Linux 5.12 Scheduler AMD Ryzen 9 5950X 16-Core testing with a ASUS ROG CROSSHAIR VIII HERO (WI-FI) (3202 BIOS) and AMD Radeon RX 5600 OEM/5600 XT / 5700/5700 8GB on Ubuntu 20.10 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2102186-PTS-LINUX51266&sro&grr .
Linux 5.12 Scheduler Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server OpenGL Vulkan Compiler File-System Screen Resolution Linux 5.11 5.12 sched preempt=none AMD Ryzen 9 5950X 16-Core @ 6.92GHz (16 Cores / 32 Threads) ASUS ROG CROSSHAIR VIII HERO (WI-FI) (3202 BIOS) AMD Starship/Matisse 32GB 2000GB Corsair Force MP600 AMD Radeon RX 5600 OEM/5600 XT / 5700/5700 8GB (2100/875MHz) AMD Navi 10 HDMI Audio ASUS MG28U Realtek RTL8125 2.5GbE + Intel I211 + Intel Wi-Fi 6 AX200 Ubuntu 20.10 5.11.0-051100-generic (x86_64) GNOME Shell 3.38.2 X Server 1.20.9 4.6 Mesa 21.1.0-devel (git-824ae64 2021-02-01 groovy-oibaf-ppa) (LLVM 11.0.1) 1.2.145 GCC 10.2.0 ext4 3840x2160 5.11.0-sched (x86_64) OpenBenchmarking.org Kernel Details - Transparent Huge Pages: madvise Compiler Details - --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-JvwpWM/gcc-10-10.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-JvwpWM/gcc-10-10.2.0/debian/tmp-gcn/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v Processor Details - Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa201009 Python Details - Python 3.8.6 Security Details - itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected
Linux 5.12 Scheduler simdjson: Kostya simdjson: PartialTweets webp2: Quality 95, Compression Effort 7 askap: tConvolve MT - Degridding askap: tConvolve MT - Gridding gromacs: water_GMX50_bare npb: BT.C webp2: Quality 75, Compression Effort 7 openfoam: Motorbike 30M dav1d: Chimera 1080p 10-bit openvkl: vklBenchmark tesseract: 3840 x 2160 warsow: 3840 x 2160 build-godot: Time To Compile v-ray: CPU npb: LU.C daphne: OpenMP - Points2Image askap: tConvolve MPI - Gridding askap: tConvolve MPI - Degridding build-gdb: Time To Compile indigobench: CPU - Bedroom indigobench: CPU - Supercar graphics-magick: Resizing graphics-magick: Rotate namd: ATPase Simulation - 327,506 Atoms npb: IS.D stockfish: Total Time financebench: Bonds OpenMP rawtherapee: Total Benchmark Time npb: SP.B build-linux-kernel: Time To Compile jpegxl-decode: All npb: FT.C financebench: Repo OpenMP m-queens: Time To Solve qmcpack: simple-H2O paraview: Many Spheres - 3840 x 2160 paraview: Many Spheres - 3840 x 2160 paraview: Many Spheres - 1920 x 1080 paraview: Many Spheres - 1920 x 1080 npb: CG.C daphne: OpenMP - NDT Mapping etcpak: ETC2 ttsiod-renderer: Phong Rendering With Soft-Shadow Mapping clomp: Static OMP Speedup askap: Hogbom Clean OpenMP npb: MG.C paraview: Wavelet Volume - 3840 x 2160 paraview: Wavelet Volume - 3840 x 2160 dav1d: Summer Nature 4K daphne: OpenMP - Euclidean Cluster oidn: Memorial dav1d: Chimera 1080p paraview: Wavelet Volume - 1920 x 1080 paraview: Wavelet Volume - 1920 x 1080 npb: EP.C askap: tConvolve OpenMP - Degridding askap: tConvolve OpenMP - Gridding paraview: Wavelet Contour - 3840 x 2160 paraview: Wavelet Contour - 3840 x 2160 paraview: Wavelet Contour - 1920 x 1080 paraview: Wavelet Contour - 1920 x 1080 n-queens: Elapsed Time dav1d: Summer Nature 1080p etcpak: DXT1 Linux 5.11 5.12 sched preempt=none 0.67 0.90 214.943 1344.59 785.016 1.264 24129.92 116.335 97.64 121.66 292 398.4990 431.7 78.962 21506 28328.86 27781.126423097 6672.02 6758.72 62.436 4.139 8.682 1892 1068 1.08110 646.03 43133645 39971.764323 45.764 7886.19 45.598 202.60 12182.06 27369.523437 30.814 22.350 6294.768 62.78 6620.179 66.03 7018.38 882.03 241.114 1043.96 21.2 216.934 9935.40 4234.713 264.67 240.77 1493.34 14.57 837.08 7823.400 488.96 1917.44 3252.89 2722.08 2653.882 254.66 3896.310 373.88 5.622 911.62 1533.222 0.71 0.94 215.277 1343.89 784.775 1.266 24051.43 116.599 97.49 122.06 293 394.3750 430.4 79.313 21626 28209.45 27567.067160148 6642.93 6846.93 62.234 4.122 8.717 1876 1053 1.08100 647.67 43554003 39641.304688 45.837 7883.48 45.028 202.61 12122.51 27208.082682 30.855 22.608 6291.432 62.75 6645.758 66.29 6957.05 888.36 235.614 1046.99 21.2 217.709 9930.81 4260.097 266.26 241.18 1496.14 14.52 838.25 7416.986 463.56 1910.88 3260.38 2698.79 2649.139 254.21 3884.718 372.77 5.636 904.93 1521.611 0.67 0.90 215.788 1347.00 786.118 1.264 24170.35 116.264 97.47 122.79 291 400.9389 432.5 79.270 21505 28236.83 28250.508449223 6642.93 6786.34 62.593 4.120 8.650 1888 1034 1.07812 648.36 43828499 39677.799479 45.863 7863.94 45.025 202.05 12128.34 27190.204427 30.871 22.362 6284.997 62.69 6659.593 66.43 7069.55 895.79 241.378 1041.60 20.9 216.139 9936.87 4281.785 267.61 241.28 1514.32 14.52 841.47 8073.098 504.57 1876.48 3260.71 2707.75 2660.836 255.33 3908.986 375.10 5.635 913.38 1545.109 OpenBenchmarking.org
simdjson Throughput Test: Kostya OpenBenchmarking.org GB/s, More Is Better simdjson 0.7.1 Throughput Test: Kostya 5.12 sched Linux 5.11 preempt=none 0.1598 0.3196 0.4794 0.6392 0.799 SE +/- 0.03, N = 15 SE +/- 0.02, N = 12 SE +/- 0.02, N = 15 0.71 0.67 0.67 1. (CXX) g++ options: -O3 -pthread
simdjson Throughput Test: PartialTweets OpenBenchmarking.org GB/s, More Is Better simdjson 0.7.1 Throughput Test: PartialTweets 5.12 sched Linux 5.11 preempt=none 0.2115 0.423 0.6345 0.846 1.0575 SE +/- 0.02, N = 15 SE +/- 0.01, N = 15 SE +/- 0.01, N = 15 0.94 0.90 0.90 1. (CXX) g++ options: -O3 -pthread
WebP2 Image Encode Encode Settings: Quality 95, Compression Effort 7 OpenBenchmarking.org Seconds, Fewer Is Better WebP2 Image Encode 20210126 Encode Settings: Quality 95, Compression Effort 7 5.12 sched Linux 5.11 preempt=none 50 100 150 200 250 SE +/- 0.64, N = 3 SE +/- 0.69, N = 3 SE +/- 1.51, N = 3 215.28 214.94 215.79 1. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -rdynamic -lpthread -ljpeg -lgif -lwebp -lwebpdemux
ASKAP Test: tConvolve MT - Degridding OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 1.0 Test: tConvolve MT - Degridding 5.12 sched Linux 5.11 preempt=none 300 600 900 1200 1500 SE +/- 2.63, N = 3 SE +/- 1.91, N = 3 SE +/- 1.28, N = 3 1343.89 1344.59 1347.00 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
ASKAP Test: tConvolve MT - Gridding OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 1.0 Test: tConvolve MT - Gridding 5.12 sched Linux 5.11 preempt=none 200 400 600 800 1000 SE +/- 2.00, N = 3 SE +/- 1.97, N = 3 SE +/- 0.66, N = 3 784.78 785.02 786.12 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
GROMACS Input: water_GMX50_bare OpenBenchmarking.org Ns Per Day, More Is Better GROMACS 2021 Input: water_GMX50_bare 5.12 sched Linux 5.11 preempt=none 0.2849 0.5698 0.8547 1.1396 1.4245 SE +/- 0.002, N = 3 SE +/- 0.002, N = 3 SE +/- 0.001, N = 3 1.266 1.264 1.264 1. (CXX) g++ options: -O3 -pthread
NAS Parallel Benchmarks Test / Class: BT.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: BT.C 5.12 sched Linux 5.11 preempt=none 5K 10K 15K 20K 25K SE +/- 23.23, N = 3 SE +/- 23.90, N = 3 SE +/- 16.10, N = 3 24051.43 24129.92 24170.35 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.0.3
WebP2 Image Encode Encode Settings: Quality 75, Compression Effort 7 OpenBenchmarking.org Seconds, Fewer Is Better WebP2 Image Encode 20210126 Encode Settings: Quality 75, Compression Effort 7 5.12 sched Linux 5.11 preempt=none 30 60 90 120 150 SE +/- 0.55, N = 3 SE +/- 1.18, N = 3 SE +/- 0.31, N = 3 116.60 116.34 116.26 1. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -rdynamic -lpthread -ljpeg -lgif -lwebp -lwebpdemux
OpenFOAM Input: Motorbike 30M OpenBenchmarking.org Seconds, Fewer Is Better OpenFOAM 8 Input: Motorbike 30M 5.12 sched Linux 5.11 preempt=none 20 40 60 80 100 SE +/- 0.14, N = 3 SE +/- 0.07, N = 3 SE +/- 0.11, N = 3 97.49 97.64 97.47 1. (CXX) g++ options: -std=c++11 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfoamToVTK -ldynamicMesh -llagrangian -lgenericPatchFields -lfileFormats -lOpenFOAM -ldl -lm
dav1d Video Input: Chimera 1080p 10-bit OpenBenchmarking.org FPS, More Is Better dav1d 0.8.1 Video Input: Chimera 1080p 10-bit 5.12 sched Linux 5.11 preempt=none 30 60 90 120 150 SE +/- 1.09, N = 3 SE +/- 0.66, N = 3 SE +/- 0.68, N = 3 122.06 121.66 122.79 MIN: 86.2 / MAX: 274.09 MIN: 87.02 / MAX: 270.79 MIN: 87.1 / MAX: 278.24 1. (CC) gcc options: -pthread
OpenVKL Benchmark: vklBenchmark OpenBenchmarking.org Items / Sec, More Is Better OpenVKL 0.9 Benchmark: vklBenchmark 5.12 sched Linux 5.11 preempt=none 60 120 180 240 300 293 292 291 MIN: 1 / MAX: 1137 MIN: 1 / MAX: 1136 MIN: 1 / MAX: 1137
Tesseract Resolution: 3840 x 2160 OpenBenchmarking.org Frames Per Second, More Is Better Tesseract 2014-05-12 Resolution: 3840 x 2160 5.12 sched Linux 5.11 preempt=none 90 180 270 360 450 SE +/- 3.88, N = 15 SE +/- 3.68, N = 6 SE +/- 3.45, N = 3 394.38 398.50 400.94
Warsow Resolution: 3840 x 2160 OpenBenchmarking.org Frames Per Second, More Is Better Warsow 2.5 Beta Resolution: 3840 x 2160 5.12 sched Linux 5.11 preempt=none 90 180 270 360 450 SE +/- 0.38, N = 3 SE +/- 0.70, N = 3 SE +/- 0.49, N = 3 430.4 431.7 432.5
Timed Godot Game Engine Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Godot Game Engine Compilation 3.2.3 Time To Compile 5.12 sched Linux 5.11 preempt=none 20 40 60 80 100 SE +/- 0.12, N = 3 SE +/- 0.18, N = 3 SE +/- 0.08, N = 3 79.31 78.96 79.27
Chaos Group V-RAY Mode: CPU OpenBenchmarking.org vsamples, More Is Better Chaos Group V-RAY 5 Mode: CPU 5.12 sched Linux 5.11 preempt=none 5K 10K 15K 20K 25K SE +/- 221.33, N = 3 SE +/- 99.08, N = 3 SE +/- 254.55, N = 4 21626 21506 21505
NAS Parallel Benchmarks Test / Class: LU.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: LU.C 5.12 sched Linux 5.11 preempt=none 6K 12K 18K 24K 30K SE +/- 19.13, N = 3 SE +/- 8.24, N = 3 SE +/- 20.73, N = 3 28209.45 28328.86 28236.83 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.0.3
Darmstadt Automotive Parallel Heterogeneous Suite Backend: OpenMP - Kernel: Points2Image OpenBenchmarking.org Test Cases Per Minute, More Is Better Darmstadt Automotive Parallel Heterogeneous Suite Backend: OpenMP - Kernel: Points2Image 5.12 sched Linux 5.11 preempt=none 6K 12K 18K 24K 30K SE +/- 392.26, N = 3 SE +/- 342.19, N = 3 SE +/- 123.70, N = 3 27567.07 27781.13 28250.51 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp
ASKAP Test: tConvolve MPI - Gridding OpenBenchmarking.org Mpix/sec, More Is Better ASKAP 1.0 Test: tConvolve MPI - Gridding 5.12 sched Linux 5.11 preempt=none 1400 2800 4200 5600 7000 SE +/- 0.00, N = 3 SE +/- 56.07, N = 3 SE +/- 0.00, N = 3 6642.93 6672.02 6642.93 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
ASKAP Test: tConvolve MPI - Degridding OpenBenchmarking.org Mpix/sec, More Is Better ASKAP 1.0 Test: tConvolve MPI - Degridding 5.12 sched Linux 5.11 preempt=none 1500 3000 4500 6000 7500 SE +/- 79.27, N = 3 SE +/- 77.23, N = 3 SE +/- 29.13, N = 3 6846.93 6758.72 6786.34 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
Timed GDB GNU Debugger Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed GDB GNU Debugger Compilation 9.1 Time To Compile 5.12 sched Linux 5.11 preempt=none 14 28 42 56 70 SE +/- 0.31, N = 3 SE +/- 0.23, N = 3 SE +/- 0.18, N = 3 62.23 62.44 62.59
IndigoBench Acceleration: CPU - Scene: Bedroom OpenBenchmarking.org M samples/s, More Is Better IndigoBench 4.4 Acceleration: CPU - Scene: Bedroom 5.12 sched Linux 5.11 preempt=none 0.9313 1.8626 2.7939 3.7252 4.6565 SE +/- 0.016, N = 3 SE +/- 0.017, N = 3 SE +/- 0.010, N = 3 4.122 4.139 4.120
IndigoBench Acceleration: CPU - Scene: Supercar OpenBenchmarking.org M samples/s, More Is Better IndigoBench 4.4 Acceleration: CPU - Scene: Supercar 5.12 sched Linux 5.11 preempt=none 2 4 6 8 10 SE +/- 0.023, N = 3 SE +/- 0.011, N = 3 SE +/- 0.012, N = 3 8.717 8.682 8.650
GraphicsMagick Operation: Resizing OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Resizing 5.12 sched Linux 5.11 preempt=none 400 800 1200 1600 2000 SE +/- 6.56, N = 3 SE +/- 4.37, N = 3 SE +/- 5.51, N = 3 1876 1892 1888 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
GraphicsMagick Operation: Rotate OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Rotate 5.12 sched Linux 5.11 preempt=none 200 400 600 800 1000 SE +/- 5.86, N = 3 SE +/- 2.91, N = 3 SE +/- 3.61, N = 3 1053 1068 1034 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
NAMD ATPase Simulation - 327,506 Atoms OpenBenchmarking.org days/ns, Fewer Is Better NAMD 2.14 ATPase Simulation - 327,506 Atoms 5.12 sched Linux 5.11 preempt=none 0.2432 0.4864 0.7296 0.9728 1.216 SE +/- 0.00363, N = 3 SE +/- 0.00393, N = 3 SE +/- 0.00152, N = 3 1.08100 1.08110 1.07812
NAS Parallel Benchmarks Test / Class: IS.D OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: IS.D 5.12 sched Linux 5.11 preempt=none 140 280 420 560 700 SE +/- 0.65, N = 3 SE +/- 2.89, N = 3 SE +/- 0.90, N = 3 647.67 646.03 648.36 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.0.3
Stockfish Total Time OpenBenchmarking.org Nodes Per Second, More Is Better Stockfish 12 Total Time 5.12 sched Linux 5.11 preempt=none 9M 18M 27M 36M 45M SE +/- 444782.82, N = 5 SE +/- 412700.59, N = 3 SE +/- 476121.40, N = 5 43554003 43133645 43828499 1. (CXX) g++ options: -m64 -lpthread -fno-exceptions -std=c++17 -pedantic -O3 -msse -msse3 -mpopcnt -msse4.1 -mssse3 -msse2 -flto -flto=jobserver
FinanceBench Benchmark: Bonds OpenMP OpenBenchmarking.org ms, Fewer Is Better FinanceBench 2016-07-25 Benchmark: Bonds OpenMP 5.12 sched Linux 5.11 preempt=none 9K 18K 27K 36K 45K SE +/- 34.33, N = 3 SE +/- 31.83, N = 3 SE +/- 33.60, N = 3 39641.30 39971.76 39677.80 1. (CXX) g++ options: -O3 -march=native -fopenmp
RawTherapee Total Benchmark Time OpenBenchmarking.org Seconds, Fewer Is Better RawTherapee Total Benchmark Time 5.12 sched Linux 5.11 preempt=none 10 20 30 40 50 SE +/- 0.22, N = 3 SE +/- 0.26, N = 3 SE +/- 0.08, N = 3 45.84 45.76 45.86 1. RawTherapee, version 5.8, command line.
NAS Parallel Benchmarks Test / Class: SP.B OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: SP.B 5.12 sched Linux 5.11 preempt=none 2K 4K 6K 8K 10K SE +/- 21.12, N = 3 SE +/- 10.12, N = 3 SE +/- 12.69, N = 3 7883.48 7886.19 7863.94 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.0.3
Timed Linux Kernel Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Linux Kernel Compilation 5.4 Time To Compile 5.12 sched Linux 5.11 preempt=none 10 20 30 40 50 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.05, N = 3 45.03 45.60 45.03
JPEG XL Decoding CPU Threads: All OpenBenchmarking.org MP/s, More Is Better JPEG XL Decoding 0.3.1 CPU Threads: All 5.12 sched Linux 5.11 preempt=none 40 80 120 160 200 SE +/- 0.33, N = 3 SE +/- 0.31, N = 3 SE +/- 0.26, N = 3 202.61 202.60 202.05
NAS Parallel Benchmarks Test / Class: FT.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: FT.C 5.12 sched Linux 5.11 preempt=none 3K 6K 9K 12K 15K SE +/- 4.72, N = 3 SE +/- 6.14, N = 3 SE +/- 19.19, N = 3 12122.51 12182.06 12128.34 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.0.3
FinanceBench Benchmark: Repo OpenMP OpenBenchmarking.org ms, Fewer Is Better FinanceBench 2016-07-25 Benchmark: Repo OpenMP 5.12 sched Linux 5.11 preempt=none 6K 12K 18K 24K 30K SE +/- 33.25, N = 3 SE +/- 288.55, N = 3 SE +/- 25.37, N = 3 27208.08 27369.52 27190.20 1. (CXX) g++ options: -O3 -march=native -fopenmp
m-queens Time To Solve OpenBenchmarking.org Seconds, Fewer Is Better m-queens 1.2 Time To Solve 5.12 sched Linux 5.11 preempt=none 7 14 21 28 35 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.06, N = 3 30.86 30.81 30.87 1. (CXX) g++ options: -fopenmp -O2 -march=native
QMCPACK Input: simple-H2O OpenBenchmarking.org Total Execution Time - Seconds, Fewer Is Better QMCPACK 3.10 Input: simple-H2O 5.12 sched Linux 5.11 preempt=none 5 10 15 20 25 SE +/- 0.24, N = 5 SE +/- 0.10, N = 3 SE +/- 0.04, N = 3 22.61 22.35 22.36 1. (CXX) g++ options: -fopenmp -finline-limit=1000 -fstrict-aliasing -funroll-all-loops -march=native -O3 -fomit-frame-pointer -ffast-math -pthread -lm
ParaView Test: Many Spheres - Resolution: 3840 x 2160 OpenBenchmarking.org MiPolys / Sec, More Is Better ParaView 5.9 Test: Many Spheres - Resolution: 3840 x 2160 5.12 sched Linux 5.11 preempt=none 1300 2600 3900 5200 6500 SE +/- 3.70, N = 3 SE +/- 1.21, N = 3 SE +/- 11.31, N = 3 6291.43 6294.77 6285.00
ParaView Test: Many Spheres - Resolution: 3840 x 2160 OpenBenchmarking.org Frames / Sec, More Is Better ParaView 5.9 Test: Many Spheres - Resolution: 3840 x 2160 5.12 sched Linux 5.11 preempt=none 14 28 42 56 70 SE +/- 0.04, N = 3 SE +/- 0.01, N = 3 SE +/- 0.11, N = 3 62.75 62.78 62.69
ParaView Test: Many Spheres - Resolution: 1920 x 1080 OpenBenchmarking.org MiPolys / Sec, More Is Better ParaView 5.9 Test: Many Spheres - Resolution: 1920 x 1080 5.12 sched Linux 5.11 preempt=none 1400 2800 4200 5600 7000 SE +/- 14.64, N = 3 SE +/- 22.52, N = 3 SE +/- 1.44, N = 3 6645.76 6620.18 6659.59
ParaView Test: Many Spheres - Resolution: 1920 x 1080 OpenBenchmarking.org Frames / Sec, More Is Better ParaView 5.9 Test: Many Spheres - Resolution: 1920 x 1080 5.12 sched Linux 5.11 preempt=none 15 30 45 60 75 SE +/- 0.15, N = 3 SE +/- 0.22, N = 3 SE +/- 0.02, N = 3 66.29 66.03 66.43
NAS Parallel Benchmarks Test / Class: CG.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: CG.C 5.12 sched Linux 5.11 preempt=none 1500 3000 4500 6000 7500 SE +/- 11.23, N = 3 SE +/- 60.15, N = 3 SE +/- 21.22, N = 3 6957.05 7018.38 7069.55 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.0.3
Darmstadt Automotive Parallel Heterogeneous Suite Backend: OpenMP - Kernel: NDT Mapping OpenBenchmarking.org Test Cases Per Minute, More Is Better Darmstadt Automotive Parallel Heterogeneous Suite Backend: OpenMP - Kernel: NDT Mapping 5.12 sched Linux 5.11 preempt=none 200 400 600 800 1000 SE +/- 2.37, N = 3 SE +/- 6.01, N = 3 SE +/- 6.20, N = 3 888.36 882.03 895.79 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp
Etcpak Configuration: ETC2 OpenBenchmarking.org Mpx/s, More Is Better Etcpak 0.7 Configuration: ETC2 5.12 sched Linux 5.11 preempt=none 50 100 150 200 250 SE +/- 1.05, N = 3 SE +/- 3.17, N = 3 SE +/- 3.03, N = 3 235.61 241.11 241.38 1. (CXX) g++ options: -O3 -march=native -std=c++11 -lpthread
TTSIOD 3D Renderer Phong Rendering With Soft-Shadow Mapping OpenBenchmarking.org FPS, More Is Better TTSIOD 3D Renderer 2.3b Phong Rendering With Soft-Shadow Mapping 5.12 sched Linux 5.11 preempt=none 200 400 600 800 1000 SE +/- 2.77, N = 3 SE +/- 9.06, N = 3 SE +/- 1.51, N = 3 1046.99 1043.96 1041.60 1. (CXX) g++ options: -O3 -fomit-frame-pointer -ffast-math -mtune=native -flto -msse -mrecip -mfpmath=sse -msse2 -mssse3 -lSDL -fopenmp -fwhole-program -lstdc++
CLOMP Static OMP Speedup OpenBenchmarking.org Speedup, More Is Better CLOMP 1.2 Static OMP Speedup 5.12 sched Linux 5.11 preempt=none 5 10 15 20 25 SE +/- 0.07, N = 3 SE +/- 0.09, N = 3 SE +/- 0.20, N = 3 21.2 21.2 20.9 1. (CC) gcc options: -fopenmp -O3 -lm
ASKAP Test: Hogbom Clean OpenMP OpenBenchmarking.org Iterations Per Second, More Is Better ASKAP 1.0 Test: Hogbom Clean OpenMP 5.12 sched Linux 5.11 preempt=none 50 100 150 200 250 SE +/- 0.42, N = 3 SE +/- 1.25, N = 3 SE +/- 0.31, N = 3 217.71 216.93 216.14 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
NAS Parallel Benchmarks Test / Class: MG.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: MG.C 5.12 sched Linux 5.11 preempt=none 2K 4K 6K 8K 10K SE +/- 6.34, N = 3 SE +/- 3.64, N = 3 SE +/- 1.48, N = 3 9930.81 9935.40 9936.87 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.0.3
ParaView Test: Wavelet Volume - Resolution: 3840 x 2160 OpenBenchmarking.org MiVoxels / Sec, More Is Better ParaView 5.9 Test: Wavelet Volume - Resolution: 3840 x 2160 5.12 sched Linux 5.11 preempt=none 900 1800 2700 3600 4500 SE +/- 4.11, N = 3 SE +/- 28.98, N = 12 SE +/- 1.94, N = 3 4260.10 4234.71 4281.79
ParaView Test: Wavelet Volume - Resolution: 3840 x 2160 OpenBenchmarking.org Frames / Sec, More Is Better ParaView 5.9 Test: Wavelet Volume - Resolution: 3840 x 2160 5.12 sched Linux 5.11 preempt=none 60 120 180 240 300 SE +/- 0.26, N = 3 SE +/- 1.81, N = 12 SE +/- 0.12, N = 3 266.26 264.67 267.61
dav1d Video Input: Summer Nature 4K OpenBenchmarking.org FPS, More Is Better dav1d 0.8.1 Video Input: Summer Nature 4K 5.12 sched Linux 5.11 preempt=none 50 100 150 200 250 SE +/- 0.13, N = 3 SE +/- 0.34, N = 3 SE +/- 0.15, N = 3 241.18 240.77 241.28 MIN: 181.33 / MAX: 249.24 MIN: 181.75 / MAX: 249.17 MIN: 183.31 / MAX: 249.11 1. (CC) gcc options: -pthread
Darmstadt Automotive Parallel Heterogeneous Suite Backend: OpenMP - Kernel: Euclidean Cluster OpenBenchmarking.org Test Cases Per Minute, More Is Better Darmstadt Automotive Parallel Heterogeneous Suite Backend: OpenMP - Kernel: Euclidean Cluster 5.12 sched Linux 5.11 preempt=none 300 600 900 1200 1500 SE +/- 6.52, N = 3 SE +/- 3.74, N = 3 SE +/- 3.49, N = 3 1496.14 1493.34 1514.32 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp
Intel Open Image Denoise Scene: Memorial OpenBenchmarking.org Images / Sec, More Is Better Intel Open Image Denoise 1.2.0 Scene: Memorial 5.12 sched Linux 5.11 preempt=none 4 8 12 16 20 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 14.52 14.57 14.52
dav1d Video Input: Chimera 1080p OpenBenchmarking.org FPS, More Is Better dav1d 0.8.1 Video Input: Chimera 1080p 5.12 sched Linux 5.11 preempt=none 200 400 600 800 1000 SE +/- 5.53, N = 3 SE +/- 7.91, N = 3 SE +/- 7.30, N = 3 838.25 837.08 841.47 MIN: 588.61 / MAX: 1047.17 MIN: 547.13 / MAX: 1054.47 MIN: 557.95 / MAX: 1052.99 1. (CC) gcc options: -pthread
ParaView Test: Wavelet Volume - Resolution: 1920 x 1080 OpenBenchmarking.org MiVoxels / Sec, More Is Better ParaView 5.9 Test: Wavelet Volume - Resolution: 1920 x 1080 5.12 sched Linux 5.11 preempt=none 2K 4K 6K 8K 10K SE +/- 229.82, N = 12 SE +/- 31.61, N = 3 SE +/- 66.86, N = 3 7416.99 7823.40 8073.10
ParaView Test: Wavelet Volume - Resolution: 1920 x 1080 OpenBenchmarking.org Frames / Sec, More Is Better ParaView 5.9 Test: Wavelet Volume - Resolution: 1920 x 1080 5.12 sched Linux 5.11 preempt=none 110 220 330 440 550 SE +/- 14.36, N = 12 SE +/- 1.98, N = 3 SE +/- 4.18, N = 3 463.56 488.96 504.57
NAS Parallel Benchmarks Test / Class: EP.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: EP.C 5.12 sched Linux 5.11 preempt=none 400 800 1200 1600 2000 SE +/- 5.65, N = 3 SE +/- 4.39, N = 3 SE +/- 14.86, N = 15 1910.88 1917.44 1876.48 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.0.3
ASKAP Test: tConvolve OpenMP - Degridding OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 1.0 Test: tConvolve OpenMP - Degridding 5.12 sched Linux 5.11 preempt=none 700 1400 2100 2800 3500 SE +/- 13.36, N = 3 SE +/- 10.36, N = 7 SE +/- 26.40, N = 3 3260.38 3252.89 3260.71 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
ASKAP Test: tConvolve OpenMP - Gridding OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 1.0 Test: tConvolve OpenMP - Gridding 5.12 sched Linux 5.11 preempt=none 600 1200 1800 2400 3000 SE +/- 18.11, N = 3 SE +/- 23.99, N = 7 SE +/- 9.15, N = 3 2698.79 2722.08 2707.75 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
ParaView Test: Wavelet Contour - Resolution: 3840 x 2160 OpenBenchmarking.org MiPolys / Sec, More Is Better ParaView 5.9 Test: Wavelet Contour - Resolution: 3840 x 2160 5.12 sched Linux 5.11 preempt=none 600 1200 1800 2400 3000 SE +/- 0.80, N = 3 SE +/- 0.59, N = 3 SE +/- 0.54, N = 3 2649.14 2653.88 2660.84
ParaView Test: Wavelet Contour - Resolution: 3840 x 2160 OpenBenchmarking.org Frames / Sec, More Is Better ParaView 5.9 Test: Wavelet Contour - Resolution: 3840 x 2160 5.12 sched Linux 5.11 preempt=none 60 120 180 240 300 SE +/- 0.08, N = 3 SE +/- 0.06, N = 3 SE +/- 0.05, N = 3 254.21 254.66 255.33
ParaView Test: Wavelet Contour - Resolution: 1920 x 1080 OpenBenchmarking.org MiPolys / Sec, More Is Better ParaView 5.9 Test: Wavelet Contour - Resolution: 1920 x 1080 5.12 sched Linux 5.11 preempt=none 800 1600 2400 3200 4000 SE +/- 1.80, N = 3 SE +/- 1.65, N = 3 SE +/- 0.88, N = 3 3884.72 3896.31 3908.99
ParaView Test: Wavelet Contour - Resolution: 1920 x 1080 OpenBenchmarking.org Frames / Sec, More Is Better ParaView 5.9 Test: Wavelet Contour - Resolution: 1920 x 1080 5.12 sched Linux 5.11 preempt=none 80 160 240 320 400 SE +/- 0.17, N = 3 SE +/- 0.16, N = 3 SE +/- 0.09, N = 3 372.77 373.88 375.10
N-Queens Elapsed Time OpenBenchmarking.org Seconds, Fewer Is Better N-Queens 1.0 Elapsed Time 5.12 sched Linux 5.11 preempt=none 1.2681 2.5362 3.8043 5.0724 6.3405 SE +/- 0.003, N = 3 SE +/- 0.003, N = 3 SE +/- 0.003, N = 3 5.636 5.622 5.635 1. (CC) gcc options: -static -fopenmp -O3 -march=native
dav1d Video Input: Summer Nature 1080p OpenBenchmarking.org FPS, More Is Better dav1d 0.8.1 Video Input: Summer Nature 1080p 5.12 sched Linux 5.11 preempt=none 200 400 600 800 1000 SE +/- 0.24, N = 3 SE +/- 4.97, N = 3 SE +/- 0.23, N = 3 904.93 911.62 913.38 MIN: 648.7 / MAX: 987.05 MIN: 618.67 / MAX: 1003.6 MIN: 683.84 / MAX: 994.59 1. (CC) gcc options: -pthread
Etcpak Configuration: DXT1 OpenBenchmarking.org Mpx/s, More Is Better Etcpak 0.7 Configuration: DXT1 5.12 sched Linux 5.11 preempt=none 300 600 900 1200 1500 SE +/- 4.22, N = 3 SE +/- 1.30, N = 3 SE +/- 2.98, N = 3 1521.61 1533.22 1545.11 1. (CXX) g++ options: -O3 -march=native -std=c++11 -lpthread
Phoronix Test Suite v10.8.4