AMD Ryzen Threadripper 3990X 64-Core benchmarks for a future article by Michael Larabel.
Compare your own system(s) to this result file with the
Phoronix Test Suite by running the command:
phoronix-test-suite benchmark 2203051-PTS-THREADRI18 Threadripper 3990X sched-core - Phoronix Test Suite Threadripper 3990X sched-core AMD Ryzen Threadripper 3990X 64-Core benchmarks for a future article by Michael Larabel.
HTML result view exported from: https://openbenchmarking.org/result/2203051-PTS-THREADRI18&grs&export=txt&rdt&rro .
Threadripper 3990X sched-core Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server OpenGL Vulkan Compiler File-System Screen Resolution sched-core Git Linux 5.17 Git 5.17 Git sched-core Git NP4 AMD Ryzen Threadripper 3990X 64-Core @ 2.90GHz (64 Cores / 128 Threads) Gigabyte TRX40 AORUS PRO WIFI (F4p BIOS) AMD Starship/Matisse 128GB Samsung SSD 970 EVO Plus 500GB AMD Radeon RX 5700 8GB (1750/875MHz) AMD Navi 10 HDMI Audio DELL P2415Q Intel I211 + Intel Wi-Fi 6 AX200 Pop 21.10 5.17.0-rc1-sched-core-phx (x86_64) GNOME Shell 40.5 X Server 4.6 Mesa 21.2.2 (LLVM 12.0.1) 1.2.182 GCC 11.2.0 ext4 3840x2160 5.17.0-051700rc6daily20220301-generic (x86_64) 5.17.0-rc1-sched-core-phx (x86_64) OpenBenchmarking.org Kernel Details - Transparent Huge Pages: madvise Compiler Details - --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --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-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-ZPT0kp/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-ZPT0kp/gcc-11-11.2.0/debian/tmp-gcn/usr --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-build-config=bootstrap-lto-lean --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: 0x8301039 Python Details - Python 3.9.7 Security Details - itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected
Threadripper 3990X sched-core onnx: super-resolution-10 - CPU onnx: shufflenet-v2-10 - CPU pgbench: 100 - 50 - Read Write pgbench: 100 - 50 - Read Write - Average Latency rocksdb: Rand Read askap: tConvolve OpenMP - Gridding aom-av1: Speed 9 Realtime - Bosphorus 4K graphics-magick: Rotate luxcorerender: Rainbow Colors and Prism - CPU pgbench: 100 - 250 - Read Only askap: tConvolve MPI - Gridding pennant: leblancbig askap: tConvolve MPI - Degridding pgbench: 100 - 250 - Read Only - Average Latency askap: tConvolve OpenMP - Degridding daphne: OpenMP - NDT Mapping pennant: sedovbig aom-av1: Speed 10 Realtime - Bosphorus 4K mt-dgemm: Sustained Floating-Point Rate luxcorerender: Danish Mood - CPU aom-av1: Speed 8 Realtime - Bosphorus 4K graph500: 26 tensorflow-lite: Mobilenet Float graph500: 26 graph500: 26 graphics-magick: Swirl rocksdb: Read Rand Write Rand tensorflow-lite: Inception ResNet V2 rocksdb: Rand Fill compress-zstd: 19 - Compression Speed graphics-magick: Noise-Gaussian libgav1: Summer Nature 1080p libgav1: Summer Nature 4K build-godot: Time To Compile mysqlslap: 128 pgbench: 100 - 50 - Read Only - Average Latency graph500: 26 graphics-magick: HWB Color Space rocksdb: Update Rand aom-av1: Speed 6 Realtime - Bosphorus 4K liquid-dsp: 16 - 256 - 57 pgbench: 100 - 100 - Read Only rocksdb: Read While Writing tensorflow-lite: Inception V4 mrbayes: Primate Phylogeny Analysis build-gdb: Time To Compile luxcorerender: Orange Juice - CPU liquid-dsp: 32 - 256 - 57 aom-av1: Speed 6 Two-Pass - Bosphorus 4K primesieve: 1e12 Prime Number Generation build-gem5: Time To Compile compress-7zip: Decompression Rating pgbench: 100 - 50 - Read Only pgbench: 100 - 100 - Read Only - Average Latency compress-zstd: 8 - Compression Speed svt-av1: Preset 8 - Bosphorus 4K qe: AUSURF112 blender: BMW27 - CPU-Only graphics-magick: Enhanced svt-av1: Preset 12 - Bosphorus 4K compress-zstd: 19, Long Mode - Decompression Speed onnx: yolov4 - CPU liquid-dsp: 64 - 256 - 57 build-linux-kernel: defconfig luxcorerender: DLSC - CPU daphne: OpenMP - Euclidean Cluster build-linux-kernel: allmodconfig graphics-magick: Sharpen svt-av1: Preset 10 - Bosphorus 4K clomp: Static OMP Speedup compress-zstd: 19, Long Mode - Compression Speed tensorflow-lite: SqueezeNet askap: Hogbom Clean OpenMP libgav1: Chimera 1080p 10-bit liquid-dsp: 128 - 256 - 57 tensorflow-lite: Mobilenet Quant dav1d: Summer Nature 4K compress-zstd: 19 - Decompression Speed gpaw: Carbon Nanotube compress-zstd: 8 - Decompression Speed compress-7zip: Compression Rating blender: Barbershop - CPU-Only dav1d: Summer Nature 1080p dav1d: Chimera 1080p 10-bit askap: tConvolve MT - Degridding askap: tConvolve MT - Gridding tensorflow-lite: NASNet Mobile onnx: fcn-resnet101-11 - CPU pgbench: 100 - 250 - Read Write - Average Latency pgbench: 100 - 250 - Read Write pgbench: 100 - 100 - Read Write - Average Latency pgbench: 100 - 100 - Read Write mysqlslap: 64 mysqlslap: 32 mysqlslap: 16 mysqlslap: 8 daphne: OpenMP - Points2Image graphics-magick: Resizing sched-core Git Linux 5.17 Git 5.17 Git sched-core Git NP4 7597 11067 5861 8.542 245874918 5831.05 44.95 619 27.82 1638373 16748.9 5.471451 18362.2 0.153 4034.18 982.56 12.45384 47.92 16.692992 6.32 33.52 164643000 28423.1 216593000 543456000 2100 2885383 568372 366831 80.4 705 132.14 43.49 49.434 230 0.047 549848000 1346 350863 9.03 962743333 1347286 9336682 623517 142.889 42.186 12.70 1777633333 10.31 3.983 194.188 360623 1068251 0.074 3638.1 89.081 391.93 28.88 1008 163.964 3392.6 292 2822833333 25.376 8.26 1139.51 252.782 671 140.692 55.4 44.3 48519.5 361.450 40.92 3040233333 29578.7 386.36 3369.4 106.720 3799.6 196330 304.22 965.12 718.74 3183.93 2146.42 74045.3 157 27.539 9116 12.886 7779 369 757 878 955 17081.147186083 1035 7570 10962 5673 8.824 250588886 6192 46.74 655 29.41 1693607 16031.5 5.300170 17596.0 0.148 3877.70 1021.96 12.08188 49.28 17.129724 6.15 34.49 160144000 28500.3 210867000 529167000 2156 2898792 564887 364172 82.1 717 134.19 44.13 49.654 232 0.048 538402000 1365 349595 9.19 972203333 1324265 9404219 627090 141.704 42.494 12.59 1786266667 10.26 3.956 191.386 363282 1053840 0.075 3652.4 89.737 390.93 28.56 1014 165.717 3365.6 294 2836166667 25.457 8.24 1141.46 253.699 674 140.044 55.3 44.2 48235.5 361.447 41.08 3036233333 29607.6 388.26 3355.8 106.930 3809.7 196124 303.91 964.33 717.75 3182.74 2145.87 74051.7 171 32.897 7612 13.653 7363 290 365 440 493 16384.655792573 1074 7600 11082 5593 8.946 262524386 6006.45 47.68 652 27.95 1703935 16190.4 5.531816 17741.4 0.147 3896.61 1018.97 12.00753 49.48 16.852743 6.13 34.50 164255000 28358.2 214688000 535841000 2144 2825065 579411 359306 81.6 700 134.42 44.18 50.538 229 0.047 542519000 1372 344526 9.03 959500000 1334038 9496567 624248 142.559 42.872 12.56 1758333333 10.27 4.014 193.184 358350 1059091 0.075 3621.9 89.952 394.97 28.86 1019 164.354 3366.9 294 2808200000 25.621 8.27 1133.26 254.726 673 141.082 55.7 44.5 48552.8 360.578 41.16 3022633333 29580.5 386.82 3361.1 107.127 3803.5 196564 304.13 966.03 717.84 3185.22 2145.29 74069.7 156 32.077 7814 13.496 7441 289 371 403 484 16427.802063793 1112 4991 12142 5433 9.210 246499126 6006.45 46.05 643 28.23 1626173 16230.9 5.343927 17739.7 0.153 3896.61 1002.86 12.08782 48.27 17.212185 6.22 33.57 163702000 29151.1 215231000 537844000 2150 2869539 573581 368411 82.4 712 131.42 43.21 49.825 227 0.047 544389000 1371 350313 9.10 955360000 1340583 9362067 616671 144.098 42.465 12.50 1778033333 10.15 4.010 191.790 360720 1062833 0.075 3606.3 88.924 395.43 28.64 1014 165.581 3401.2 291 2810933333 25.514 8.20 1142.18 253.847 669 140.747 55.6 44.3 48336.7 359.282 40.99 3024233333 29737.8 387.57 3355.5 106.686 3795.0 196815 304.50 965.73 717.96 3187.01 2143.90 74047.5 159 31.896 7874 14.226 7034 284 367 397 509 16699.641600630 1040 OpenBenchmarking.org
ONNX Runtime Model: super-resolution-10 - Device: CPU OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.10 Model: super-resolution-10 - Device: CPU sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 1600 3200 4800 6400 8000 SE +/- 60.33, N = 3 SE +/- 40.84, N = 3 SE +/- 41.64, N = 3 SE +/- 30.29, N = 3 4991 7600 7570 7597 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: shufflenet-v2-10 - Device: CPU OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.10 Model: shufflenet-v2-10 - Device: CPU sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 3K 6K 9K 12K 15K SE +/- 157.27, N = 3 SE +/- 29.46, N = 3 SE +/- 23.74, N = 3 SE +/- 21.42, N = 3 12142 11082 10962 11067 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt
PostgreSQL pgbench Scaling Factor: 100 - Clients: 50 - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 14.0 Scaling Factor: 100 - Clients: 50 - Mode: Read Write sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 1300 2600 3900 5200 6500 SE +/- 40.72, N = 12 SE +/- 47.73, N = 12 SE +/- 61.29, N = 12 SE +/- 62.50, N = 12 5433 5593 5673 5861 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
PostgreSQL pgbench Scaling Factor: 100 - Clients: 50 - Mode: Read Write - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 14.0 Scaling Factor: 100 - Clients: 50 - Mode: Read Write - Average Latency sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 3 6 9 12 15 SE +/- 0.069, N = 12 SE +/- 0.074, N = 12 SE +/- 0.094, N = 12 SE +/- 0.089, N = 12 9.210 8.946 8.824 8.542 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
Facebook RocksDB Test: Random Read OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Random Read sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 60M 120M 180M 240M 300M SE +/- 3530680.86, N = 15 SE +/- 1198937.39, N = 3 SE +/- 2676219.89, N = 5 SE +/- 3795798.11, N = 15 246499126 262524386 250588886 245874918 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
ASKAP Test: tConvolve OpenMP - Gridding OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 1.0 Test: tConvolve OpenMP - Gridding sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 1300 2600 3900 5200 6500 SE +/- 44.82, N = 3 SE +/- 44.82, N = 3 SE +/- 0.00, N = 3 SE +/- 42.88, N = 3 6006.45 6006.45 6192.00 5831.05 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
AOM AV1 Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.3 Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4K sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 11 22 33 44 55 SE +/- 0.33, N = 15 SE +/- 0.23, N = 3 SE +/- 0.40, N = 3 SE +/- 0.33, N = 3 46.05 47.68 46.74 44.95 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
GraphicsMagick Operation: Rotate OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Rotate sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 140 280 420 560 700 SE +/- 0.58, N = 3 SE +/- 3.79, N = 3 SE +/- 1.73, N = 3 SE +/- 1.86, N = 3 643 652 655 619 1. (CC) gcc options: -fopenmp -O2 -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
LuxCoreRender Scene: Rainbow Colors and Prism - Acceleration: CPU OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.6 Scene: Rainbow Colors and Prism - Acceleration: CPU sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 7 14 21 28 35 SE +/- 0.29, N = 3 SE +/- 0.29, N = 5 SE +/- 0.29, N = 3 SE +/- 0.34, N = 3 28.23 27.95 29.41 27.82 MIN: 24.36 / MAX: 28.77 MIN: 23.78 / MAX: 28.64 MIN: 28.59 / MAX: 30.36 MIN: 24.19 / MAX: 28.68
PostgreSQL pgbench Scaling Factor: 100 - Clients: 250 - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 14.0 Scaling Factor: 100 - Clients: 250 - Mode: Read Only sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 400K 800K 1200K 1600K 2000K SE +/- 7034.52, N = 3 SE +/- 5641.56, N = 3 SE +/- 9806.45, N = 3 SE +/- 13238.24, N = 3 1626173 1703935 1693607 1638373 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
ASKAP Test: tConvolve MPI - Gridding OpenBenchmarking.org Mpix/sec, More Is Better ASKAP 1.0 Test: tConvolve MPI - Gridding sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 4K 8K 12K 16K 20K SE +/- 41.73, N = 3 SE +/- 110.51, N = 3 SE +/- 241.07, N = 3 SE +/- 44.43, N = 3 16230.9 16190.4 16031.5 16748.9 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
Pennant Test: leblancbig OpenBenchmarking.org Hydro Cycle Time - Seconds, Fewer Is Better Pennant 1.0.1 Test: leblancbig sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 1.2447 2.4894 3.7341 4.9788 6.2235 SE +/- 0.062281, N = 15 SE +/- 0.006985, N = 3 SE +/- 0.050854, N = 3 SE +/- 0.053394, N = 15 5.343927 5.531816 5.300170 5.471451 1. (CXX) g++ options: -fopenmp -lmpi_cxx -lmpi
ASKAP Test: tConvolve MPI - Degridding OpenBenchmarking.org Mpix/sec, More Is Better ASKAP 1.0 Test: tConvolve MPI - Degridding sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 4K 8K 12K 16K 20K SE +/- 49.83, N = 3 SE +/- 131.72, N = 3 SE +/- 213.40, N = 3 SE +/- 141.05, N = 3 17739.7 17741.4 17596.0 18362.2 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
PostgreSQL pgbench Scaling Factor: 100 - Clients: 250 - Mode: Read Only - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 14.0 Scaling Factor: 100 - Clients: 250 - Mode: Read Only - Average Latency sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 0.0344 0.0688 0.1032 0.1376 0.172 SE +/- 0.001, N = 3 SE +/- 0.001, N = 3 SE +/- 0.001, N = 3 SE +/- 0.001, N = 3 0.153 0.147 0.148 0.153 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
ASKAP Test: tConvolve OpenMP - Degridding OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 1.0 Test: tConvolve OpenMP - Degridding sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 900 1800 2700 3600 4500 SE +/- 18.92, N = 3 SE +/- 18.92, N = 3 SE +/- 18.92, N = 3 SE +/- 0.00, N = 3 3896.61 3896.61 3877.70 4034.18 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
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 sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 200 400 600 800 1000 SE +/- 6.84, N = 3 SE +/- 1.49, N = 3 SE +/- 2.55, N = 3 SE +/- 7.91, N = 3 1002.86 1018.97 1021.96 982.56 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp
Pennant Test: sedovbig OpenBenchmarking.org Hydro Cycle Time - Seconds, Fewer Is Better Pennant 1.0.1 Test: sedovbig sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 3 6 9 12 15 SE +/- 0.11, N = 7 SE +/- 0.10, N = 3 SE +/- 0.07, N = 3 SE +/- 0.07, N = 3 12.09 12.01 12.08 12.45 1. (CXX) g++ options: -fopenmp -lmpi_cxx -lmpi
AOM AV1 Encoder Mode: Speed 10 Realtime - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.3 Encoder Mode: Speed 10 Realtime - Input: Bosphorus 4K sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 11 22 33 44 55 SE +/- 0.44, N = 3 SE +/- 0.52, N = 3 SE +/- 0.03, N = 3 SE +/- 0.47, N = 3 48.27 49.48 49.28 47.92 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
ACES DGEMM Sustained Floating-Point Rate OpenBenchmarking.org GFLOP/s, More Is Better ACES DGEMM 1.0 Sustained Floating-Point Rate sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 4 8 12 16 20 SE +/- 0.07, N = 3 SE +/- 0.12, N = 15 SE +/- 0.04, N = 3 SE +/- 0.23, N = 15 17.21 16.85 17.13 16.69 1. (CC) gcc options: -O3 -march=native -fopenmp
LuxCoreRender Scene: Danish Mood - Acceleration: CPU OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.6 Scene: Danish Mood - Acceleration: CPU sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 2 4 6 8 10 SE +/- 0.06, N = 3 SE +/- 0.06, N = 3 SE +/- 0.04, N = 3 SE +/- 0.07, N = 5 6.22 6.13 6.15 6.32 MIN: 2.6 / MAX: 7.31 MIN: 2.54 / MAX: 7.22 MIN: 2.51 / MAX: 7.23 MIN: 2.59 / MAX: 7.54
AOM AV1 Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.3 Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4K sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 8 16 24 32 40 SE +/- 0.16, N = 3 SE +/- 0.25, N = 3 SE +/- 0.26, N = 3 SE +/- 0.30, N = 3 33.57 34.50 34.49 33.52 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
Graph500 Scale: 26 OpenBenchmarking.org sssp median_TEPS, More Is Better Graph500 3.0 Scale: 26 sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 40M 80M 120M 160M 200M 163702000 164255000 160144000 164643000 1. (CC) gcc options: -fcommon -O3 -lpthread -lm -lmpi
TensorFlow Lite Model: Mobilenet Float OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Mobilenet Float sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 6K 12K 18K 24K 30K SE +/- 266.82, N = 15 SE +/- 198.28, N = 3 SE +/- 207.54, N = 11 SE +/- 289.21, N = 3 29151.1 28358.2 28500.3 28423.1
Graph500 Scale: 26 OpenBenchmarking.org sssp max_TEPS, More Is Better Graph500 3.0 Scale: 26 sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 50M 100M 150M 200M 250M 215231000 214688000 210867000 216593000 1. (CC) gcc options: -fcommon -O3 -lpthread -lm -lmpi
Graph500 Scale: 26 OpenBenchmarking.org bfs median_TEPS, More Is Better Graph500 3.0 Scale: 26 sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 120M 240M 360M 480M 600M 537844000 535841000 529167000 543456000 1. (CC) gcc options: -fcommon -O3 -lpthread -lm -lmpi
GraphicsMagick Operation: Swirl OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Swirl sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 500 1000 1500 2000 2500 SE +/- 4.91, N = 3 SE +/- 4.91, N = 3 SE +/- 7.36, N = 3 SE +/- 10.97, N = 3 2150 2144 2156 2100 1. (CC) gcc options: -fopenmp -O2 -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
Facebook RocksDB Test: Read Random Write Random OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Read Random Write Random sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 600K 1200K 1800K 2400K 3000K SE +/- 6097.61, N = 3 SE +/- 604.62, N = 3 SE +/- 8841.26, N = 3 SE +/- 18021.62, N = 3 2869539 2825065 2898792 2885383 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
TensorFlow Lite Model: Inception ResNet V2 OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Inception ResNet V2 sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 120K 240K 360K 480K 600K SE +/- 3097.81, N = 3 SE +/- 4184.62, N = 15 SE +/- 5074.92, N = 3 SE +/- 7021.35, N = 3 573581 579411 564887 568372
Facebook RocksDB Test: Random Fill OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Random Fill sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 80K 160K 240K 320K 400K SE +/- 494.07, N = 3 SE +/- 2870.08, N = 3 SE +/- 2998.42, N = 3 SE +/- 1716.59, N = 3 368411 359306 364172 366831 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
Zstd Compression Compression Level: 19 - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 19 - Compression Speed sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 20 40 60 80 100 SE +/- 0.77, N = 7 SE +/- 1.14, N = 3 SE +/- 0.54, N = 15 SE +/- 0.73, N = 3 82.4 81.6 82.1 80.4 1. (CC) gcc options: -O3 -pthread -lz -llzma
GraphicsMagick Operation: Noise-Gaussian OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Noise-Gaussian sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 150 300 450 600 750 SE +/- 0.67, N = 3 SE +/- 1.53, N = 3 SE +/- 1.45, N = 3 SE +/- 0.33, N = 3 712 700 717 705 1. (CC) gcc options: -fopenmp -O2 -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
libgav1 Video Input: Summer Nature 1080p OpenBenchmarking.org FPS, More Is Better libgav1 0.17 Video Input: Summer Nature 1080p sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 30 60 90 120 150 SE +/- 0.09, N = 3 SE +/- 0.13, N = 3 SE +/- 0.22, N = 3 SE +/- 0.33, N = 3 131.42 134.42 134.19 132.14 1. (CXX) g++ options: -O3 -lrt
libgav1 Video Input: Summer Nature 4K OpenBenchmarking.org FPS, More Is Better libgav1 0.17 Video Input: Summer Nature 4K sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 10 20 30 40 50 SE +/- 0.03, N = 3 SE +/- 0.05, N = 3 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 43.21 44.18 44.13 43.49 1. (CXX) g++ options: -O3 -lrt
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 sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 11 22 33 44 55 SE +/- 0.30, N = 3 SE +/- 0.11, N = 3 SE +/- 0.35, N = 3 SE +/- 0.06, N = 3 49.83 50.54 49.65 49.43
MariaDB Clients: 128 OpenBenchmarking.org Queries Per Second, More Is Better MariaDB 10.8.2 Clients: 128 sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 50 100 150 200 250 SE +/- 1.53, N = 3 SE +/- 1.94, N = 3 SE +/- 2.49, N = 3 SE +/- 1.81, N = 3 227 229 232 230 1. (CXX) g++ options: -fPIC -pie -fstack-protector -O3 -shared -lrt -lpthread -lz -ldl -lm -lstdc++
PostgreSQL pgbench Scaling Factor: 100 - Clients: 50 - Mode: Read Only - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 14.0 Scaling Factor: 100 - Clients: 50 - Mode: Read Only - Average Latency sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 0.0108 0.0216 0.0324 0.0432 0.054 SE +/- 0.000, N = 3 SE +/- 0.001, N = 3 SE +/- 0.000, N = 3 SE +/- 0.001, N = 3 0.047 0.047 0.048 0.047 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
Graph500 Scale: 26 OpenBenchmarking.org bfs max_TEPS, More Is Better Graph500 3.0 Scale: 26 sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 120M 240M 360M 480M 600M 544389000 542519000 538402000 549848000 1. (CC) gcc options: -fcommon -O3 -lpthread -lm -lmpi
GraphicsMagick Operation: HWB Color Space OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: HWB Color Space sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 300 600 900 1200 1500 SE +/- 1.45, N = 3 SE +/- 5.36, N = 3 SE +/- 3.06, N = 3 SE +/- 6.17, N = 3 1371 1372 1365 1346 1. (CC) gcc options: -fopenmp -O2 -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
Facebook RocksDB Test: Update Random OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Update Random sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 80K 160K 240K 320K 400K SE +/- 373.85, N = 3 SE +/- 492.86, N = 3 SE +/- 173.12, N = 3 SE +/- 129.48, N = 3 350313 344526 349595 350863 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
AOM AV1 Encoder Mode: Speed 6 Realtime - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.3 Encoder Mode: Speed 6 Realtime - Input: Bosphorus 4K sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 3 6 9 12 15 SE +/- 0.03, N = 3 SE +/- 0.13, N = 3 SE +/- 0.02, N = 3 SE +/- 0.07, N = 3 9.10 9.03 9.19 9.03 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
Liquid-DSP Threads: 16 - Buffer Length: 256 - Filter Length: 57 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 2021.01.31 Threads: 16 - Buffer Length: 256 - Filter Length: 57 sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 200M 400M 600M 800M 1000M SE +/- 1496429.08, N = 3 SE +/- 828090.17, N = 3 SE +/- 2670919.53, N = 3 SE +/- 4496355.31, N = 3 955360000 959500000 972203333 962743333 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
PostgreSQL pgbench Scaling Factor: 100 - Clients: 100 - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 14.0 Scaling Factor: 100 - Clients: 100 - Mode: Read Only sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 300K 600K 900K 1200K 1500K SE +/- 4583.17, N = 3 SE +/- 2403.45, N = 3 SE +/- 3253.09, N = 3 SE +/- 3473.78, N = 3 1340583 1334038 1324265 1347286 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
Facebook RocksDB Test: Read While Writing OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Read While Writing sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 2M 4M 6M 8M 10M SE +/- 16321.05, N = 3 SE +/- 16305.13, N = 3 SE +/- 11254.13, N = 3 SE +/- 132127.81, N = 3 9362067 9496567 9404219 9336682 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
TensorFlow Lite Model: Inception V4 OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Inception V4 sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 130K 260K 390K 520K 650K SE +/- 5635.52, N = 7 SE +/- 4260.89, N = 3 SE +/- 6723.08, N = 3 SE +/- 8370.13, N = 3 616671 624248 627090 623517
Timed MrBayes Analysis Primate Phylogeny Analysis OpenBenchmarking.org Seconds, Fewer Is Better Timed MrBayes Analysis 3.2.7 Primate Phylogeny Analysis sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 30 60 90 120 150 SE +/- 1.55, N = 3 SE +/- 1.43, N = 3 SE +/- 1.77, N = 3 SE +/- 1.07, N = 3 144.10 142.56 141.70 142.89 1. (CC) gcc options: -mmmx -msse -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -msse4a -msha -maes -mavx -mfma -mavx2 -mrdrnd -mbmi -mbmi2 -madx -mabm -O3 -std=c99 -pedantic -lm
Timed GDB GNU Debugger Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed GDB GNU Debugger Compilation 10.2 Time To Compile sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 10 20 30 40 50 SE +/- 0.12, N = 3 SE +/- 0.15, N = 3 SE +/- 0.09, N = 3 SE +/- 0.16, N = 3 42.47 42.87 42.49 42.19
LuxCoreRender Scene: Orange Juice - Acceleration: CPU OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.6 Scene: Orange Juice - Acceleration: CPU sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 3 6 9 12 15 SE +/- 0.12, N = 3 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 SE +/- 0.12, N = 6 12.50 12.56 12.59 12.70 MIN: 10.56 / MAX: 14.36 MIN: 10.71 / MAX: 14.48 MIN: 10.73 / MAX: 14.54 MIN: 10.69 / MAX: 15.2
Liquid-DSP Threads: 32 - Buffer Length: 256 - Filter Length: 57 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 2021.01.31 Threads: 32 - Buffer Length: 256 - Filter Length: 57 sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 400M 800M 1200M 1600M 2000M SE +/- 1922093.77, N = 3 SE +/- 9820613.24, N = 3 SE +/- 6854763.15, N = 3 SE +/- 5607534.61, N = 3 1778033333 1758333333 1786266667 1777633333 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
AOM AV1 Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.3 Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 4K sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 3 6 9 12 15 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 10.15 10.27 10.26 10.31 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
Primesieve 1e12 Prime Number Generation OpenBenchmarking.org Seconds, Fewer Is Better Primesieve 7.7 1e12 Prime Number Generation sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 0.9032 1.8064 2.7096 3.6128 4.516 SE +/- 0.010, N = 3 SE +/- 0.017, N = 3 SE +/- 0.007, N = 3 SE +/- 0.012, N = 3 4.010 4.014 3.956 3.983 1. (CXX) g++ options: -O3
Timed Gem5 Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Gem5 Compilation 21.2 Time To Compile sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 40 80 120 160 200 SE +/- 1.76, N = 3 SE +/- 2.42, N = 3 SE +/- 0.67, N = 3 SE +/- 2.27, N = 3 191.79 193.18 191.39 194.19
7-Zip Compression Test: Decompression Rating OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 21.06 Test: Decompression Rating sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 80K 160K 240K 320K 400K SE +/- 2560.97, N = 3 SE +/- 1951.45, N = 3 SE +/- 2278.14, N = 3 SE +/- 2391.99, N = 3 360720 358350 363282 360623 1. (CXX) g++ options: -lpthread -ldl -O2 -fPIC
PostgreSQL pgbench Scaling Factor: 100 - Clients: 50 - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 14.0 Scaling Factor: 100 - Clients: 50 - Mode: Read Only sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 200K 400K 600K 800K 1000K SE +/- 2778.20, N = 3 SE +/- 11328.60, N = 3 SE +/- 9389.82, N = 3 SE +/- 10375.50, N = 3 1062833 1059091 1053840 1068251 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
PostgreSQL pgbench Scaling Factor: 100 - Clients: 100 - Mode: Read Only - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 14.0 Scaling Factor: 100 - Clients: 100 - Mode: Read Only - Average Latency sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 0.0169 0.0338 0.0507 0.0676 0.0845 SE +/- 0.000, N = 3 SE +/- 0.000, N = 3 SE +/- 0.000, N = 3 SE +/- 0.000, N = 3 0.075 0.075 0.075 0.074 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
Zstd Compression Compression Level: 8 - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 8 - Compression Speed sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 800 1600 2400 3200 4000 SE +/- 29.97, N = 3 SE +/- 29.73, N = 3 SE +/- 37.56, N = 4 SE +/- 19.62, N = 3 3606.3 3621.9 3652.4 3638.1 1. (CC) gcc options: -O3 -pthread -lz -llzma
SVT-AV1 Encoder Mode: Preset 8 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 0.9 Encoder Mode: Preset 8 - Input: Bosphorus 4K sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 20 40 60 80 100 SE +/- 1.25, N = 3 SE +/- 0.32, N = 3 SE +/- 0.98, N = 3 SE +/- 0.56, N = 3 88.92 89.95 89.74 89.08 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
Quantum ESPRESSO Input: AUSURF112 OpenBenchmarking.org Seconds, Fewer Is Better Quantum ESPRESSO 7.0 Input: AUSURF112 sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 90 180 270 360 450 SE +/- 0.80, N = 3 SE +/- 1.35, N = 3 SE +/- 1.11, N = 3 SE +/- 2.53, N = 3 395.43 394.97 390.93 391.93 1. (F9X) gfortran options: -pthread -fopenmp -ldevXlib -lopenblas -lFoX_dom -lFoX_sax -lFoX_wxml -lFoX_common -lFoX_utils -lFoX_fsys -lfftw3_omp -lfftw3 -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz
Blender Blend File: BMW27 - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.0 Blend File: BMW27 - Compute: CPU-Only sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 7 14 21 28 35 SE +/- 0.13, N = 3 SE +/- 0.05, N = 3 SE +/- 0.04, N = 3 SE +/- 0.13, N = 3 28.64 28.86 28.56 28.88
GraphicsMagick Operation: Enhanced OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Enhanced sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 200 400 600 800 1000 SE +/- 5.04, N = 3 SE +/- 2.73, N = 3 SE +/- 4.93, N = 3 SE +/- 4.70, N = 3 1014 1019 1014 1008 1. (CC) gcc options: -fopenmp -O2 -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
SVT-AV1 Encoder Mode: Preset 12 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 0.9 Encoder Mode: Preset 12 - Input: Bosphorus 4K sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 40 80 120 160 200 SE +/- 0.74, N = 3 SE +/- 0.75, N = 3 SE +/- 0.46, N = 3 SE +/- 0.18, N = 3 165.58 164.35 165.72 163.96 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
Zstd Compression Compression Level: 19, Long Mode - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 19, Long Mode - Decompression Speed sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 700 1400 2100 2800 3500 SE +/- 7.09, N = 3 SE +/- 7.80, N = 3 SE +/- 5.28, N = 3 SE +/- 9.15, N = 3 3401.2 3366.9 3365.6 3392.6 1. (CC) gcc options: -O3 -pthread -lz -llzma
ONNX Runtime Model: yolov4 - Device: CPU OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.10 Model: yolov4 - Device: CPU sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 60 120 180 240 300 SE +/- 1.76, N = 3 SE +/- 3.53, N = 3 SE +/- 4.94, N = 12 SE +/- 1.88, N = 3 291 294 294 292 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt
Liquid-DSP Threads: 64 - Buffer Length: 256 - Filter Length: 57 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 2021.01.31 Threads: 64 - Buffer Length: 256 - Filter Length: 57 sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 600M 1200M 1800M 2400M 3000M SE +/- 7592174.33, N = 3 SE +/- 17159933.95, N = 3 SE +/- 5117399.51, N = 3 SE +/- 1927289.40, N = 3 2810933333 2808200000 2836166667 2822833333 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
Timed Linux Kernel Compilation Build: defconfig OpenBenchmarking.org Seconds, Fewer Is Better Timed Linux Kernel Compilation 5.16 Build: defconfig sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 6 12 18 24 30 SE +/- 0.07, N = 3 SE +/- 0.01, N = 3 SE +/- 0.06, N = 3 SE +/- 0.03, N = 3 25.51 25.62 25.46 25.38
LuxCoreRender Scene: DLSC - Acceleration: CPU OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.6 Scene: DLSC - Acceleration: CPU sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 2 4 6 8 10 SE +/- 0.06, N = 3 SE +/- 0.09, N = 4 SE +/- 0.08, N = 3 SE +/- 0.02, N = 3 8.20 8.27 8.24 8.26 MIN: 7.96 / MAX: 8.96 MIN: 7.92 / MAX: 9.16 MIN: 7.96 / MAX: 9.08 MIN: 8.09 / MAX: 8.98
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 sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 200 400 600 800 1000 SE +/- 4.29, N = 3 SE +/- 0.99, N = 3 SE +/- 1.61, N = 3 SE +/- 1.51, N = 3 1142.18 1133.26 1141.46 1139.51 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp
Timed Linux Kernel Compilation Build: allmodconfig OpenBenchmarking.org Seconds, Fewer Is Better Timed Linux Kernel Compilation 5.16 Build: allmodconfig sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 60 120 180 240 300 SE +/- 0.66, N = 3 SE +/- 0.85, N = 3 SE +/- 0.67, N = 3 SE +/- 0.62, N = 3 253.85 254.73 253.70 252.78
GraphicsMagick Operation: Sharpen OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Sharpen sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 150 300 450 600 750 SE +/- 4.33, N = 3 SE +/- 3.61, N = 3 SE +/- 4.16, N = 3 SE +/- 4.04, N = 3 669 673 674 671 1. (CC) gcc options: -fopenmp -O2 -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
SVT-AV1 Encoder Mode: Preset 10 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 0.9 Encoder Mode: Preset 10 - Input: Bosphorus 4K sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 30 60 90 120 150 SE +/- 0.24, N = 3 SE +/- 0.24, N = 3 SE +/- 0.70, N = 3 SE +/- 1.03, N = 3 140.75 141.08 140.04 140.69 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
CLOMP Static OMP Speedup OpenBenchmarking.org Speedup, More Is Better CLOMP 1.2 Static OMP Speedup sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 13 26 39 52 65 SE +/- 0.15, N = 3 SE +/- 0.47, N = 3 SE +/- 0.70, N = 3 SE +/- 0.52, N = 3 55.6 55.7 55.3 55.4 1. (CC) gcc options: -fopenmp -O3 -lm
Zstd Compression Compression Level: 19, Long Mode - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 19, Long Mode - Compression Speed sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 10 20 30 40 50 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.07, N = 3 44.3 44.5 44.2 44.3 1. (CC) gcc options: -O3 -pthread -lz -llzma
TensorFlow Lite Model: SqueezeNet OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: SqueezeNet sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 10K 20K 30K 40K 50K SE +/- 264.42, N = 3 SE +/- 156.02, N = 3 SE +/- 371.63, N = 3 SE +/- 248.76, N = 3 48336.7 48552.8 48235.5 48519.5
ASKAP Test: Hogbom Clean OpenMP OpenBenchmarking.org Iterations Per Second, More Is Better ASKAP 1.0 Test: Hogbom Clean OpenMP sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 80 160 240 320 400 SE +/- 0.43, N = 3 SE +/- 0.43, N = 3 SE +/- 0.44, N = 3 SE +/- 0.87, N = 3 359.28 360.58 361.45 361.45 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
libgav1 Video Input: Chimera 1080p 10-bit OpenBenchmarking.org FPS, More Is Better libgav1 0.17 Video Input: Chimera 1080p 10-bit sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 9 18 27 36 45 SE +/- 0.07, N = 3 SE +/- 0.05, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 40.99 41.16 41.08 40.92 1. (CXX) g++ options: -O3 -lrt
Liquid-DSP Threads: 128 - Buffer Length: 256 - Filter Length: 57 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 2021.01.31 Threads: 128 - Buffer Length: 256 - Filter Length: 57 sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 700M 1400M 2100M 2800M 3500M SE +/- 7316040.22, N = 3 SE +/- 4035398.92, N = 3 SE +/- 16229226.04, N = 3 SE +/- 8936131.40, N = 3 3024233333 3022633333 3036233333 3040233333 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
TensorFlow Lite Model: Mobilenet Quant OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Mobilenet Quant sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 6K 12K 18K 24K 30K SE +/- 131.15, N = 3 SE +/- 106.55, N = 3 SE +/- 197.07, N = 3 SE +/- 51.85, N = 3 29737.8 29580.5 29607.6 29578.7
dav1d Video Input: Summer Nature 4K OpenBenchmarking.org FPS, More Is Better dav1d 0.9.2 Video Input: Summer Nature 4K sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 80 160 240 320 400 SE +/- 0.23, N = 3 SE +/- 0.11, N = 3 SE +/- 0.85, N = 3 SE +/- 1.22, N = 3 387.57 386.82 388.26 386.36 MIN: 192.81 / MAX: 414.05 MIN: 195.12 / MAX: 412.7 MIN: 192.76 / MAX: 414.49 MIN: 186.53 / MAX: 414.14 1. (CC) gcc options: -pthread -lm
Zstd Compression Compression Level: 19 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 19 - Decompression Speed sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 700 1400 2100 2800 3500 SE +/- 7.47, N = 7 SE +/- 3.38, N = 3 SE +/- 4.49, N = 15 SE +/- 14.49, N = 3 3355.5 3361.1 3355.8 3369.4 1. (CC) gcc options: -O3 -pthread -lz -llzma
GPAW Input: Carbon Nanotube OpenBenchmarking.org Seconds, Fewer Is Better GPAW 22.1 Input: Carbon Nanotube sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 20 40 60 80 100 SE +/- 0.20, N = 3 SE +/- 0.16, N = 3 SE +/- 0.08, N = 3 SE +/- 0.12, N = 3 106.69 107.13 106.93 106.72 1. (CC) gcc options: -shared -fwrapv -O2 -lxc -lblas -lmpi
Zstd Compression Compression Level: 8 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 8 - Decompression Speed sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 800 1600 2400 3200 4000 SE +/- 3.18, N = 3 SE +/- 11.98, N = 3 SE +/- 9.40, N = 4 SE +/- 9.46, N = 3 3795.0 3803.5 3809.7 3799.6 1. (CC) gcc options: -O3 -pthread -lz -llzma
7-Zip Compression Test: Compression Rating OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 21.06 Test: Compression Rating sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 40K 80K 120K 160K 200K SE +/- 179.15, N = 3 SE +/- 94.41, N = 3 SE +/- 237.69, N = 3 SE +/- 256.55, N = 3 196815 196564 196124 196330 1. (CXX) g++ options: -lpthread -ldl -O2 -fPIC
Blender Blend File: Barbershop - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.0 Blend File: Barbershop - Compute: CPU-Only sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 70 140 210 280 350 SE +/- 1.17, N = 3 SE +/- 1.37, N = 3 SE +/- 1.48, N = 3 SE +/- 0.50, N = 3 304.50 304.13 303.91 304.22
dav1d Video Input: Summer Nature 1080p OpenBenchmarking.org FPS, More Is Better dav1d 0.9.2 Video Input: Summer Nature 1080p sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 200 400 600 800 1000 SE +/- 2.54, N = 3 SE +/- 1.54, N = 3 SE +/- 0.74, N = 3 SE +/- 6.97, N = 3 965.73 966.03 964.33 965.12 MIN: 449.13 / MAX: 1072.56 MIN: 447.16 / MAX: 1070.54 MIN: 439 / MAX: 1069.47 MIN: 411.89 / MAX: 1082.48 1. (CC) gcc options: -pthread -lm
dav1d Video Input: Chimera 1080p 10-bit OpenBenchmarking.org FPS, More Is Better dav1d 0.9.2 Video Input: Chimera 1080p 10-bit sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 160 320 480 640 800 SE +/- 2.08, N = 3 SE +/- 0.97, N = 3 SE +/- 0.76, N = 3 SE +/- 1.64, N = 3 717.96 717.84 717.75 718.74 MIN: 466.86 / MAX: 895.99 MIN: 458.34 / MAX: 895.68 MIN: 460.19 / MAX: 898.59 MIN: 461.45 / MAX: 897.2 1. (CC) gcc options: -pthread -lm
ASKAP Test: tConvolve MT - Degridding OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 1.0 Test: tConvolve MT - Degridding sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 700 1400 2100 2800 3500 SE +/- 2.08, N = 3 SE +/- 0.49, N = 3 SE +/- 0.79, N = 3 SE +/- 1.07, N = 3 3187.01 3185.22 3182.74 3183.93 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 sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 500 1000 1500 2000 2500 SE +/- 1.38, N = 3 SE +/- 0.44, N = 3 SE +/- 0.74, N = 3 SE +/- 0.95, N = 3 2143.90 2145.29 2145.87 2146.42 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
TensorFlow Lite Model: NASNet Mobile OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: NASNet Mobile sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 16K 32K 48K 64K 80K SE +/- 189.83, N = 3 SE +/- 549.36, N = 3 SE +/- 72.89, N = 3 SE +/- 537.01, N = 3 74047.5 74069.7 74051.7 74045.3
ONNX Runtime Model: fcn-resnet101-11 - Device: CPU OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.10 Model: fcn-resnet101-11 - Device: CPU sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 40 80 120 160 200 SE +/- 0.58, N = 3 SE +/- 0.17, N = 3 SE +/- 4.86, N = 12 SE +/- 0.33, N = 3 159 156 171 157 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt
PostgreSQL pgbench Scaling Factor: 100 - Clients: 250 - Mode: Read Write - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 14.0 Scaling Factor: 100 - Clients: 250 - Mode: Read Write - Average Latency sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 8 16 24 32 40 SE +/- 0.63, N = 12 SE +/- 0.48, N = 12 SE +/- 0.41, N = 12 SE +/- 0.54, N = 12 31.90 32.08 32.90 27.54 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
PostgreSQL pgbench Scaling Factor: 100 - Clients: 250 - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 14.0 Scaling Factor: 100 - Clients: 250 - Mode: Read Write sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 2K 4K 6K 8K 10K SE +/- 168.64, N = 12 SE +/- 121.23, N = 12 SE +/- 93.95, N = 12 SE +/- 175.38, N = 12 7874 7814 7612 9116 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
PostgreSQL pgbench Scaling Factor: 100 - Clients: 100 - Mode: Read Write - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 14.0 Scaling Factor: 100 - Clients: 100 - Mode: Read Write - Average Latency sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 4 8 12 16 20 SE +/- 0.11, N = 12 SE +/- 0.31, N = 9 SE +/- 0.30, N = 12 SE +/- 0.19, N = 12 14.23 13.50 13.65 12.89 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
PostgreSQL pgbench Scaling Factor: 100 - Clients: 100 - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 14.0 Scaling Factor: 100 - Clients: 100 - Mode: Read Write sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 2K 4K 6K 8K 10K SE +/- 52.20, N = 12 SE +/- 168.09, N = 9 SE +/- 160.77, N = 12 SE +/- 114.09, N = 12 7034 7441 7363 7779 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
MariaDB Clients: 64 OpenBenchmarking.org Queries Per Second, More Is Better MariaDB 10.8.2 Clients: 64 sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 80 160 240 320 400 SE +/- 3.43, N = 9 SE +/- 7.08, N = 9 SE +/- 6.49, N = 6 SE +/- 43.05, N = 6 284 289 290 369 1. (CXX) g++ options: -fPIC -pie -fstack-protector -O3 -shared -lrt -lpthread -lz -ldl -lm -lstdc++
MariaDB Clients: 32 OpenBenchmarking.org Queries Per Second, More Is Better MariaDB 10.8.2 Clients: 32 sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 160 320 480 640 800 SE +/- 12.32, N = 7 SE +/- 1.86, N = 3 SE +/- 13.41, N = 6 SE +/- 0.83, N = 3 367 371 365 757 1. (CXX) g++ options: -fPIC -pie -fstack-protector -O3 -shared -lrt -lpthread -lz -ldl -lm -lstdc++
MariaDB Clients: 16 OpenBenchmarking.org Queries Per Second, More Is Better MariaDB 10.8.2 Clients: 16 sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 200 400 600 800 1000 SE +/- 8.43, N = 9 SE +/- 13.56, N = 9 SE +/- 22.18, N = 9 SE +/- 2.19, N = 3 397 403 440 878 1. (CXX) g++ options: -fPIC -pie -fstack-protector -O3 -shared -lrt -lpthread -lz -ldl -lm -lstdc++
MariaDB Clients: 8 OpenBenchmarking.org Queries Per Second, More Is Better MariaDB 10.8.2 Clients: 8 sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 200 400 600 800 1000 SE +/- 27.52, N = 9 SE +/- 21.18, N = 9 SE +/- 26.78, N = 9 SE +/- 4.78, N = 3 509 484 493 955 1. (CXX) g++ options: -fPIC -pie -fstack-protector -O3 -shared -lrt -lpthread -lz -ldl -lm -lstdc++
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 sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 4K 8K 12K 16K 20K SE +/- 614.76, N = 12 SE +/- 437.55, N = 15 SE +/- 654.80, N = 12 SE +/- 404.40, N = 12 16699.64 16427.80 16384.66 17081.15 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp
GraphicsMagick Operation: Resizing OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Resizing sched-core Git NP4 5.17 Git Linux 5.17 Git sched-core Git 200 400 600 800 1000 SE +/- 19.03, N = 15 SE +/- 21.81, N = 15 SE +/- 19.31, N = 15 SE +/- 14.80, N = 15 1040 1112 1074 1035 1. (CC) gcc options: -fopenmp -O2 -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
Phoronix Test Suite v10.8.4