Core i7 5775C Perf In September 2020 Intel Core i7-5775C testing with a MSI Z97-G45 GAMING (MS-7821) v1.0 (V2.9 BIOS) and MSI Intel Iris Pro 6200 3GB on Ubuntu 18.10 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2009259-FI-COREI757768&grs&rdt .
Core i7 5775C Perf In September 2020 Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server Display Driver OpenGL Vulkan Compiler File-System Screen Resolution Run 1 Run 2 Run 3 Intel Core i7-5775C @ 3.70GHz (4 Cores / 8 Threads) MSI Z97-G45 GAMING (MS-7821) v1.0 (V2.9 BIOS) Intel Broadwell-U DMI 16GB 120GB CT120BX100SSD1 MSI Intel Iris Pro 6200 3GB (1150MHz) Intel Broadwell-U Audio VA2431 Qualcomm Atheros Killer E220x Ubuntu 18.10 5.0.0-999-generic (x86_64) 20190223 GNOME Shell 3.30.2 X Server 1.20.1 modesetting 1.20.1 4.5 Mesa 19.2.0-devel (git-2631fd3 2019-07-24 cosmic-oibaf-ppa) 1.1.102 GCC 8.3.0 ext4 1920x1080 OpenBenchmarking.org Compiler Details - --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --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 --with-tune=generic --without-cuda-driver -v Processor Details - Scaling Governor: intel_pstate powersave - CPU Microcode: 0x20 Java Details - OpenJDK Runtime Environment (build 11.0.3+7-Ubuntu-1ubuntu218.10.1) Python Details - Python 2.7.16 + Python 3.6.8 Security Details - l1tf: Mitigation of PTE Inversion; VMX: conditional cache flushes SMT vulnerable + meltdown: Mitigation of PTI + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Mitigation of Full generic retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling
Core i7 5775C Perf In September 2020 stress-ng: Memory Copying onednn: Recurrent Neural Network Training - f32 - CPU onednn: Deconvolution Batch deconv_3d - f32 - CPU onednn: Recurrent Neural Network Inference - f32 - CPU onednn: Convolution Batch Shapes Auto - f32 - CPU stress-ng: MEMFD neatbench: CPU build2: Time To Compile stress-ng: System V Message Passing stress-ng: Glibc C String Functions ncnn: CPU - alexnet renaissance: Savina Reactors.IO mpv: Big Buck Bunny Sunflower 4K - Software Only renaissance: In-Memory Database Shootout java-gradle-perf: Reactor stress-ng: Atomic stress-ng: Malloc stress-ng: Context Switching influxdb: 4 - 10000 - 2,5000,1 - 10000 renaissance: Apache Spark ALS ncnn: CPU - blazeface renaissance: Akka Unbalanced Cobwebbed Tree renaissance: Scala Dotty stress-ng: CPU Stress stress-ng: Socket Activity ncnn: CPU - mnasnet renaissance: Rand Forest onednn: IP Batch All - f32 - CPU blosc: blosclz ncnn: CPU - mobilenetv2_yolov3 dacapobench: Tradebeans build-linux-kernel: Time To Compile influxdb: 64 - 10000 - 2,5000,1 - 10000 mnn: SqueezeNetV1.0 mnn: resnet-v2-50 influxdb: 1024 - 10000 - 2,5000,1 - 10000 dacapobench: Tradesoap avifenc: 10 ncnn: CPU - vgg16_int8 libraw: Post-Processing Benchmark mpv: Big Buck Bunny Sunflower 1080p - Software Only hugin: Panorama Photo Assistant + Stitching Time dacapobench: H2 stress-ng: Matrix Math mnn: inception-v3 compress-zstd: 19 ncnn: CPU - squeezenet_int8 aom-av1: Speed 6 Two-Pass espeak: Text-To-Speech Synthesis gpaw: Carbon Nanotube mocassin: Dust 2D tau100.0 onednn: IP Batch 1D - f32 - CPU octave-benchmark: stress-ng: NUMA onednn: Deconvolution Batch deconv_1d - f32 - CPU glmark2: 1920 x 1080 ncnn: CPU - squeezenet aom-av1: Speed 4 Two-Pass dacapobench: Jython ncnn: CPU - mobilenet_v3 aom-av1: Speed 8 Realtime stress-ng: Forking stress-ng: Glibc Qsort Data Sorting avifenc: 2 namd: ATPase Simulation - 327,506 Atoms ncnn: CPU - googlenet_int8 tensorflow-lite: NASNet Mobile avifenc: 8 mnn: mobilenet-v1-1.0 incompact3d: Cylinder compress-zstd: 3 build-apache: Time To Compile montage: Mosaic of M17, K band, 1.5 deg x 1.5 deg stress-ng: Crypto tensorflow-lite: Mobilenet Float brl-cad: VGR Performance Metric mnn: MobileNetV2_224 stress-ng: MMAP astcenc: Fast aom-av1: Speed 6 Realtime stress-ng: Vector Math tensorflow-lite: Mobilenet Quant lammps: Rhodopsin Protein gromacs: Water Benchmark svt-av1: Enc Mode 8 - 1080p tensorflow-lite: Inception V4 tensorflow-lite: Inception ResNet V2 tensorflow-lite: SqueezeNet ncnn: CPU - resnet18_int8 stress-ng: Semaphores ocrmypdf: Processing 60 Page PDF Document svt-av1: Enc Mode 4 - 1080p astcenc: Exhaustive stress-ng: SENDFILE ncnn: CPU - resnet50_int8 astcenc: Medium astcenc: Thorough avifenc: 0 stress-ng: RdRand luxcorerender: DLSC aom-av1: Speed 0 Two-Pass opencv: DNN - Deep Neural Network stress-ng: CPU Cache system-decompress-gzip: onednn: Matrix Multiply Batch Shapes Transformer - f32 - CPU renaissance: Apache Spark PageRank renaissance: Apache Spark Bayes Run 1 Run 2 Run 3 2591.44 558.903 15.9594 175.569 21.1609 286.58 8.16 215.345 6263395.17 453045.74 24.89 19921.229 353.18 3735.454 265.780 202671.08 31337895.18 1693803.99 855281.8 2664.261 2.20 9284.598 1974.916 1751.85 6030.69 6.57 2138.857 120.147 6788.0 26.87 4573 177.847 909598.9 9.271 44.341 971205.0 7852 7.877 243.01 28.13 902.29 81.906 3356 19391.27 54.380 23.1 25.32 2.64 40.640 653.110 296 8.26351 8.707 85.99 10.0662 985 4.92 1.65 5257 6.00 33.82 37547.26 58.69 115.298 4.10818 71.78 387372 8.517 6.928 769.230143 2494.7 30.578 92.332 817.97 366589 45474 4.956 54.22 8.40 13.44 25159.22 354486 2.864 0.485 12.194 7825710 7077587 541870 39.46 743806.03 56.164 1.496 589.16 46822.85 133.02 10.93 72.66 195.324 240337.19 0.67 0.2 5441 45.27 3.447 3.38848 4865.500 3779.503 2617.52 535.209 15.7029 169.755 20.3775 297.06 8.11 209.965 6453494.07 445829.21 24.20 19713.402 349.48 3700.012 260.304 205022.47 32002407.75 1698242.99 852344.4 2671.803 2.19 9409.744 1964.481 1741.82 6030.96 6.55 2135.787 120.298 6787.7 26.66 4621 177.883 915807.8 9.390 44.851 982263.6 7871 7.789 240.49 28.24 911.23 82.225 3364 19265.77 54.888 23.2 25.53 2.66 40.756 648.613 295 8.30212 8.653 85.43 10.0611 982 4.95 1.66 5242 5.99 33.67 37723.77 58.60 115.440 4.09223 71.54 386514 8.492 6.949 768.573588 2498.2 30.602 92.236 818.90 365619 45358 4.967 54.32 8.41 13.47 25153.83 353741 2.866 0.484 12.219 7809863 7063550 540887 39.43 744929.81 56.080 1.498 588.40 46865.51 132.94 10.92 72.61 195.312 240331.88 0.67 0.2 4928 44.21 3.385 3.66649 4803.630 3989.697 2396.66 577.334 16.4471 176.760 20.8491 293.65 7.89 208.529 6385777.22 458759.57 24.33 19384.784 344.54 3787.312 260.036 207144.00 31529776.24 1728927.62 838679.5 2620.757 2.23 9242.485 1999.386 1770.49 6125.05 6.65 2106.813 118.529 6887.9 26.49 4638 180.367 903216.0 9.399 44.901 982578.8 7942 7.797 240.88 27.95 911.49 82.736 3332 19207.24 54.713 23.3 25.38 2.65 40.456 648.325 294 8.31908 8.710 85.43 10.1249 988 4.93 1.66 5228 6.02 33.83 37590.58 58.43 114.989 4.09524 71.58 386168 8.491 6.935 766.920431 2502.0 30.518 92.087 816.73 365631 45365 4.968 54.19 8.42 13.47 25103.46 353786 2.870 0.485 12.209 7810147 7064830 540902 39.39 744313.54 56.118 1.498 588.48 46879.66 132.87 10.92 72.61 195.390 240319.26 0.67 0.2 5494 45.91 3.381 3.71663 4712.366 3909.150 OpenBenchmarking.org
Stress-NG Test: Memory Copying OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Memory Copying Run 1 Run 2 Run 3 600 1200 1800 2400 3000 SE +/- 6.23, N = 3 SE +/- 2.87, N = 3 SE +/- 10.61, N = 3 2591.44 2617.52 2396.66 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
oneDNN Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 1.5 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU Run 1 Run 2 Run 3 120 240 360 480 600 SE +/- 8.18, N = 4 SE +/- 4.58, N = 3 SE +/- 4.80, N = 3 558.90 535.21 577.33 MIN: 532.11 MIN: 527.99 MIN: 569.19 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
oneDNN Harness: Deconvolution Batch deconv_3d - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 1.5 Harness: Deconvolution Batch deconv_3d - Data Type: f32 - Engine: CPU Run 1 Run 2 Run 3 4 8 12 16 20 SE +/- 0.04, N = 3 SE +/- 0.04, N = 3 SE +/- 0.07, N = 3 15.96 15.70 16.45 MIN: 15.64 MIN: 15.54 MIN: 16.19 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
oneDNN Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 1.5 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU Run 1 Run 2 Run 3 40 80 120 160 200 SE +/- 1.99, N = 15 SE +/- 2.75, N = 4 SE +/- 1.78, N = 15 175.57 169.76 176.76 MIN: 161.6 MIN: 166.09 MIN: 164.88 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
oneDNN Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 1.5 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU Run 1 Run 2 Run 3 5 10 15 20 25 SE +/- 0.06, N = 3 SE +/- 0.02, N = 3 SE +/- 0.17, N = 3 21.16 20.38 20.85 MIN: 20.76 MIN: 19.16 MIN: 20.23 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
Stress-NG Test: MEMFD OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: MEMFD Run 1 Run 2 Run 3 60 120 180 240 300 SE +/- 0.44, N = 3 SE +/- 0.84, N = 3 SE +/- 2.18, N = 3 286.58 297.06 293.65 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
NeatBench Acceleration: CPU OpenBenchmarking.org FPS, More Is Better NeatBench 5 Acceleration: CPU Run 1 Run 2 Run 3 2 4 6 8 10 SE +/- 0.06, N = 3 SE +/- 0.02, N = 3 SE +/- 0.07, N = 3 8.16 8.11 7.89
Build2 Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Build2 0.12 Time To Compile Run 1 Run 2 Run 3 50 100 150 200 250 SE +/- 3.72, N = 3 SE +/- 1.30, N = 3 SE +/- 1.52, N = 3 215.35 209.97 208.53
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 Run 1 Run 2 Run 3 1.4M 2.8M 4.2M 5.6M 7M SE +/- 110965.05, N = 3 SE +/- 20978.35, N = 3 SE +/- 98775.41, N = 5 6263395.17 6453494.07 6385777.22 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
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 Run 1 Run 2 Run 3 100K 200K 300K 400K 500K SE +/- 384.03, N = 3 SE +/- 7777.27, N = 3 SE +/- 2883.26, N = 3 453045.74 445829.21 458759.57 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
NCNN Target: CPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: alexnet Run 1 Run 2 Run 3 6 12 18 24 30 SE +/- 0.16, N = 3 SE +/- 0.22, N = 3 SE +/- 0.31, N = 3 24.89 24.20 24.33 MIN: 24.39 / MAX: 26.77 MIN: 23.76 / MAX: 25.06 MIN: 23.74 / MAX: 27.78 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Renaissance Test: Savina Reactors.IO OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.10.0 Test: Savina Reactors.IO Run 1 Run 2 Run 3 4K 8K 12K 16K 20K SE +/- 208.42, N = 11 SE +/- 201.83, N = 5 SE +/- 150.18, N = 5 19921.23 19713.40 19384.78
MPV Video Input: Big Buck Bunny Sunflower 4K - Decode: Software Only OpenBenchmarking.org FPS, More Is Better MPV Video Input: Big Buck Bunny Sunflower 4K - Decode: Software Only Run 1 Run 2 Run 3 80 160 240 320 400 SE +/- 1.84, N = 3 SE +/- 6.84, N = 3 SE +/- 2.64, N = 3 353.18 349.48 344.54 MIN: 243.18 / MAX: 461.46 MIN: 232.45 / MAX: 461.62 MIN: 237.94 / MAX: 441.79 1. mpv 0.29.0
Renaissance Test: In-Memory Database Shootout OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.10.0 Test: In-Memory Database Shootout Run 1 Run 2 Run 3 800 1600 2400 3200 4000 SE +/- 29.28, N = 25 SE +/- 43.96, N = 5 SE +/- 8.96, N = 5 3735.45 3700.01 3787.31
Java Gradle Build Gradle Build: Reactor OpenBenchmarking.org Seconds, Fewer Is Better Java Gradle Build Gradle Build: Reactor Run 1 Run 2 Run 3 60 120 180 240 300 SE +/- 3.33, N = 7 SE +/- 3.55, N = 9 SE +/- 4.63, N = 9 265.78 260.30 260.04
Stress-NG Test: Atomic OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Atomic Run 1 Run 2 Run 3 40K 80K 120K 160K 200K SE +/- 533.86, N = 3 SE +/- 2587.53, N = 7 SE +/- 2157.56, N = 15 202671.08 205022.47 207144.00 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
Stress-NG Test: Malloc OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Malloc Run 1 Run 2 Run 3 7M 14M 21M 28M 35M SE +/- 56736.14, N = 3 SE +/- 170156.05, N = 3 SE +/- 17315.95, N = 3 31337895.18 32002407.75 31529776.24 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
Stress-NG Test: Context Switching OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Context Switching Run 1 Run 2 Run 3 400K 800K 1200K 1600K 2000K SE +/- 19078.01, N = 3 SE +/- 14863.93, N = 3 SE +/- 16739.57, N = 3 1693803.99 1698242.99 1728927.62 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
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 Run 1 Run 2 Run 3 200K 400K 600K 800K 1000K SE +/- 12233.47, N = 3 SE +/- 3868.34, N = 3 SE +/- 3971.45, N = 3 855281.8 852344.4 838679.5
Renaissance Test: Apache Spark ALS OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.10.0 Test: Apache Spark ALS Run 1 Run 2 Run 3 600 1200 1800 2400 3000 SE +/- 28.08, N = 5 SE +/- 26.47, N = 25 SE +/- 21.08, N = 5 2664.26 2671.80 2620.76
NCNN Target: CPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: blazeface Run 1 Run 2 Run 3 0.5018 1.0036 1.5054 2.0072 2.509 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 2.20 2.19 2.23 MIN: 2.16 / MAX: 2.8 MIN: 2.12 / MAX: 2.46 MIN: 2.17 / MAX: 2.43 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Renaissance Test: Akka Unbalanced Cobwebbed Tree OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.10.0 Test: Akka Unbalanced Cobwebbed Tree Run 1 Run 2 Run 3 2K 4K 6K 8K 10K SE +/- 119.47, N = 7 SE +/- 124.27, N = 5 SE +/- 86.29, N = 5 9284.60 9409.74 9242.49
Renaissance Test: Scala Dotty OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.10.0 Test: Scala Dotty Run 1 Run 2 Run 3 400 800 1200 1600 2000 SE +/- 12.40, N = 5 SE +/- 15.89, N = 5 SE +/- 15.65, N = 5 1974.92 1964.48 1999.39
Stress-NG Test: CPU Stress OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: CPU Stress Run 1 Run 2 Run 3 400 800 1200 1600 2000 SE +/- 10.47, N = 3 SE +/- 9.37, N = 3 SE +/- 4.44, N = 3 1751.85 1741.82 1770.49 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
Stress-NG Test: Socket Activity OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Socket Activity Run 1 Run 2 Run 3 1300 2600 3900 5200 6500 SE +/- 57.67, N = 3 SE +/- 102.63, N = 3 SE +/- 72.33, N = 3 6030.69 6030.96 6125.05 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
NCNN Target: CPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: mnasnet Run 1 Run 2 Run 3 2 4 6 8 10 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 6.57 6.55 6.65 MIN: 6.5 / MAX: 7.61 MIN: 6.5 / MAX: 9.36 MIN: 6.59 / MAX: 6.71 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Renaissance Test: Random Forest OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.10.0 Test: Random Forest Run 1 Run 2 Run 3 500 1000 1500 2000 2500 SE +/- 25.11, N = 5 SE +/- 17.20, N = 25 SE +/- 26.67, N = 5 2138.86 2135.79 2106.81
oneDNN Harness: IP Batch All - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 1.5 Harness: IP Batch All - Data Type: f32 - Engine: CPU Run 1 Run 2 Run 3 30 60 90 120 150 SE +/- 0.31, N = 3 SE +/- 1.07, N = 3 SE +/- 0.44, N = 3 120.15 120.30 118.53 MIN: 118.47 MIN: 117.48 MIN: 116.71 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
C-Blosc Compressor: blosclz OpenBenchmarking.org MB/s, More Is Better C-Blosc 2.0 Beta 5 Compressor: blosclz Run 1 Run 2 Run 3 1500 3000 4500 6000 7500 SE +/- 15.22, N = 3 SE +/- 11.18, N = 3 SE +/- 12.72, N = 3 6788.0 6787.7 6887.9 1. (CXX) g++ options: -rdynamic
NCNN Target: CPU - Model: mobilenetv2_yolov3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: mobilenetv2_yolov3 Run 1 Run 2 Run 3 6 12 18 24 30 SE +/- 0.04, N = 3 SE +/- 0.15, N = 3 SE +/- 0.30, N = 3 26.87 26.66 26.49 MIN: 26.43 / MAX: 27.62 MIN: 25.93 / MAX: 40.64 MIN: 25.81 / MAX: 27.66 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
DaCapo Benchmark Java Test: Tradebeans OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 9.12-MR1 Java Test: Tradebeans Run 1 Run 2 Run 3 1000 2000 3000 4000 5000 SE +/- 49.10, N = 10 SE +/- 52.68, N = 3 SE +/- 104.15, N = 4 4573 4621 4638
Timed Linux Kernel Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Linux Kernel Compilation 5.4 Time To Compile Run 1 Run 2 Run 3 40 80 120 160 200 SE +/- 0.67, N = 3 SE +/- 0.85, N = 3 SE +/- 2.90, N = 3 177.85 177.88 180.37
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 Run 1 Run 2 Run 3 200K 400K 600K 800K 1000K SE +/- 5150.33, N = 3 SE +/- 3710.45, N = 3 SE +/- 2328.20, N = 3 909598.9 915807.8 903216.0
Mobile Neural Network Model: SqueezeNetV1.0 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2020-09-17 Model: SqueezeNetV1.0 Run 1 Run 2 Run 3 3 6 9 12 15 SE +/- 0.069, N = 3 SE +/- 0.008, N = 3 SE +/- 0.014, N = 3 9.271 9.390 9.399 MIN: 9.11 / MAX: 10.35 MIN: 9.34 / MAX: 10.45 MIN: 9.34 / MAX: 22.37 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
Mobile Neural Network Model: resnet-v2-50 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2020-09-17 Model: resnet-v2-50 Run 1 Run 2 Run 3 10 20 30 40 50 SE +/- 0.23, N = 3 SE +/- 0.11, N = 3 SE +/- 0.20, N = 3 44.34 44.85 44.90 MIN: 43.74 / MAX: 91.68 MIN: 44.55 / MAX: 73.46 MIN: 44.57 / MAX: 57.52 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
InfluxDB Concurrent Streams: 1024 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000 OpenBenchmarking.org val/sec, More Is Better InfluxDB 1.8.2 Concurrent Streams: 1024 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000 Run 1 Run 2 Run 3 200K 400K 600K 800K 1000K SE +/- 4110.61, N = 3 SE +/- 3299.07, N = 3 SE +/- 4766.81, N = 3 971205.0 982263.6 982578.8
DaCapo Benchmark Java Test: Tradesoap OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 9.12-MR1 Java Test: Tradesoap Run 1 Run 2 Run 3 2K 4K 6K 8K 10K SE +/- 34.21, N = 4 SE +/- 81.37, N = 4 SE +/- 38.63, N = 3 7852 7871 7942
libavif avifenc Encoder Speed: 10 OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.7.3 Encoder Speed: 10 Run 1 Run 2 Run 3 2 4 6 8 10 SE +/- 0.014, N = 3 SE +/- 0.012, N = 3 SE +/- 0.021, N = 3 7.877 7.789 7.797 1. (CXX) g++ options: -O3 -fPIC
NCNN Target: CPU - Model: vgg16_int8 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: vgg16_int8 Run 1 Run 2 Run 3 50 100 150 200 250 SE +/- 0.98, N = 3 SE +/- 0.25, N = 3 SE +/- 1.27, N = 3 243.01 240.49 240.88 MIN: 239.48 / MAX: 317.06 MIN: 238.92 / MAX: 251.71 MIN: 237.74 / MAX: 295.55 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
LibRaw Post-Processing Benchmark OpenBenchmarking.org Mpix/sec, More Is Better LibRaw 0.20 Post-Processing Benchmark Run 1 Run 2 Run 3 7 14 21 28 35 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 SE +/- 0.10, N = 3 28.13 28.24 27.95 1. (CXX) g++ options: -O2 -fopenmp -ljpeg -lz -lm
MPV Video Input: Big Buck Bunny Sunflower 1080p - Decode: Software Only OpenBenchmarking.org FPS, More Is Better MPV Video Input: Big Buck Bunny Sunflower 1080p - Decode: Software Only Run 1 Run 2 Run 3 200 400 600 800 1000 SE +/- 6.74, N = 3 SE +/- 1.33, N = 3 SE +/- 3.09, N = 3 902.29 911.23 911.49 MIN: 560.47 / MAX: 995.42 MIN: 570.75 / MAX: 995.92 MIN: 602.06 / MAX: 994.9 1. mpv 0.29.0
Hugin Panorama Photo Assistant + Stitching Time OpenBenchmarking.org Seconds, Fewer Is Better Hugin Panorama Photo Assistant + Stitching Time Run 1 Run 2 Run 3 20 40 60 80 100 SE +/- 0.44, N = 3 SE +/- 0.19, N = 3 SE +/- 0.57, N = 3 81.91 82.23 82.74
DaCapo Benchmark Java Test: H2 OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 9.12-MR1 Java Test: H2 Run 1 Run 2 Run 3 700 1400 2100 2800 3500 SE +/- 28.03, N = 20 SE +/- 31.72, N = 20 SE +/- 28.23, N = 20 3356 3364 3332
Stress-NG Test: Matrix Math OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Matrix Math Run 1 Run 2 Run 3 4K 8K 12K 16K 20K SE +/- 45.24, N = 3 SE +/- 68.81, N = 3 SE +/- 102.55, N = 3 19391.27 19265.77 19207.24 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
Mobile Neural Network Model: inception-v3 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2020-09-17 Model: inception-v3 Run 1 Run 2 Run 3 12 24 36 48 60 SE +/- 0.40, N = 3 SE +/- 0.07, N = 3 SE +/- 0.07, N = 3 54.38 54.89 54.71 MIN: 53.57 / MAX: 66.62 MIN: 54.66 / MAX: 73.33 MIN: 54.42 / MAX: 67.42 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
Zstd Compression Compression Level: 19 OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.4.5 Compression Level: 19 Run 1 Run 2 Run 3 6 12 18 24 30 SE +/- 0.22, N = 3 SE +/- 0.32, N = 3 SE +/- 0.29, N = 3 23.1 23.2 23.3 1. (CC) gcc options: -O3 -pthread -lz -llzma
NCNN Target: CPU - Model: squeezenet_int8 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: squeezenet_int8 Run 1 Run 2 Run 3 6 12 18 24 30 SE +/- 0.03, N = 3 SE +/- 0.16, N = 3 SE +/- 0.07, N = 3 25.32 25.53 25.38 MIN: 25.06 / MAX: 26.6 MIN: 25.2 / MAX: 106.62 MIN: 25.08 / MAX: 38.1 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
AOM AV1 Encoder Mode: Speed 6 Two-Pass OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 2.0 Encoder Mode: Speed 6 Two-Pass Run 1 Run 2 Run 3 0.5985 1.197 1.7955 2.394 2.9925 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 2.64 2.66 2.65 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
eSpeak-NG Speech Engine Text-To-Speech Synthesis OpenBenchmarking.org Seconds, Fewer Is Better eSpeak-NG Speech Engine 20200907 Text-To-Speech Synthesis Run 1 Run 2 Run 3 9 18 27 36 45 SE +/- 0.35, N = 17 SE +/- 0.44, N = 4 SE +/- 0.37, N = 4 40.64 40.76 40.46 1. (CC) gcc options: -O2 -std=c99
GPAW Input: Carbon Nanotube OpenBenchmarking.org Seconds, Fewer Is Better GPAW 20.1 Input: Carbon Nanotube Run 1 Run 2 Run 3 140 280 420 560 700 SE +/- 0.92, N = 3 SE +/- 0.96, N = 3 SE +/- 0.86, N = 3 653.11 648.61 648.33 1. (CC) gcc options: -pthread -shared -lxc -lblas -lmpi
Monte Carlo Simulations of Ionised Nebulae Input: Dust 2D tau100.0 OpenBenchmarking.org Seconds, Fewer Is Better Monte Carlo Simulations of Ionised Nebulae 2019-03-24 Input: Dust 2D tau100.0 Run 1 Run 2 Run 3 60 120 180 240 300 SE +/- 1.53, N = 3 SE +/- 0.88, N = 3 SE +/- 0.33, N = 3 296 295 294 1. (F9X) gfortran options: -cpp -Jsource/ -ffree-line-length-0 -lm -std=legacy -O3 -O2 -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi
oneDNN Harness: IP Batch 1D - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 1.5 Harness: IP Batch 1D - Data Type: f32 - Engine: CPU Run 1 Run 2 Run 3 2 4 6 8 10 SE +/- 0.01407, N = 3 SE +/- 0.05947, N = 3 SE +/- 0.07930, N = 3 8.26351 8.30212 8.31908 MIN: 8.06 MIN: 8.01 MIN: 8.03 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
GNU Octave Benchmark OpenBenchmarking.org Seconds, Fewer Is Better GNU Octave Benchmark 4.4.1 Run 1 Run 2 Run 3 2 4 6 8 10 SE +/- 0.037, N = 5 SE +/- 0.039, N = 5 SE +/- 0.042, N = 5 8.707 8.653 8.710
Stress-NG Test: NUMA OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: NUMA Run 1 Run 2 Run 3 20 40 60 80 100 SE +/- 0.41, N = 3 SE +/- 0.41, N = 3 SE +/- 0.22, N = 3 85.99 85.43 85.43 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
oneDNN Harness: Deconvolution Batch deconv_1d - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 1.5 Harness: Deconvolution Batch deconv_1d - Data Type: f32 - Engine: CPU Run 1 Run 2 Run 3 3 6 9 12 15 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 10.07 10.06 10.12 MIN: 9.96 MIN: 9.97 MIN: 10 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
GLmark2 Resolution: 1920 x 1080 OpenBenchmarking.org Score, More Is Better GLmark2 2020.04 Resolution: 1920 x 1080 Run 1 Run 2 Run 3 200 400 600 800 1000 985 982 988
NCNN Target: CPU - Model: squeezenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: squeezenet Run 1 Run 2 Run 3 1.1138 2.2276 3.3414 4.4552 5.569 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 4.92 4.95 4.93 MIN: 4.86 / MAX: 5.52 MIN: 4.89 / MAX: 9.04 MIN: 4.86 / MAX: 5.04 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
AOM AV1 Encoder Mode: Speed 4 Two-Pass OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 2.0 Encoder Mode: Speed 4 Two-Pass Run 1 Run 2 Run 3 0.3735 0.747 1.1205 1.494 1.8675 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 1.65 1.66 1.66 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
DaCapo Benchmark Java Test: Jython OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 9.12-MR1 Java Test: Jython Run 1 Run 2 Run 3 1100 2200 3300 4400 5500 SE +/- 47.91, N = 4 SE +/- 72.34, N = 4 SE +/- 55.50, N = 4 5257 5242 5228
NCNN Target: CPU - Model: mobilenet_v3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: mobilenet_v3 Run 1 Run 2 Run 3 2 4 6 8 10 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 6.00 5.99 6.02 MIN: 5.94 / MAX: 6.48 MIN: 5.94 / MAX: 6.2 MIN: 5.93 / MAX: 6.12 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
AOM AV1 Encoder Mode: Speed 8 Realtime OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 2.0 Encoder Mode: Speed 8 Realtime Run 1 Run 2 Run 3 8 16 24 32 40 SE +/- 0.05, N = 3 SE +/- 0.23, N = 3 SE +/- 0.06, N = 3 33.82 33.67 33.83 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
Stress-NG Test: Forking OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Forking Run 1 Run 2 Run 3 8K 16K 24K 32K 40K SE +/- 221.11, N = 3 SE +/- 73.58, N = 3 SE +/- 193.79, N = 3 37547.26 37723.77 37590.58 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
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 Run 1 Run 2 Run 3 13 26 39 52 65 SE +/- 0.28, N = 3 SE +/- 0.13, N = 3 SE +/- 0.11, N = 3 58.69 58.60 58.43 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
libavif avifenc Encoder Speed: 2 OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.7.3 Encoder Speed: 2 Run 1 Run 2 Run 3 30 60 90 120 150 SE +/- 0.10, N = 3 SE +/- 0.16, N = 3 SE +/- 0.03, N = 3 115.30 115.44 114.99 1. (CXX) g++ options: -O3 -fPIC
NAMD ATPase Simulation - 327,506 Atoms OpenBenchmarking.org days/ns, Fewer Is Better NAMD 2.14 ATPase Simulation - 327,506 Atoms Run 1 Run 2 Run 3 0.9243 1.8486 2.7729 3.6972 4.6215 SE +/- 0.01035, N = 3 SE +/- 0.00571, N = 3 SE +/- 0.00576, N = 3 4.10818 4.09223 4.09524
NCNN Target: CPU - Model: googlenet_int8 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: googlenet_int8 Run 1 Run 2 Run 3 16 32 48 64 80 SE +/- 0.11, N = 3 SE +/- 0.07, N = 3 SE +/- 0.09, N = 3 71.78 71.54 71.58 MIN: 71.24 / MAX: 84.94 MIN: 71.13 / MAX: 84.34 MIN: 71.35 / MAX: 75.03 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 Run 1 Run 2 Run 3 80K 160K 240K 320K 400K SE +/- 122.99, N = 3 SE +/- 40.08, N = 3 SE +/- 37.63, N = 3 387372 386514 386168
libavif avifenc Encoder Speed: 8 OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.7.3 Encoder Speed: 8 Run 1 Run 2 Run 3 2 4 6 8 10 SE +/- 0.029, N = 3 SE +/- 0.002, N = 3 SE +/- 0.009, N = 3 8.517 8.492 8.491 1. (CXX) g++ options: -O3 -fPIC
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 Run 1 Run 2 Run 3 2 4 6 8 10 SE +/- 0.009, N = 3 SE +/- 0.018, N = 3 SE +/- 0.009, N = 3 6.928 6.949 6.935 MIN: 6.88 / MAX: 7.79 MIN: 6.9 / MAX: 19.59 MIN: 6.9 / MAX: 19.71 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
Incompact3D Input: Cylinder OpenBenchmarking.org Seconds, Fewer Is Better Incompact3D 2020-09-17 Input: Cylinder Run 1 Run 2 Run 3 170 340 510 680 850 SE +/- 0.56, N = 3 SE +/- 0.27, N = 3 SE +/- 0.78, N = 3 769.23 768.57 766.92 1. (F9X) gfortran options: -cpp -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi
Zstd Compression Compression Level: 3 OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.4.5 Compression Level: 3 Run 1 Run 2 Run 3 500 1000 1500 2000 2500 SE +/- 0.95, N = 3 SE +/- 2.17, N = 3 SE +/- 1.88, N = 3 2494.7 2498.2 2502.0 1. (CC) gcc options: -O3 -pthread -lz -llzma
Timed Apache Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Apache Compilation 2.4.41 Time To Compile Run 1 Run 2 Run 3 7 14 21 28 35 SE +/- 0.09, N = 3 SE +/- 0.03, N = 3 SE +/- 0.07, N = 3 30.58 30.60 30.52
Montage Astronomical Image Mosaic Engine Mosaic of M17, K band, 1.5 deg x 1.5 deg OpenBenchmarking.org Seconds, Fewer Is Better Montage Astronomical Image Mosaic Engine 6.0 Mosaic of M17, K band, 1.5 deg x 1.5 deg Run 1 Run 2 Run 3 20 40 60 80 100 SE +/- 0.24, N = 3 SE +/- 0.04, N = 3 SE +/- 0.01, N = 3 92.33 92.24 92.09 1. (CC) gcc options: -std=gnu99 -lcfitsio -lm -O2
Stress-NG Test: Crypto OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Crypto Run 1 Run 2 Run 3 200 400 600 800 1000 SE +/- 0.22, N = 3 SE +/- 0.45, N = 3 SE +/- 1.75, N = 3 817.97 818.90 816.73 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
TensorFlow Lite Model: Mobilenet Float OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Mobilenet Float Run 1 Run 2 Run 3 80K 160K 240K 320K 400K SE +/- 67.22, N = 3 SE +/- 25.78, N = 3 SE +/- 23.50, N = 3 366589 365619 365631
BRL-CAD VGR Performance Metric OpenBenchmarking.org VGR Performance Metric, More Is Better BRL-CAD 7.30.8 VGR Performance Metric Run 1 Run 2 Run 3 10K 20K 30K 40K 50K 45474 45358 45365 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
Mobile Neural Network Model: MobileNetV2_224 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2020-09-17 Model: MobileNetV2_224 Run 1 Run 2 Run 3 1.1178 2.2356 3.3534 4.4712 5.589 SE +/- 0.003, N = 3 SE +/- 0.018, N = 3 SE +/- 0.023, N = 3 4.956 4.967 4.968 MIN: 4.92 / MAX: 5.83 MIN: 4.91 / MAX: 6.37 MIN: 4.92 / MAX: 6.4 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: MMAP OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: MMAP Run 1 Run 2 Run 3 12 24 36 48 60 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 54.22 54.32 54.19 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
ASTC Encoder Preset: Fast OpenBenchmarking.org Seconds, Fewer Is Better ASTC Encoder 2.0 Preset: Fast Run 1 Run 2 Run 3 2 4 6 8 10 SE +/- 0.04, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 8.40 8.41 8.42 1. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread
AOM AV1 Encoder Mode: Speed 6 Realtime OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 2.0 Encoder Mode: Speed 6 Realtime Run 1 Run 2 Run 3 3 6 9 12 15 SE +/- 0.06, N = 3 SE +/- 0.05, N = 3 SE +/- 0.06, N = 3 13.44 13.47 13.47 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
Stress-NG Test: Vector Math OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Vector Math Run 1 Run 2 Run 3 5K 10K 15K 20K 25K SE +/- 1.66, N = 3 SE +/- 1.27, N = 3 SE +/- 60.90, N = 3 25159.22 25153.83 25103.46 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -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 Run 1 Run 2 Run 3 80K 160K 240K 320K 400K SE +/- 49.05, N = 3 SE +/- 22.82, N = 3 SE +/- 65.69, N = 3 354486 353741 353786
LAMMPS Molecular Dynamics Simulator Model: Rhodopsin Protein OpenBenchmarking.org ns/day, More Is Better LAMMPS Molecular Dynamics Simulator 24Aug2020 Model: Rhodopsin Protein Run 1 Run 2 Run 3 0.6458 1.2916 1.9374 2.5832 3.229 SE +/- 0.012, N = 3 SE +/- 0.007, N = 3 SE +/- 0.014, N = 3 2.864 2.866 2.870 1. (CXX) g++ options: -O3 -pthread -lm
GROMACS Water Benchmark OpenBenchmarking.org Ns Per Day, More Is Better GROMACS 2020.1 Water Benchmark Run 1 Run 2 Run 3 0.1091 0.2182 0.3273 0.4364 0.5455 SE +/- 0.001, N = 3 SE +/- 0.002, N = 3 SE +/- 0.002, N = 3 0.485 0.484 0.485 1. (CXX) g++ options: -O3 -pthread -lrt -lpthread -lm
SVT-AV1 Encoder Mode: Enc Mode 8 - Input: 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 0.8 Encoder Mode: Enc Mode 8 - Input: 1080p Run 1 Run 2 Run 3 3 6 9 12 15 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 12.19 12.22 12.21 1. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie
TensorFlow Lite Model: Inception V4 OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Inception V4 Run 1 Run 2 Run 3 2M 4M 6M 8M 10M SE +/- 551.94, N = 3 SE +/- 600.45, N = 3 SE +/- 496.06, N = 3 7825710 7809863 7810147
TensorFlow Lite Model: Inception ResNet V2 OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Inception ResNet V2 Run 1 Run 2 Run 3 1.5M 3M 4.5M 6M 7.5M SE +/- 488.48, N = 3 SE +/- 384.23, N = 3 SE +/- 160.93, N = 3 7077587 7063550 7064830
TensorFlow Lite Model: SqueezeNet OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: SqueezeNet Run 1 Run 2 Run 3 120K 240K 360K 480K 600K SE +/- 37.42, N = 3 SE +/- 15.59, N = 3 SE +/- 19.86, N = 3 541870 540887 540902
NCNN Target: CPU - Model: resnet18_int8 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: resnet18_int8 Run 1 Run 2 Run 3 9 18 27 36 45 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 39.46 39.43 39.39 MIN: 39.21 / MAX: 41.03 MIN: 39.25 / MAX: 41.06 MIN: 39.26 / MAX: 40.72 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 Run 1 Run 2 Run 3 160K 320K 480K 640K 800K SE +/- 103.59, N = 3 SE +/- 226.37, N = 3 SE +/- 504.30, N = 3 743806.03 744929.81 744313.54 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
OCRMyPDF Processing 60 Page PDF Document OpenBenchmarking.org Seconds, Fewer Is Better OCRMyPDF 6.2.4 Processing 60 Page PDF Document Run 1 Run 2 Run 3 13 26 39 52 65 SE +/- 0.19, N = 3 SE +/- 0.51, N = 3 SE +/- 0.07, N = 3 56.16 56.08 56.12
SVT-AV1 Encoder Mode: Enc Mode 4 - Input: 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 0.8 Encoder Mode: Enc Mode 4 - Input: 1080p Run 1 Run 2 Run 3 0.3371 0.6742 1.0113 1.3484 1.6855 SE +/- 0.000, N = 3 SE +/- 0.002, N = 3 SE +/- 0.001, N = 3 1.496 1.498 1.498 1. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie
ASTC Encoder Preset: Exhaustive OpenBenchmarking.org Seconds, Fewer Is Better ASTC Encoder 2.0 Preset: Exhaustive Run 1 Run 2 Run 3 130 260 390 520 650 SE +/- 0.06, N = 3 SE +/- 0.20, N = 3 SE +/- 0.06, N = 3 589.16 588.40 588.48 1. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread
Stress-NG Test: SENDFILE OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: SENDFILE Run 1 Run 2 Run 3 10K 20K 30K 40K 50K SE +/- 45.03, N = 3 SE +/- 55.35, N = 3 SE +/- 23.83, N = 3 46822.85 46865.51 46879.66 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
NCNN Target: CPU - Model: resnet50_int8 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: resnet50_int8 Run 1 Run 2 Run 3 30 60 90 120 150 SE +/- 0.08, N = 3 SE +/- 0.14, N = 3 SE +/- 0.25, N = 3 133.02 132.94 132.87 MIN: 132.43 / MAX: 145.46 MIN: 132.44 / MAX: 146.41 MIN: 132.31 / MAX: 135.34 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
ASTC Encoder Preset: Medium OpenBenchmarking.org Seconds, Fewer Is Better ASTC Encoder 2.0 Preset: Medium Run 1 Run 2 Run 3 3 6 9 12 15 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 10.93 10.92 10.92 1. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread
ASTC Encoder Preset: Thorough OpenBenchmarking.org Seconds, Fewer Is Better ASTC Encoder 2.0 Preset: Thorough Run 1 Run 2 Run 3 16 32 48 64 80 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 72.66 72.61 72.61 1. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread
libavif avifenc Encoder Speed: 0 OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.7.3 Encoder Speed: 0 Run 1 Run 2 Run 3 40 80 120 160 200 SE +/- 0.31, N = 3 SE +/- 0.22, N = 3 SE +/- 0.30, N = 3 195.32 195.31 195.39 1. (CXX) g++ options: -O3 -fPIC
Stress-NG Test: RdRand OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: RdRand Run 1 Run 2 Run 3 50K 100K 150K 200K 250K SE +/- 51.51, N = 3 SE +/- 49.46, N = 3 SE +/- 41.56, N = 3 240337.19 240331.88 240319.26 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
LuxCoreRender Scene: DLSC OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.3 Scene: DLSC Run 1 Run 2 Run 3 0.1508 0.3016 0.4524 0.6032 0.754 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.67 0.67 0.67 MIN: 0.65 / MAX: 0.68 MIN: 0.65 / MAX: 0.68 MIN: 0.65 / MAX: 0.68
AOM AV1 Encoder Mode: Speed 0 Two-Pass OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 2.0 Encoder Mode: Speed 0 Two-Pass Run 1 Run 2 Run 3 0.045 0.09 0.135 0.18 0.225 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.2 0.2 0.2 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenCV Test: DNN - Deep Neural Network OpenBenchmarking.org ms, Fewer Is Better OpenCV 4.4 Test: DNN - Deep Neural Network Run 1 Run 2 Run 3 1200 2400 3600 4800 6000 SE +/- 336.20, N = 12 SE +/- 68.30, N = 3 SE +/- 173.70, N = 15 5441 4928 5494 1. (CXX) g++ options: -fsigned-char -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -msse -msse2 -msse3 -fvisibility=hidden -O3 -ldl -lm -lpthread -lrt
Stress-NG Test: CPU Cache OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: CPU Cache Run 1 Run 2 Run 3 10 20 30 40 50 SE +/- 0.81, N = 15 SE +/- 0.67, N = 15 SE +/- 0.64, N = 5 45.27 44.21 45.91 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
System GZIP Decompression OpenBenchmarking.org Seconds, Fewer Is Better System GZIP Decompression Run 1 Run 2 Run 3 0.7756 1.5512 2.3268 3.1024 3.878 SE +/- 0.068, N = 14 SE +/- 0.010, N = 3 SE +/- 0.004, N = 3 3.447 3.385 3.381
oneDNN Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 1.5 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU Run 1 Run 2 Run 3 0.8362 1.6724 2.5086 3.3448 4.181 SE +/- 0.03639, N = 15 SE +/- 0.03590, N = 3 SE +/- 0.06193, N = 15 3.38848 3.66649 3.71663 MIN: 3.17 MIN: 3.46 MIN: 3.28 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
Renaissance Test: Apache Spark PageRank OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.10.0 Test: Apache Spark PageRank Run 1 Run 2 Run 3 1000 2000 3000 4000 5000 SE +/- 116.60, N = 20 SE +/- 125.25, N = 20 SE +/- 87.30, N = 20 4865.50 4803.63 4712.37
Renaissance Test: Apache Spark Bayes OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.10.0 Test: Apache Spark Bayes Run 1 Run 2 Run 3 900 1800 2700 3600 4500 SE +/- 108.68, N = 20 SE +/- 92.43, N = 20 SE +/- 109.38, N = 20 3779.50 3989.70 3909.15
Phoronix Test Suite v10.8.4