AMD FX-8370 2021 AMD FX-8370 Eight-Core testing with a MSI 970 GAMING (MS-7693) v4.0 (V22.3 BIOS) and AMD Radeon HD 5770 1GB on Ubuntu 20.10 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2101033-HA-AMDFX837036&sro&grs&export=txt .
AMD FX-8370 2021 Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server Display Driver OpenGL Compiler File-System Screen Resolution Vet 1 Vet 2 AMD FX-8370 Eight-Core @ 4.00GHz (4 Cores / 8 Threads) MSI 970 GAMING (MS-7693) v4.0 (V22.3 BIOS) AMD RD9x0/RX980 8GB 120GB TOSHIBA TR150 AMD Radeon HD 5770 1GB Realtek ALC1150 G237HL Qualcomm Atheros Killer E220x Ubuntu 20.10 5.8.0-33-generic (x86_64) GNOME Shell 3.38.1 X Server 1.20.9 modesetting 1.20.9 3.3 Mesa 20.2.1 (LLVM 11.0.0) GCC 10.2.0 ext4 1920x1080 OpenBenchmarking.org 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 ondemand (Boost: Enabled) - CPU Microcode: 0x6000852 Graphics Details - GLAMOR 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 STIBP: disabled RSB filling + srbds: Not affected + tsx_async_abort: Not affected
AMD FX-8370 2021 redis: LPOP redis: GET clomp: Static OMP Speedup luxcorerender: DLSC basis: UASTC Level 3 stress-ng: Context Switching simdjson: Kostya onednn: Convolution Batch Shapes Auto - f32 - CPU onednn: IP Shapes 3D - u8s8f32 - CPU node-web-tooling: ncnn: CPU - blazeface redis: SET darktable: Boat - CPU-only ncnn: CPU - shufflenet-v2 influxdb: 4 - 10000 - 2,5000,1 - 10000 onednn: IP Shapes 3D - f32 - CPU darktable: Server Rack - CPU-only stockfish: Total Time webp: Quality 100, Lossless luxcorerender: Rainbow Colors and Prism influxdb: 64 - 10000 - 2,5000,1 - 10000 onednn: Convolution Batch Shapes Auto - u8s8f32 - CPU mnn: inception-v3 stress-ng: MEMFD redis: LPUSH lczero: BLAS warsow: 1920 x 1080 mnn: SqueezeNetV1.0 openvkl: vklBenchmark avifenc: 2 build-eigen: Time To Compile phpbench: PHP Benchmark Suite cryptsetup: Twofish-XTS 256b Decryption compress-lz4: 1 - Decompression Speed x265: Bosphorus 1080p indigobench: CPU - Bedroom kvazaar: Bosphorus 4K - Ultra Fast ncnn: CPU-v2-v2 - mobilenet-v2 onednn: IP Shapes 1D - f32 - CPU stress-ng: Malloc build-ffmpeg: Time To Compile cryptsetup: AES-XTS 256b Encryption compress-lz4: 9 - Decompression Speed compress-lz4: 3 - Decompression Speed stress-ng: Glibc Qsort Data Sorting cryptsetup: Twofish-XTS 512b Encryption compress-lz4: 1 - Compression Speed mnn: MobileNetV2_224 gimp: unsharp-mask ncnn: CPU - regnety_400m cryptsetup: Twofish-XTS 512b Decryption asmfish: 1024 Hash Memory, 26 Depth compress-zstd: 19 cryptsetup: AES-XTS 512b Decryption ncnn: CPU - alexnet webp: Quality 100 redis: SADD ncnn: CPU - mobilenet gimp: auto-levels rnnoise: webp: Default stress-ng: CPU Stress stress-ng: Forking ncnn: CPU-v3-v3 - mobilenet-v3 onednn: Deconvolution Batch shapes_1d - u8s8f32 - CPU stress-ng: Crypto gimp: rotate stress-ng: Socket Activity darktable: Masskrug - CPU-only cryptsetup: Serpent-XTS 256b Decryption avifenc: 8 cryptsetup: AES-XTS 256b Decryption cryptsetup: Serpent-XTS 256b Encryption stress-ng: Atomic yafaray: Total Time For Sample Scene webp: Quality 100, Lossless, Highest Compression avifenc: 10 rav1e: 5 caffe: AlexNet - CPU - 100 deepspeech: CPU mnn: resnet-v2-50 stress-ng: System V Message Passing onednn: Deconvolution Batch shapes_3d - f32 - CPU lammps: Rhodopsin Protein x264: H.264 Video Encoding onednn: IP Shapes 1D - u8s8f32 - CPU ncnn: CPU - yolov4-tiny cryptsetup: Serpent-XTS 512b Decryption cryptsetup: PBKDF2-whirlpool indigobench: CPU - Supercar coremark: CoreMark Size 666 - Iterations Per Second stress-ng: Glibc C String Functions rav1e: 6 caffe: GoogleNet - CPU - 100 build-linux-kernel: Time To Compile stress-ng: SENDFILE basis: UASTC Level 2 + RDO Post-Processing basis: UASTC Level 2 gimp: resize encode-opus: WAV To Opus Encode compress-7zip: Compress Speed Test compress-lz4: 9 - Compression Speed stress-ng: Memory Copying hugin: Panorama Photo Assistant + Stitching Time sqlite-speedtest: Timed Time - Size 1,000 basis: ETC1S stress-ng: NUMA build-gdb: Time To Compile ncnn: CPU - efficientnet-b0 encode-flac: WAV To FLAC onednn: Recurrent Neural Network Training - bf16bf16bf16 - CPU basis: UASTC Level 0 rsvg: SVG Files To PNG avifenc: 0 cryptsetup: PBKDF2-sha512 ocrmypdf: Processing 60 Page PDF Document rays1bench: Large Scene build-apache: Time To Compile onednn: Recurrent Neural Network Training - f32 - CPU onednn: Matrix Multiply Batch Shapes Transformer - f32 - CPU webp: Quality 100, Highest Compression onednn: Deconvolution Batch shapes_1d - f32 - CPU tensorflow-lite: SqueezeNet cryptsetup: Serpent-XTS 512b Encryption onednn: Recurrent Neural Network Inference - u8s8f32 - CPU onednn: Recurrent Neural Network Training - u8s8f32 - CPU encode-mp3: WAV To MP3 stress-ng: Matrix Math rav1e: 10 kvazaar: Bosphorus 1080p - Ultra Fast cryptsetup: Twofish-XTS 256b Encryption ncnn: CPU - mnasnet build-mplayer: Time To Compile stress-ng: Vector Math onednn: Recurrent Neural Network Inference - f32 - CPU tensorflow-lite: Mobilenet Float onednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPU onednn: Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPU tensorflow-lite: Inception V4 mnn: mobilenet-v1-1.0 numpy: crafty: Elapsed Time compress-lz4: 3 - Compression Speed cryptsetup: AES-XTS 512b Encryption john-the-ripper: MD5 build2: Time To Compile ncnn: CPU - resnet50 tensorflow-lite: NASNet Mobile ncnn: CPU - googlenet ncnn: CPU - squeezenet_ssd stress-ng: Semaphores tensorflow-lite: Mobilenet Quant tnn: CPU - SqueezeNet v1.1 ncnn: CPU - resnet18 encode-ape: WAV To APE encode-wavpack: WAV To WavPack tnn: CPU - MobileNet v2 onednn: Deconvolution Batch shapes_3d - u8s8f32 - CPU john-the-ripper: Blowfish hmmer: Pfam Database Search rawtherapee: Total Benchmark Time ncnn: CPU - vgg16 tensorflow-lite: Inception ResNet V2 darktable: Server Room - CPU-only compress-zstd: 3 gromacs: Water Benchmark oidn: Memorial x265: Bosphorus 4K rav1e: 1 kvazaar: Bosphorus 1080p - Very Fast kvazaar: Bosphorus 4K - Very Fast kvazaar: Bosphorus 1080p - Medium kvazaar: Bosphorus 4K - Medium libraw: Post-Processing Benchmark simdjson: DistinctUserID simdjson: PartialTweets simdjson: LargeRand lczero: Eigen glmark2: 1920 x 1080 unpack-firefox: firefox-84.0.source.tar.xz stress-ng: CPU Cache stress-ng: MMAP espeak: Text-To-Speech Synthesis Vet 1 Vet 2 1483179.58 1420635.00 2.8 0.49 178.488 958188.67 0.29 48.1517 5.74220 5.31 4.55 1077335.42 35.370 18.80 594226.4 24.0710 0.491 6971484 30.648 0.52 721348.2 38.9137 1344.893 127.99 806438.96 160 143.7 159.814 32.27 168.708 134.655 415846 242.7 3697.1 19.52 0.490 2.95 25.05 32.6203 22154552.21 156.342 1081.7 3653.9 3656.0 55.09 247.2 3387.29 84.922 28.987 40.24 247.9 10590695 16.9 944.8 49.72 3.573 1212043.04 98.29 25.469 47.768 2.444 1823.75 18452.92 23.00 21.6285 872.89 24.238 1776.16 28.640 320.2 12.859 1093.6 312.0 54519.87 439.466 66.556 11.901 0.322 71021 287.01245 1131.683 2212153.79 113.860 1.514 30.29 10.2245 201.70 316.4 395398 1.210 122656.510810 267246.20 0.416 177755 252.491 50924.75 1121.056 88.179 18.960 15.708 21231 29.81 1002.06 105.809 122.125 104.183 84.19 231.262 39.88 16.928 44728.9 14.904 43.324 275.517 1273595 62.368 9.06 48.374 44739.8 13.5855 11.408 71.2033 512325 315.2 22769.0 44745.0 13.633 15073.34 1.170 11.84 244.1 24.69 113.039 23898.11 22758.6 351171 22771.8 11.7489 7343657 169.003 150.23 5195271 30.96 943.8 256221 392.482 211.76 383504 99.74 103.79 505610.19 357144 513.823 91.23 26.397 22.974 528.347 22.2088 6411 191.720 138.968 767.38 6618533 26.729 1745.5 0.074 0.87 4.55 0.115 5.55 1.35 2.09 0.45 17.99 0.38 0.37 0.24 138 1322 32.992 14.76 12.10 57.487 823801.38 1291856.21 3.0 0.52 169.517 917908.08 0.3 49.7819 5.92877 5.15 4.43 1106164.79 36.306 18.33 579620.2 24.6753 0.503 6814594 30.026 0.51 707886.5 38.2274 1325.195 126.33 796182.64 158 145.5 157.847 32.67 166.702 136.251 420714 245.5 3657.2 19.32 0.485 2.98 24.80 32.9295 21949359.53 157.770 1091.1 3622.7 3625.3 55.53 245.3 3362.32 85.549 29.169 39.99 246.4 10527008 16.8 950.1 49.99 3.554 1205601.54 97.78 25.340 47.541 2.433 1831.98 18535.23 23.10 21.5349 869.13 24.137 1783.24 28.751 319.0 12.813 1089.7 310.9 54711.61 437.992 66.776 11.862 0.321 70801 286.13076 1128.306 2206047.98 114.163 1.510 30.21 10.1979 202.21 317.2 394414 1.207 122356.312586 266600.95 0.415 178137 251.959 50818.29 1118.926 88.014 18.994 15.736 21195 29.86 1003.73 105.648 122.302 104.327 84.08 230.971 39.93 16.907 44784.2 14.886 43.376 275.205 1272166 62.437 9.05 48.321 44788.0 13.5999 11.396 71.1316 512833 314.9 22789.7 44784.5 13.621 15086.29 1.171 11.85 243.9 24.71 112.950 23915.82 22775.3 351424 22787.9 11.7571 7348723 168.889 150.33 5198696 30.94 944.4 256381 392.276 211.65 383701 99.69 103.84 505851.94 357312 513.594 91.27 26.386 22.965 528.550 22.2003 6409 191.666 139.005 767.18 6619900 26.734 1745.6 0.074 0.87 4.55 0.115 5.55 1.35 2.09 0.45 17.99 0.38 0.37 0.24 138 1322 38.114 15.31 9.86 60.334 OpenBenchmarking.org
Redis Test: LPOP OpenBenchmarking.org Requests Per Second, More Is Better Redis 6.0.9 Test: LPOP Vet 1 Vet 2 300K 600K 900K 1200K 1500K SE +/- 9551.20, N = 3 SE +/- 5581.05, N = 3 1483179.58 823801.38 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
Redis Test: GET OpenBenchmarking.org Requests Per Second, More Is Better Redis 6.0.9 Test: GET Vet 1 Vet 2 300K 600K 900K 1200K 1500K SE +/- 7264.81, N = 3 SE +/- 16057.72, N = 3 1420635.00 1291856.21 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
CLOMP Static OMP Speedup OpenBenchmarking.org Speedup, More Is Better CLOMP 1.2 Static OMP Speedup Vet 1 Vet 2 0.675 1.35 2.025 2.7 3.375 SE +/- 0.03, N = 3 SE +/- 0.03, N = 12 2.8 3.0 1. (CC) gcc options: -fopenmp -O3 -lm
LuxCoreRender Scene: DLSC OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.3 Scene: DLSC Vet 1 Vet 2 0.117 0.234 0.351 0.468 0.585 SE +/- 0.01, N = 15 SE +/- 0.00, N = 3 0.49 0.52 MIN: 0.44 / MAX: 0.52 MIN: 0.51
Basis Universal Settings: UASTC Level 3 OpenBenchmarking.org Seconds, Fewer Is Better Basis Universal 1.12 Settings: UASTC Level 3 Vet 1 Vet 2 40 80 120 160 200 SE +/- 3.41, N = 9 SE +/- 0.10, N = 3 178.49 169.52 1. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
Stress-NG Test: Context Switching OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Context Switching Vet 1 Vet 2 200K 400K 600K 800K 1000K SE +/- 9262.61, N = 3 SE +/- 6076.39, N = 3 958188.67 917908.08 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
simdjson Throughput Test: Kostya OpenBenchmarking.org GB/s, More Is Better simdjson 0.7.1 Throughput Test: Kostya Vet 1 Vet 2 0.0675 0.135 0.2025 0.27 0.3375 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.29 0.30 1. (CXX) g++ options: -O3 -pthread
oneDNN Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU Vet 1 Vet 2 11 22 33 44 55 SE +/- 0.07, N = 3 SE +/- 0.06, N = 3 48.15 49.78 MIN: 46.47 MIN: 47.68 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
oneDNN Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU Vet 1 Vet 2 1.334 2.668 4.002 5.336 6.67 SE +/- 0.00798, N = 3 SE +/- 0.01645, N = 3 5.74220 5.92877 MIN: 5.23 MIN: 5.41 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
Node.js V8 Web Tooling Benchmark OpenBenchmarking.org runs/s, More Is Better Node.js V8 Web Tooling Benchmark Vet 1 Vet 2 1.1948 2.3896 3.5844 4.7792 5.974 SE +/- 0.02, N = 3 SE +/- 0.07, N = 3 5.31 5.15 1. Nodejs
v12.18.2
NCNN Target: CPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: blazeface Vet 1 Vet 2 1.0238 2.0476 3.0714 4.0952 5.119 SE +/- 0.03, N = 3 SE +/- 0.05, N = 3 4.55 4.43 MIN: 3.95 / MAX: 18.03 MIN: 3.96 / MAX: 22.46 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Redis Test: SET OpenBenchmarking.org Requests Per Second, More Is Better Redis 6.0.9 Test: SET Vet 1 Vet 2 200K 400K 600K 800K 1000K SE +/- 6967.52, N = 3 SE +/- 11513.44, N = 3 1077335.42 1106164.79 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
Darktable Test: Boat - Acceleration: CPU-only OpenBenchmarking.org Seconds, Fewer Is Better Darktable 3.2.1 Test: Boat - Acceleration: CPU-only Vet 1 Vet 2 8 16 24 32 40 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 35.37 36.31
NCNN Target: CPU - Model: shufflenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: shufflenet-v2 Vet 1 Vet 2 5 10 15 20 25 SE +/- 0.10, N = 3 SE +/- 0.15, N = 3 18.80 18.33 MIN: 16.63 / MAX: 34.89 MIN: 16.43 / MAX: 32.5 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
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 Vet 1 Vet 2 130K 260K 390K 520K 650K SE +/- 4437.95, N = 3 SE +/- 8990.08, N = 12 594226.4 579620.2
oneDNN Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU Vet 1 Vet 2 6 12 18 24 30 SE +/- 0.13, N = 3 SE +/- 0.08, N = 3 24.07 24.68 MIN: 23.42 MIN: 23.97 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
Darktable Test: Server Rack - Acceleration: CPU-only OpenBenchmarking.org Seconds, Fewer Is Better Darktable 3.2.1 Test: Server Rack - Acceleration: CPU-only Vet 1 Vet 2 0.1132 0.2264 0.3396 0.4528 0.566 SE +/- 0.001, N = 3 SE +/- 0.001, N = 3 0.491 0.503
Stockfish Total Time OpenBenchmarking.org Nodes Per Second, More Is Better Stockfish 12 Total Time Vet 1 Vet 2 1.5M 3M 4.5M 6M 7.5M SE +/- 92057.35, N = 3 SE +/- 53835.86, N = 13 6971484 6814594 1. (CXX) g++ options: -m64 -lpthread -fno-exceptions -std=c++17 -pedantic -O3 -msse -msse3 -mpopcnt -msse4.1 -mssse3 -msse2 -flto -flto=jobserver
WebP Image Encode Encode Settings: Quality 100, Lossless OpenBenchmarking.org Encode Time - Seconds, Fewer Is Better WebP Image Encode 1.1 Encode Settings: Quality 100, Lossless Vet 1 Vet 2 7 14 21 28 35 SE +/- 0.04, N = 3 SE +/- 0.18, N = 3 30.65 30.03 1. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff
LuxCoreRender Scene: Rainbow Colors and Prism OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.3 Scene: Rainbow Colors and Prism Vet 1 Vet 2 0.117 0.234 0.351 0.468 0.585 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 0.52 0.51 MIN: 0.49 / MAX: 0.58 MIN: 0.49 / MAX: 0.58
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 Vet 1 Vet 2 150K 300K 450K 600K 750K SE +/- 7598.50, N = 5 SE +/- 7227.41, N = 5 721348.2 707886.5
oneDNN Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU Vet 1 Vet 2 9 18 27 36 45 SE +/- 0.11, N = 3 SE +/- 0.14, N = 3 38.91 38.23 MIN: 36.73 MIN: 35.84 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
Mobile Neural Network Model: inception-v3 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2020-09-17 Model: inception-v3 Vet 1 Vet 2 300 600 900 1200 1500 SE +/- 16.11, N = 3 SE +/- 2.29, N = 3 1344.89 1325.20 MIN: 1285.6 / MAX: 1579.75 MIN: 1283.55 / MAX: 1801.49 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
Stress-NG Test: MEMFD OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: MEMFD Vet 1 Vet 2 30 60 90 120 150 SE +/- 0.95, N = 3 SE +/- 0.92, N = 3 127.99 126.33 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
Redis Test: LPUSH OpenBenchmarking.org Requests Per Second, More Is Better Redis 6.0.9 Test: LPUSH Vet 1 Vet 2 200K 400K 600K 800K 1000K SE +/- 8135.45, N = 3 SE +/- 9548.09, N = 4 806438.96 796182.64 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
LeelaChessZero Backend: BLAS OpenBenchmarking.org Nodes Per Second, More Is Better LeelaChessZero 0.26 Backend: BLAS Vet 1 Vet 2 40 80 120 160 200 SE +/- 0.58, N = 3 SE +/- 0.67, N = 3 160 158 1. (CXX) g++ options: -flto -pthread
Warsow Resolution: 1920 x 1080 OpenBenchmarking.org Frames Per Second, More Is Better Warsow 2.5 Beta Resolution: 1920 x 1080 Vet 1 Vet 2 30 60 90 120 150 SE +/- 1.92, N = 3 SE +/- 0.23, N = 3 143.7 145.5
Mobile Neural Network Model: SqueezeNetV1.0 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2020-09-17 Model: SqueezeNetV1.0 Vet 1 Vet 2 40 80 120 160 200 SE +/- 2.02, N = 3 SE +/- 0.77, N = 3 159.81 157.85 MIN: 150.79 / MAX: 263.93 MIN: 151.35 / MAX: 262.21 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
OpenVKL Benchmark: vklBenchmark OpenBenchmarking.org Items / Sec, More Is Better OpenVKL 0.9 Benchmark: vklBenchmark Vet 1 Vet 2 8 16 24 32 40 SE +/- 0.10, N = 3 SE +/- 0.08, N = 3 32.27 32.67 MIN: 1 / MAX: 76 MIN: 1 / MAX: 77
libavif avifenc Encoder Speed: 2 OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.7.3 Encoder Speed: 2 Vet 1 Vet 2 40 80 120 160 200 SE +/- 1.23, N = 3 SE +/- 1.16, N = 3 168.71 166.70 1. (CXX) g++ options: -O3 -fPIC
Timed Eigen Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Eigen Compilation 3.3.9 Time To Compile Vet 1 Vet 2 30 60 90 120 150 SE +/- 0.17, N = 3 SE +/- 1.80, N = 3 134.66 136.25
PHPBench PHP Benchmark Suite OpenBenchmarking.org Score, More Is Better PHPBench 0.8.1 PHP Benchmark Suite Vet 1 Vet 2 90K 180K 270K 360K 450K SE +/- 4041.48, N = 12 SE +/- 1456.68, N = 3 415846 420714
Cryptsetup Twofish-XTS 256b Decryption OpenBenchmarking.org MiB/s, More Is Better Cryptsetup Twofish-XTS 256b Decryption Vet 1 Vet 2 50 100 150 200 250 SE +/- 4.37, N = 3 SE +/- 1.82, N = 3 242.7 245.5
LZ4 Compression Compression Level: 1 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better LZ4 Compression 1.9.3 Compression Level: 1 - Decompression Speed Vet 1 Vet 2 800 1600 2400 3200 4000 SE +/- 4.86, N = 3 SE +/- 9.10, N = 3 3697.1 3657.2 1. (CC) gcc options: -O3
x265 Video Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better x265 3.4 Video Input: Bosphorus 1080p Vet 1 Vet 2 5 10 15 20 25 SE +/- 0.04, N = 3 SE +/- 0.08, N = 3 19.52 19.32 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
IndigoBench Acceleration: CPU - Scene: Bedroom OpenBenchmarking.org M samples/s, More Is Better IndigoBench 4.4 Acceleration: CPU - Scene: Bedroom Vet 1 Vet 2 0.1103 0.2206 0.3309 0.4412 0.5515 SE +/- 0.002, N = 3 SE +/- 0.003, N = 3 0.490 0.485
Kvazaar Video Input: Bosphorus 4K - Video Preset: Ultra Fast OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.0 Video Input: Bosphorus 4K - Video Preset: Ultra Fast Vet 1 Vet 2 0.6705 1.341 2.0115 2.682 3.3525 SE +/- 0.04, N = 4 SE +/- 0.00, N = 3 2.95 2.98 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
NCNN Target: CPU-v2-v2 - Model: mobilenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU-v2-v2 - Model: mobilenet-v2 Vet 1 Vet 2 6 12 18 24 30 SE +/- 0.09, N = 3 SE +/- 0.09, N = 3 25.05 24.80 MIN: 22.78 / MAX: 36.55 MIN: 23.05 / MAX: 35.19 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
oneDNN Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU Vet 1 Vet 2 8 16 24 32 40 SE +/- 0.06, N = 3 SE +/- 0.08, N = 3 32.62 32.93 MIN: 31.6 MIN: 31.78 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
Stress-NG Test: Malloc OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Malloc Vet 1 Vet 2 5M 10M 15M 20M 25M SE +/- 161586.44, N = 3 SE +/- 274937.61, N = 3 22154552.21 21949359.53 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
Timed FFmpeg Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed FFmpeg Compilation 4.2.2 Time To Compile Vet 1 Vet 2 30 60 90 120 150 SE +/- 0.84, N = 3 SE +/- 2.09, N = 12 156.34 157.77
Cryptsetup AES-XTS 256b Encryption OpenBenchmarking.org MiB/s, More Is Better Cryptsetup AES-XTS 256b Encryption Vet 1 Vet 2 200 400 600 800 1000 SE +/- 10.94, N = 3 SE +/- 3.78, N = 3 1081.7 1091.1
LZ4 Compression Compression Level: 9 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better LZ4 Compression 1.9.3 Compression Level: 9 - Decompression Speed Vet 1 Vet 2 800 1600 2400 3200 4000 SE +/- 1.08, N = 3 SE +/- 1.53, N = 3 3653.9 3622.7 1. (CC) gcc options: -O3
LZ4 Compression Compression Level: 3 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better LZ4 Compression 1.9.3 Compression Level: 3 - Decompression Speed Vet 1 Vet 2 800 1600 2400 3200 4000 SE +/- 5.46, N = 3 SE +/- 6.33, N = 3 3656.0 3625.3 1. (CC) gcc options: -O3
Stress-NG Test: Glibc Qsort Data Sorting OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Glibc Qsort Data Sorting Vet 1 Vet 2 12 24 36 48 60 SE +/- 0.40, N = 3 SE +/- 0.11, N = 3 55.09 55.53 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
Cryptsetup Twofish-XTS 512b Encryption OpenBenchmarking.org MiB/s, More Is Better Cryptsetup Twofish-XTS 512b Encryption Vet 1 Vet 2 50 100 150 200 250 SE +/- 0.96, N = 3 SE +/- 1.24, N = 3 247.2 245.3
LZ4 Compression Compression Level: 1 - Compression Speed OpenBenchmarking.org MB/s, More Is Better LZ4 Compression 1.9.3 Compression Level: 1 - Compression Speed Vet 1 Vet 2 700 1400 2100 2800 3500 SE +/- 4.52, N = 3 SE +/- 5.68, N = 3 3387.29 3362.32 1. (CC) gcc options: -O3
Mobile Neural Network Model: MobileNetV2_224 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2020-09-17 Model: MobileNetV2_224 Vet 1 Vet 2 20 40 60 80 100 SE +/- 0.30, N = 3 SE +/- 0.84, N = 3 84.92 85.55 MIN: 81.76 / MAX: 138.82 MIN: 81.09 / MAX: 142.92 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
GIMP Test: unsharp-mask OpenBenchmarking.org Seconds, Fewer Is Better GIMP 2.10.18 Test: unsharp-mask Vet 1 Vet 2 7 14 21 28 35 SE +/- 0.05, N = 3 SE +/- 0.24, N = 3 28.99 29.17
NCNN Target: CPU - Model: regnety_400m OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: regnety_400m Vet 1 Vet 2 9 18 27 36 45 SE +/- 0.31, N = 3 SE +/- 0.12, N = 3 40.24 39.99 MIN: 36.63 / MAX: 98.56 MIN: 36.36 / MAX: 56.98 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Cryptsetup Twofish-XTS 512b Decryption OpenBenchmarking.org MiB/s, More Is Better Cryptsetup Twofish-XTS 512b Decryption Vet 1 Vet 2 50 100 150 200 250 SE +/- 1.33, N = 3 SE +/- 1.39, N = 3 247.9 246.4
asmFish 1024 Hash Memory, 26 Depth OpenBenchmarking.org Nodes/second, More Is Better asmFish 2018-07-23 1024 Hash Memory, 26 Depth Vet 1 Vet 2 2M 4M 6M 8M 10M SE +/- 22277.77, N = 3 SE +/- 136672.28, N = 3 10590695 10527008
Zstd Compression Compression Level: 19 OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.4.5 Compression Level: 19 Vet 1 Vet 2 4 8 12 16 20 SE +/- 0.16, N = 12 SE +/- 0.21, N = 3 16.9 16.8 1. (CC) gcc options: -O3 -pthread -lz -llzma
Cryptsetup AES-XTS 512b Decryption OpenBenchmarking.org MiB/s, More Is Better Cryptsetup AES-XTS 512b Decryption Vet 1 Vet 2 200 400 600 800 1000 SE +/- 5.40, N = 3 SE +/- 0.07, N = 3 944.8 950.1
NCNN Target: CPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: alexnet Vet 1 Vet 2 11 22 33 44 55 SE +/- 0.08, N = 3 SE +/- 0.09, N = 3 49.72 49.99 MIN: 47.15 / MAX: 75.12 MIN: 47.21 / MAX: 77.98 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
WebP Image Encode Encode Settings: Quality 100 OpenBenchmarking.org Encode Time - Seconds, Fewer Is Better WebP Image Encode 1.1 Encode Settings: Quality 100 Vet 1 Vet 2 0.8039 1.6078 2.4117 3.2156 4.0195 SE +/- 0.010, N = 3 SE +/- 0.008, N = 3 3.573 3.554 1. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff
Redis Test: SADD OpenBenchmarking.org Requests Per Second, More Is Better Redis 6.0.9 Test: SADD Vet 1 Vet 2 300K 600K 900K 1200K 1500K SE +/- 10820.63, N = 3 SE +/- 10488.62, N = 3 1212043.04 1205601.54 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
NCNN Target: CPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: mobilenet Vet 1 Vet 2 20 40 60 80 100 SE +/- 0.24, N = 3 SE +/- 0.21, N = 3 98.29 97.78 MIN: 93.92 / MAX: 120.36 MIN: 94.04 / MAX: 112.57 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
GIMP Test: auto-levels OpenBenchmarking.org Seconds, Fewer Is Better GIMP 2.10.18 Test: auto-levels Vet 1 Vet 2 6 12 18 24 30 SE +/- 0.05, N = 3 SE +/- 0.02, N = 3 25.47 25.34
RNNoise OpenBenchmarking.org Seconds, Fewer Is Better RNNoise 2020-06-28 Vet 1 Vet 2 11 22 33 44 55 SE +/- 0.65, N = 3 SE +/- 0.62, N = 3 47.77 47.54 1. (CC) gcc options: -O2 -pedantic -fvisibility=hidden
WebP Image Encode Encode Settings: Default OpenBenchmarking.org Encode Time - Seconds, Fewer Is Better WebP Image Encode 1.1 Encode Settings: Default Vet 1 Vet 2 0.5499 1.0998 1.6497 2.1996 2.7495 SE +/- 0.005, N = 3 SE +/- 0.006, N = 3 2.444 2.433 1. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff
Stress-NG Test: CPU Stress OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: CPU Stress Vet 1 Vet 2 400 800 1200 1600 2000 SE +/- 6.19, N = 3 SE +/- 16.57, N = 3 1823.75 1831.98 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
Stress-NG Test: Forking OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Forking Vet 1 Vet 2 4K 8K 12K 16K 20K SE +/- 48.99, N = 3 SE +/- 143.47, N = 3 18452.92 18535.23 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
NCNN Target: CPU-v3-v3 - Model: mobilenet-v3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU-v3-v3 - Model: mobilenet-v3 Vet 1 Vet 2 6 12 18 24 30 SE +/- 0.06, N = 3 SE +/- 0.04, N = 3 23.00 23.10 MIN: 21.42 / MAX: 41.88 MIN: 21.25 / MAX: 39.1 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
oneDNN Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU Vet 1 Vet 2 5 10 15 20 25 SE +/- 0.07, N = 3 SE +/- 0.03, N = 3 21.63 21.53 MIN: 19.96 MIN: 20.01 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
Stress-NG Test: Crypto OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Crypto Vet 1 Vet 2 200 400 600 800 1000 SE +/- 1.19, N = 3 SE +/- 0.06, N = 3 872.89 869.13 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
GIMP Test: rotate OpenBenchmarking.org Seconds, Fewer Is Better GIMP 2.10.18 Test: rotate Vet 1 Vet 2 6 12 18 24 30 SE +/- 0.05, N = 3 SE +/- 0.05, N = 3 24.24 24.14
Stress-NG Test: Socket Activity OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Socket Activity Vet 1 Vet 2 400 800 1200 1600 2000 SE +/- 7.16, N = 3 SE +/- 6.82, N = 3 1776.16 1783.24 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
Darktable Test: Masskrug - Acceleration: CPU-only OpenBenchmarking.org Seconds, Fewer Is Better Darktable 3.2.1 Test: Masskrug - Acceleration: CPU-only Vet 1 Vet 2 7 14 21 28 35 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 28.64 28.75
Cryptsetup Serpent-XTS 256b Decryption OpenBenchmarking.org MiB/s, More Is Better Cryptsetup Serpent-XTS 256b Decryption Vet 1 Vet 2 70 140 210 280 350 SE +/- 0.50, N = 3 SE +/- 2.43, N = 3 320.2 319.0
libavif avifenc Encoder Speed: 8 OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.7.3 Encoder Speed: 8 Vet 1 Vet 2 3 6 9 12 15 SE +/- 0.11, N = 3 SE +/- 0.10, N = 3 12.86 12.81 1. (CXX) g++ options: -O3 -fPIC
Cryptsetup AES-XTS 256b Decryption OpenBenchmarking.org MiB/s, More Is Better Cryptsetup AES-XTS 256b Decryption Vet 1 Vet 2 200 400 600 800 1000 SE +/- 5.61, N = 3 SE +/- 3.99, N = 3 1093.6 1089.7
Cryptsetup Serpent-XTS 256b Encryption OpenBenchmarking.org MiB/s, More Is Better Cryptsetup Serpent-XTS 256b Encryption Vet 1 Vet 2 70 140 210 280 350 SE +/- 1.25, N = 3 SE +/- 3.18, N = 3 312.0 310.9
Stress-NG Test: Atomic OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Atomic Vet 1 Vet 2 12K 24K 36K 48K 60K SE +/- 32.93, N = 3 SE +/- 114.37, N = 3 54519.87 54711.61 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
YafaRay Total Time For Sample Scene OpenBenchmarking.org Seconds, Fewer Is Better YafaRay 3.4.1 Total Time For Sample Scene Vet 1 Vet 2 100 200 300 400 500 SE +/- 0.95, N = 3 SE +/- 1.55, N = 3 439.47 437.99 1. (CXX) g++ options: -std=c++11 -O3 -ffast-math -rdynamic -ldl -lImath -lIlmImf -lIex -lHalf -lz -lIlmThread -lxml2 -lfreetype -lpthread
WebP Image Encode Encode Settings: Quality 100, Lossless, Highest Compression OpenBenchmarking.org Encode Time - Seconds, Fewer Is Better WebP Image Encode 1.1 Encode Settings: Quality 100, Lossless, Highest Compression Vet 1 Vet 2 15 30 45 60 75 SE +/- 0.20, N = 3 SE +/- 0.06, N = 3 66.56 66.78 1. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff
libavif avifenc Encoder Speed: 10 OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.7.3 Encoder Speed: 10 Vet 1 Vet 2 3 6 9 12 15 SE +/- 0.07, N = 3 SE +/- 0.04, N = 3 11.90 11.86 1. (CXX) g++ options: -O3 -fPIC
rav1e Speed: 5 OpenBenchmarking.org Frames Per Second, More Is Better rav1e 0.4 Alpha Speed: 5 Vet 1 Vet 2 0.0725 0.145 0.2175 0.29 0.3625 SE +/- 0.000, N = 3 SE +/- 0.001, N = 3 0.322 0.321
Caffe Model: AlexNet - Acceleration: CPU - Iterations: 100 OpenBenchmarking.org Milli-Seconds, Fewer Is Better Caffe 2020-02-13 Model: AlexNet - Acceleration: CPU - Iterations: 100 Vet 1 Vet 2 15K 30K 45K 60K 75K SE +/- 204.80, N = 3 SE +/- 73.54, N = 3 71021 70801 1. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas
DeepSpeech Acceleration: CPU OpenBenchmarking.org Seconds, Fewer Is Better DeepSpeech 0.6 Acceleration: CPU Vet 1 Vet 2 60 120 180 240 300 SE +/- 1.20, N = 3 SE +/- 1.12, N = 3 287.01 286.13
Mobile Neural Network Model: resnet-v2-50 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2020-09-17 Model: resnet-v2-50 Vet 1 Vet 2 200 400 600 800 1000 SE +/- 2.09, N = 3 SE +/- 2.75, N = 3 1131.68 1128.31 MIN: 1108.54 / MAX: 1212.22 MIN: 1107.01 / MAX: 1197.55 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
Stress-NG Test: System V Message Passing OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: System V Message Passing Vet 1 Vet 2 500K 1000K 1500K 2000K 2500K SE +/- 5483.77, N = 3 SE +/- 6160.98, N = 3 2212153.79 2206047.98 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
oneDNN Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU Vet 1 Vet 2 30 60 90 120 150 SE +/- 0.07, N = 3 SE +/- 0.24, N = 3 113.86 114.16 MIN: 111.71 MIN: 111.81 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
LAMMPS Molecular Dynamics Simulator Model: Rhodopsin Protein OpenBenchmarking.org ns/day, More Is Better LAMMPS Molecular Dynamics Simulator 29Oct2020 Model: Rhodopsin Protein Vet 1 Vet 2 0.3407 0.6814 1.0221 1.3628 1.7035 SE +/- 0.015, N = 15 SE +/- 0.007, N = 3 1.514 1.510 1. (CXX) g++ options: -O3 -pthread -lm
x264 H.264 Video Encoding OpenBenchmarking.org Frames Per Second, More Is Better x264 2019-12-17 H.264 Video Encoding Vet 1 Vet 2 7 14 21 28 35 SE +/- 0.22, N = 11 SE +/- 0.27, N = 7 30.29 30.21 1. (CC) gcc options: -ldl -lavformat -lavcodec -lavutil -lswscale -m64 -lm -lpthread -O3 -ffast-math -std=gnu99 -fPIC -fomit-frame-pointer -fno-tree-vectorize
oneDNN Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU Vet 1 Vet 2 3 6 9 12 15 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 10.22 10.20 MIN: 9.53 MIN: 9.52 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
NCNN Target: CPU - Model: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: yolov4-tiny Vet 1 Vet 2 40 80 120 160 200 SE +/- 0.34, N = 3 SE +/- 0.27, N = 3 201.70 202.21 MIN: 197.09 / MAX: 225.22 MIN: 197.31 / MAX: 217.34 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Cryptsetup Serpent-XTS 512b Decryption OpenBenchmarking.org MiB/s, More Is Better Cryptsetup Serpent-XTS 512b Decryption Vet 1 Vet 2 70 140 210 280 350 SE +/- 6.70, N = 2 SE +/- 2.67, N = 3 316.4 317.2
Cryptsetup PBKDF2-whirlpool OpenBenchmarking.org Iterations Per Second, More Is Better Cryptsetup PBKDF2-whirlpool Vet 1 Vet 2 80K 160K 240K 320K 400K SE +/- 1238.75, N = 3 SE +/- 1763.06, N = 3 395398 394414
IndigoBench Acceleration: CPU - Scene: Supercar OpenBenchmarking.org M samples/s, More Is Better IndigoBench 4.4 Acceleration: CPU - Scene: Supercar Vet 1 Vet 2 0.2723 0.5446 0.8169 1.0892 1.3615 SE +/- 0.003, N = 3 SE +/- 0.007, N = 3 1.210 1.207
Coremark CoreMark Size 666 - Iterations Per Second OpenBenchmarking.org Iterations/Sec, More Is Better Coremark 1.0 CoreMark Size 666 - Iterations Per Second Vet 1 Vet 2 30K 60K 90K 120K 150K SE +/- 563.65, N = 3 SE +/- 243.76, N = 3 122656.51 122356.31 1. (CC) gcc options: -O2 -lrt" -lrt
Stress-NG Test: Glibc C String Functions OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Glibc C String Functions Vet 1 Vet 2 60K 120K 180K 240K 300K SE +/- 202.00, N = 3 SE +/- 439.83, N = 3 267246.20 266600.95 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
rav1e Speed: 6 OpenBenchmarking.org Frames Per Second, More Is Better rav1e 0.4 Alpha Speed: 6 Vet 1 Vet 2 0.0936 0.1872 0.2808 0.3744 0.468 SE +/- 0.000, N = 3 SE +/- 0.001, N = 3 0.416 0.415
Caffe Model: GoogleNet - Acceleration: CPU - Iterations: 100 OpenBenchmarking.org Milli-Seconds, Fewer Is Better Caffe 2020-02-13 Model: GoogleNet - Acceleration: CPU - Iterations: 100 Vet 1 Vet 2 40K 80K 120K 160K 200K SE +/- 126.85, N = 3 SE +/- 98.17, N = 3 177755 178137 1. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas
Timed Linux Kernel Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Linux Kernel Compilation 5.4 Time To Compile Vet 1 Vet 2 60 120 180 240 300 SE +/- 0.89, N = 3 SE +/- 1.18, N = 3 252.49 251.96
Stress-NG Test: SENDFILE OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: SENDFILE Vet 1 Vet 2 11K 22K 33K 44K 55K SE +/- 40.91, N = 3 SE +/- 19.61, N = 3 50924.75 50818.29 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
Basis Universal Settings: UASTC Level 2 + RDO Post-Processing OpenBenchmarking.org Seconds, Fewer Is Better Basis Universal 1.12 Settings: UASTC Level 2 + RDO Post-Processing Vet 1 Vet 2 200 400 600 800 1000 SE +/- 9.83, N = 9 SE +/- 7.10, N = 3 1121.06 1118.93 1. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
Basis Universal Settings: UASTC Level 2 OpenBenchmarking.org Seconds, Fewer Is Better Basis Universal 1.12 Settings: UASTC Level 2 Vet 1 Vet 2 20 40 60 80 100 SE +/- 0.13, N = 3 SE +/- 0.04, N = 3 88.18 88.01 1. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
GIMP Test: resize OpenBenchmarking.org Seconds, Fewer Is Better GIMP 2.10.18 Test: resize Vet 1 Vet 2 5 10 15 20 25 SE +/- 0.16, N = 3 SE +/- 0.17, N = 3 18.96 18.99
Opus Codec Encoding WAV To Opus Encode OpenBenchmarking.org Seconds, Fewer Is Better Opus Codec Encoding 1.3.1 WAV To Opus Encode Vet 1 Vet 2 4 8 12 16 20 SE +/- 0.03, N = 5 SE +/- 0.03, N = 5 15.71 15.74 1. (CXX) g++ options: -fvisibility=hidden -logg -lm
7-Zip Compression Compress Speed Test OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 16.02 Compress Speed Test Vet 1 Vet 2 5K 10K 15K 20K 25K SE +/- 14.62, N = 3 SE +/- 34.22, N = 3 21231 21195 1. (CXX) g++ options: -pipe -lpthread
LZ4 Compression Compression Level: 9 - Compression Speed OpenBenchmarking.org MB/s, More Is Better LZ4 Compression 1.9.3 Compression Level: 9 - Compression Speed Vet 1 Vet 2 7 14 21 28 35 SE +/- 0.06, N = 3 SE +/- 0.04, N = 3 29.81 29.86 1. (CC) gcc options: -O3
Stress-NG Test: Memory Copying OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Memory Copying Vet 1 Vet 2 200 400 600 800 1000 SE +/- 2.90, N = 3 SE +/- 2.16, N = 3 1002.06 1003.73 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
Hugin Panorama Photo Assistant + Stitching Time OpenBenchmarking.org Seconds, Fewer Is Better Hugin Panorama Photo Assistant + Stitching Time Vet 1 Vet 2 20 40 60 80 100 SE +/- 0.45, N = 3 SE +/- 1.14, N = 3 105.81 105.65
SQLite Speedtest Timed Time - Size 1,000 OpenBenchmarking.org Seconds, Fewer Is Better SQLite Speedtest 3.30 Timed Time - Size 1,000 Vet 1 Vet 2 30 60 90 120 150 SE +/- 0.33, N = 3 SE +/- 0.40, N = 3 122.13 122.30 1. (CC) gcc options: -O2 -ldl -lz -lpthread
Basis Universal Settings: ETC1S OpenBenchmarking.org Seconds, Fewer Is Better Basis Universal 1.12 Settings: ETC1S Vet 1 Vet 2 20 40 60 80 100 SE +/- 0.16, N = 3 SE +/- 0.39, N = 3 104.18 104.33 1. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
Stress-NG Test: NUMA OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: NUMA Vet 1 Vet 2 20 40 60 80 100 SE +/- 0.28, N = 3 SE +/- 0.62, N = 3 84.19 84.08 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
Timed GDB GNU Debugger Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed GDB GNU Debugger Compilation 9.1 Time To Compile Vet 1 Vet 2 50 100 150 200 250 SE +/- 0.19, N = 3 SE +/- 0.15, N = 3 231.26 230.97
NCNN Target: CPU - Model: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: efficientnet-b0 Vet 1 Vet 2 9 18 27 36 45 SE +/- 0.14, N = 3 SE +/- 0.20, N = 3 39.88 39.93 MIN: 37.27 / MAX: 56.04 MIN: 37.28 / MAX: 54.83 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
FLAC Audio Encoding WAV To FLAC OpenBenchmarking.org Seconds, Fewer Is Better FLAC Audio Encoding 1.3.2 WAV To FLAC Vet 1 Vet 2 4 8 12 16 20 SE +/- 0.04, N = 5 SE +/- 0.06, N = 5 16.93 16.91 1. (CXX) g++ options: -O2 -fvisibility=hidden -logg -lm
oneDNN Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU Vet 1 Vet 2 10K 20K 30K 40K 50K SE +/- 13.80, N = 3 SE +/- 2.68, N = 3 44728.9 44784.2 MIN: 44551.4 MIN: 44656.6 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
Basis Universal Settings: UASTC Level 0 OpenBenchmarking.org Seconds, Fewer Is Better Basis Universal 1.12 Settings: UASTC Level 0 Vet 1 Vet 2 4 8 12 16 20 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 14.90 14.89 1. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
librsvg Operation: SVG Files To PNG OpenBenchmarking.org Seconds, Fewer Is Better librsvg Operation: SVG Files To PNG Vet 1 Vet 2 10 20 30 40 50 SE +/- 0.10, N = 3 SE +/- 0.13, N = 3 43.32 43.38 1. rsvg-convert version 2.50.1
libavif avifenc Encoder Speed: 0 OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.7.3 Encoder Speed: 0 Vet 1 Vet 2 60 120 180 240 300 SE +/- 0.68, N = 3 SE +/- 0.50, N = 3 275.52 275.21 1. (CXX) g++ options: -O3 -fPIC
Cryptsetup PBKDF2-sha512 OpenBenchmarking.org Iterations Per Second, More Is Better Cryptsetup PBKDF2-sha512 Vet 1 Vet 2 300K 600K 900K 1200K 1500K SE +/- 3710.07, N = 3 SE +/- 9354.11, N = 3 1273595 1272166
OCRMyPDF Processing 60 Page PDF Document OpenBenchmarking.org Seconds, Fewer Is Better OCRMyPDF 10.3.1+dfsg Processing 60 Page PDF Document Vet 1 Vet 2 14 28 42 56 70 SE +/- 0.15, N = 3 SE +/- 0.34, N = 3 62.37 62.44
rays1bench Large Scene OpenBenchmarking.org mrays/s, More Is Better rays1bench 2020-01-09 Large Scene Vet 1 Vet 2 3 6 9 12 15 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 9.06 9.05
Timed Apache Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Apache Compilation 2.4.41 Time To Compile Vet 1 Vet 2 11 22 33 44 55 SE +/- 0.49, N = 3 SE +/- 0.22, N = 3 48.37 48.32
oneDNN Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU Vet 1 Vet 2 10K 20K 30K 40K 50K SE +/- 11.37, N = 3 SE +/- 6.26, N = 3 44739.8 44788.0 MIN: 44603 MIN: 44662.9 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
oneDNN Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU Vet 1 Vet 2 3 6 9 12 15 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 13.59 13.60 MIN: 12.65 MIN: 12.65 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
WebP Image Encode Encode Settings: Quality 100, Highest Compression OpenBenchmarking.org Encode Time - Seconds, Fewer Is Better WebP Image Encode 1.1 Encode Settings: Quality 100, Highest Compression Vet 1 Vet 2 3 6 9 12 15 SE +/- 0.05, N = 3 SE +/- 0.04, N = 3 11.41 11.40 1. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff
oneDNN Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU Vet 1 Vet 2 16 32 48 64 80 SE +/- 0.12, N = 3 SE +/- 0.09, N = 3 71.20 71.13 MIN: 68.92 MIN: 68.74 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
TensorFlow Lite Model: SqueezeNet OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: SqueezeNet Vet 1 Vet 2 110K 220K 330K 440K 550K SE +/- 78.87, N = 3 SE +/- 469.08, N = 3 512325 512833
Cryptsetup Serpent-XTS 512b Encryption OpenBenchmarking.org MiB/s, More Is Better Cryptsetup Serpent-XTS 512b Encryption Vet 1 Vet 2 70 140 210 280 350 SE +/- 0.07, N = 3 SE +/- 1.47, N = 3 315.2 314.9
oneDNN Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU Vet 1 Vet 2 5K 10K 15K 20K 25K SE +/- 7.47, N = 3 SE +/- 15.06, N = 3 22769.0 22789.7 MIN: 22649.1 MIN: 22662.3 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
oneDNN Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU Vet 1 Vet 2 10K 20K 30K 40K 50K SE +/- 4.04, N = 3 SE +/- 15.69, N = 3 44745.0 44784.5 MIN: 44611.3 MIN: 44650.3 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
LAME MP3 Encoding WAV To MP3 OpenBenchmarking.org Seconds, Fewer Is Better LAME MP3 Encoding 3.100 WAV To MP3 Vet 1 Vet 2 4 8 12 16 20 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 13.63 13.62 1. (CC) gcc options: -O3 -ffast-math -funroll-loops -fschedule-insns2 -fbranch-count-reg -fforce-addr -pipe -lm
Stress-NG Test: Matrix Math OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Matrix Math Vet 1 Vet 2 3K 6K 9K 12K 15K SE +/- 4.41, N = 3 SE +/- 2.24, N = 3 15073.34 15086.29 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
rav1e Speed: 10 OpenBenchmarking.org Frames Per Second, More Is Better rav1e 0.4 Alpha Speed: 10 Vet 1 Vet 2 0.2635 0.527 0.7905 1.054 1.3175 SE +/- 0.003, N = 3 SE +/- 0.002, N = 3 1.170 1.171
Kvazaar Video Input: Bosphorus 1080p - Video Preset: Ultra Fast OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.0 Video Input: Bosphorus 1080p - Video Preset: Ultra Fast Vet 1 Vet 2 3 6 9 12 15 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 11.84 11.85 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
Cryptsetup Twofish-XTS 256b Encryption OpenBenchmarking.org MiB/s, More Is Better Cryptsetup Twofish-XTS 256b Encryption Vet 1 Vet 2 50 100 150 200 250 SE +/- 3.08, N = 3 SE +/- 1.80, N = 3 244.1 243.9
NCNN Target: CPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: mnasnet Vet 1 Vet 2 6 12 18 24 30 SE +/- 0.04, N = 3 SE +/- 0.08, N = 3 24.69 24.71 MIN: 22.88 / MAX: 37.47 MIN: 22.88 / MAX: 34 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Timed MPlayer Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed MPlayer Compilation 1.4 Time To Compile Vet 1 Vet 2 30 60 90 120 150 SE +/- 0.12, N = 3 SE +/- 0.06, N = 3 113.04 112.95
Stress-NG Test: Vector Math OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Vector Math Vet 1 Vet 2 5K 10K 15K 20K 25K SE +/- 9.23, N = 3 SE +/- 6.13, N = 3 23898.11 23915.82 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
oneDNN Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU Vet 1 Vet 2 5K 10K 15K 20K 25K SE +/- 11.99, N = 3 SE +/- 1.32, N = 3 22758.6 22775.3 MIN: 22625.2 MIN: 22676.4 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
TensorFlow Lite Model: Mobilenet Float OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Mobilenet Float Vet 1 Vet 2 80K 160K 240K 320K 400K SE +/- 124.25, N = 3 SE +/- 235.83, N = 3 351171 351424
oneDNN Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU Vet 1 Vet 2 5K 10K 15K 20K 25K SE +/- 10.92, N = 3 SE +/- 1.49, N = 3 22771.8 22787.9 MIN: 22638.3 MIN: 22661.6 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
oneDNN Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU Vet 1 Vet 2 3 6 9 12 15 SE +/- 0.05, N = 3 SE +/- 0.03, N = 3 11.75 11.76 MIN: 10.39 MIN: 10.37 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
TensorFlow Lite Model: Inception V4 OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Inception V4 Vet 1 Vet 2 1.6M 3.2M 4.8M 6.4M 8M SE +/- 5425.43, N = 3 SE +/- 1824.37, N = 3 7343657 7348723
Mobile Neural Network Model: mobilenet-v1-1.0 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2020-09-17 Model: mobilenet-v1-1.0 Vet 1 Vet 2 40 80 120 160 200 SE +/- 0.45, N = 3 SE +/- 0.50, N = 3 169.00 168.89 MIN: 165.04 / MAX: 249.99 MIN: 164.85 / MAX: 289.14 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
Numpy Benchmark OpenBenchmarking.org Score, More Is Better Numpy Benchmark Vet 1 Vet 2 30 60 90 120 150 SE +/- 0.06, N = 3 SE +/- 0.33, N = 3 150.23 150.33
Crafty Elapsed Time OpenBenchmarking.org Nodes Per Second, More Is Better Crafty 25.2 Elapsed Time Vet 1 Vet 2 1.1M 2.2M 3.3M 4.4M 5.5M SE +/- 522.74, N = 3 SE +/- 11611.33, N = 3 5195271 5198696 1. (CC) gcc options: -pthread -lstdc++ -fprofile-use -lm
LZ4 Compression Compression Level: 3 - Compression Speed OpenBenchmarking.org MB/s, More Is Better LZ4 Compression 1.9.3 Compression Level: 3 - Compression Speed Vet 1 Vet 2 7 14 21 28 35 SE +/- 0.02, N = 3 SE +/- 0.07, N = 3 30.96 30.94 1. (CC) gcc options: -O3
Cryptsetup AES-XTS 512b Encryption OpenBenchmarking.org MiB/s, More Is Better Cryptsetup AES-XTS 512b Encryption Vet 1 Vet 2 200 400 600 800 1000 SE +/- 2.47, N = 3 SE +/- 5.29, N = 3 943.8 944.4
John The Ripper Test: MD5 OpenBenchmarking.org Real C/S, More Is Better John The Ripper 1.9.0-jumbo-1 Test: MD5 Vet 1 Vet 2 50K 100K 150K 200K 250K SE +/- 72.37, N = 3 SE +/- 146.86, N = 3 256221 256381 1. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -pthread -lm -lz -ldl -lcrypt
Build2 Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Build2 0.13 Time To Compile Vet 1 Vet 2 90 180 270 360 450 SE +/- 2.77, N = 3 SE +/- 2.02, N = 3 392.48 392.28
NCNN Target: CPU - Model: resnet50 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: resnet50 Vet 1 Vet 2 50 100 150 200 250 SE +/- 0.15, N = 3 SE +/- 0.29, N = 3 211.76 211.65 MIN: 205.66 / MAX: 235.93 MIN: 206.15 / MAX: 234.2 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
TensorFlow Lite Model: NASNet Mobile OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: NASNet Mobile Vet 1 Vet 2 80K 160K 240K 320K 400K SE +/- 325.92, N = 3 SE +/- 57.94, N = 3 383504 383701
NCNN Target: CPU - Model: googlenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: googlenet Vet 1 Vet 2 20 40 60 80 100 SE +/- 0.10, N = 3 SE +/- 0.16, N = 3 99.74 99.69 MIN: 95.23 / MAX: 114.59 MIN: 95.68 / MAX: 117.36 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: squeezenet_ssd OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: squeezenet_ssd Vet 1 Vet 2 20 40 60 80 100 SE +/- 0.20, N = 3 SE +/- 0.21, N = 3 103.79 103.84 MIN: 97.27 / MAX: 120.35 MIN: 96.54 / MAX: 140.32 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Stress-NG Test: Semaphores OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Semaphores Vet 1 Vet 2 110K 220K 330K 440K 550K SE +/- 6.77, N = 3 SE +/- 151.49, N = 3 505610.19 505851.94 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
TensorFlow Lite Model: Mobilenet Quant OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Mobilenet Quant Vet 1 Vet 2 80K 160K 240K 320K 400K SE +/- 293.40, N = 3 SE +/- 50.50, N = 3 357144 357312
TNN Target: CPU - Model: SqueezeNet v1.1 OpenBenchmarking.org ms, Fewer Is Better TNN 0.2.3 Target: CPU - Model: SqueezeNet v1.1 Vet 1 Vet 2 110 220 330 440 550 SE +/- 0.29, N = 3 SE +/- 0.39, N = 3 513.82 513.59 MIN: 510.88 / MAX: 517.71 MIN: 509.34 / MAX: 530.2 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -O3 -rdynamic -ldl
NCNN Target: CPU - Model: resnet18 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: resnet18 Vet 1 Vet 2 20 40 60 80 100 SE +/- 0.16, N = 3 SE +/- 0.03, N = 3 91.23 91.27 MIN: 88.35 / MAX: 106.84 MIN: 88.86 / MAX: 108.88 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Monkey Audio Encoding WAV To APE OpenBenchmarking.org Seconds, Fewer Is Better Monkey Audio Encoding 3.99.6 WAV To APE Vet 1 Vet 2 6 12 18 24 30 SE +/- 0.08, N = 5 SE +/- 0.06, N = 5 26.40 26.39 1. (CXX) g++ options: -O3 -pedantic -rdynamic -lrt
WavPack Audio Encoding WAV To WavPack OpenBenchmarking.org Seconds, Fewer Is Better WavPack Audio Encoding 5.3 WAV To WavPack Vet 1 Vet 2 6 12 18 24 30 SE +/- 0.05, N = 5 SE +/- 0.08, N = 5 22.97 22.97 1. (CXX) g++ options: -rdynamic
TNN Target: CPU - Model: MobileNet v2 OpenBenchmarking.org ms, Fewer Is Better TNN 0.2.3 Target: CPU - Model: MobileNet v2 Vet 1 Vet 2 110 220 330 440 550 SE +/- 0.75, N = 3 SE +/- 0.14, N = 3 528.35 528.55 MIN: 519.59 / MAX: 546.48 MIN: 518.27 / MAX: 548.78 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -O3 -rdynamic -ldl
oneDNN Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU Vet 1 Vet 2 5 10 15 20 25 SE +/- 0.02, N = 3 SE +/- 0.07, N = 3 22.21 22.20 MIN: 21.47 MIN: 21.45 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
John The Ripper Test: Blowfish OpenBenchmarking.org Real C/S, More Is Better John The Ripper 1.9.0-jumbo-1 Test: Blowfish Vet 1 Vet 2 1400 2800 4200 5600 7000 SE +/- 3.48, N = 3 SE +/- 1.33, N = 3 6411 6409 1. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -pthread -lm -lz -ldl -lcrypt
Timed HMMer Search Pfam Database Search OpenBenchmarking.org Seconds, Fewer Is Better Timed HMMer Search 3.3.1 Pfam Database Search Vet 1 Vet 2 40 80 120 160 200 SE +/- 0.11, N = 3 SE +/- 0.44, N = 3 191.72 191.67 1. (CC) gcc options: -O3 -pthread -lhmmer -leasel -lm
RawTherapee Total Benchmark Time OpenBenchmarking.org Seconds, Fewer Is Better RawTherapee Total Benchmark Time Vet 1 Vet 2 30 60 90 120 150 SE +/- 0.27, N = 3 SE +/- 0.13, N = 3 138.97 139.01 1. RawTherapee, version 5.8, command line.
NCNN Target: CPU - Model: vgg16 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: vgg16 Vet 1 Vet 2 170 340 510 680 850 SE +/- 0.31, N = 3 SE +/- 0.31, N = 3 767.38 767.18 MIN: 748.84 / MAX: 812.65 MIN: 749.76 / MAX: 809.52 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
TensorFlow Lite Model: Inception ResNet V2 OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Inception ResNet V2 Vet 1 Vet 2 1.4M 2.8M 4.2M 5.6M 7M SE +/- 401.43, N = 3 SE +/- 1881.66, N = 3 6618533 6619900
Darktable Test: Server Room - Acceleration: CPU-only OpenBenchmarking.org Seconds, Fewer Is Better Darktable 3.2.1 Test: Server Room - Acceleration: CPU-only Vet 1 Vet 2 6 12 18 24 30 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 26.73 26.73
Zstd Compression Compression Level: 3 OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.4.5 Compression Level: 3 Vet 1 Vet 2 400 800 1200 1600 2000 SE +/- 1.21, N = 3 SE +/- 0.65, N = 3 1745.5 1745.6 1. (CC) gcc options: -O3 -pthread -lz -llzma
GROMACS Water Benchmark OpenBenchmarking.org Ns Per Day, More Is Better GROMACS 2020.3 Water Benchmark Vet 1 Vet 2 0.0167 0.0334 0.0501 0.0668 0.0835 SE +/- 0.000, N = 3 SE +/- 0.000, N = 3 0.074 0.074 1. (CXX) g++ options: -O3 -pthread -lrt -lpthread -lm
Intel Open Image Denoise Scene: Memorial OpenBenchmarking.org Images / Sec, More Is Better Intel Open Image Denoise 1.2.0 Scene: Memorial Vet 1 Vet 2 0.1958 0.3916 0.5874 0.7832 0.979 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.87 0.87
x265 Video Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better x265 3.4 Video Input: Bosphorus 4K Vet 1 Vet 2 1.0238 2.0476 3.0714 4.0952 5.119 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 4.55 4.55 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
rav1e Speed: 1 OpenBenchmarking.org Frames Per Second, More Is Better rav1e 0.4 Alpha Speed: 1 Vet 1 Vet 2 0.0259 0.0518 0.0777 0.1036 0.1295 SE +/- 0.000, N = 3 SE +/- 0.000, N = 3 0.115 0.115
Kvazaar Video Input: Bosphorus 1080p - Video Preset: Very Fast OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.0 Video Input: Bosphorus 1080p - Video Preset: Very Fast Vet 1 Vet 2 1.2488 2.4976 3.7464 4.9952 6.244 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 5.55 5.55 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
Kvazaar Video Input: Bosphorus 4K - Video Preset: Very Fast OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.0 Video Input: Bosphorus 4K - Video Preset: Very Fast Vet 1 Vet 2 0.3038 0.6076 0.9114 1.2152 1.519 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 1.35 1.35 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
Kvazaar Video Input: Bosphorus 1080p - Video Preset: Medium OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.0 Video Input: Bosphorus 1080p - Video Preset: Medium Vet 1 Vet 2 0.4703 0.9406 1.4109 1.8812 2.3515 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 2.09 2.09 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
Kvazaar Video Input: Bosphorus 4K - Video Preset: Medium OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.0 Video Input: Bosphorus 4K - Video Preset: Medium Vet 1 Vet 2 0.1013 0.2026 0.3039 0.4052 0.5065 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.45 0.45 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
LibRaw Post-Processing Benchmark OpenBenchmarking.org Mpix/sec, More Is Better LibRaw 0.20 Post-Processing Benchmark Vet 1 Vet 2 4 8 12 16 20 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 17.99 17.99 1. (CXX) g++ options: -O2 -fopenmp -ljpeg -lz -lm
simdjson Throughput Test: DistinctUserID OpenBenchmarking.org GB/s, More Is Better simdjson 0.7.1 Throughput Test: DistinctUserID Vet 1 Vet 2 0.0855 0.171 0.2565 0.342 0.4275 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.38 0.38 1. (CXX) g++ options: -O3 -pthread
simdjson Throughput Test: PartialTweets OpenBenchmarking.org GB/s, More Is Better simdjson 0.7.1 Throughput Test: PartialTweets Vet 1 Vet 2 0.0833 0.1666 0.2499 0.3332 0.4165 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.37 0.37 1. (CXX) g++ options: -O3 -pthread
simdjson Throughput Test: LargeRandom OpenBenchmarking.org GB/s, More Is Better simdjson 0.7.1 Throughput Test: LargeRandom Vet 1 Vet 2 0.054 0.108 0.162 0.216 0.27 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.24 0.24 1. (CXX) g++ options: -O3 -pthread
LeelaChessZero Backend: Eigen OpenBenchmarking.org Nodes Per Second, More Is Better LeelaChessZero 0.26 Backend: Eigen Vet 1 Vet 2 30 60 90 120 150 SE +/- 1.20, N = 3 138 138 1. (CXX) g++ options: -flto -pthread
GLmark2 Resolution: 1920 x 1080 OpenBenchmarking.org Score, More Is Better GLmark2 2020.04 Resolution: 1920 x 1080 Vet 1 Vet 2 300 600 900 1200 1500 1322 1322
Unpacking Firefox Extracting: firefox-84.0.source.tar.xz OpenBenchmarking.org Seconds, Fewer Is Better Unpacking Firefox 84.0 Extracting: firefox-84.0.source.tar.xz Vet 1 Vet 2 9 18 27 36 45 SE +/- 1.07, N = 20 SE +/- 2.01, N = 16 32.99 38.11
Stress-NG Test: CPU Cache OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: CPU Cache Vet 1 Vet 2 4 8 12 16 20 SE +/- 0.30, N = 15 SE +/- 0.17, N = 15 14.76 15.31 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
Stress-NG Test: MMAP OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: MMAP Vet 1 Vet 2 3 6 9 12 15 SE +/- 1.07, N = 15 SE +/- 0.68, N = 12 12.10 9.86 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
eSpeak-NG Speech Engine Text-To-Speech Synthesis OpenBenchmarking.org Seconds, Fewer Is Better eSpeak-NG Speech Engine 20200907 Text-To-Speech Synthesis Vet 1 Vet 2 14 28 42 56 70 SE +/- 0.68, N = 4 SE +/- 0.91, N = 16 57.49 60.33 1. (CC) gcc options: -O2 -std=c99
Phoronix Test Suite v10.8.5