03 %) sorted arrays in 0.000e+00 s (0.00 %) - shuffled partitions in 1.662e-02 s (30.41 %) - memory allocations took 8.821e-06 s (0.02 %) - leafs setup took 5.007e-06 s (0.01 %) - halfword conversion took 1.263e-02 s (23.11 %) -Built (6 x 6)[0xaaaae65a12f0]{Z} @ (0(0..0),0(0..0)) (36 nnz, 6 nnz/r) flags 0x42046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 28, symflags:'' + shuffled partitions in 9.811e-04 s (28.04 %) + memory allocations took 4.053e-06 s (0.12 %) + leafs setup took 9.537e-07 s (0.03 %) + halfword conversion took 1.224e-03 s (34.98 %) +Built (6 x 6)[0xaaaafb0a9cd0]{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)[0xaaaae65a12f0]{Z} @ (0(0..0),0(0..0)) (36 nnz, 6 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 28, symflags:'' +(6 x 6)[0xaaaafb0a9cd0]{Z} @ (0(0..0),0(0..0)) (36 nnz, 6 nnz/r) flags 0x2046186 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 28, symflags:'' Will use autotuning routine to sample matrix: 6 x 6, type Z, 36 nnz, 6 nnz/r, 37 subms, 28 lsubms, 4.4444 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:0.1 -3 iterations (12 th.) took 0.02712s; avg 0.009039s ( +/- 16.03/ 25.24 %); best 0.00759s; worst 0.01132s; std dev. 0.001633 (taking best). -Reference operation time is 0.00759006 s (0.07589 Mflops) with 12 threads. -After 0.027153s, autotuning routine did not find a better threads count configuration. +3 iterations (12 th.) took 0.002859s; avg 0.000953s ( +/- 6.29/ 5.47 %); best 0.0008931s; worst 0.001005s; std dev. 4.608e-05 (taking best). +Reference operation time is 0.000893116 s (0.6449 Mflops) with 12 threads. +After 0.002871s, autotuning routine did not find a better threads count configuration. Will autotune matrix: 6 x 6, type Z, 36 nnz, 6 nnz/r, 37 subms, 28 lsubms, 4.4444 bpnz. Parameters: verbosity:1 mintimes:3 maxtimes:10 mindt:0 maxdt:0.1 -3 iterations (12 th.) took 0.004178s; avg 0.001393s ( +/- 39.48/ 20.85 %); best 0.0008428s; worst 0.001683s; std dev. 0.000389 (taking best). -Reference operation time is 0.00084281 s (0.6834 Mflops) with 12 threads. -Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=2, order=cols) (max 6 steps, inclusive 3 grace steps) on: 6 x 6, type Z, 36 nnz, 6 nnz/r, 37 subms, 28 lsubms, 4.4444 bpnz (tpop: 0.0008428 Mflops: 0.683) -Merge (28 -> 22 leaves) took w.c.t. of 0.0002689s, ~8.821e-06s of computing time (of which 2.146e-06s sorting, 3.099e-06s analysis) -3 iterations (12 th.) took 0.02562s; avg 0.008541s ( +/- 6.50/ 12.79 %); best 0.007986s; worst 0.009633s; std dev. 0.0007722 (taking best). -Reference operation time is 0.00798607 s (0.07213 Mflops) with 12 threads. -After merge step 1: tpop: 0.007986 s ~Mflops: 0.072 nsubm:22 otn:12 -Applying merge (28 -> 22 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 9.476x: 0.0008428s -> 0.007986s. +3 iterations (12 th.) took 0.00238s; avg 0.0007933s ( +/- 23.60/ 14.21 %); best 0.0006061s; worst 0.000906s; std dev. 0.0001333 (taking best). +Reference operation time is 0.00060606 s (0.9504 Mflops) with 12 threads. +Starting merge (same threads) based auto-tuning procedure (transA=N, nrhs=2, order=cols) (max 6 steps, inclusive 3 grace steps) on: 6 x 6, type Z, 36 nnz, 6 nnz/r, 37 subms, 28 lsubms, 4.4444 bpnz (tpop: 0.0006061 Mflops: 0.950) +Merge (28 -> 22 leaves) took w.c.t. of 8.988e-05s, ~8.106e-06s of computing time (of which 9.537e-07s sorting, 1.907e-06s analysis) +3 iterations (12 th.) took 0.002272s; avg 0.0007573s ( +/- 33.16/ 38.37 %); best 0.0005062s; worst 0.001048s; std dev. 0.0002229 (taking best). +Reference operation time is 0.000506163 s (1.138 Mflops) with 12 threads. +After merge step 1: tpop: 0.0005062 s ~Mflops: 1.138 nsubm:22 otn:12 +Applying merge (28 -> 22 leaves, 12 th.) yielded SPEEDUP of 1.197x: 0.0006061s -> 0.0005062s, so taking this instance. +Merge (22 -> 16 leaves) took w.c.t. of 0.0002511s, ~7.153e-06s of computing time (of which 0s sorting, 3.099e-06s analysis) +3 iterations (12 th.) took 0.002695s; avg 0.0008984s ( +/- 24.07/ 29.46 %); best 0.0006821s; worst 0.001163s; std dev. 0.0001993 (taking best). +Reference operation time is 0.000682116 s (0.8444 Mflops) with 12 threads. +After merge step 2: tpop: 0.0006821 s ~Mflops: 0.844 nsubm:16 otn:12 +Applying merge (22 -> 16 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.348x: 0.0005062s -> 0.0006821s. Skipping further merge based tests after 1 definite performance degradations in a row (and last exceeding limit). -A total of 1 merge steps (of max 6) (28 -> 22 subms) took 0.02592s (of which 0.000272s partitioning, 0s I/O); computing times: 8.821e-06s in par. loops, 2.146e-06s sorting, 3.099e-06s analyzing) -Total merge + benchmarking process took 0.02592s, equivalent to 30.8/30.8 new/old ops (0.01346s for 1 clones -- as 16.0/16.0 ops, or 16.0/16.0 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) -Merging based autotuning FAILED (=NO SPEEDUP); let's try splitting then... -3 iterations (12 th.) took 0.01997s; avg 0.006656s ( +/- 36.81/ 22.87 %); best 0.004206s; worst 0.008178s; std dev. 0.001749 (taking best). -Reference operation time is 0.00420594 s (0.1369 Mflops) with 12 threads. -Starting split (same threads) based auto-tuning procedure (transA=N, nrhs=2, order=cols) (max 6 steps, inclusive 3 grace steps) on: 6 x 6, type Z, 36 nnz, 6 nnz/r, 37 subms, 28 lsubms, 4.4444 bpnz (tpop: 0.004206 Mflops: 0.137) -Split (28 -> 28 leaves, 37 -> 37 subms) took 0.01595s (of which: 5.007e-06s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. -3 iterations (12 th.) took 0.0196s; avg 0.006534s ( +/- 35.35/ 25.40 %); best 0.004224s; worst 0.008194s; std dev. 0.001685 (taking best). -Reference operation time is 0.00422406 s (0.1364 Mflops) with 12 threads. -After split step 1: tpop: 0.004224 s ~Mflops: 0.136 nsubm:28 otn:12 -Applying split (28 -> 28 leaves, 12 th.) yielded NEGLIGIBLE change (1th in a row) (old/new=0.99571x): 0.004206s -> 0.004224s, so IGNORING this instance. -Split (28 -> 28 leaves, 37 -> 37 subms) took 0.01599s (of which: 5.007e-06s analysis, 0s mem.mgmt); compute time: 0s overall, 0s searches, 0s shuffle, 0s switch, 0s quadrants. -3 iterations (12 th.) took 0.02812s; avg 0.009373s ( +/- 16.82/ 29.33 %); best 0.007796s; worst 0.01212s; std dev. 0.001951 (taking best). -Reference operation time is 0.00779605 s (0.07388 Mflops) with 12 threads. -After split step 2: tpop: 0.007796 s ~Mflops: 0.074 nsubm:28 otn:12 -Applying split (28 -> 28 leaves, 12 th.) yielded SLOWDOWN (1th of 3 tolerable) of 1.854x: 0.004206s -> 0.007796s. -Skipping further split based tests after 1 definite performance degradations in a row (and last exceeding limit). -A total of 2 split steps (of max 6) (28 -> 28 subms) took 0.07975s (of which 0.03199s partitioning, 0s I/O); computing times: 0s in par. loops, 0s sorting, 1.001e-05s analyzing) -Total split + benchmarking process took 0.07975s, equivalent to 19.0/19.0 new/old ops (0.02842s for 1 clones -- as 6.8/6.8 ops, or 6.8/6.8 ops per clone), SPEEDUP of 1.000x (NO SPEEDUP) -In 1 tuning rounds (tot. 0.17s, 0.042s for constructor, 2 clones) obtained NO speedup (best stays 0.1369 Mflops). -After 0.171802s, global autotuning found old matrix optimal, with declared speedup 1 x when using 12 threads +A total of 2 merge steps (of max 6) (28 -> 16 subms) took 0.006639s (of which 0.0003459s partitioning, 0s I/O); computing times: 1.526e-05s in par. loops, 9.537e-07s sorting, 5.007e-06s analyzing) +Total merge + benchmarking process took 0.006639s, equivalent to 13.1/11.0 new/old ops (0.002807s for 2 clones -- as 5.5/4.6 ops, or 2.8/2.3 ops per clone), SPEEDUP of 1.197x +Applying multi-merge (28 -> 22 leaves, 1 steps, 0 -> 12 th.sp.) yielded SPEEDUP of 1.197x (0.0006061s -> 0.0005062s), will amortize in 66.5 ops by saving 9.99e-05s per op. +In 1 tuning rounds (tot. 0.011s, 0.0028s for constructor, 2 clones) obtained a SPEEDUP of 19.7% (1.197x) (from 0.9504 to 1.138 Mflops). +After 0.010710s, global autotuning declared speedup of 1.19736 x, when using threads count of 12 and a new matrix: +(6 x 6)[0xaaaafb0ad420]{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:'' 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' @@ -9085,19 +9165,18 @@ 4 0 DIFF PRINT TEST END Beginning large binary search test. -Detected 33603571712 bytes of memory, comprehensive of 9136594944 of free memory. +Detected 33603571712 bytes of memory, comprehensive of 17438625792 of free memory. On this system, maximal array of coordinates can have 2147483137 elements and occupy 8589932548 bytes. -Will perform the test using less memory (6535 MB) than on the maximal coordinate indices array (6852446208) allows. -(c)allocated 1713111552 nnz (6852446208 bytes) -Succeeded retrieving array last element. -Successfully performed large binary search test. +Will perform the test using less memory (17592186040505 MB) than on the maximal coordinate indices array (18446744069608651776) allows. +Skipping test: too little memory. +Skipping large binary search test. BASIC SPARSE BLAS TEST: BEGIN INIT INTERFACE TEST: BEGIN got RSB_IO_WANT_EXTRA_VERBOSE_INTERFACE: -1 got RSB_IO_WANT_IS_INITIALIZED_MARKER: 1 INIT INTERFACE TEST: END (SUCCESS) DEVEL PRINT TEST: BEGIN -(4 x 4)[0xaaaae16ba2a0]{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)[0xaaaafedcb2a0]{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 | @@ -9106,8 +9185,8 @@ RSB_FLAG_ASSEMBLED_IN_COO_ARRAYS | RSB_FLAG_OWN_PARTITIONING_ARRAYS | RSB_FLAG_SORT_INPUT -(2 x 2)[0xaaaae16ba3b0]{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)[0xaaaae16ba4c0]{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)[0xaaaafedcb3b0]{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)[0xaaaafedcb4c0]{S} @ (2(2..4),2(2..4)) (2 nnz, 1 nnz/r) flags 0x2144386 (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 0, symflags:'' #R 4 x 4, 4 nnz (16 bytes), 16 index space for bytes, 544 bytes for 2 structs (2 of which are on the diagonal) (1e+02% of nnz are on the diagonal) #N at 0 0, 4 x 4, 4 nnz ( 25%) #T at 0 0, 2 x 2, 2 nnz ( 50%) @@ -9115,9 +9194,9 @@ ( 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)[0xaaaae16ba3b0]{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)[0xaaaae16ba4c0]{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)[0xaaaae16ba2a0]{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)[0xaaaafedcb3b0]{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)[0xaaaafedcb4c0]{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)[0xaaaafedcb2a0]{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 | @@ -9135,8 +9214,8 @@ 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 30.002745 s, max allowed was 30.000000. - PASSED:15844 +Terminating testing earlier due to user timeout request: test took 30.025979 s, max allowed was 30.000000. + PASSED:19921 FAILED:0 ADVANCED SPARSE BLAS TEST: END (SUCCESS) gmake qtests -C librsbpp @@ -9145,10 +9224,10 @@ 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 +++ wc -l + test 54 = 54 ++ ./rsbpp Td G.mtx ++ grep Z-sort @@ -9158,32 +9237,32 @@ ++ grep Z-sort ++ wc -l + test 54 = 54 -++ ./rsbpp vTd,z G.mtx -++ grep Z-sort ++ wc -l +++ grep Z-sort +++ ./rsbpp vTd,z G.mtx + test 54 = 54 ++ ./rsbpp vTd,z G.mtx ++ grep Z-sort ++ wc -l + test 54 = 54 +++ wc -l ++ ./rsbpp vvvTd,z G.mtx ++ grep Zorted -++ wc -l + test 8 = 8 ++ ./rsbpp vvTd,z G.mtx ++ grep Z-sort ++ wc -l + test 54 = 54 -++ ./rsbpp vvTd,z G.mtx ++ grep Range +++ ./rsbpp vvTd,z G.mtx ++ wc -l + test 0 = 0 ++ ./rsbpp vvvTd,z G.mtx ++ grep Range ++ wc -l + test 258 -gt 0 -++ ./rsbpp vvvTd,z S.mtx ++ grep Range +++ ./rsbpp vvvTd,z S.mtx ++ wc -l + test 0 -eq 0 ++ ./rsbpp vvvTd,z G.mtx @@ -9192,18 +9271,18 @@ + test 258 = 258 ++ OMP_NUM_THREADS=1 ++ ./rsbpp m10M10I1r1,4,8sFv -++ grep spmm- ++ wc -l +++ grep spmm- + test 9 = 9 ++ OMP_NUM_THREADS=1 ++ ./rsbpp C1000m100M100I1r1,4,8sFv -++ wc -l ++ grep spmm- +++ wc -l + test 9 = 9 ++ OMP_NUM_THREADS=1 ++ ./rsbpp C1000m100M100I1r1sFvtN,T -++ wc -l ++ grep spmm- +++ wc -l + test 3 = 3 ++ OMP_NUM_THREADS=1 ++ ./rsbpp C1000m100M100I1r1vtN,TsF @@ -9284,7 +9363,7 @@ 0 0 0 0 before tuning for SPMV: -(3 x 3)[0xaaab061d2d00]{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)[0xaaaafcc6a0c0]{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 @@ -9373,18 +9452,18 @@ BEGIN Rsb_Matrix_test_multimatrix_ms_mnrhs BEGIN -(3 x 3)[0xaaab061fc830]{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 1.01189: -(3 x 3)[0xaaab0620a640]{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)[0xaaab061ccfb0]{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 1.02255: -(3 x 3)[0xaaab0620c9b0]{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)[0xaaab061fc830]{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 1.02105: -(3 x 3)[0xaaab0620a640]{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)[0xaaab061ccfb0]{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)[0xaaaafcc86f70]{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 1.00224: +(3 x 3)[0xaaaafcca0640]{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)[0xaaaafcc86f70]{D} @ (0(0..0),0(0..0)) (6 nnz, 2 nnz/r) flags 0x204619e (coo:1, csr:1, hw:1, ic:1, fi:0), storage: 40, subm: 3, symflags:'LT' Tuned with speedup factor of 1: -(3 x 3)[0xaaab061ccfb0]{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)[0xaaaafcc86f70]{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)[0xaaaafcca3d00]{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 1.00279: +(3 x 3)[0xaaaafcca1d20]{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)[0xaaaafcc86f70]{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 1.00222: +(3 x 3)[0xaaaafcca4370]{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 ! @@ -9401,10 +9480,10 @@ ./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 codethink03-arm64 +running on i-capture-the-hostname Built without the MKL. ( ! ./rsbtest --unrecognized-option-triggers-abort ) -running on codethink03-arm64 +running on i-capture-the-hostname /build/reproducible-path/librsb-1.3.0.2+dfsg/rsbtest/.libs/rsbtest: unrecognized option '--unrecognized-option-triggers-abort' unrecognized option, aborting. ( ./rsbtest --no-tune --max_t 0.01 --skip-loading-hermitian-matrices --skip-loading-unsymmetric-matrices --tune-maxt 10 --tune-maxr 10 --verbose-tuning --extra-verbose-interface --min_t 0.01 --max_t 0.01 --mintimes 1 --maxtimes 1 --verbose --skip-loading-symmetric-matrices A.mtx | dd if=/dev/stdin of=/dev/stdout bs=16M status=none iflag=fullblock | grep -q skip ) @@ -9413,7 +9492,7 @@ ( ! ./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 codethink03-arm64 +running on i-capture-the-hostname Will not invoke autotuning routine. Benchmark will sample for at most 0.01 s Built without render support! @@ -9466,7 +9545,7 @@ 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' /bin/mkdir -p '/build/reproducible-path/librsb-1.3.0.2+dfsg/debian/tmp/usr/lib/aarch64-linux-gnu' - /bin/bash ./libtool --mode=install /usr/bin/install -c librsb.la '/build/reproducible-path/librsb-1.3.0.2+dfsg/debian/tmp/usr/lib/aarch64-linux-gnu' + /bin/sh ./libtool --mode=install /usr/bin/install -c librsb.la '/build/reproducible-path/librsb-1.3.0.2+dfsg/debian/tmp/usr/lib/aarch64-linux-gnu' libtool: install: /usr/bin/install -c .libs/librsb.so.0.0.0 /build/reproducible-path/librsb-1.3.0.2+dfsg/debian/tmp/usr/lib/aarch64-linux-gnu/librsb.so.0.0.0 libtool: install: (cd /build/reproducible-path/librsb-1.3.0.2+dfsg/debian/tmp/usr/lib/aarch64-linux-gnu && { ln -s -f librsb.so.0.0.0 librsb.so.0 || { rm -f librsb.so.0 && ln -s librsb.so.0.0.0 librsb.so.0; }; }) libtool: install: (cd /build/reproducible-path/librsb-1.3.0.2+dfsg/debian/tmp/usr/lib/aarch64-linux-gnu && { ln -s -f librsb.so.0.0.0 librsb.so || { rm -f librsb.so && ln -s librsb.so.0.0.0 librsb.so; }; }) @@ -9476,7 +9555,7 @@ libtool: install: ranlib /build/reproducible-path/librsb-1.3.0.2+dfsg/debian/tmp/usr/lib/aarch64-linux-gnu/librsb.a libtool: warning: remember to run 'libtool --finish /usr/lib/aarch64-linux-gnu' /bin/mkdir -p '/build/reproducible-path/librsb-1.3.0.2+dfsg/debian/tmp/usr/bin' - /bin/bash ./libtool --mode=install /usr/bin/install -c rsbench '/build/reproducible-path/librsb-1.3.0.2+dfsg/debian/tmp/usr/bin' + /bin/sh ./libtool --mode=install /usr/bin/install -c rsbench '/build/reproducible-path/librsb-1.3.0.2+dfsg/debian/tmp/usr/bin' libtool: warning: 'librsb.la' has not been installed in '/usr/lib/aarch64-linux-gnu' libtool: install: /usr/bin/install -c .libs/rsbench /build/reproducible-path/librsb-1.3.0.2+dfsg/debian/tmp/usr/bin/rsbench /bin/mkdir -p '/build/reproducible-path/librsb-1.3.0.2+dfsg/debian/tmp/usr/bin' @@ -9604,12 +9683,12 @@ dh_gencontrol -O--no-parallel dh_md5sums -O--no-parallel dh_builddeb -O--no-parallel +dpkg-deb: building package 'librsb-tools' in '../librsb-tools_1.3.0.2+dfsg-4_arm64.deb'. dpkg-deb: building package 'librsb0' in '../librsb0_1.3.0.2+dfsg-4_arm64.deb'. -dpkg-deb: building package 'librsb0-dbgsym' in '../librsb0-dbgsym_1.3.0.2+dfsg-4_arm64.deb'. +dpkg-deb: building package 'librsb-dev' in '../librsb-dev_1.3.0.2+dfsg-4_arm64.deb'. dpkg-deb: building package 'librsb-tools-dbgsym' in '../librsb-tools-dbgsym_1.3.0.2+dfsg-4_arm64.deb'. -dpkg-deb: building package 'librsb-tools' in '../librsb-tools_1.3.0.2+dfsg-4_arm64.deb'. +dpkg-deb: building package 'librsb0-dbgsym' in '../librsb0-dbgsym_1.3.0.2+dfsg-4_arm64.deb'. dpkg-deb: building package 'librsb-doc' in '../librsb-doc_1.3.0.2+dfsg-4_all.deb'. -dpkg-deb: building package 'librsb-dev' in '../librsb-dev_1.3.0.2+dfsg-4_arm64.deb'. dpkg-genbuildinfo --build=binary -O../librsb_1.3.0.2+dfsg-4_arm64.buildinfo dpkg-genchanges --build=binary -O../librsb_1.3.0.2+dfsg-4_arm64.changes dpkg-genchanges: info: binary-only upload (no source code included) @@ -9618,12 +9697,14 @@ 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/3272415/tmp/hooks/B01_cleanup starting +I: user script /srv/workspace/pbuilder/3272415/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/3156444 and its subdirectories -I: Current time: Sun Feb 9 06:55:56 -12 2025 -I: pbuilder-time-stamp: 1739127356 +I: removing directory /srv/workspace/pbuilder/3272415 and its subdirectories +I: Current time: Tue Jan 9 02:52:12 +14 2024 +I: pbuilder-time-stamp: 1704718332