Ryzen 5 3600XT 2021 AMD Ryzen 5 3600XT 6-Core testing with a MSI X470 GAMING M7 AC (MS-7B77) v1.0 (1.E0 BIOS) and MSI AMD Radeon R7 370 / R9 270/370 OEM 4GB on Ubuntu 20.10 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2101018-HA-RYZEN536000&grs&sro .
Ryzen 5 3600XT 2021 Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server Display Driver OpenGL Compiler File-System Screen Resolution Linux 5.8 Repeat 2 Repeat 3 AMD Ryzen 5 3600XT 6-Core @ 3.80GHz (6 Cores / 12 Threads) MSI X470 GAMING M7 AC (MS-7B77) v1.0 (1.E0 BIOS) AMD Starship/Matisse 16GB 500GB CT500P2SSD8 MSI AMD Radeon R7 370 / R9 270/370 OEM 4GB AMD Oland/Hainan/Cape G237HL Qualcomm Atheros Killer E2500 + Intel 8265 / 8275 Ubuntu 20.10 5.8.0-28-generic (x86_64) GNOME Shell 3.38.1 X Server 1.20.9 modesetting 1.20.9 4.5 Mesa 20.2.1 (LLVM 11.0.0) GCC 10.2.0 ext4 1920x1080 OpenBenchmarking.org Compiler Details - --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-JvwpWM/gcc-10-10.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-JvwpWM/gcc-10-10.2.0/debian/tmp-gcn/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v Processor Details - Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0x8701021 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 5 3600XT 2021 ncnn: CPU - blazeface ncnn: CPU-v3-v3 - mobilenet-v3 ncnn: CPU - alexnet simdjson: DistinctUserID cryptsetup: PBKDF2-sha512 cryptsetup: PBKDF2-whirlpool ncnn: CPU - mobilenet mafft: Multiple Sequence Alignment - LSU RNA onednn: IP Shapes 3D - u8s8f32 - CPU clomp: Static OMP Speedup onednn: IP Shapes 1D - f32 - CPU ncnn: CPU - efficientnet-b0 cryptsetup: AES-XTS 512b Encryption ncnn: CPU-v2-v2 - mobilenet-v2 encode-opus: WAV To Opus Encode cryptsetup: AES-XTS 512b Decryption sqlite-speedtest: Timed Time - Size 1,000 encode-ogg: WAV To Ogg cryptsetup: Twofish-XTS 512b Decryption simdjson: Kostya onednn: IP Shapes 3D - f32 - CPU cryptsetup: AES-XTS 256b Encryption ncnn: CPU - squeezenet_ssd simdjson: PartialTweets brl-cad: VGR Performance Metric ncnn: CPU - googlenet cryptsetup: Twofish-XTS 256b Decryption cryptsetup: Twofish-XTS 512b Encryption cryptsetup: Serpent-XTS 512b Encryption phpbench: PHP Benchmark Suite node-web-tooling: onednn: Deconvolution Batch shapes_1d - u8s8f32 - CPU coremark: CoreMark Size 666 - Iterations Per Second cryptsetup: AES-XTS 256b Decryption ncnn: CPU - mnasnet ncnn: CPU - vgg16 onednn: Matrix Multiply Batch Shapes Transformer - f32 - CPU ncnn: CPU - regnety_400m onednn: Recurrent Neural Network Inference - f32 - CPU onednn: Recurrent Neural Network Inference - u8s8f32 - CPU ncnn: CPU - resnet18 ncnn: CPU - resnet50 cryptsetup: Twofish-XTS 256b Encryption cryptsetup: Serpent-XTS 512b Decryption hmmer: Pfam Database Search encode-wavpack: WAV To WavPack onednn: IP Shapes 1D - u8s8f32 - CPU ncnn: CPU - yolov4-tiny encode-ape: WAV To APE ncnn: CPU - shufflenet-v2 onednn: Recurrent Neural Network Training - bf16bf16bf16 - CPU onednn: Convolution Batch Shapes Auto - u8s8f32 - CPU cryptsetup: Serpent-XTS 256b Decryption onednn: Recurrent Neural Network Training - u8s8f32 - CPU onednn: Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPU build-eigen: Time To Compile build-clash: Time To Compile onednn: Convolution Batch Shapes Auto - f32 - CPU onednn: Deconvolution Batch shapes_3d - f32 - CPU cryptsetup: Serpent-XTS 256b Encryption onednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPU build2: Time To Compile unpack-firefox: firefox-84.0.source.tar.xz onednn: Recurrent Neural Network Training - f32 - CPU build-ffmpeg: Time To Compile onednn: Deconvolution Batch shapes_1d - f32 - CPU onednn: Deconvolution Batch shapes_3d - u8s8f32 - CPU simdjson: LargeRand Linux 5.8 Repeat 2 Repeat 3 2.53 5.29 14.94 0.77 1800801 753350 20.14 11.542 3.06815 16.9 5.82329 8.30 1826.8 6.12 7.138 1828.5 57.470 18.719 428.4 0.68 12.6446 2073.5 24.87 0.76 93535 17.94 425.4 429.4 737.8 663340 11.31 8.78558 269797.669527 2080.6 5.27 68.66 5.04874 17.66 3385.70 3389.04 18.52 34.89 429.5 726.3 106.406 12.412 3.49733 30.78 11.422 7.76 5135.69 23.6698 722.0 5110.57 4.41400 75.134 376.604 24.6072 9.18729 733.5 3378.54 177.258 17.506 5069.40 65.486 6.78426 6.67768 0.44 2.45 5.20 14.79 0.79 1757676 735744 19.72 11.347 3.01204 17.1 5.92486 8.21 1840.9 6.10 7.197 1843.9 56.652 18.427 435.0 0.67 12.5818 2095.4 24.54 0.76 92847 17.88 427.1 433.6 742.4 666507 11.19 8.76683 271723.339322 2088.5 5.22 68.51 5.03612 17.81 3357.80 3361.25 18.50 34.85 426.7 730.6 106.978 12.404 3.51698 30.61 11.452 7.72 5141.79 23.7672 718.6 5109.67 4.39427 75.400 375.108 24.5346 9.18130 734.9 3385.30 176.752 17.458 5078.51 65.425 6.79426 6.68031 0.44 2.43 5.36 15.19 0.77 1768539 743090 19.89 11.324 3.04147 16.8 5.92397 8.35 1857.5 6.02 7.081 1858.4 57.559 18.645 433.3 0.67 12.7571 2067.5 24.58 0.75 92316 17.71 430.9 434.6 746.7 659345 11.29 8.69285 268921.700728 2068.2 5.23 69.12 5.08034 17.74 3366.59 3387.66 18.65 34.62 426.2 731.4 107.042 12.477 3.50419 30.71 11.392 7.74 5162.11 23.6542 721.0 5132.65 4.41212 75.438 376.490 24.5161 9.15703 735.7 3388.22 176.924 17.470 5080.07 65.540 6.78786 6.68541 0.44 OpenBenchmarking.org
NCNN Target: CPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: blazeface Linux 5.8 Repeat 2 Repeat 3 0.5693 1.1386 1.7079 2.2772 2.8465 SE +/- 0.05, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 2.53 2.45 2.43 MIN: 2.29 / MAX: 7.81 MIN: 2.29 / MAX: 7.26 MIN: 2.29 / MAX: 7.08 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 Linux 5.8 Repeat 2 Repeat 3 1.206 2.412 3.618 4.824 6.03 SE +/- 0.08, N = 3 SE +/- 0.05, N = 3 SE +/- 0.05, N = 3 5.29 5.20 5.36 MIN: 4.69 / MAX: 30.34 MIN: 4.65 / MAX: 25.68 MIN: 4.81 / MAX: 14.77 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: alexnet Linux 5.8 Repeat 2 Repeat 3 4 8 12 16 20 SE +/- 0.03, N = 3 SE +/- 0.22, N = 3 SE +/- 0.07, N = 3 14.94 14.79 15.19 MIN: 13.91 / MAX: 38.48 MIN: 13.34 / MAX: 40.9 MIN: 13.48 / MAX: 42.73 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
simdjson Throughput Test: DistinctUserID OpenBenchmarking.org GB/s, More Is Better simdjson 0.7.1 Throughput Test: DistinctUserID Linux 5.8 Repeat 2 Repeat 3 0.1778 0.3556 0.5334 0.7112 0.889 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 0.77 0.79 0.77 1. (CXX) g++ options: -O3 -pthread
Cryptsetup PBKDF2-sha512 OpenBenchmarking.org Iterations Per Second, More Is Better Cryptsetup PBKDF2-sha512 Linux 5.8 Repeat 2 Repeat 3 400K 800K 1200K 1600K 2000K SE +/- 11811.84, N = 3 SE +/- 15938.76, N = 3 SE +/- 15858.95, N = 3 1800801 1757676 1768539
Cryptsetup PBKDF2-whirlpool OpenBenchmarking.org Iterations Per Second, More Is Better Cryptsetup PBKDF2-whirlpool Linux 5.8 Repeat 2 Repeat 3 160K 320K 480K 640K 800K SE +/- 4850.18, N = 3 SE +/- 5231.74, N = 3 SE +/- 6755.62, N = 3 753350 735744 743090
NCNN Target: CPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: mobilenet Linux 5.8 Repeat 2 Repeat 3 5 10 15 20 25 SE +/- 0.07, N = 3 SE +/- 0.11, N = 3 SE +/- 0.03, N = 3 20.14 19.72 19.89 MIN: 18.78 / MAX: 54.72 MIN: 18.42 / MAX: 58.23 MIN: 18.82 / MAX: 52.28 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Timed MAFFT Alignment Multiple Sequence Alignment - LSU RNA OpenBenchmarking.org Seconds, Fewer Is Better Timed MAFFT Alignment 7.471 Multiple Sequence Alignment - LSU RNA Linux 5.8 Repeat 2 Repeat 3 3 6 9 12 15 SE +/- 0.06, N = 3 SE +/- 0.12, N = 3 SE +/- 0.06, N = 3 11.54 11.35 11.32 1. (CC) gcc options: -std=c99 -O3 -lm -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 Linux 5.8 Repeat 2 Repeat 3 0.6903 1.3806 2.0709 2.7612 3.4515 SE +/- 0.01517, N = 3 SE +/- 0.04368, N = 3 SE +/- 0.02149, N = 3 3.06815 3.01204 3.04147 MIN: 2.76 MIN: 2.74 MIN: 2.76 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 Linux 5.8 Repeat 2 Repeat 3 4 8 12 16 20 SE +/- 0.23, N = 3 SE +/- 0.06, N = 3 SE +/- 0.21, N = 3 16.9 17.1 16.8 1. (CC) gcc options: -fopenmp -O3 -lm
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 Linux 5.8 Repeat 2 Repeat 3 1.3331 2.6662 3.9993 5.3324 6.6655 SE +/- 0.01960, N = 3 SE +/- 0.01363, N = 3 SE +/- 0.00727, N = 3 5.82329 5.92486 5.92397 MIN: 5.31 MIN: 5.36 MIN: 5.37 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
NCNN Target: CPU - Model: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: efficientnet-b0 Linux 5.8 Repeat 2 Repeat 3 2 4 6 8 10 SE +/- 0.03, N = 3 SE +/- 0.06, N = 3 SE +/- 0.08, N = 3 8.30 8.21 8.35 MIN: 7.42 / MAX: 26.44 MIN: 7.37 / MAX: 31.37 MIN: 7.51 / MAX: 32.39 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Cryptsetup AES-XTS 512b Encryption OpenBenchmarking.org MiB/s, More Is Better Cryptsetup AES-XTS 512b Encryption Linux 5.8 Repeat 2 Repeat 3 400 800 1200 1600 2000 SE +/- 17.03, N = 3 SE +/- 17.19, N = 3 SE +/- 2.66, N = 3 1826.8 1840.9 1857.5
NCNN Target: CPU-v2-v2 - Model: mobilenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU-v2-v2 - Model: mobilenet-v2 Linux 5.8 Repeat 2 Repeat 3 2 4 6 8 10 SE +/- 0.03, N = 3 SE +/- 0.07, N = 3 SE +/- 0.03, N = 3 6.12 6.10 6.02 MIN: 5.4 / MAX: 58 MIN: 5.43 / MAX: 16.66 MIN: 5.47 / MAX: 14.76 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 Linux 5.8 Repeat 2 Repeat 3 2 4 6 8 10 SE +/- 0.040, N = 5 SE +/- 0.019, N = 5 SE +/- 0.044, N = 5 7.138 7.197 7.081 1. (CXX) g++ options: -fvisibility=hidden -logg -lm
Cryptsetup AES-XTS 512b Decryption OpenBenchmarking.org MiB/s, More Is Better Cryptsetup AES-XTS 512b Decryption Linux 5.8 Repeat 2 Repeat 3 400 800 1200 1600 2000 SE +/- 17.25, N = 3 SE +/- 16.96, N = 3 SE +/- 2.48, N = 3 1828.5 1843.9 1858.4
SQLite Speedtest Timed Time - Size 1,000 OpenBenchmarking.org Seconds, Fewer Is Better SQLite Speedtest 3.30 Timed Time - Size 1,000 Linux 5.8 Repeat 2 Repeat 3 13 26 39 52 65 SE +/- 0.13, N = 3 SE +/- 0.30, N = 3 SE +/- 0.40, N = 3 57.47 56.65 57.56 1. (CC) gcc options: -O2 -ldl -lz -lpthread
Ogg Audio Encoding WAV To Ogg OpenBenchmarking.org Seconds, Fewer Is Better Ogg Audio Encoding 1.3.4 WAV To Ogg Linux 5.8 Repeat 2 Repeat 3 5 10 15 20 25 SE +/- 0.07, N = 3 SE +/- 0.12, N = 3 SE +/- 0.15, N = 3 18.72 18.43 18.65 1. (CC) gcc options: -O2 -ffast-math -fsigned-char
Cryptsetup Twofish-XTS 512b Decryption OpenBenchmarking.org MiB/s, More Is Better Cryptsetup Twofish-XTS 512b Decryption Linux 5.8 Repeat 2 Repeat 3 90 180 270 360 450 SE +/- 4.97, N = 3 SE +/- 0.27, N = 3 SE +/- 0.17, N = 3 428.4 435.0 433.3
simdjson Throughput Test: Kostya OpenBenchmarking.org GB/s, More Is Better simdjson 0.7.1 Throughput Test: Kostya Linux 5.8 Repeat 2 Repeat 3 0.153 0.306 0.459 0.612 0.765 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 0.68 0.67 0.67 1. (CXX) g++ options: -O3 -pthread
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 Linux 5.8 Repeat 2 Repeat 3 3 6 9 12 15 SE +/- 0.06, N = 3 SE +/- 0.05, N = 3 SE +/- 0.03, N = 3 12.64 12.58 12.76 MIN: 12.06 MIN: 11.93 MIN: 12.06 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
Cryptsetup AES-XTS 256b Encryption OpenBenchmarking.org MiB/s, More Is Better Cryptsetup AES-XTS 256b Encryption Linux 5.8 Repeat 2 Repeat 3 400 800 1200 1600 2000 SE +/- 19.49, N = 3 SE +/- 11.85, N = 3 SE +/- 17.56, N = 3 2073.5 2095.4 2067.5
NCNN Target: CPU - Model: squeezenet_ssd OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: squeezenet_ssd Linux 5.8 Repeat 2 Repeat 3 6 12 18 24 30 SE +/- 0.46, N = 3 SE +/- 0.16, N = 3 SE +/- 0.16, N = 3 24.87 24.54 24.58 MIN: 22.53 / MAX: 78.77 MIN: 22.47 / MAX: 71.41 MIN: 22.83 / MAX: 56.42 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 Linux 5.8 Repeat 2 Repeat 3 0.171 0.342 0.513 0.684 0.855 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 0.76 0.76 0.75 1. (CXX) g++ options: -O3 -pthread
BRL-CAD VGR Performance Metric OpenBenchmarking.org VGR Performance Metric, More Is Better BRL-CAD 7.30.8 VGR Performance Metric Linux 5.8 Repeat 2 Repeat 3 20K 40K 60K 80K 100K 93535 92847 92316 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: googlenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: googlenet Linux 5.8 Repeat 2 Repeat 3 4 8 12 16 20 SE +/- 0.25, N = 3 SE +/- 0.10, N = 3 SE +/- 0.25, N = 3 17.94 17.88 17.71 MIN: 16.31 / MAX: 59.55 MIN: 16.43 / MAX: 56.75 MIN: 16.4 / MAX: 48.5 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Cryptsetup Twofish-XTS 256b Decryption OpenBenchmarking.org MiB/s, More Is Better Cryptsetup Twofish-XTS 256b Decryption Linux 5.8 Repeat 2 Repeat 3 90 180 270 360 450 SE +/- 4.33, N = 3 SE +/- 4.01, N = 3 SE +/- 2.68, N = 3 425.4 427.1 430.9
Cryptsetup Twofish-XTS 512b Encryption OpenBenchmarking.org MiB/s, More Is Better Cryptsetup Twofish-XTS 512b Encryption Linux 5.8 Repeat 2 Repeat 3 90 180 270 360 450 SE +/- 4.82, N = 3 SE +/- 2.88, N = 3 SE +/- 0.15, N = 3 429.4 433.6 434.6
Cryptsetup Serpent-XTS 512b Encryption OpenBenchmarking.org MiB/s, More Is Better Cryptsetup Serpent-XTS 512b Encryption Linux 5.8 Repeat 2 Repeat 3 160 320 480 640 800 SE +/- 6.76, N = 3 SE +/- 7.66, N = 3 SE +/- 0.33, N = 3 737.8 742.4 746.7
PHPBench PHP Benchmark Suite OpenBenchmarking.org Score, More Is Better PHPBench 0.8.1 PHP Benchmark Suite Linux 5.8 Repeat 2 Repeat 3 140K 280K 420K 560K 700K SE +/- 4754.65, N = 3 SE +/- 2399.07, N = 3 SE +/- 4604.42, N = 3 663340 666507 659345
Node.js V8 Web Tooling Benchmark OpenBenchmarking.org runs/s, More Is Better Node.js V8 Web Tooling Benchmark Linux 5.8 Repeat 2 Repeat 3 3 6 9 12 15 SE +/- 0.11, N = 3 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 11.31 11.19 11.29 1. Nodejs
v12.18.2
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 Linux 5.8 Repeat 2 Repeat 3 2 4 6 8 10 SE +/- 0.12505, N = 3 SE +/- 0.07453, N = 3 SE +/- 0.01336, N = 3 8.78558 8.76683 8.69285 MIN: 7.9 MIN: 7.9 MIN: 7.91 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
Coremark CoreMark Size 666 - Iterations Per Second OpenBenchmarking.org Iterations/Sec, More Is Better Coremark 1.0 CoreMark Size 666 - Iterations Per Second Linux 5.8 Repeat 2 Repeat 3 60K 120K 180K 240K 300K SE +/- 48.96, N = 3 SE +/- 1424.10, N = 3 SE +/- 1381.97, N = 3 269797.67 271723.34 268921.70 1. (CC) gcc options: -O2 -lrt" -lrt
Cryptsetup AES-XTS 256b Decryption OpenBenchmarking.org MiB/s, More Is Better Cryptsetup AES-XTS 256b Decryption Linux 5.8 Repeat 2 Repeat 3 400 800 1200 1600 2000 SE +/- 9.96, N = 3 SE +/- 13.17, N = 3 SE +/- 18.26, N = 3 2080.6 2088.5 2068.2
NCNN Target: CPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: mnasnet Linux 5.8 Repeat 2 Repeat 3 1.1858 2.3716 3.5574 4.7432 5.929 SE +/- 0.03, N = 3 SE +/- 0.08, N = 3 SE +/- 0.05, N = 3 5.27 5.22 5.23 MIN: 4.67 / MAX: 10.78 MIN: 4.63 / MAX: 10.82 MIN: 4.66 / MAX: 36.04 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 Linux 5.8 Repeat 2 Repeat 3 15 30 45 60 75 SE +/- 0.29, N = 3 SE +/- 0.25, N = 3 SE +/- 0.22, N = 3 68.66 68.51 69.12 MIN: 65.3 / MAX: 107.34 MIN: 65.01 / MAX: 111.99 MIN: 65.47 / MAX: 108.3 1. (CXX) g++ options: -O3 -rdynamic -lgomp -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 Linux 5.8 Repeat 2 Repeat 3 1.1431 2.2862 3.4293 4.5724 5.7155 SE +/- 0.01204, N = 3 SE +/- 0.01578, N = 3 SE +/- 0.00785, N = 3 5.04874 5.03612 5.08034 MIN: 4.36 MIN: 4.31 MIN: 4.39 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
NCNN Target: CPU - Model: regnety_400m OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: regnety_400m Linux 5.8 Repeat 2 Repeat 3 4 8 12 16 20 SE +/- 0.21, N = 3 SE +/- 0.23, N = 3 SE +/- 0.06, N = 3 17.66 17.81 17.74 MIN: 17.1 / MAX: 57.9 MIN: 16.9 / MAX: 53.49 MIN: 17.04 / MAX: 62.12 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 Linux 5.8 Repeat 2 Repeat 3 700 1400 2100 2800 3500 SE +/- 14.40, N = 3 SE +/- 4.46, N = 3 SE +/- 4.76, N = 3 3385.70 3357.80 3366.59 MIN: 3314.6 MIN: 3305.01 MIN: 3318.41 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -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 Linux 5.8 Repeat 2 Repeat 3 700 1400 2100 2800 3500 SE +/- 19.15, N = 3 SE +/- 10.93, N = 3 SE +/- 6.23, N = 3 3389.04 3361.25 3387.66 MIN: 3314.6 MIN: 3290.33 MIN: 3326.97 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
NCNN Target: CPU - Model: resnet18 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: resnet18 Linux 5.8 Repeat 2 Repeat 3 5 10 15 20 25 SE +/- 0.12, N = 3 SE +/- 0.14, N = 3 SE +/- 0.07, N = 3 18.52 18.50 18.65 MIN: 17.05 / MAX: 56.7 MIN: 17.04 / MAX: 37.4 MIN: 17.29 / MAX: 40.02 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: resnet50 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: resnet50 Linux 5.8 Repeat 2 Repeat 3 8 16 24 32 40 SE +/- 0.19, N = 3 SE +/- 0.10, N = 3 SE +/- 0.29, N = 3 34.89 34.85 34.62 MIN: 33.24 / MAX: 80.99 MIN: 32.75 / MAX: 81.04 MIN: 32.92 / MAX: 80.63 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Cryptsetup Twofish-XTS 256b Encryption OpenBenchmarking.org MiB/s, More Is Better Cryptsetup Twofish-XTS 256b Encryption Linux 5.8 Repeat 2 Repeat 3 90 180 270 360 450 SE +/- 3.09, N = 3 SE +/- 5.15, N = 3 SE +/- 4.25, N = 3 429.5 426.7 426.2
Cryptsetup Serpent-XTS 512b Decryption OpenBenchmarking.org MiB/s, More Is Better Cryptsetup Serpent-XTS 512b Decryption Linux 5.8 Repeat 2 Repeat 3 160 320 480 640 800 SE +/- 5.24, N = 3 SE +/- 3.91, N = 3 SE +/- 0.18, N = 3 726.3 730.6 731.4
Timed HMMer Search Pfam Database Search OpenBenchmarking.org Seconds, Fewer Is Better Timed HMMer Search 3.3.1 Pfam Database Search Linux 5.8 Repeat 2 Repeat 3 20 40 60 80 100 SE +/- 0.06, N = 3 SE +/- 0.30, N = 3 SE +/- 0.28, N = 3 106.41 106.98 107.04 1. (CC) gcc options: -O3 -pthread -lhmmer -leasel -lm
WavPack Audio Encoding WAV To WavPack OpenBenchmarking.org Seconds, Fewer Is Better WavPack Audio Encoding 5.3 WAV To WavPack Linux 5.8 Repeat 2 Repeat 3 3 6 9 12 15 SE +/- 0.07, N = 5 SE +/- 0.07, N = 5 SE +/- 0.06, N = 5 12.41 12.40 12.48 1. (CXX) g++ options: -rdynamic
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 Linux 5.8 Repeat 2 Repeat 3 0.7913 1.5826 2.3739 3.1652 3.9565 SE +/- 0.00924, N = 3 SE +/- 0.01058, N = 3 SE +/- 0.00745, N = 3 3.49733 3.51698 3.50419 MIN: 3.35 MIN: 3.35 MIN: 3.36 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
NCNN Target: CPU - Model: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: yolov4-tiny Linux 5.8 Repeat 2 Repeat 3 7 14 21 28 35 SE +/- 0.30, N = 3 SE +/- 0.17, N = 3 SE +/- 0.14, N = 3 30.78 30.61 30.71 MIN: 28.76 / MAX: 80.19 MIN: 28.74 / MAX: 89.42 MIN: 29.37 / MAX: 65.42 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Monkey Audio Encoding WAV To APE OpenBenchmarking.org Seconds, Fewer Is Better Monkey Audio Encoding 3.99.6 WAV To APE Linux 5.8 Repeat 2 Repeat 3 3 6 9 12 15 SE +/- 0.06, N = 5 SE +/- 0.12, N = 21 SE +/- 0.06, N = 5 11.42 11.45 11.39 1. (CXX) g++ options: -O3 -pedantic -rdynamic -lrt
NCNN Target: CPU - Model: shufflenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: shufflenet-v2 Linux 5.8 Repeat 2 Repeat 3 2 4 6 8 10 SE +/- 0.06, N = 3 SE +/- 0.09, N = 3 SE +/- 0.12, N = 3 7.76 7.72 7.74 MIN: 7.17 / MAX: 17.03 MIN: 7.17 / MAX: 13.38 MIN: 7.17 / MAX: 15.91 1. (CXX) g++ options: -O3 -rdynamic -lgomp -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 Linux 5.8 Repeat 2 Repeat 3 1100 2200 3300 4400 5500 SE +/- 2.49, N = 3 SE +/- 12.15, N = 3 SE +/- 8.57, N = 3 5135.69 5141.79 5162.11 MIN: 5062.6 MIN: 5067.78 MIN: 5091.71 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -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 Linux 5.8 Repeat 2 Repeat 3 6 12 18 24 30 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 SE +/- 0.10, N = 3 23.67 23.77 23.65 MIN: 22.69 MIN: 22.4 MIN: 22.52 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
Cryptsetup Serpent-XTS 256b Decryption OpenBenchmarking.org MiB/s, More Is Better Cryptsetup Serpent-XTS 256b Decryption Linux 5.8 Repeat 2 Repeat 3 160 320 480 640 800 SE +/- 5.38, N = 3 SE +/- 7.77, N = 3 SE +/- 6.51, N = 3 722.0 718.6 721.0
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 Linux 5.8 Repeat 2 Repeat 3 1100 2200 3300 4400 5500 SE +/- 5.15, N = 3 SE +/- 0.87, N = 3 SE +/- 0.83, N = 3 5110.57 5109.67 5132.65 MIN: 5045.23 MIN: 5045.96 MIN: 5073.41 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 Linux 5.8 Repeat 2 Repeat 3 0.9932 1.9864 2.9796 3.9728 4.966 SE +/- 0.01035, N = 3 SE +/- 0.01709, N = 3 SE +/- 0.01222, N = 3 4.41400 4.39427 4.41212 MIN: 3.95 MIN: 4.04 MIN: 3.97 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
Timed Eigen Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Eigen Compilation 3.3.9 Time To Compile Linux 5.8 Repeat 2 Repeat 3 20 40 60 80 100 SE +/- 0.39, N = 3 SE +/- 0.34, N = 3 SE +/- 0.22, N = 3 75.13 75.40 75.44
Timed Clash Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Clash Compilation Time To Compile Linux 5.8 Repeat 2 Repeat 3 80 160 240 320 400 SE +/- 2.24, N = 3 SE +/- 1.96, N = 3 SE +/- 1.29, N = 3 376.60 375.11 376.49
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 Linux 5.8 Repeat 2 Repeat 3 6 12 18 24 30 SE +/- 0.09, N = 3 SE +/- 0.17, N = 3 SE +/- 0.05, N = 3 24.61 24.53 24.52 MIN: 22.92 MIN: 22.85 MIN: 22.82 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
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 Linux 5.8 Repeat 2 Repeat 3 3 6 9 12 15 SE +/- 0.02921, N = 3 SE +/- 0.01634, N = 3 SE +/- 0.03988, N = 3 9.18729 9.18130 9.15703 MIN: 8.84 MIN: 8.9 MIN: 8.89 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
Cryptsetup Serpent-XTS 256b Encryption OpenBenchmarking.org MiB/s, More Is Better Cryptsetup Serpent-XTS 256b Encryption Linux 5.8 Repeat 2 Repeat 3 160 320 480 640 800 SE +/- 6.74, N = 3 SE +/- 7.26, N = 3 SE +/- 7.00, N = 3 733.5 734.9 735.7
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 Linux 5.8 Repeat 2 Repeat 3 700 1400 2100 2800 3500 SE +/- 14.47, N = 3 SE +/- 7.72, N = 3 SE +/- 15.22, N = 3 3378.54 3385.30 3388.22 MIN: 3306.98 MIN: 3320.3 MIN: 3306.01 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 Linux 5.8 Repeat 2 Repeat 3 40 80 120 160 200 SE +/- 0.55, N = 3 SE +/- 0.69, N = 3 SE +/- 0.28, N = 3 177.26 176.75 176.92
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 Linux 5.8 Repeat 2 Repeat 3 4 8 12 16 20 SE +/- 0.09, N = 4 SE +/- 0.05, N = 4 SE +/- 0.04, N = 4 17.51 17.46 17.47
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 Linux 5.8 Repeat 2 Repeat 3 1100 2200 3300 4400 5500 SE +/- 11.85, N = 3 SE +/- 21.00, N = 3 SE +/- 26.15, N = 3 5069.40 5078.51 5080.07 MIN: 4979.47 MIN: 4971.76 MIN: 4976 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
Timed FFmpeg Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed FFmpeg Compilation 4.2.2 Time To Compile Linux 5.8 Repeat 2 Repeat 3 15 30 45 60 75 SE +/- 0.29, N = 3 SE +/- 0.14, N = 3 SE +/- 0.26, N = 3 65.49 65.43 65.54
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 Linux 5.8 Repeat 2 Repeat 3 2 4 6 8 10 SE +/- 0.03755, N = 3 SE +/- 0.03413, N = 3 SE +/- 0.02855, N = 3 6.78426 6.79426 6.78786 MIN: 6.33 MIN: 6.3 MIN: 6.35 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -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 Linux 5.8 Repeat 2 Repeat 3 2 4 6 8 10 SE +/- 0.00919, N = 3 SE +/- 0.01083, N = 3 SE +/- 0.01027, N = 3 6.67768 6.68031 6.68541 MIN: 6.47 MIN: 6.47 MIN: 6.46 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 Linux 5.8 Repeat 2 Repeat 3 0.099 0.198 0.297 0.396 0.495 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 0.44 0.44 0.44 1. (CXX) g++ options: -O3 -pthread
Phoronix Test Suite v10.8.4