Ryzen 3 3300X Xmas AMD Ryzen 3 3300X 4-Core testing with a MSI B350M GAMING PRO (MS-7A39) v1.0 (2.NR BIOS) and AMD FirePro V3800 512MB on Ubuntu 20.04 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2012288-HA-RYZEN333058&sor&grs .
Ryzen 3 3300X Xmas 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 AMD Ryzen 3 3300X 4-Core @ 3.80GHz (4 Cores / 8 Threads) MSI B350M GAMING PRO (MS-7A39) v1.0 (2.NR BIOS) AMD Starship/Matisse 8GB 256GB INTEL SSDPEKKW256G7 AMD FirePro V3800 512MB AMD Redwood HDMI Audio VA2431 Realtek RTL8111/8168/8411 Ubuntu 20.04 5.9.0-rc5-14sep-patch (x86_64) 20200914 GNOME Shell 3.36.4 X Server 1.20.8 modesetting 1.20.8 3.3 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 Disk Details - NONE / errors=remount-ro,relatime,rw / Block Size: 4096 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 3 3300X Xmas onednn: IP Shapes 3D - f32 - CPU onednn: IP Shapes 3D - u8s8f32 - CPU clomp: Static OMP Speedup onednn: Matrix Multiply Batch Shapes Transformer - f32 - CPU ncnn: CPU - googlenet ncnn: CPU-v2-v2 - mobilenet-v2 ncnn: CPU-v3-v3 - mobilenet-v3 onednn: Convolution Batch Shapes Auto - u8s8f32 - CPU build2: Time To Compile onednn: Convolution Batch Shapes Auto - f32 - CPU openvino: Age Gender Recognition Retail 0013 FP32 - CPU node-web-tooling: ncnn: CPU - shufflenet-v2 openvino: Age Gender Recognition Retail 0013 FP32 - CPU openvino: Age Gender Recognition Retail 0013 FP16 - CPU rav1e: 1 stockfish: Total Time simdjson: Kostya openvino: Face Detection 0106 FP32 - CPU ncnn: CPU - regnety_400m onednn: Recurrent Neural Network Inference - f32 - CPU ncnn: CPU - mobilenet rav1e: 5 simdjson: PartialTweets simdjson: DistinctUserID onednn: IP Shapes 1D - f32 - CPU openvino: Age Gender Recognition Retail 0013 FP16 - CPU onednn: Deconvolution Batch shapes_1d - u8s8f32 - CPU onednn: IP Shapes 1D - u8s8f32 - CPU onednn: Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPU onednn: Recurrent Neural Network Training - f32 - CPU phpbench: PHP Benchmark Suite openvino: Face Detection 0106 FP16 - CPU coremark: CoreMark Size 666 - Iterations Per Second ncnn: CPU - yolov4-tiny ncnn: CPU - resnet18 brl-cad: VGR Performance Metric ncnn: CPU - alexnet onednn: Recurrent Neural Network Training - u8s8f32 - CPU onednn: Deconvolution Batch shapes_1d - f32 - CPU rav1e: 6 onednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPU openvino: Person Detection 0106 FP16 - CPU openvino: Face Detection 0106 FP32 - CPU onednn: Deconvolution Batch shapes_3d - f32 - CPU ncnn: CPU - vgg16 sqlite-speedtest: Timed Time - Size 1,000 asmfish: 1024 Hash Memory, 26 Depth astcenc: Fast onednn: Deconvolution Batch shapes_3d - u8s8f32 - CPU rav1e: 10 build-eigen: Time To Compile unpack-firefox: firefox-84.0.source.tar.xz build-clash: Time To Compile onednn: Recurrent Neural Network Training - bf16bf16bf16 - CPU ncnn: CPU - squeezenet_ssd build-ffmpeg: Time To Compile ncnn: CPU - mnasnet encode-opus: WAV To Opus Encode hmmer: Pfam Database Search ncnn: CPU - resnet50 encode-wavpack: WAV To WavPack unpack-linux: linux-4.15.tar.xz astcenc: Exhaustive encode-ape: WAV To APE openvino: Person Detection 0106 FP32 - CPU astcenc: Thorough openvino: Person Detection 0106 FP32 - CPU openvino: Person Detection 0106 FP16 - CPU openvino: Face Detection 0106 FP16 - CPU astcenc: Medium simdjson: LargeRand ncnn: CPU - blazeface ncnn: CPU - efficientnet-b0 onednn: Recurrent Neural Network Inference - u8s8f32 - CPU 1 2 3 8.52111 2.50766 3.2 4.75671 15.30 5.35 4.53 21.8841 211.747 21.2521 1.02 12.57 8.05 3893.18 1.00 0.387 10378430 0.60 1.26 10.85 3081.19 20.84 1.163 0.68 0.7 6.84371 3955.38 11.3793 4.92904 5.72711 5947.85 671321 3131.88 182448.275786 28.30 15.82 66712 14.45 5994.08 9.12080 1.542 3093.57 4532.98 3187.96 11.4080 65.70 57.686 14970912 7.47 9.98594 3.469 72.834 17.504 242.931 5991.49 27.10 94.307 4.89 7.180 103.421 33.67 12.376 4.944 410.74 11.553 4567.40 50.94 0.87 0.88 1.27 8.32 0.43 2.27 7.62 3080.42 9.81054 2.64117 3.0 4.90760 15.94 5.41 4.69 22.6474 205.345 21.5989 1.00 12.23 8.25 3962.81 0.99 0.390 10313214 0.60 1.26 10.98 3106.43 20.74 1.146 0.69 0.69 6.86396 3992.29 11.5146 4.96126 5.76708 5999.78 678566 3165.51 180553.023278 28.59 15.70 66332 14.58 6027.19 9.16172 1.553 3114.62 4536.61 3178.77 11.4275 66.06 58.043 15051454 7.50 10.02125 3.483 73.103 17.459 241.827 6018.26 27.13 94.693 4.89 7.160 103.275 33.77 12.412 4.931 411.15 11.528 4557.65 50.96 0.87 0.88 1.27 8.32 0.43 2.15 7.77 3114.00 7.80639 2.40369 3.1 5.02241 15.78 5.21 4.60 22.0029 206.090 20.9470 0.99 12.50 8.03 3973.20 1.01 0.394 10202806 0.59 1.28 11.02 3058.79 21.06 1.156 0.68 0.7 6.76855 3937.05 11.3620 4.89977 5.79035 5934.31 678009 3149.60 181403.672422 28.46 15.86 66953 14.46 5977.34 9.09468 1.551 3101.65 4506.69 3167.39 11.3538 66.12 57.870 15000176 7.46 9.96837 3.486 73.184 17.424 242.572 6010.57 27.01 94.431 4.91 7.157 103.101 33.77 12.387 4.937 410.20 11.537 4562.87 50.93 0.87 0.88 1.27 8.32 0.43 2.20 7.54 7762.44 OpenBenchmarking.org
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 3 1 2 3 6 9 12 15 SE +/- 0.03984, N = 3 SE +/- 0.06499, N = 3 SE +/- 0.03478, N = 3 7.80639 8.52111 9.81054 MIN: 7.52 MIN: 8.23 MIN: 9.58 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 3 1 2 0.5943 1.1886 1.7829 2.3772 2.9715 SE +/- 0.01203, N = 3 SE +/- 0.00755, N = 3 SE +/- 0.02828, N = 3 2.40369 2.50766 2.64117 MIN: 2.16 MIN: 2.23 MIN: 2.35 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
CLOMP Static OMP Speedup OpenBenchmarking.org Speedup, More Is Better CLOMP 1.2 Static OMP Speedup 1 3 2 0.72 1.44 2.16 2.88 3.6 SE +/- 0.03, N = 11 SE +/- 0.00, N = 3 SE +/- 0.03, N = 11 3.2 3.1 3.0 1. (CC) gcc options: -fopenmp -O3 -lm
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 1.13 2.26 3.39 4.52 5.65 SE +/- 0.01568, N = 3 SE +/- 0.00870, N = 3 SE +/- 0.01272, N = 3 4.75671 4.90760 5.02241 MIN: 4.6 MIN: 4.73 MIN: 4.92 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
NCNN Target: CPU - Model: googlenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: googlenet 1 3 2 4 8 12 16 20 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.09, N = 3 15.30 15.78 15.94 MIN: 15.16 / MAX: 15.91 MIN: 15.23 / MAX: 81.78 MIN: 15.25 / MAX: 84.78 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU-v2-v2 - Model: mobilenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU-v2-v2 - Model: mobilenet-v2 3 1 2 1.2173 2.4346 3.6519 4.8692 6.0865 SE +/- 0.02, N = 3 SE +/- 0.11, N = 3 SE +/- 0.19, N = 3 5.21 5.35 5.41 MIN: 5.11 / MAX: 6.57 MIN: 5.09 / MAX: 69.96 MIN: 5.09 / MAX: 6.58 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU-v3-v3 - Model: mobilenet-v3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU-v3-v3 - Model: mobilenet-v3 1 3 2 1.0553 2.1106 3.1659 4.2212 5.2765 SE +/- 0.01, N = 3 SE +/- 0.12, N = 3 SE +/- 0.08, N = 3 4.53 4.60 4.69 MIN: 4.45 / MAX: 5.67 MIN: 4.41 / MAX: 69.02 MIN: 4.41 / MAX: 69 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
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 3 2 5 10 15 20 25 SE +/- 0.20, N = 3 SE +/- 0.02, N = 3 SE +/- 0.17, N = 3 21.88 22.00 22.65 MIN: 21.29 MIN: 21.19 MIN: 21.5 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
Build2 Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Build2 0.13 Time To Compile 2 3 1 50 100 150 200 250 SE +/- 0.43, N = 3 SE +/- 0.42, N = 3 SE +/- 2.92, N = 4 205.35 206.09 211.75
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 3 1 2 5 10 15 20 25 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 20.95 21.25 21.60 MIN: 20.52 MIN: 20.85 MIN: 21.27 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 3 2 1 0.2295 0.459 0.6885 0.918 1.1475 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 0.99 1.00 1.02
Node.js V8 Web Tooling Benchmark OpenBenchmarking.org runs/s, More Is Better Node.js V8 Web Tooling Benchmark 1 3 2 3 6 9 12 15 SE +/- 0.05, N = 3 SE +/- 0.06, N = 3 SE +/- 0.16, N = 4 12.57 12.50 12.23 1. Nodejs
v10.19.0
NCNN Target: CPU - Model: shufflenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: shufflenet-v2 3 1 2 2 4 6 8 10 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 SE +/- 0.10, N = 3 8.03 8.05 8.25 MIN: 7.92 / MAX: 9.24 MIN: 7.93 / MAX: 9.17 MIN: 7.96 / MAX: 75.31 1. (CXX) g++ options: -O3 -rdynamic -lgomp -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 3 2 1 900 1800 2700 3600 4500 SE +/- 8.41, N = 3 SE +/- 9.30, N = 3 SE +/- 31.32, N = 3 3973.20 3962.81 3893.18
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 2 1 3 0.2273 0.4546 0.6819 0.9092 1.1365 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 0.99 1.00 1.01
rav1e Speed: 1 OpenBenchmarking.org Frames Per Second, More Is Better rav1e 0.4 Alpha Speed: 1 3 2 1 0.0887 0.1774 0.2661 0.3548 0.4435 SE +/- 0.002, N = 3 SE +/- 0.002, N = 3 SE +/- 0.003, N = 3 0.394 0.390 0.387
Stockfish Total Time OpenBenchmarking.org Nodes Per Second, More Is Better Stockfish 12 Total Time 1 2 3 2M 4M 6M 8M 10M SE +/- 79093.81, N = 3 SE +/- 94152.17, N = 3 SE +/- 8582.84, N = 3 10378430 10313214 10202806 1. (CXX) g++ options: -m64 -lpthread -fno-exceptions -std=c++17 -pedantic -O3 -msse -msse3 -mpopcnt -msse4.1 -mssse3 -msse2 -flto -flto=jobserver
simdjson Throughput Test: Kostya OpenBenchmarking.org GB/s, More Is Better simdjson 0.7.1 Throughput Test: Kostya 2 1 3 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 0.60 0.60 0.59 1. (CXX) g++ options: -O3 -pthread
OpenVINO Model: Face Detection 0106 FP32 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2021.1 Model: Face Detection 0106 FP32 - Device: CPU 3 2 1 0.288 0.576 0.864 1.152 1.44 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 1.28 1.26 1.26
NCNN Target: CPU - Model: regnety_400m OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: regnety_400m 1 2 3 3 6 9 12 15 SE +/- 0.06, N = 3 SE +/- 0.11, N = 3 SE +/- 0.16, N = 3 10.85 10.98 11.02 MIN: 10.64 / MAX: 10.99 MIN: 10.77 / MAX: 70.39 MIN: 10.72 / MAX: 84.03 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
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 3 1 2 700 1400 2100 2800 3500 SE +/- 13.63, N = 3 SE +/- 7.11, N = 3 SE +/- 10.42, N = 3 3058.79 3081.19 3106.43 MIN: 3017.19 MIN: 3046.69 MIN: 3065.93 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
NCNN Target: CPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: mobilenet 2 1 3 5 10 15 20 25 SE +/- 0.12, N = 3 SE +/- 0.14, N = 3 SE +/- 0.15, N = 3 20.74 20.84 21.06 MIN: 20.13 / MAX: 85.1 MIN: 20.05 / MAX: 85.85 MIN: 20.64 / MAX: 85.28 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
rav1e Speed: 5 OpenBenchmarking.org Frames Per Second, More Is Better rav1e 0.4 Alpha Speed: 5 1 3 2 0.2617 0.5234 0.7851 1.0468 1.3085 SE +/- 0.002, N = 3 SE +/- 0.004, N = 3 SE +/- 0.002, N = 3 1.163 1.156 1.146
simdjson Throughput Test: PartialTweets OpenBenchmarking.org GB/s, More Is Better simdjson 0.7.1 Throughput Test: PartialTweets 2 3 1 0.1553 0.3106 0.4659 0.6212 0.7765 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.69 0.68 0.68 1. (CXX) g++ options: -O3 -pthread
simdjson Throughput Test: DistinctUserID OpenBenchmarking.org GB/s, More Is Better simdjson 0.7.1 Throughput Test: DistinctUserID 3 1 2 0.1575 0.315 0.4725 0.63 0.7875 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.70 0.70 0.69 1. (CXX) g++ options: -O3 -pthread
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 3 1 2 2 4 6 8 10 SE +/- 0.02602, N = 3 SE +/- 0.05247, N = 3 SE +/- 0.03795, N = 3 6.76855 6.84371 6.86396 MIN: 6.51 MIN: 6.52 MIN: 6.54 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 FPS, More Is Better OpenVINO 2021.1 Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU 2 1 3 900 1800 2700 3600 4500 SE +/- 12.96, N = 3 SE +/- 39.98, N = 3 SE +/- 18.26, N = 3 3992.29 3955.38 3937.05
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 3 1 2 3 6 9 12 15 SE +/- 0.15, N = 4 SE +/- 0.16, N = 4 SE +/- 0.15, N = 5 11.36 11.38 11.51 MIN: 10.63 MIN: 10.71 MIN: 10.71 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
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 3 1 2 1.1163 2.2326 3.3489 4.4652 5.5815 SE +/- 0.00538, N = 3 SE +/- 0.01238, N = 3 SE +/- 0.02534, N = 3 4.89977 4.92904 4.96126 MIN: 4.78 MIN: 4.71 MIN: 4.76 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 1.3028 2.6056 3.9084 5.2112 6.514 SE +/- 0.04335, N = 3 SE +/- 0.03992, N = 3 SE +/- 0.01983, N = 3 5.72711 5.76708 5.79035 MIN: 5.59 MIN: 5.59 MIN: 5.62 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 3 1 2 1300 2600 3900 5200 6500 SE +/- 17.38, N = 3 SE +/- 16.84, N = 3 SE +/- 23.42, N = 3 5934.31 5947.85 5999.78 MIN: 5855.05 MIN: 5859.06 MIN: 5908.37 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 2 3 1 150K 300K 450K 600K 750K SE +/- 4627.72, N = 3 SE +/- 4938.52, N = 3 SE +/- 2818.40, N = 3 678566 678009 671321
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 3 2 700 1400 2100 2800 3500 SE +/- 28.67, N = 3 SE +/- 15.76, N = 3 SE +/- 7.31, N = 3 3131.88 3149.60 3165.51
Coremark CoreMark Size 666 - Iterations Per Second OpenBenchmarking.org Iterations/Sec, More Is Better Coremark 1.0 CoreMark Size 666 - Iterations Per Second 1 3 2 40K 80K 120K 160K 200K SE +/- 1723.09, N = 3 SE +/- 1517.62, N = 3 SE +/- 84.93, N = 3 182448.28 181403.67 180553.02 1. (CC) gcc options: -O2 -lrt" -lrt
NCNN Target: CPU - Model: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: yolov4-tiny 1 3 2 7 14 21 28 35 SE +/- 0.20, N = 3 SE +/- 0.10, N = 3 SE +/- 0.11, N = 3 28.30 28.46 28.59 MIN: 28 / MAX: 91.83 MIN: 28.22 / MAX: 94.14 MIN: 28.06 / MAX: 97.11 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: resnet18 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: resnet18 2 1 3 4 8 12 16 20 SE +/- 0.03, N = 3 SE +/- 0.12, N = 3 SE +/- 0.11, N = 3 15.70 15.82 15.86 MIN: 15.54 / MAX: 16.16 MIN: 15.58 / MAX: 81.57 MIN: 15.57 / MAX: 80.58 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
BRL-CAD VGR Performance Metric OpenBenchmarking.org VGR Performance Metric, More Is Better BRL-CAD 7.30.8 VGR Performance Metric 3 1 2 14K 28K 42K 56K 70K 66953 66712 66332 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
NCNN Target: CPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: alexnet 1 3 2 4 8 12 16 20 SE +/- 0.13, N = 3 SE +/- 0.08, N = 3 SE +/- 0.12, N = 3 14.45 14.46 14.58 MIN: 14.18 / MAX: 55.84 MIN: 14.24 / MAX: 54.81 MIN: 14.33 / MAX: 76.14 1. (CXX) g++ options: -O3 -rdynamic -lgomp -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 3 1 2 1300 2600 3900 5200 6500 SE +/- 4.69, N = 3 SE +/- 13.74, N = 3 SE +/- 5.71, N = 3 5977.34 5994.08 6027.19 MIN: 5910.31 MIN: 5912.47 MIN: 5962.76 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 3 1 2 3 6 9 12 15 SE +/- 0.03667, N = 3 SE +/- 0.04737, N = 3 SE +/- 0.04005, N = 3 9.09468 9.12080 9.16172 MIN: 8.68 MIN: 8.82 MIN: 8.85 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
rav1e Speed: 6 OpenBenchmarking.org Frames Per Second, More Is Better rav1e 0.4 Alpha Speed: 6 2 3 1 0.3494 0.6988 1.0482 1.3976 1.747 SE +/- 0.007, N = 3 SE +/- 0.005, N = 3 SE +/- 0.006, N = 3 1.553 1.551 1.542
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 3 2 700 1400 2100 2800 3500 SE +/- 12.41, N = 3 SE +/- 4.05, N = 3 SE +/- 2.70, N = 3 3093.57 3101.65 3114.62 MIN: 3053.45 MIN: 3056.76 MIN: 3079.42 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenVINO Model: Person Detection 0106 FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2021.1 Model: Person Detection 0106 FP16 - Device: CPU 3 1 2 1000 2000 3000 4000 5000 SE +/- 4.32, N = 3 SE +/- 0.63, N = 3 SE +/- 3.72, N = 3 4506.69 4532.98 4536.61
OpenVINO Model: Face Detection 0106 FP32 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2021.1 Model: Face Detection 0106 FP32 - Device: CPU 3 2 1 700 1400 2100 2800 3500 SE +/- 15.34, N = 3 SE +/- 7.74, N = 3 SE +/- 15.42, N = 3 3167.39 3178.77 3187.96
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 3 1 2 3 6 9 12 15 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 SE +/- 0.09, N = 3 11.35 11.41 11.43 MIN: 11.07 MIN: 10.92 MIN: 11.08 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
NCNN Target: CPU - Model: vgg16 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: vgg16 1 2 3 15 30 45 60 75 SE +/- 0.10, N = 3 SE +/- 0.00, N = 3 SE +/- 0.24, N = 3 65.70 66.06 66.12 MIN: 65 / MAX: 137.08 MIN: 65.09 / MAX: 141.18 MIN: 65.21 / MAX: 155.64 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
SQLite Speedtest Timed Time - Size 1,000 OpenBenchmarking.org Seconds, Fewer Is Better SQLite Speedtest 3.30 Timed Time - Size 1,000 1 3 2 13 26 39 52 65 SE +/- 0.08, N = 3 SE +/- 0.44, N = 3 SE +/- 0.30, N = 3 57.69 57.87 58.04 1. (CC) gcc options: -O2 -ldl -lz -lpthread
asmFish 1024 Hash Memory, 26 Depth OpenBenchmarking.org Nodes/second, More Is Better asmFish 2018-07-23 1024 Hash Memory, 26 Depth 2 3 1 3M 6M 9M 12M 15M SE +/- 141821.97, N = 3 SE +/- 259111.24, N = 3 SE +/- 147023.02, N = 3 15051454 15000176 14970912
ASTC Encoder Preset: Fast OpenBenchmarking.org Seconds, Fewer Is Better ASTC Encoder 2.0 Preset: Fast 3 1 2 2 4 6 8 10 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 7.46 7.47 7.50 1. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread
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 3 1 2 3 6 9 12 15 SE +/- 0.06352, N = 3 SE +/- 0.06333, N = 3 SE +/- 0.07668, N = 3 9.96837 9.98594 10.02125 MIN: 9.67 MIN: 9.73 MIN: 9.73 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
rav1e Speed: 10 OpenBenchmarking.org Frames Per Second, More Is Better rav1e 0.4 Alpha Speed: 10 3 2 1 0.7844 1.5688 2.3532 3.1376 3.922 SE +/- 0.009, N = 3 SE +/- 0.011, N = 3 SE +/- 0.031, N = 3 3.486 3.483 3.469
Timed Eigen Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Eigen Compilation 3.3.9 Time To Compile 1 2 3 16 32 48 64 80 SE +/- 0.05, N = 3 SE +/- 0.22, N = 3 SE +/- 0.07, N = 3 72.83 73.10 73.18
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 3 2 1 4 8 12 16 20 SE +/- 0.10, N = 4 SE +/- 0.06, N = 4 SE +/- 0.10, N = 4 17.42 17.46 17.50
Timed Clash Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Clash Compilation Time To Compile 2 3 1 50 100 150 200 250 SE +/- 0.49, N = 3 SE +/- 1.22, N = 3 SE +/- 1.59, N = 3 241.83 242.57 242.93
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 3 2 1300 2600 3900 5200 6500 SE +/- 12.75, N = 3 SE +/- 11.64, N = 3 SE +/- 6.95, N = 3 5991.49 6010.57 6018.26 MIN: 5916.15 MIN: 5938.75 MIN: 5963.79 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
NCNN Target: CPU - Model: squeezenet_ssd OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: squeezenet_ssd 3 1 2 6 12 18 24 30 SE +/- 0.20, N = 3 SE +/- 0.20, N = 3 SE +/- 0.07, N = 3 27.01 27.10 27.13 MIN: 26.46 / MAX: 92.67 MIN: 26.69 / MAX: 85.76 MIN: 26.52 / MAX: 93.78 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Timed FFmpeg Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed FFmpeg Compilation 4.2.2 Time To Compile 1 3 2 20 40 60 80 100 SE +/- 0.05, N = 3 SE +/- 0.12, N = 3 SE +/- 0.04, N = 3 94.31 94.43 94.69
NCNN Target: CPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: mnasnet 1 2 3 1.1048 2.2096 3.3144 4.4192 5.524 SE +/- 0.10, N = 3 SE +/- 0.12, N = 3 SE +/- 0.20, N = 2 4.89 4.89 4.91 MIN: 4.65 / MAX: 73.36 MIN: 4.66 / MAX: 9.93 MIN: 4.66 / MAX: 69.67 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Opus Codec Encoding WAV To Opus Encode OpenBenchmarking.org Seconds, Fewer Is Better Opus Codec Encoding 1.3.1 WAV To Opus Encode 3 2 1 2 4 6 8 10 SE +/- 0.011, N = 5 SE +/- 0.009, N = 5 SE +/- 0.014, N = 5 7.157 7.160 7.180 1. (CXX) g++ options: -fvisibility=hidden -logg -lm
Timed HMMer Search Pfam Database Search OpenBenchmarking.org Seconds, Fewer Is Better Timed HMMer Search 3.3.1 Pfam Database Search 3 2 1 20 40 60 80 100 SE +/- 0.06, N = 3 SE +/- 0.36, N = 3 SE +/- 0.21, N = 3 103.10 103.28 103.42 1. (CC) gcc options: -O3 -pthread -lhmmer -leasel -lm
NCNN Target: CPU - Model: resnet50 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: resnet50 1 2 3 8 16 24 32 40 SE +/- 0.12, N = 3 SE +/- 0.14, N = 3 SE +/- 0.13, N = 3 33.67 33.77 33.77 MIN: 33.27 / MAX: 101.28 MIN: 33.47 / MAX: 97.95 MIN: 33.37 / MAX: 101.45 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 3 2 3 6 9 12 15 SE +/- 0.03, N = 5 SE +/- 0.01, N = 5 SE +/- 0.02, N = 5 12.38 12.39 12.41 1. (CXX) g++ options: -rdynamic
Unpacking The Linux Kernel linux-4.15.tar.xz OpenBenchmarking.org Seconds, Fewer Is Better Unpacking The Linux Kernel linux-4.15.tar.xz 2 3 1 1.1124 2.2248 3.3372 4.4496 5.562 SE +/- 0.012, N = 4 SE +/- 0.016, N = 4 SE +/- 0.016, N = 4 4.931 4.937 4.944
ASTC Encoder Preset: Exhaustive OpenBenchmarking.org Seconds, Fewer Is Better ASTC Encoder 2.0 Preset: Exhaustive 3 1 2 90 180 270 360 450 SE +/- 0.35, N = 3 SE +/- 0.25, N = 3 SE +/- 0.26, N = 3 410.20 410.74 411.15 1. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread
Monkey Audio Encoding WAV To APE OpenBenchmarking.org Seconds, Fewer Is Better Monkey Audio Encoding 3.99.6 WAV To APE 2 3 1 3 6 9 12 15 SE +/- 0.01, N = 5 SE +/- 0.04, N = 5 SE +/- 0.05, N = 5 11.53 11.54 11.55 1. (CXX) g++ options: -O3 -pedantic -rdynamic -lrt
OpenVINO Model: Person Detection 0106 FP32 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2021.1 Model: Person Detection 0106 FP32 - Device: CPU 2 3 1 1000 2000 3000 4000 5000 SE +/- 11.91, N = 3 SE +/- 21.64, N = 3 SE +/- 10.36, N = 3 4557.65 4562.87 4567.40
ASTC Encoder Preset: Thorough OpenBenchmarking.org Seconds, Fewer Is Better ASTC Encoder 2.0 Preset: Thorough 3 1 2 11 22 33 44 55 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.05, N = 3 50.93 50.94 50.96 1. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -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 3 2 1 0.1958 0.3916 0.5874 0.7832 0.979 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.87 0.87 0.87
OpenVINO Model: Person Detection 0106 FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2021.1 Model: Person Detection 0106 FP16 - Device: CPU 3 2 1 0.198 0.396 0.594 0.792 0.99 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.88 0.88 0.88
OpenVINO Model: Face Detection 0106 FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2021.1 Model: Face Detection 0106 FP16 - Device: CPU 3 2 1 0.2858 0.5716 0.8574 1.1432 1.429 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 1.27 1.27 1.27
ASTC Encoder Preset: Medium OpenBenchmarking.org Seconds, Fewer Is Better ASTC Encoder 2.0 Preset: Medium 1 2 3 2 4 6 8 10 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 8.32 8.32 8.32 1. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread
simdjson Throughput Test: LargeRandom OpenBenchmarking.org GB/s, More Is Better simdjson 0.7.1 Throughput Test: LargeRandom 3 2 1 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 0.43 0.43 0.43 1. (CXX) g++ options: -O3 -pthread
NCNN Target: CPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: blazeface 2 3 1 0.5108 1.0216 1.5324 2.0432 2.554 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.14, N = 3 2.15 2.20 2.27 MIN: 2.08 / MAX: 2.2 MIN: 2.14 / MAX: 2.3 MIN: 2.06 / MAX: 70.26 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: efficientnet-b0 3 1 2 2 4 6 8 10 SE +/- 0.09, N = 3 SE +/- 0.10, N = 3 SE +/- 0.27, N = 3 7.54 7.62 7.77 MIN: 7.28 / MAX: 7.74 MIN: 7.29 / MAX: 76.04 MIN: 7.29 / MAX: 72.43 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
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 1700 3400 5100 6800 8500 SE +/- 3.85, N = 3 SE +/- 3.69, N = 3 SE +/- 1898.38, N = 12 3080.42 3114.00 7762.44 MIN: 3048.92 MIN: 3078.33 MIN: 3053.57 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
Phoronix Test Suite v10.8.4