ryzen 7 3700x dec AMD Ryzen 7 3700X 8-Core testing with a Gigabyte A320M-S2H-CF (F52a BIOS) and HIS AMD Radeon HD 7750/8740 / R7 250E 1GB on Ubuntu 20.04 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2012245-HA-RYZEN737018&grs .
ryzen 7 3700x dec Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server Display Driver OpenGL Compiler File-System Screen Resolution 1 2 3 4 AMD Ryzen 7 3700X 8-Core @ 3.60GHz (8 Cores / 16 Threads) Gigabyte A320M-S2H-CF (F52a BIOS) AMD Starship/Matisse 8GB 240GB TOSHIBA RC100 HIS AMD Radeon HD 7750/8740 / R7 250E 1GB AMD Oland/Hainan/Cape VA2431 Realtek RTL8111/8168/8411 Ubuntu 20.04 5.8.1-050801-generic (x86_64) GNOME Shell 3.36.4 X Server 1.20.8 modesetting 1.20.8 4.5 Mesa 20.0.8 (LLVM 10.0.0) GCC 9.3.0 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++,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-HskZEa/gcc-9-9.3.0/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: 0x8701021 Python Details - Python 3.8.5 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: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected
ryzen 7 3700x dec onednn: IP Shapes 3D - u8s8f32 - CPU onednn: Matrix Multiply Batch Shapes Transformer - f32 - CPU onednn: IP Shapes 1D - f32 - CPU onednn: Deconvolution Batch shapes_1d - f32 - CPU openvino: Age Gender Recognition Retail 0013 FP16 - CPU openvino: Age Gender Recognition Retail 0013 FP16 - CPU crafty: Elapsed Time onednn: Deconvolution Batch shapes_3d - f32 - CPU onednn: Convolution Batch Shapes Auto - f32 - CPU onednn: Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPU openvino: Age Gender Recognition Retail 0013 FP32 - CPU ncnn: CPU - blazeface simdjson: PartialTweets stockfish: Total Time onednn: Deconvolution Batch shapes_1d - u8s8f32 - CPU compress-lz4: 3 - Compression Speed onednn: Recurrent Neural Network Inference - f32 - CPU openvino: Age Gender Recognition Retail 0013 FP32 - CPU onednn: Convolution Batch Shapes Auto - u8s8f32 - CPU onednn: IP Shapes 3D - f32 - CPU simdjson: LargeRand openvino: Person Detection 0106 FP16 - CPU astcenc: Fast build2: Time To Compile brl-cad: VGR Performance Metric onednn: Recurrent Neural Network Training - u8s8f32 - CPU onednn: Recurrent Neural Network Training - bf16bf16bf16 - CPU openvino: Person Detection 0106 FP16 - CPU onednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPU onednn: Recurrent Neural Network Training - f32 - CPU compress-lz4: 9 - Compression Speed clomp: Static OMP Speedup asmfish: 1024 Hash Memory, 26 Depth ncnn: CPU - googlenet build-clash: Time To Compile ncnn: CPU-v3-v3 - mobilenet-v3 openvino: Person Detection 0106 FP32 - CPU ncnn: CPU-v2-v2 - mobilenet-v2 encode-wavpack: WAV To WavPack ncnn: CPU - squeezenet_ssd hpcg: sqlite-speedtest: Timed Time - Size 1,000 ncnn: CPU - yolov4-tiny build-eigen: Time To Compile openvino: Face Detection 0106 FP16 - CPU rav1e: 1 coremark: CoreMark Size 666 - Iterations Per Second onednn: Deconvolution Batch shapes_3d - u8s8f32 - CPU ncnn: CPU - mnasnet node-web-tooling: ncnn: CPU - resnet18 hmmer: Pfam Database Search encode-ape: WAV To APE onednn: IP Shapes 1D - u8s8f32 - CPU phpbench: PHP Benchmark Suite build-ffmpeg: Time To Compile compress-lz4: 1 - Decompression Speed ncnn: CPU - mobilenet openvino: Face Detection 0106 FP16 - CPU astcenc: Exhaustive rav1e: 5 encode-ogg: WAV To Ogg compress-lz4: 1 - Compression Speed compress-lz4: 9 - Decompression Speed ncnn: CPU - resnet50 compress-lz4: 3 - Decompression Speed ncnn: CPU - efficientnet-b0 openvino: Face Detection 0106 FP32 - CPU openvino: Person Detection 0106 FP32 - CPU ncnn: CPU - shufflenet-v2 ncnn: CPU - vgg16 rav1e: 6 rav1e: 10 encode-opus: WAV To Opus Encode astcenc: Thorough ncnn: CPU - alexnet ncnn: CPU - regnety_400m astcenc: Medium openvino: Face Detection 0106 FP32 - CPU simdjson: DistinctUserID simdjson: Kostya unpack-firefox: firefox-84.0.source.tar.xz onednn: Recurrent Neural Network Inference - u8s8f32 - CPU 1 2 3 4 1.92313 4.18422 6.41982 5.46401 0.60 6575.88 8546471 6.98587 21.8821 2.95246 0.59 2.38 0.69 20160779 6.51376 51.50 2647.28 6689.73 20.3999 9.36757 0.43 2640.59 5.97 119.006 120993 3848.17 3905.20 1.50 2691.72 3822.92 50.69 23.0 27502562 17.02 248.032 5.23 1.52 6.18 12.624 23.51 4.15940 59.241 28.75 74.181 1.90 0.402 353574.858058 5.32109 5.14 12.06 17.87 107.499 11.565 2.59978 674200 56.277 10310.6 19.21 2105.37 215.92 1.186 18.840 9360.33 9942.5 32.59 9919.0 8.14 2125.78 2589.43 6.72 67.04 1.587 3.457 7.194 26.68 14.20 18.67 8.68 1.88 0.7 0.59 18.129 2870.93 2.24347 4.46430 5.63807 5.09666 0.62 6385.20 8920559 6.73147 22.5039 2.90638 0.60 2.38 0.68 19613677 6.43594 50.73 2716.83 6618.49 20.5986 9.21133 0.42 2586.64 6.02 118.888 119540 3841.65 3828.39 1.53 2671.70 3843.11 49.77 23.4 27582263 17.14 249.576 5.18 1.51 6.12 12.596 23.63 4.13952 59.934 29.07 74.094 1.91 0.402 353496.410708 5.30594 5.11 12.13 17.96 107.861 11.601 2.62207 669279 56.166 10300.3 19.36 2092.82 216.19 1.183 18.899 9307.53 9964.5 32.61 9895.1 8.16 2128.47 2600.09 6.70 67.23 1.586 3.450 7.213 26.70 14.19 18.66 8.69 1.88 0.70 0.59 18.224 2680.98 2.35658 4.42827 5.71737 5.14679 0.59 6637.86 8893425 6.76584 22.1752 2.86008 0.58 2.31 0.67 19737025 6.37617 51.59 2700.05 6784.44 20.9056 9.43065 0.43 2584.40 6.11 117.139 121138 3906.57 3885.91 1.53 2656.26 3876.27 50.47 23.4 27974508 16.86 247.213 5.25 1.52 6.20 12.508 23.41 4.14396 59.490 29.08 74.084 1.89 0.398 352288.838866 5.26936 5.13 12.17 17.80 108.068 11.502 2.61510 670904 56.009 10277.4 19.27 2107.64 215.24 1.185 18.846 9368.21 9943.8 32.76 9901.3 8.17 2120.16 2598.96 6.71 67.05 1.582 3.447 7.204 26.64 14.22 18.69 8.69 1.88 0.70 0.59 18.395 2686.22 2.32680 4.92533 5.47702 5.06969 0.59 6685.19 8823060 6.69818 22.7344 2.84703 0.59 2.33 0.68 19931000 6.33997 52.10 2668.89 6715.20 20.6116 9.22956 0.43 2579.88 5.99 119.841 122061 3828.50 3872.86 1.53 2707.27 3804.05 50.16 23.2 27935855 16.96 245.507 5.25 1.50 6.19 12.464 23.34 4.18942 59.413 29.05 73.346 1.91 0.400 355783.638913 5.28923 5.16 12.09 17.86 107.122 11.518 2.60889 668752 56.453 10229.8 19.28 2092.01 214.69 1.178 18.773 9333.49 9903.2 32.58 9944.8 8.13 2129.83 2601.17 6.69 66.95 1.582 3.455 7.212 26.64 14.21 18.67 8.69 1.88 0.70 0.59 18.779 2877.16 OpenBenchmarking.org
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 1 2 3 4 0.5302 1.0604 1.5906 2.1208 2.651 SE +/- 0.01532, N = 3 SE +/- 0.00242, N = 3 SE +/- 0.00400, N = 3 SE +/- 0.00821, N = 3 1.92313 2.24347 2.35658 2.32680 MIN: 1.77 MIN: 2.16 MIN: 2.27 MIN: 2.26 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 1 2 3 4 1.1082 2.2164 3.3246 4.4328 5.541 SE +/- 0.00828, N = 3 SE +/- 0.00615, N = 3 SE +/- 0.02300, N = 3 SE +/- 0.01211, N = 3 4.18422 4.46430 4.42827 4.92533 MIN: 4.11 MIN: 4.37 MIN: 4.29 MIN: 4.78 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -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 1 2 3 4 2 4 6 8 10 SE +/- 0.03713, N = 3 SE +/- 0.02140, N = 3 SE +/- 0.09674, N = 3 SE +/- 0.01309, N = 3 6.41982 5.63807 5.71737 5.47702 MIN: 6.16 MIN: 5.46 MIN: 5.44 MIN: 5.33 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
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 1 2 3 4 1.2294 2.4588 3.6882 4.9176 6.147 SE +/- 0.06268, N = 3 SE +/- 0.01540, N = 3 SE +/- 0.03943, N = 3 SE +/- 0.02681, N = 3 5.46401 5.09666 5.14679 5.06969 MIN: 5.24 MIN: 4.97 MIN: 4.96 MIN: 4.93 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenVINO Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2021.1 Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU 1 2 3 4 0.1395 0.279 0.4185 0.558 0.6975 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 0.60 0.62 0.59 0.59
OpenVINO Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2021.1 Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU 1 2 3 4 1400 2800 4200 5600 7000 SE +/- 104.51, N = 3 SE +/- 45.76, N = 3 SE +/- 37.70, N = 3 SE +/- 48.76, N = 3 6575.88 6385.20 6637.86 6685.19
Crafty Elapsed Time OpenBenchmarking.org Nodes Per Second, More Is Better Crafty 25.2 Elapsed Time 1 2 3 4 2M 4M 6M 8M 10M SE +/- 40721.86, N = 3 SE +/- 23311.86, N = 3 SE +/- 39685.50, N = 3 SE +/- 10375.27, N = 3 8546471 8920559 8893425 8823060 1. (CC) gcc options: -pthread -lstdc++ -fprofile-use -lm
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 1 2 3 4 2 4 6 8 10 SE +/- 0.00565, N = 3 SE +/- 0.01088, N = 3 SE +/- 0.03140, N = 3 SE +/- 0.00633, N = 3 6.98587 6.73147 6.76584 6.69818 MIN: 6.9 MIN: 6.65 MIN: 6.66 MIN: 6.61 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
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 1 2 3 4 5 10 15 20 25 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.07, N = 3 SE +/- 0.03, N = 3 21.88 22.50 22.18 22.73 MIN: 21.72 MIN: 22.23 MIN: 21.92 MIN: 22.57 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 1 2 3 4 0.6643 1.3286 1.9929 2.6572 3.3215 SE +/- 0.01867, N = 3 SE +/- 0.02849, N = 3 SE +/- 0.02222, N = 3 SE +/- 0.00316, N = 3 2.95246 2.90638 2.86008 2.84703 MIN: 2.78 MIN: 2.78 MIN: 2.74 MIN: 2.79 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenVINO Model: Age Gender Recognition Retail 0013 FP32 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2021.1 Model: Age Gender Recognition Retail 0013 FP32 - Device: CPU 1 2 3 4 0.135 0.27 0.405 0.54 0.675 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 0.59 0.60 0.58 0.59
NCNN Target: CPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: blazeface 1 2 3 4 0.5355 1.071 1.6065 2.142 2.6775 SE +/- 0.07, N = 3 SE +/- 0.05, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 2.38 2.38 2.31 2.33 MIN: 2.27 / MAX: 19.28 MIN: 2.27 / MAX: 2.52 MIN: 2.25 / MAX: 2.91 MIN: 2.27 / MAX: 2.43 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
simdjson Throughput Test: PartialTweets OpenBenchmarking.org GB/s, More Is Better simdjson 0.7.1 Throughput Test: PartialTweets 1 2 3 4 0.1553 0.3106 0.4659 0.6212 0.7765 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.69 0.68 0.67 0.68 1. (CXX) g++ options: -O3 -pthread
Stockfish Total Time OpenBenchmarking.org Nodes Per Second, More Is Better Stockfish 12 Total Time 1 2 3 4 4M 8M 12M 16M 20M SE +/- 110311.00, N = 3 SE +/- 217803.95, N = 3 SE +/- 129535.89, N = 3 SE +/- 210476.75, N = 3 20160779 19613677 19737025 19931000 1. (CXX) g++ options: -m64 -lpthread -fno-exceptions -std=c++17 -pedantic -O3 -msse -msse3 -mpopcnt -msse4.1 -mssse3 -msse2 -flto -flto=jobserver
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 1 2 3 4 2 4 6 8 10 SE +/- 0.09124, N = 4 SE +/- 0.04033, N = 3 SE +/- 0.01483, N = 3 SE +/- 0.00504, N = 3 6.51376 6.43594 6.37617 6.33997 MIN: 6.15 MIN: 6.16 MIN: 6.19 MIN: 6.13 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
LZ4 Compression Compression Level: 3 - Compression Speed OpenBenchmarking.org MB/s, More Is Better LZ4 Compression 1.9.3 Compression Level: 3 - Compression Speed 1 2 3 4 12 24 36 48 60 SE +/- 0.13, N = 3 SE +/- 0.43, N = 3 SE +/- 0.61, N = 3 SE +/- 0.80, N = 3 51.50 50.73 51.59 52.10 1. (CC) gcc options: -O3
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 1 2 3 4 600 1200 1800 2400 3000 SE +/- 6.44, N = 3 SE +/- 7.32, N = 3 SE +/- 13.71, N = 3 SE +/- 3.97, N = 3 2647.28 2716.83 2700.05 2668.89 MIN: 2623.28 MIN: 2679.78 MIN: 2664.68 MIN: 2653.57 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenVINO Model: Age Gender Recognition Retail 0013 FP32 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2021.1 Model: Age Gender Recognition Retail 0013 FP32 - Device: CPU 1 2 3 4 1500 3000 4500 6000 7500 SE +/- 45.45, N = 3 SE +/- 24.26, N = 3 SE +/- 15.68, N = 3 SE +/- 68.15, N = 3 6689.73 6618.49 6784.44 6715.20
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 1 2 3 4 5 10 15 20 25 SE +/- 0.14, N = 3 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 SE +/- 0.08, N = 3 20.40 20.60 20.91 20.61 MIN: 19.84 MIN: 20.17 MIN: 20.6 MIN: 20.13 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
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 1 2 3 4 3 6 9 12 15 SE +/- 0.02026, N = 3 SE +/- 0.03208, N = 3 SE +/- 0.00670, N = 3 SE +/- 0.00920, N = 3 9.36757 9.21133 9.43065 9.22956 MIN: 8.65 MIN: 8.73 MIN: 8.94 MIN: 8.81 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
simdjson Throughput Test: LargeRandom OpenBenchmarking.org GB/s, More Is Better simdjson 0.7.1 Throughput Test: LargeRandom 1 2 3 4 0.0968 0.1936 0.2904 0.3872 0.484 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.43 0.42 0.43 0.43 1. (CXX) g++ options: -O3 -pthread
OpenVINO Model: Person Detection 0106 FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2021.1 Model: Person Detection 0106 FP16 - Device: CPU 1 2 3 4 600 1200 1800 2400 3000 SE +/- 53.72, N = 3 SE +/- 5.45, N = 3 SE +/- 3.37, N = 3 SE +/- 1.17, N = 3 2640.59 2586.64 2584.40 2579.88
ASTC Encoder Preset: Fast OpenBenchmarking.org Seconds, Fewer Is Better ASTC Encoder 2.0 Preset: Fast 1 2 3 4 2 4 6 8 10 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.06, N = 3 SE +/- 0.03, N = 3 5.97 6.02 6.11 5.99 1. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread
Build2 Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Build2 0.13 Time To Compile 1 2 3 4 30 60 90 120 150 SE +/- 0.53, N = 3 SE +/- 0.87, N = 3 SE +/- 0.68, N = 3 SE +/- 0.61, N = 3 119.01 118.89 117.14 119.84
BRL-CAD VGR Performance Metric OpenBenchmarking.org VGR Performance Metric, More Is Better BRL-CAD 7.30.8 VGR Performance Metric 1 2 3 4 30K 60K 90K 120K 150K 120993 119540 121138 122061 1. (CXX) g++ options: -std=c++11 -pipe -fno-strict-aliasing -fno-common -fexceptions -ftemplate-depth-128 -m64 -ggdb3 -O3 -fipa-pta -fstrength-reduce -finline-functions -flto -pedantic -rdynamic -lSM -lICE -lXi -lGLU -lGL -lGLdispatch -lX11 -lXext -lXrender -lpthread -ldl -luuid -lm
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 1 2 3 4 800 1600 2400 3200 4000 SE +/- 3.51, N = 3 SE +/- 7.95, N = 3 SE +/- 7.82, N = 3 SE +/- 10.35, N = 3 3848.17 3841.65 3906.57 3828.50 MIN: 3835.87 MIN: 3822.65 MIN: 3881.33 MIN: 3796.66 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
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 1 2 3 4 800 1600 2400 3200 4000 SE +/- 9.21, N = 3 SE +/- 15.67, N = 3 SE +/- 18.76, N = 3 SE +/- 13.24, N = 3 3905.20 3828.39 3885.91 3872.86 MIN: 3873.81 MIN: 3789.68 MIN: 3857.9 MIN: 3841.97 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenVINO Model: Person Detection 0106 FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2021.1 Model: Person Detection 0106 FP16 - Device: CPU 1 2 3 4 0.3443 0.6886 1.0329 1.3772 1.7215 SE +/- 0.02, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 1.50 1.53 1.53 1.53
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 1 2 3 4 600 1200 1800 2400 3000 SE +/- 16.87, N = 3 SE +/- 11.78, N = 3 SE +/- 21.78, N = 3 SE +/- 17.38, N = 3 2691.72 2671.70 2656.26 2707.27 MIN: 2656.78 MIN: 2634.62 MIN: 2609.52 MIN: 2664.29 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
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 1 2 3 4 800 1600 2400 3200 4000 SE +/- 15.33, N = 3 SE +/- 10.50, N = 3 SE +/- 7.78, N = 3 SE +/- 9.46, N = 3 3822.92 3843.11 3876.27 3804.05 MIN: 3794.35 MIN: 3822.5 MIN: 3849.36 MIN: 3774.53 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -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 1 2 3 4 11 22 33 44 55 SE +/- 0.61, N = 3 SE +/- 0.09, N = 3 SE +/- 0.56, N = 3 SE +/- 0.24, N = 3 50.69 49.77 50.47 50.16 1. (CC) gcc options: -O3
CLOMP Static OMP Speedup OpenBenchmarking.org Speedup, More Is Better CLOMP 1.2 Static OMP Speedup 1 2 3 4 6 12 18 24 30 SE +/- 0.33, N = 4 SE +/- 0.15, N = 3 SE +/- 0.25, N = 3 SE +/- 0.09, N = 3 23.0 23.4 23.4 23.2 1. (CC) gcc options: -fopenmp -O3 -lm
asmFish 1024 Hash Memory, 26 Depth OpenBenchmarking.org Nodes/second, More Is Better asmFish 2018-07-23 1024 Hash Memory, 26 Depth 1 2 3 4 6M 12M 18M 24M 30M SE +/- 236042.73, N = 3 SE +/- 392976.00, N = 4 SE +/- 375615.15, N = 3 SE +/- 413508.74, N = 3 27502562 27582263 27974508 27935855
NCNN Target: CPU - Model: googlenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: googlenet 1 2 3 4 4 8 12 16 20 SE +/- 0.15, N = 3 SE +/- 0.19, N = 3 SE +/- 0.01, N = 3 SE +/- 0.10, N = 3 17.02 17.14 16.86 16.96 MIN: 16.66 / MAX: 19.25 MIN: 16.66 / MAX: 17.83 MIN: 16.71 / MAX: 17.29 MIN: 16.69 / MAX: 17.55 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Timed Clash Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Clash Compilation Time To Compile 1 2 3 4 50 100 150 200 250 SE +/- 2.91, N = 3 SE +/- 3.62, N = 3 SE +/- 2.51, N = 3 SE +/- 1.63, N = 3 248.03 249.58 247.21 245.51
NCNN Target: CPU-v3-v3 - Model: mobilenet-v3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU-v3-v3 - Model: mobilenet-v3 1 2 3 4 1.1813 2.3626 3.5439 4.7252 5.9065 SE +/- 0.01, N = 3 SE +/- 0.06, N = 3 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 5.23 5.18 5.25 5.25 MIN: 5.15 / MAX: 6.2 MIN: 4.98 / MAX: 6.67 MIN: 5.16 / MAX: 10.04 MIN: 5.12 / MAX: 14.04 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenVINO Model: Person Detection 0106 FP32 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2021.1 Model: Person Detection 0106 FP32 - Device: CPU 1 2 3 4 0.342 0.684 1.026 1.368 1.71 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 1.52 1.51 1.52 1.50
NCNN Target: CPU-v2-v2 - Model: mobilenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU-v2-v2 - Model: mobilenet-v2 1 2 3 4 2 4 6 8 10 SE +/- 0.02, N = 3 SE +/- 0.07, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 6.18 6.12 6.20 6.19 MIN: 6.06 / MAX: 8.19 MIN: 5.85 / MAX: 7.6 MIN: 6.09 / MAX: 8.16 MIN: 6.03 / MAX: 10.92 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
WavPack Audio Encoding WAV To WavPack OpenBenchmarking.org Seconds, Fewer Is Better WavPack Audio Encoding 5.3 WAV To WavPack 1 2 3 4 3 6 9 12 15 SE +/- 0.02, N = 5 SE +/- 0.02, N = 5 SE +/- 0.04, N = 5 SE +/- 0.03, N = 5 12.62 12.60 12.51 12.46 1. (CXX) g++ options: -rdynamic
NCNN Target: CPU - Model: squeezenet_ssd OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: squeezenet_ssd 1 2 3 4 6 12 18 24 30 SE +/- 0.11, N = 3 SE +/- 0.13, N = 3 SE +/- 0.04, N = 3 SE +/- 0.06, N = 3 23.51 23.63 23.41 23.34 MIN: 23.25 / MAX: 25.8 MIN: 23.22 / MAX: 24.08 MIN: 23.19 / MAX: 25.44 MIN: 23.02 / MAX: 43.03 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
High Performance Conjugate Gradient OpenBenchmarking.org GFLOP/s, More Is Better High Performance Conjugate Gradient 3.1 1 2 3 4 0.9426 1.8852 2.8278 3.7704 4.713 SE +/- 0.01048, N = 3 SE +/- 0.00654, N = 3 SE +/- 0.00914, N = 3 SE +/- 0.00261, N = 3 4.15940 4.13952 4.14396 4.18942 1. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -pthread -lmpi_cxx -lmpi
SQLite Speedtest Timed Time - Size 1,000 OpenBenchmarking.org Seconds, Fewer Is Better SQLite Speedtest 3.30 Timed Time - Size 1,000 1 2 3 4 13 26 39 52 65 SE +/- 0.32, N = 3 SE +/- 0.21, N = 3 SE +/- 0.76, N = 3 SE +/- 0.24, N = 3 59.24 59.93 59.49 59.41 1. (CC) gcc options: -O2 -ldl -lz -lpthread
NCNN Target: CPU - Model: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: yolov4-tiny 1 2 3 4 7 14 21 28 35 SE +/- 0.52, N = 3 SE +/- 0.12, N = 3 SE +/- 0.03, N = 3 SE +/- 0.06, N = 3 28.75 29.07 29.08 29.05 MIN: 27.61 / MAX: 64.45 MIN: 28.75 / MAX: 29.65 MIN: 28.89 / MAX: 29.73 MIN: 28.82 / MAX: 29.73 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Timed Eigen Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Eigen Compilation 3.3.9 Time To Compile 1 2 3 4 16 32 48 64 80 SE +/- 0.37, N = 3 SE +/- 0.35, N = 3 SE +/- 0.46, N = 3 SE +/- 0.27, N = 3 74.18 74.09 74.08 73.35
OpenVINO Model: Face Detection 0106 FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2021.1 Model: Face Detection 0106 FP16 - Device: CPU 1 2 3 4 0.4298 0.8596 1.2894 1.7192 2.149 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 1.90 1.91 1.89 1.91
rav1e Speed: 1 OpenBenchmarking.org Frames Per Second, More Is Better rav1e 0.4 Alpha Speed: 1 1 2 3 4 0.0905 0.181 0.2715 0.362 0.4525 SE +/- 0.001, N = 3 SE +/- 0.000, N = 3 SE +/- 0.005, N = 3 SE +/- 0.001, N = 3 0.402 0.402 0.398 0.400
Coremark CoreMark Size 666 - Iterations Per Second OpenBenchmarking.org Iterations/Sec, More Is Better Coremark 1.0 CoreMark Size 666 - Iterations Per Second 1 2 3 4 80K 160K 240K 320K 400K SE +/- 433.03, N = 3 SE +/- 1791.95, N = 3 SE +/- 551.56, N = 3 SE +/- 2489.73, N = 3 353574.86 353496.41 352288.84 355783.64 1. (CC) gcc options: -O2 -lrt" -lrt
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 1 2 3 4 1.1972 2.3944 3.5916 4.7888 5.986 SE +/- 0.00290, N = 3 SE +/- 0.01452, N = 3 SE +/- 0.01044, N = 3 SE +/- 0.00180, N = 3 5.32109 5.30594 5.26936 5.28923 MIN: 5.19 MIN: 5.15 MIN: 5.13 MIN: 5.14 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
NCNN Target: CPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: mnasnet 1 2 3 4 1.161 2.322 3.483 4.644 5.805 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 5.14 5.11 5.13 5.16 MIN: 5.05 / MAX: 6.45 MIN: 5.01 / MAX: 6.04 MIN: 5.04 / MAX: 6.51 MIN: 5.06 / MAX: 6.5 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Node.js V8 Web Tooling Benchmark OpenBenchmarking.org runs/s, More Is Better Node.js V8 Web Tooling Benchmark 1 2 3 4 3 6 9 12 15 SE +/- 0.11, N = 3 SE +/- 0.14, N = 3 SE +/- 0.05, N = 3 SE +/- 0.08, N = 3 12.06 12.13 12.17 12.09 1. Nodejs
v10.19.0
NCNN Target: CPU - Model: resnet18 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: resnet18 1 2 3 4 4 8 12 16 20 SE +/- 0.06, N = 3 SE +/- 0.07, N = 3 SE +/- 0.01, N = 3 SE +/- 0.06, N = 3 17.87 17.96 17.80 17.86 MIN: 17.67 / MAX: 19.64 MIN: 17.69 / MAX: 18.83 MIN: 17.69 / MAX: 18.2 MIN: 17.69 / MAX: 19.08 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Timed HMMer Search Pfam Database Search OpenBenchmarking.org Seconds, Fewer Is Better Timed HMMer Search 3.3.1 Pfam Database Search 1 2 3 4 20 40 60 80 100 SE +/- 0.21, N = 3 SE +/- 0.08, N = 3 SE +/- 0.11, N = 3 SE +/- 0.02, N = 3 107.50 107.86 108.07 107.12 1. (CC) gcc options: -O3 -pthread -lhmmer -leasel -lm
Monkey Audio Encoding WAV To APE OpenBenchmarking.org Seconds, Fewer Is Better Monkey Audio Encoding 3.99.6 WAV To APE 1 2 3 4 3 6 9 12 15 SE +/- 0.03, N = 5 SE +/- 0.02, N = 5 SE +/- 0.06, N = 5 SE +/- 0.04, N = 5 11.57 11.60 11.50 11.52 1. (CXX) g++ options: -O3 -pedantic -rdynamic -lrt
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 1 2 3 4 0.59 1.18 1.77 2.36 2.95 SE +/- 0.00707, N = 3 SE +/- 0.00999, N = 3 SE +/- 0.00458, N = 3 SE +/- 0.00294, N = 3 2.59978 2.62207 2.61510 2.60889 MIN: 2.54 MIN: 2.53 MIN: 2.55 MIN: 2.55 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
PHPBench PHP Benchmark Suite OpenBenchmarking.org Score, More Is Better PHPBench 0.8.1 PHP Benchmark Suite 1 2 3 4 140K 280K 420K 560K 700K SE +/- 847.75, N = 3 SE +/- 2076.23, N = 3 SE +/- 3673.00, N = 3 SE +/- 2049.04, N = 3 674200 669279 670904 668752
Timed FFmpeg Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed FFmpeg Compilation 4.2.2 Time To Compile 1 2 3 4 13 26 39 52 65 SE +/- 0.35, N = 3 SE +/- 0.79, N = 3 SE +/- 0.30, N = 3 SE +/- 0.38, N = 3 56.28 56.17 56.01 56.45
LZ4 Compression Compression Level: 1 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better LZ4 Compression 1.9.3 Compression Level: 1 - Decompression Speed 1 2 3 4 2K 4K 6K 8K 10K SE +/- 75.38, N = 3 SE +/- 29.70, N = 3 SE +/- 20.35, N = 3 SE +/- 16.57, N = 3 10310.6 10300.3 10277.4 10229.8 1. (CC) gcc options: -O3
NCNN Target: CPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: mobilenet 1 2 3 4 5 10 15 20 25 SE +/- 0.16, N = 3 SE +/- 0.17, N = 3 SE +/- 0.11, N = 3 SE +/- 0.08, N = 3 19.21 19.36 19.27 19.28 MIN: 18.78 / MAX: 21.15 MIN: 18.77 / MAX: 35.98 MIN: 18.88 / MAX: 44.34 MIN: 18.9 / MAX: 29.46 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenVINO Model: Face Detection 0106 FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2021.1 Model: Face Detection 0106 FP16 - Device: CPU 1 2 3 4 500 1000 1500 2000 2500 SE +/- 10.65, N = 3 SE +/- 10.32, N = 3 SE +/- 3.44, N = 3 SE +/- 4.55, N = 3 2105.37 2092.82 2107.64 2092.01
ASTC Encoder Preset: Exhaustive OpenBenchmarking.org Seconds, Fewer Is Better ASTC Encoder 2.0 Preset: Exhaustive 1 2 3 4 50 100 150 200 250 SE +/- 0.84, N = 3 SE +/- 0.86, N = 3 SE +/- 0.76, N = 3 SE +/- 0.59, N = 3 215.92 216.19 215.24 214.69 1. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread
rav1e Speed: 5 OpenBenchmarking.org Frames Per Second, More Is Better rav1e 0.4 Alpha Speed: 5 1 2 3 4 0.2669 0.5338 0.8007 1.0676 1.3345 SE +/- 0.002, N = 3 SE +/- 0.004, N = 3 SE +/- 0.004, N = 3 SE +/- 0.003, N = 3 1.186 1.183 1.185 1.178
Ogg Audio Encoding WAV To Ogg OpenBenchmarking.org Seconds, Fewer Is Better Ogg Audio Encoding 1.3.4 WAV To Ogg 1 2 3 4 5 10 15 20 25 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 SE +/- 0.04, N = 3 18.84 18.90 18.85 18.77 1. (CC) gcc options: -O2 -ffast-math -fsigned-char
LZ4 Compression Compression Level: 1 - Compression Speed OpenBenchmarking.org MB/s, More Is Better LZ4 Compression 1.9.3 Compression Level: 1 - Compression Speed 1 2 3 4 2K 4K 6K 8K 10K SE +/- 28.64, N = 3 SE +/- 35.67, N = 3 SE +/- 58.52, N = 3 SE +/- 17.75, N = 3 9360.33 9307.53 9368.21 9333.49 1. (CC) gcc options: -O3
LZ4 Compression Compression Level: 9 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better LZ4 Compression 1.9.3 Compression Level: 9 - Decompression Speed 1 2 3 4 2K 4K 6K 8K 10K SE +/- 34.85, N = 3 SE +/- 13.58, N = 3 SE +/- 11.11, N = 3 SE +/- 20.54, N = 3 9942.5 9964.5 9943.8 9903.2 1. (CC) gcc options: -O3
NCNN Target: CPU - Model: resnet50 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: resnet50 1 2 3 4 8 16 24 32 40 SE +/- 0.18, N = 3 SE +/- 0.24, N = 3 SE +/- 0.27, N = 3 SE +/- 0.20, N = 3 32.59 32.61 32.76 32.58 MIN: 32.08 / MAX: 33.46 MIN: 31.97 / MAX: 34.1 MIN: 32.03 / MAX: 34.5 MIN: 32.05 / MAX: 36.85 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
LZ4 Compression Compression Level: 3 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better LZ4 Compression 1.9.3 Compression Level: 3 - Decompression Speed 1 2 3 4 2K 4K 6K 8K 10K SE +/- 22.08, N = 3 SE +/- 28.51, N = 3 SE +/- 18.23, N = 3 SE +/- 31.18, N = 3 9919.0 9895.1 9901.3 9944.8 1. (CC) gcc options: -O3
NCNN Target: CPU - Model: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: efficientnet-b0 1 2 3 4 2 4 6 8 10 SE +/- 0.01, N = 3 SE +/- 0.13, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 8.14 8.16 8.17 8.13 MIN: 8.02 / MAX: 8.83 MIN: 7.88 / MAX: 9.12 MIN: 8.06 / MAX: 8.32 MIN: 8.03 / MAX: 8.49 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenVINO Model: Face Detection 0106 FP32 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2021.1 Model: Face Detection 0106 FP32 - Device: CPU 1 2 3 4 500 1000 1500 2000 2500 SE +/- 7.97, N = 3 SE +/- 10.63, N = 3 SE +/- 12.17, N = 3 SE +/- 5.04, N = 3 2125.78 2128.47 2120.16 2129.83
OpenVINO Model: Person Detection 0106 FP32 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2021.1 Model: Person Detection 0106 FP32 - Device: CPU 1 2 3 4 600 1200 1800 2400 3000 SE +/- 2.01, N = 3 SE +/- 12.53, N = 3 SE +/- 10.76, N = 3 SE +/- 11.32, N = 3 2589.43 2600.09 2598.96 2601.17
NCNN Target: CPU - Model: shufflenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: shufflenet-v2 1 2 3 4 2 4 6 8 10 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 6.72 6.70 6.71 6.69 MIN: 6.65 / MAX: 7.66 MIN: 6.61 / MAX: 7.44 MIN: 6.63 / MAX: 7.73 MIN: 6.58 / MAX: 7.67 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: vgg16 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: vgg16 1 2 3 4 15 30 45 60 75 SE +/- 0.13, N = 3 SE +/- 0.08, N = 3 SE +/- 0.08, N = 3 SE +/- 0.12, N = 3 67.04 67.23 67.05 66.95 MIN: 66.37 / MAX: 76.88 MIN: 66.76 / MAX: 69.07 MIN: 66.64 / MAX: 85.47 MIN: 66.49 / MAX: 77.52 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
rav1e Speed: 6 OpenBenchmarking.org Frames Per Second, More Is Better rav1e 0.4 Alpha Speed: 6 1 2 3 4 0.3571 0.7142 1.0713 1.4284 1.7855 SE +/- 0.001, N = 3 SE +/- 0.004, N = 3 SE +/- 0.004, N = 3 SE +/- 0.001, N = 3 1.587 1.586 1.582 1.582
rav1e Speed: 10 OpenBenchmarking.org Frames Per Second, More Is Better rav1e 0.4 Alpha Speed: 10 1 2 3 4 0.7778 1.5556 2.3334 3.1112 3.889 SE +/- 0.009, N = 3 SE +/- 0.016, N = 3 SE +/- 0.010, N = 3 SE +/- 0.020, N = 3 3.457 3.450 3.447 3.455
Opus Codec Encoding WAV To Opus Encode OpenBenchmarking.org Seconds, Fewer Is Better Opus Codec Encoding 1.3.1 WAV To Opus Encode 1 2 3 4 2 4 6 8 10 SE +/- 0.026, N = 5 SE +/- 0.035, N = 5 SE +/- 0.021, N = 5 SE +/- 0.025, N = 5 7.194 7.213 7.204 7.212 1. (CXX) g++ options: -fvisibility=hidden -logg -lm
ASTC Encoder Preset: Thorough OpenBenchmarking.org Seconds, Fewer Is Better ASTC Encoder 2.0 Preset: Thorough 1 2 3 4 6 12 18 24 30 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 26.68 26.70 26.64 26.64 1. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread
NCNN Target: CPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: alexnet 1 2 3 4 4 8 12 16 20 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 SE +/- 0.03, N = 3 SE +/- 0.07, N = 3 14.20 14.19 14.22 14.21 MIN: 14 / MAX: 14.91 MIN: 14.01 / MAX: 17.99 MIN: 14.02 / MAX: 29.08 MIN: 13.97 / MAX: 34.17 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: regnety_400m OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: regnety_400m 1 2 3 4 5 10 15 20 25 SE +/- 0.02, N = 3 SE +/- 0.13, N = 3 SE +/- 0.01, N = 3 SE +/- 0.06, N = 3 18.67 18.66 18.69 18.67 MIN: 18.49 / MAX: 19.91 MIN: 18.24 / MAX: 19.92 MIN: 18.54 / MAX: 19.88 MIN: 18.39 / MAX: 19.85 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
ASTC Encoder Preset: Medium OpenBenchmarking.org Seconds, Fewer Is Better ASTC Encoder 2.0 Preset: Medium 1 2 3 4 2 4 6 8 10 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 8.68 8.69 8.69 8.69 1. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread
OpenVINO Model: Face Detection 0106 FP32 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2021.1 Model: Face Detection 0106 FP32 - Device: CPU 1 2 3 4 0.423 0.846 1.269 1.692 2.115 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 1.88 1.88 1.88 1.88
simdjson Throughput Test: DistinctUserID OpenBenchmarking.org GB/s, More Is Better simdjson 0.7.1 Throughput Test: DistinctUserID 1 2 3 4 0.1575 0.315 0.4725 0.63 0.7875 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 0.70 0.70 0.70 0.70 1. (CXX) g++ options: -O3 -pthread
simdjson Throughput Test: Kostya OpenBenchmarking.org GB/s, More Is Better simdjson 0.7.1 Throughput Test: Kostya 1 2 3 4 0.1328 0.2656 0.3984 0.5312 0.664 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.59 0.59 0.59 0.59 1. (CXX) g++ options: -O3 -pthread
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 1 2 3 4 5 10 15 20 25 SE +/- 0.14, N = 20 SE +/- 0.16, N = 4 SE +/- 0.27, N = 20 SE +/- 0.24, N = 5 18.13 18.22 18.40 18.78
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 1 2 3 4 600 1200 1800 2400 3000 SE +/- 164.47, N = 15 SE +/- 18.41, N = 3 SE +/- 26.06, N = 3 SE +/- 112.58, N = 15 2870.93 2680.98 2686.22 2877.16 MIN: 2616.42 MIN: 2639.83 MIN: 2623.98 MIN: 2678.01 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
Phoronix Test Suite v10.8.4