2970WX April 2022 AMD Ryzen Threadripper 2970WX 24-Core testing with a Gigabyte X399 AORUS Gaming 7 (F12h BIOS) and Sapphire AMD Radeon RX 560 4GB on Ubuntu 20.04 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2204264-NE-2970WXAPR29&export=pdf&grs&sor&rro .
2970WX April 2022 Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server OpenGL Compiler File-System Screen Resolution A B C CC AMD Ryzen Threadripper 2970WX 24-Core @ 3.00GHz (24 Cores / 48 Threads) Gigabyte X399 AORUS Gaming 7 (F12h BIOS) AMD 17h 16GB 120GB Corsair Force MP500 Sapphire AMD Radeon RX 560 4GB (1300/1750MHz) Realtek ALC1220 DELL S2409W Qualcomm Atheros Killer E2500 + 2 x QLogic cLOM8214 1/10GbE + Intel 8265 / 8275 Ubuntu 20.04 5.9.0-050900rc6daily20200926-generic (x86_64) 20200925 GNOME Shell 3.36.4 X Server 1.20.13 4.6 Mesa 21.2.6 (LLVM 12.0.0) GCC 9.4.0 ext4 1920x1080 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++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-Av3uEd/gcc-9-9.4.0/debian/tmp-nvptx/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 ondemand (Boost: Enabled) - CPU Microcode: 0x800820d Java Details - OpenJDK Runtime Environment (build 11.0.14.1+1-Ubuntu-0ubuntu1.20.04) Python Details - Python 3.8.10 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 STIBP: disabled RSB filling + srbds: Not affected + tsx_async_abort: Not affected
2970WX April 2022 onednn: Recurrent Neural Network Training - bf16bf16bf16 - CPU svt-av1: Preset 12 - Bosphorus 4K compress-pbzip2: FreeBSD-13.0-RELEASE-amd64-memstick.img Compression ospray-studio: 3 - 1080p - 16 - Path Tracer svt-av1: Preset 10 - Bosphorus 1080p ospray-studio: 3 - 1080p - 1 - Path Tracer ospray-studio: 1 - 1080p - 16 - Path Tracer svt-av1: Preset 10 - Bosphorus 4K aom-av1: Speed 10 Realtime - Bosphorus 1080p rocksdb: Update Rand build-linux-kernel: defconfig ospray-studio: 2 - 1080p - 32 - Path Tracer ospray-studio: 2 - 1080p - 1 - Path Tracer onednn: IP Shapes 3D - f32 - CPU ospray-studio: 1 - 1080p - 1 - Path Tracer aom-av1: Speed 10 Realtime - Bosphorus 4K onednn: Matrix Multiply Batch Shapes Transformer - f32 - CPU aom-av1: Speed 8 Realtime - Bosphorus 1080p onednn: IP Shapes 3D - u8s8f32 - CPU svt-av1: Preset 12 - Bosphorus 1080p avifenc: 10, Lossless avifenc: 6, Lossless onednn: Recurrent Neural Network Training - u8s8f32 - CPU aom-av1: Speed 9 Realtime - Bosphorus 1080p onednn: Deconvolution Batch shapes_1d - f32 - CPU onednn: Recurrent Neural Network Training - f32 - CPU onednn: Deconvolution Batch shapes_3d - f32 - CPU ospray: particle_volume/pathtracer/real_time gpaw: Carbon Nanotube onednn: Deconvolution Batch shapes_3d - u8s8f32 - CPU onednn: IP Shapes 1D - f32 - CPU ospray-studio: 1 - 1080p - 32 - Path Tracer aom-av1: Speed 6 Realtime - Bosphorus 4K ospray-studio: 2 - 1080p - 16 - Path Tracer rocksdb: Read While Writing aom-av1: Speed 6 Two-Pass - Bosphorus 1080p aom-av1: Speed 8 Realtime - Bosphorus 4K svt-av1: Preset 4 - Bosphorus 1080p rocksdb: Read Rand Write Rand webp2: Default aom-av1: Speed 9 Realtime - Bosphorus 4K ospray-studio: 3 - 1080p - 32 - Path Tracer webp2: Quality 100, Compression Effort 5 svt-av1: Preset 8 - Bosphorus 4K svt-av1: Preset 8 - Bosphorus 1080p build-linux-kernel: allmodconfig onednn: Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPU aom-av1: Speed 4 Two-Pass - Bosphorus 4K avifenc: 6 aom-av1: Speed 6 Realtime - Bosphorus 1080p build-wasmer: Time To Compile aom-av1: Speed 6 Two-Pass - Bosphorus 4K onednn: Recurrent Neural Network Inference - f32 - CPU libgav1: Summer Nature 4K libgav1: Summer Nature 1080p ospray: gravity_spheres_volume/dim_512/scivis/real_time onednn: Recurrent Neural Network Inference - u8s8f32 - CPU rocksdb: Rand Read avifenc: 2 onednn: Deconvolution Batch shapes_1d - u8s8f32 - CPU ospray: gravity_spheres_volume/dim_512/ao/real_time influxdb: 4 - 10000 - 2,5000,1 - 10000 webp2: Quality 95, Compression Effort 7 libgav1: Chimera 1080p 10-bit onednn: Convolution Batch Shapes Auto - u8s8f32 - CPU draco: Lion libgav1: Chimera 1080p avifenc: 0 influxdb: 64 - 10000 - 2,5000,1 - 10000 influxdb: 1024 - 10000 - 2,5000,1 - 10000 ospray: particle_volume/scivis/real_time ospray: particle_volume/ao/real_time tachyon: Total Time java-jmh: Throughput openjpeg: NASA Curiosity Panorama M34 ospray: gravity_spheres_volume/dim_512/pathtracer/real_time onednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPU aom-av1: Speed 4 Two-Pass - Bosphorus 1080p onednn: Convolution Batch Shapes Auto - f32 - CPU webp2: Quality 100, Lossless Compression webp2: Quality 75, Compression Effort 7 onednn: IP Shapes 1D - u8s8f32 - CPU build-mplayer: Time To Compile draco: Church Facade aom-av1: Speed 0 Two-Pass - Bosphorus 1080p aom-av1: Speed 0 Two-Pass - Bosphorus 4K A B C CC 6703.11 60.961 6.319 51491 164.52 3126 44830 56.609 83.7 416520 62.112 93952 2617 11.5716 2652 35.72 1.81564 60.07 3.03689 236.162 6.928 10.361 6938.36 73.19 7.01336 6908.45 6.2435 160.524 1016.765 5.55139 6.41531 92781 9.61 39666 3541784 15.87 26.18 4.865 1812704 2.993 32.71 102475 3.913 30.238 88.168 750.804 1.56021 3.53 6.573 5.88 85.361 6.22 3791.48 37.09 116.5 2.24638 3785.7 85480972 74.567 3.05707 2.34665 887533.2 297.224 34.9 25.1668 5677 87.84 148.59 962385.4 993172.7 18.6117 19.2224 81.7825 37868394352.57 122291 3.64966 3791.29 6.18 20.0133 632.633 139.184 2.77871 24.419 7885 0.27 0.11 15240 40.73 6.886 64829 161.33 3683 40610 58.239 77.97 481249 63.616 96035 2952 13.0751 2506 36.46 1.8439 59.05 3.04125 247.7 6.734 10.877 6453.13 77.59 7.068 6511.86 6.28422 150.385 1060.2 5.30791 6.71676 95635 9.65 41681 3446954 15.15 25.85 4.812 1880888 2.906 33.53 102443 3.957 30.265 88.742 743.009 1.5719 3.6 6.578 5.99 86.713 6.24 3730.88 37.26 115.82 2.29061 3794.73 85339560 75.846 3.01827 2.37403 879034.9 294.081 35.33 25.3943 5690 87.4 148.655 971393 984192 18.5253 19.2045 81.1224 38111196527.704 123091 3.66312 3769.13 6.16 20.063 629.848 139.021 2.77399 24.396 7894 0.27 0.11 44.408 4.668 160.131 57.004 81.9 67.562 12.9417 34.88 54.42 3.05982 246.575 6.371 10.066 6966.51 78.87 7.50846 6990.33 6.04388 151.319 5.22635 6.81115 9.6 15.83 25.97 5.01 32.36 30.939 90.749 756.089 3.63 6.398 5.87 6.16 3814.55 37.92 115.83 2.28306 74.775 3.01777 2.37208 35.17 25.4212 87.75 147.218 18.6206 19.3202 3.67481 6.17 20.0272 2.77424 24.35 0.27 0.11 6540.47 60.892 5.194 66624 130.488 3200 38284 49.836 71.78 484164 58.96 84174 2594 12.6362 2807 32.7 2.00883 58.02 2.80323 257.119 6.366 10.04 6742.98 73.97 7.55499 6799.72 6.48557 151.925 1083.391 5.46977 6.71225 90448 9.18 40304 3614362 15.45 25 5.039 1801414 2.871 32.51 98900 4.049 31.193 90.394 734.689 1.52823 3.55 6.495 5.84 84.693 6.3 3796.73 37.77 114.1 2.29135 3728.81 86820807 75.745 3.06571 2.38245 874975.6 293.551 35.16 25.1572 5631 86.99 147.731 970489.9 988748 18.6919 19.377 81.0686 38139877502.891 122247 3.65733 3769.17 6.15 19.966 630.222 138.671 2.78345 24.42 7878 0.27 0.11 OpenBenchmarking.org
oneDNN Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU B A CC 3K 6K 9K 12K 15K 15240.00 6703.11 6540.47 MIN: 12784.1 MIN: 6613.33 MIN: 6514.67 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl
SVT-AV1 Encoder Mode: Preset 12 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.0 Encoder Mode: Preset 12 - Input: Bosphorus 4K B C CC A 14 28 42 56 70 40.73 44.41 60.89 60.96 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
Parallel BZIP2 Compression FreeBSD-13.0-RELEASE-amd64-memstick.img Compression OpenBenchmarking.org Seconds, Fewer Is Better Parallel BZIP2 Compression 1.1.13 FreeBSD-13.0-RELEASE-amd64-memstick.img Compression B A CC C 2 4 6 8 10 6.886 6.319 5.194 4.668 1. (CXX) g++ options: -O2 -pthread -lbz2 -lpthread
OSPray Studio Camera: 3 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer OpenBenchmarking.org ms, Fewer Is Better OSPray Studio 0.10 Camera: 3 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer CC B A 14K 28K 42K 56K 70K 66624 64829 51491 1. (CXX) g++ options: -O3 -lm -ldl -lpthread -pthread
SVT-AV1 Encoder Mode: Preset 10 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.0 Encoder Mode: Preset 10 - Input: Bosphorus 1080p CC C B A 40 80 120 160 200 130.49 160.13 161.33 164.52 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
OSPray Studio Camera: 3 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer OpenBenchmarking.org ms, Fewer Is Better OSPray Studio 0.10 Camera: 3 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer B CC A 800 1600 2400 3200 4000 3683 3200 3126 1. (CXX) g++ options: -O3 -lm -ldl -lpthread -pthread
OSPray Studio Camera: 1 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer OpenBenchmarking.org ms, Fewer Is Better OSPray Studio 0.10 Camera: 1 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer A B CC 10K 20K 30K 40K 50K 44830 40610 38284 1. (CXX) g++ options: -O3 -lm -ldl -lpthread -pthread
SVT-AV1 Encoder Mode: Preset 10 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.0 Encoder Mode: Preset 10 - Input: Bosphorus 4K CC A C B 13 26 39 52 65 49.84 56.61 57.00 58.24 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
AOM AV1 Encoder Mode: Speed 10 Realtime - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.3 Encoder Mode: Speed 10 Realtime - Input: Bosphorus 1080p CC B C A 20 40 60 80 100 71.78 77.97 81.90 83.70 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
Facebook RocksDB Test: Update Random OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 7.0.1 Test: Update Random A B CC 100K 200K 300K 400K 500K 416520 481249 484164 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
Timed Linux Kernel Compilation Build: defconfig OpenBenchmarking.org Seconds, Fewer Is Better Timed Linux Kernel Compilation 5.16 Build: defconfig C B A CC 15 30 45 60 75 67.56 63.62 62.11 58.96
OSPray Studio Camera: 2 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer OpenBenchmarking.org ms, Fewer Is Better OSPray Studio 0.10 Camera: 2 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer B A CC 20K 40K 60K 80K 100K 96035 93952 84174 1. (CXX) g++ options: -O3 -lm -ldl -lpthread -pthread
OSPray Studio Camera: 2 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer OpenBenchmarking.org ms, Fewer Is Better OSPray Studio 0.10 Camera: 2 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer B A CC 600 1200 1800 2400 3000 2952 2617 2594 1. (CXX) g++ options: -O3 -lm -ldl -lpthread -pthread
oneDNN Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU B C CC A 3 6 9 12 15 13.08 12.94 12.64 11.57 MIN: 12.85 MIN: 12.71 MIN: 10.09 MIN: 11.33 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl
OSPray Studio Camera: 1 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer OpenBenchmarking.org ms, Fewer Is Better OSPray Studio 0.10 Camera: 1 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer CC A B 600 1200 1800 2400 3000 2807 2652 2506 1. (CXX) g++ options: -O3 -lm -ldl -lpthread -pthread
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 CC C A B 8 16 24 32 40 32.70 34.88 35.72 36.46 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
oneDNN Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU CC B A 0.452 0.904 1.356 1.808 2.26 2.00883 1.84390 1.81564 MIN: 1.78 MIN: 1.54 MIN: 1.51 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl
AOM AV1 Encoder Mode: Speed 8 Realtime - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.3 Encoder Mode: Speed 8 Realtime - Input: Bosphorus 1080p C CC B A 13 26 39 52 65 54.42 58.02 59.05 60.07 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
oneDNN Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU C B A CC 0.6885 1.377 2.0655 2.754 3.4425 3.05982 3.04125 3.03689 2.80323 MIN: 2.88 MIN: 2.86 MIN: 2.86 MIN: 2.62 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl
SVT-AV1 Encoder Mode: Preset 12 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.0 Encoder Mode: Preset 12 - Input: Bosphorus 1080p A C B CC 60 120 180 240 300 236.16 246.58 247.70 257.12 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
libavif avifenc Encoder Speed: 10, Lossless OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.10 Encoder Speed: 10, Lossless A B C CC 2 4 6 8 10 6.928 6.734 6.371 6.366 1. (CXX) g++ options: -O3 -fPIC -lm
libavif avifenc Encoder Speed: 6, Lossless OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.10 Encoder Speed: 6, Lossless B A C CC 3 6 9 12 15 10.88 10.36 10.07 10.04 1. (CXX) g++ options: -O3 -fPIC -lm
oneDNN Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU C A CC B 1500 3000 4500 6000 7500 6966.51 6938.36 6742.98 6453.13 MIN: 6737.45 MIN: 6911.81 MIN: 6704.15 MIN: 6413.73 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl
AOM AV1 Encoder Mode: Speed 9 Realtime - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.3 Encoder Mode: Speed 9 Realtime - Input: Bosphorus 1080p A CC B C 20 40 60 80 100 73.19 73.97 77.59 78.87 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
oneDNN Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU CC C B A 2 4 6 8 10 7.55499 7.50846 7.06800 7.01336 MIN: 6.41 MIN: 6.38 MIN: 6.39 MIN: 6.38 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl
oneDNN Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU C A CC B 1500 3000 4500 6000 7500 6990.33 6908.45 6799.72 6511.86 MIN: 6953.94 MIN: 6853.12 MIN: 6715.92 MIN: 6388.55 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl
oneDNN Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU CC B A C 2 4 6 8 10 6.48557 6.28422 6.24350 6.04388 MIN: 5.44 MIN: 5.43 MIN: 5.43 MIN: 5.39 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl
OSPray Benchmark: particle_volume/pathtracer/real_time OpenBenchmarking.org Items Per Second, More Is Better OSPray 2.9 Benchmark: particle_volume/pathtracer/real_time B C CC A 40 80 120 160 200 150.39 151.32 151.93 160.52
GPAW Input: Carbon Nanotube OpenBenchmarking.org Seconds, Fewer Is Better GPAW 22.1 Input: Carbon Nanotube CC B A 200 400 600 800 1000 1083.39 1060.20 1016.77 1. (CC) gcc options: -pthread -shared -fwrapv -O2 -lxc -lblas -lmpi
oneDNN Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU A CC B C 1.2491 2.4982 3.7473 4.9964 6.2455 5.55139 5.46977 5.30791 5.22635 MIN: 4.73 MIN: 4.73 MIN: 4.72 MIN: 4.71 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl
oneDNN Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU C B CC A 2 4 6 8 10 6.81115 6.71676 6.71225 6.41531 MIN: 5.94 MIN: 5.77 MIN: 5.92 MIN: 5.81 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl
OSPray Studio Camera: 1 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer OpenBenchmarking.org ms, Fewer Is Better OSPray Studio 0.10 Camera: 1 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer B A CC 20K 40K 60K 80K 100K 95635 92781 90448 1. (CXX) g++ options: -O3 -lm -ldl -lpthread -pthread
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 CC C A B 3 6 9 12 15 9.18 9.60 9.61 9.65 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OSPray Studio Camera: 2 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer OpenBenchmarking.org ms, Fewer Is Better OSPray Studio 0.10 Camera: 2 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer B CC A 9K 18K 27K 36K 45K 41681 40304 39666 1. (CXX) g++ options: -O3 -lm -ldl -lpthread -pthread
Facebook RocksDB Test: Read While Writing OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 7.0.1 Test: Read While Writing B A CC 800K 1600K 2400K 3200K 4000K 3446954 3541784 3614362 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
AOM AV1 Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.3 Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 1080p B CC C A 4 8 12 16 20 15.15 15.45 15.83 15.87 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
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 CC B C A 6 12 18 24 30 25.00 25.85 25.97 26.18 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
SVT-AV1 Encoder Mode: Preset 4 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.0 Encoder Mode: Preset 4 - Input: Bosphorus 1080p B A C CC 1.1338 2.2676 3.4014 4.5352 5.669 4.812 4.865 5.010 5.039 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
Facebook RocksDB Test: Read Random Write Random OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 7.0.1 Test: Read Random Write Random CC A B 400K 800K 1200K 1600K 2000K 1801414 1812704 1880888 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
WebP2 Image Encode Encode Settings: Default OpenBenchmarking.org Seconds, Fewer Is Better WebP2 Image Encode 20220422 Encode Settings: Default A B CC 0.6734 1.3468 2.0202 2.6936 3.367 2.993 2.906 2.871 1. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -ldl -lpthread
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 C CC A B 8 16 24 32 40 32.36 32.51 32.71 33.53 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OSPray Studio Camera: 3 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer OpenBenchmarking.org ms, Fewer Is Better OSPray Studio 0.10 Camera: 3 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer A B CC 20K 40K 60K 80K 100K 102475 102443 98900 1. (CXX) g++ options: -O3 -lm -ldl -lpthread -pthread
WebP2 Image Encode Encode Settings: Quality 100, Compression Effort 5 OpenBenchmarking.org Seconds, Fewer Is Better WebP2 Image Encode 20220422 Encode Settings: Quality 100, Compression Effort 5 CC B A 0.911 1.822 2.733 3.644 4.555 4.049 3.957 3.913 1. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -ldl -lpthread
SVT-AV1 Encoder Mode: Preset 8 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.0 Encoder Mode: Preset 8 - Input: Bosphorus 4K A B C CC 7 14 21 28 35 30.24 30.27 30.94 31.19 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
SVT-AV1 Encoder Mode: Preset 8 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.0 Encoder Mode: Preset 8 - Input: Bosphorus 1080p A B CC C 20 40 60 80 100 88.17 88.74 90.39 90.75 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
Timed Linux Kernel Compilation Build: allmodconfig OpenBenchmarking.org Seconds, Fewer Is Better Timed Linux Kernel Compilation 5.16 Build: allmodconfig C A B CC 160 320 480 640 800 756.09 750.80 743.01 734.69
oneDNN Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU B A CC 0.3537 0.7074 1.0611 1.4148 1.7685 1.57190 1.56021 1.52823 MIN: 1.27 MIN: 1.33 MIN: 1.27 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl
AOM AV1 Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.3 Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 4K A CC B C 0.8168 1.6336 2.4504 3.2672 4.084 3.53 3.55 3.60 3.63 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
libavif avifenc Encoder Speed: 6 OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.10 Encoder Speed: 6 B A CC C 2 4 6 8 10 6.578 6.573 6.495 6.398 1. (CXX) g++ options: -O3 -fPIC -lm
AOM AV1 Encoder Mode: Speed 6 Realtime - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.3 Encoder Mode: Speed 6 Realtime - Input: Bosphorus 1080p CC C A B 1.3478 2.6956 4.0434 5.3912 6.739 5.84 5.87 5.88 5.99 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
Timed Wasmer Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Wasmer Compilation 2.2 Time To Compile B A CC 20 40 60 80 100 86.71 85.36 84.69 1. (CC) gcc options: -m64 -ldl -lxkbcommon -lgcc_s -lutil -lrt -lpthread -lm -lc -pie -nodefaultlibs
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 C A B CC 2 4 6 8 10 6.16 6.22 6.24 6.30 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
oneDNN Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU C CC A B 800 1600 2400 3200 4000 3814.55 3796.73 3791.48 3730.88 MIN: 3714.21 MIN: 3743.74 MIN: 3735.82 MIN: 3640.39 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl
libgav1 Video Input: Summer Nature 4K OpenBenchmarking.org FPS, More Is Better libgav1 0.17 Video Input: Summer Nature 4K A B CC C 9 18 27 36 45 37.09 37.26 37.77 37.92 1. (CXX) g++ options: -O3 -lpthread -lrt
libgav1 Video Input: Summer Nature 1080p OpenBenchmarking.org FPS, More Is Better libgav1 0.17 Video Input: Summer Nature 1080p CC B C A 30 60 90 120 150 114.10 115.82 115.83 116.50 1. (CXX) g++ options: -O3 -lpthread -lrt
OSPray Benchmark: gravity_spheres_volume/dim_512/scivis/real_time OpenBenchmarking.org Items Per Second, More Is Better OSPray 2.9 Benchmark: gravity_spheres_volume/dim_512/scivis/real_time A C B CC 0.5156 1.0312 1.5468 2.0624 2.578 2.24638 2.28306 2.29061 2.29135
oneDNN Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU B A CC 800 1600 2400 3200 4000 3794.73 3785.70 3728.81 MIN: 3742.14 MIN: 3713.61 MIN: 3693.42 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl
Facebook RocksDB Test: Random Read OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 7.0.1 Test: Random Read B A CC 20M 40M 60M 80M 100M 85339560 85480972 86820807 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
libavif avifenc Encoder Speed: 2 OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.10 Encoder Speed: 2 B CC C A 20 40 60 80 100 75.85 75.75 74.78 74.57 1. (CXX) g++ options: -O3 -fPIC -lm
oneDNN Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU CC A B C 0.6898 1.3796 2.0694 2.7592 3.449 3.06571 3.05707 3.01827 3.01777 MIN: 3 MIN: 2.99 MIN: 2.94 MIN: 2.95 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl
OSPray Benchmark: gravity_spheres_volume/dim_512/ao/real_time OpenBenchmarking.org Items Per Second, More Is Better OSPray 2.9 Benchmark: gravity_spheres_volume/dim_512/ao/real_time A C B CC 0.5361 1.0722 1.6083 2.1444 2.6805 2.34665 2.37208 2.37403 2.38245
InfluxDB Concurrent Streams: 4 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000 OpenBenchmarking.org val/sec, More Is Better InfluxDB 1.8.2 Concurrent Streams: 4 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000 CC B A 200K 400K 600K 800K 1000K 874975.6 879034.9 887533.2
WebP2 Image Encode Encode Settings: Quality 95, Compression Effort 7 OpenBenchmarking.org Seconds, Fewer Is Better WebP2 Image Encode 20220422 Encode Settings: Quality 95, Compression Effort 7 A B CC 60 120 180 240 300 297.22 294.08 293.55 1. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -ldl -lpthread
libgav1 Video Input: Chimera 1080p 10-bit OpenBenchmarking.org FPS, More Is Better libgav1 0.17 Video Input: Chimera 1080p 10-bit A CC C B 8 16 24 32 40 34.90 35.16 35.17 35.33 1. (CXX) g++ options: -O3 -lpthread -lrt
oneDNN Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU C B A CC 6 12 18 24 30 25.42 25.39 25.17 25.16 MIN: 24.5 MIN: 24.35 MIN: 24.25 MIN: 24.27 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl
Google Draco Model: Lion OpenBenchmarking.org ms, Fewer Is Better Google Draco 1.5.0 Model: Lion B A CC 1200 2400 3600 4800 6000 5690 5677 5631 1. (CXX) g++ options: -O3
libgav1 Video Input: Chimera 1080p OpenBenchmarking.org FPS, More Is Better libgav1 0.17 Video Input: Chimera 1080p CC B C A 20 40 60 80 100 86.99 87.40 87.75 87.84 1. (CXX) g++ options: -O3 -lpthread -lrt
libavif avifenc Encoder Speed: 0 OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.10 Encoder Speed: 0 B A CC C 30 60 90 120 150 148.66 148.59 147.73 147.22 1. (CXX) g++ options: -O3 -fPIC -lm
InfluxDB Concurrent Streams: 64 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000 OpenBenchmarking.org val/sec, More Is Better InfluxDB 1.8.2 Concurrent Streams: 64 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000 A CC B 200K 400K 600K 800K 1000K 962385.4 970489.9 971393.0
InfluxDB Concurrent Streams: 1024 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000 OpenBenchmarking.org val/sec, More Is Better InfluxDB 1.8.2 Concurrent Streams: 1024 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000 B CC A 200K 400K 600K 800K 1000K 984192.0 988748.0 993172.7
OSPray Benchmark: particle_volume/scivis/real_time OpenBenchmarking.org Items Per Second, More Is Better OSPray 2.9 Benchmark: particle_volume/scivis/real_time B A C CC 5 10 15 20 25 18.53 18.61 18.62 18.69
OSPray Benchmark: particle_volume/ao/real_time OpenBenchmarking.org Items Per Second, More Is Better OSPray 2.9 Benchmark: particle_volume/ao/real_time B A C CC 5 10 15 20 25 19.20 19.22 19.32 19.38
Tachyon Total Time OpenBenchmarking.org Seconds, Fewer Is Better Tachyon 0.99.2 Total Time A B CC 20 40 60 80 100 81.78 81.12 81.07 1. (CC) gcc options: -m64 -O3 -fomit-frame-pointer -ffast-math -ltachyon -lm -lpthread
Java JMH Throughput OpenBenchmarking.org Ops/s, More Is Better Java JMH Throughput A B CC 8000M 16000M 24000M 32000M 40000M 37868394352.57 38111196527.70 38139877502.89
OpenJPEG Encode: NASA Curiosity Panorama M34 OpenBenchmarking.org ms, Fewer Is Better OpenJPEG 2.4 Encode: NASA Curiosity Panorama M34 B A CC 30K 60K 90K 120K 150K 123091 122291 122247 1. (CXX) g++ options: -rdynamic
OSPray Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_time OpenBenchmarking.org Items Per Second, More Is Better OSPray 2.9 Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_time A CC B C 0.8268 1.6536 2.4804 3.3072 4.134 3.64966 3.65733 3.66312 3.67481
oneDNN Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU A CC B 800 1600 2400 3200 4000 3791.29 3769.17 3769.13 MIN: 3757.89 MIN: 3734.15 MIN: 3714 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl
AOM AV1 Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.3 Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 1080p CC B C A 2 4 6 8 10 6.15 6.16 6.17 6.18 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
oneDNN Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU B C A CC 5 10 15 20 25 20.06 20.03 20.01 19.97 MIN: 19.21 MIN: 19.23 MIN: 19.13 MIN: 19.24 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl
WebP2 Image Encode Encode Settings: Quality 100, Lossless Compression OpenBenchmarking.org Seconds, Fewer Is Better WebP2 Image Encode 20220422 Encode Settings: Quality 100, Lossless Compression A CC B 140 280 420 560 700 632.63 630.22 629.85 1. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -ldl -lpthread
WebP2 Image Encode Encode Settings: Quality 75, Compression Effort 7 OpenBenchmarking.org Seconds, Fewer Is Better WebP2 Image Encode 20220422 Encode Settings: Quality 75, Compression Effort 7 A B CC 30 60 90 120 150 139.18 139.02 138.67 1. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -ldl -lpthread
oneDNN Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU CC A C B 0.6263 1.2526 1.8789 2.5052 3.1315 2.78345 2.77871 2.77424 2.77399 MIN: 2.67 MIN: 2.67 MIN: 2.68 MIN: 2.66 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -lpthread -ldl
Timed MPlayer Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed MPlayer Compilation 1.5 Time To Compile CC A B C 6 12 18 24 30 24.42 24.42 24.40 24.35
Google Draco Model: Church Facade OpenBenchmarking.org ms, Fewer Is Better Google Draco 1.5.0 Model: Church Facade B A CC 2K 4K 6K 8K 10K 7894 7885 7878 1. (CXX) g++ options: -O3
AOM AV1 Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.3 Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 1080p A B C CC 0.0608 0.1216 0.1824 0.2432 0.304 0.27 0.27 0.27 0.27 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
AOM AV1 Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.3 Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 4K A B C CC 0.0248 0.0496 0.0744 0.0992 0.124 0.11 0.11 0.11 0.11 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
Phoronix Test Suite v10.8.5