AMD EPYC 7601 Xmas 2020

AMD EPYC 7601 32-Core testing with a TYAN B8026T70AE24HR (V1.02.B10 BIOS) and llvmpipe on Ubuntu 20.04 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2012222-HA-AMDEPYC7628&sor.

AMD EPYC 7601 Xmas 2020ProcessorMotherboardChipsetMemoryDiskGraphicsMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLCompilerFile-SystemScreen ResolutionRun 1Run 2Run 3AMD EPYC 7601 32-Core @ 2.20GHz (32 Cores / 64 Threads)TYAN B8026T70AE24HR (V1.02.B10 BIOS)AMD 17h126GB280GB INTEL SSDPE21D280GAllvmpipeVE2282 x Broadcom NetXtreme BCM5720 2-port PCIeUbuntu 20.045.4.0-53-generic (x86_64)GNOME Shell 3.36.4X Server 1.20.8modesetting 1.20.83.3 Mesa 20.0.8 (LLVM 10.0.0 128 bits)GCC 9.3.0ext41920x1080OpenBenchmarking.orgCompiler Details- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-HskZEa/gcc-9-9.3.0/debian/tmp-nvptx/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v Processor Details- Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0x8001250 Security Details- itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: disabled RSB filling + srbds: Not affected + tsx_async_abort: Not affected

AMD EPYC 7601 Xmas 2020clomp: Static OMP Speeduphmmer: Pfam Database Searchmafft: Multiple Sequence Alignment - LSU RNAsimdjson: Kostyasimdjson: LargeRandsimdjson: PartialTweetssimdjson: DistinctUserIDonednn: IP Shapes 1D - f32 - CPUonednn: IP Shapes 3D - f32 - CPUonednn: IP Shapes 1D - u8s8f32 - CPUonednn: IP Shapes 3D - u8s8f32 - CPUonednn: Convolution Batch Shapes Auto - f32 - CPUonednn: Deconvolution Batch shapes_1d - f32 - CPUonednn: Deconvolution Batch shapes_3d - f32 - CPUonednn: Convolution Batch Shapes Auto - u8s8f32 - CPUonednn: Deconvolution Batch shapes_1d - u8s8f32 - CPUonednn: Deconvolution Batch shapes_3d - u8s8f32 - CPUonednn: Recurrent Neural Network Training - f32 - CPUonednn: Recurrent Neural Network Inference - f32 - CPUonednn: Recurrent Neural Network Training - u8s8f32 - CPUonednn: Recurrent Neural Network Inference - u8s8f32 - CPUonednn: Matrix Multiply Batch Shapes Transformer - f32 - CPUonednn: Recurrent Neural Network Training - bf16bf16bf16 - CPUonednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPUonednn: Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPUcoremark: CoreMark Size 666 - Iterations Per Secondbuild-ffmpeg: Time To Compilebuild2: Time To Compilebuild-eigen: Time To Compileencode-ape: WAV To APEencode-opus: WAV To Opus Encodenode-web-tooling: sqlite-speedtest: Timed Time - Size 1,000ncnn: CPU - mobilenetncnn: CPU-v2-v2 - mobilenet-v2ncnn: CPU-v3-v3 - mobilenet-v3ncnn: CPU - shufflenet-v2ncnn: CPU - mnasnetncnn: CPU - efficientnet-b0ncnn: CPU - blazefacencnn: CPU - googlenetncnn: CPU - vgg16ncnn: CPU - resnet18ncnn: CPU - alexnetncnn: CPU - resnet50ncnn: CPU - yolov4-tinyncnn: CPU - squeezenet_ssdncnn: CPU - regnety_400mencode-wavpack: WAV To WavPackRun 1Run 2Run 357.1200.29515.0180.330.280.360.375.3477112.41772.679373.5651118.51284.032819.0443923.30304.602484.4131410732.733293.4910583.103300.071.7122010689.163332.791.78892879248.02263839.094102.295120.01618.34610.1876.7890.11643.1017.4216.3017.5116.1722.197.7948.06100.7241.8333.2060.7857.9946.68117.0217.31957.7199.70815.1470.330.280.360.374.4914811.76992.685113.5597018.68004.007139.0389322.45764.714734.3709710747.53322.6810647.603434.141.7405610915.653312.301.77953879237.12207839.108102.588119.98118.33210.2156.7490.32041.8419.4217.4817.3515.7622.247.8946.9994.3345.7030.1959.2455.8046.89119.2317.31257.8200.75315.0230.330.280.360.374.3351912.08562.665093.5715318.65564.018279.0876723.21204.228414.4004910314.223393.8210812.543327.911.6651211077.93405.821.79366876909.95000139.189102.354120.19118.41610.1956.8590.10743.2618.2216.9116.9416.2623.227.9049.8188.5543.6431.9259.4956.5244.81118.4817.292OpenBenchmarking.org

CLOMP

Static OMP Speedup

OpenBenchmarking.orgSpeedup, More Is BetterCLOMP 1.2Static OMP SpeedupRun 3Run 2Run 11326395265SE +/- 0.43, N = 3SE +/- 0.70, N = 3SE +/- 0.32, N = 357.857.757.11. (CC) gcc options: -fopenmp -O3 -lm

Timed HMMer Search

Pfam Database Search

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed HMMer Search 3.3.1Pfam Database SearchRun 2Run 1Run 34080120160200SE +/- 0.82, N = 3SE +/- 0.06, N = 3SE +/- 0.16, N = 3199.71200.30200.751. (CC) gcc options: -O3 -pthread -lhmmer -leasel -lm

Timed MAFFT Alignment

Multiple Sequence Alignment - LSU RNA

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MAFFT Alignment 7.471Multiple Sequence Alignment - LSU RNARun 1Run 3Run 248121620SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.11, N = 315.0215.0215.151. (CC) gcc options: -std=c99 -O3 -lm -lpthread

simdjson

Throughput Test: Kostya

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 0.7.1Throughput Test: KostyaRun 3Run 2Run 10.07430.14860.22290.29720.3715SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.330.330.331. (CXX) g++ options: -O3 -pthread

simdjson

Throughput Test: LargeRandom

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 0.7.1Throughput Test: LargeRandomRun 3Run 2Run 10.0630.1260.1890.2520.315SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.280.280.281. (CXX) g++ options: -O3 -pthread

simdjson

Throughput Test: PartialTweets

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 0.7.1Throughput Test: PartialTweetsRun 3Run 2Run 10.0810.1620.2430.3240.405SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.360.360.361. (CXX) g++ options: -O3 -pthread

simdjson

Throughput Test: DistinctUserID

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 0.7.1Throughput Test: DistinctUserIDRun 3Run 2Run 10.08330.16660.24990.33320.4165SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.370.370.371. (CXX) g++ options: -O3 -pthread

oneDNN

Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: IP Shapes 1D - Data Type: f32 - Engine: CPURun 3Run 2Run 11.20322.40643.60964.81286.016SE +/- 0.13685, N = 12SE +/- 0.07284, N = 15SE +/- 0.52810, N = 154.335194.491485.34771MIN: 2.85MIN: 2.85MIN: 2.821. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

oneDNN

Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: IP Shapes 3D - Data Type: f32 - Engine: CPURun 2Run 3Run 13691215SE +/- 0.25, N = 15SE +/- 0.23, N = 15SE +/- 0.32, N = 1511.7712.0912.42MIN: 3.13MIN: 3.14MIN: 3.031. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

oneDNN

Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPURun 3Run 1Run 20.60411.20821.81232.41643.0205SE +/- 0.00279, N = 3SE +/- 0.01516, N = 3SE +/- 0.00743, N = 32.665092.679372.68511MIN: 2.55MIN: 2.56MIN: 2.551. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

oneDNN

Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPURun 2Run 1Run 30.80361.60722.41083.21444.018SE +/- 0.02517, N = 3SE +/- 0.01645, N = 3SE +/- 0.00955, N = 33.559703.565113.57153MIN: 1.89MIN: 1.9MIN: 1.891. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

oneDNN

Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPURun 1Run 3Run 2510152025SE +/- 0.19, N = 3SE +/- 0.25, N = 3SE +/- 0.29, N = 318.5118.6618.68MIN: 17.06MIN: 17.14MIN: 17.21. (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.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPURun 2Run 3Run 10.90741.81482.72223.62964.537SE +/- 0.02054, N = 3SE +/- 0.03270, N = 3SE +/- 0.02609, N = 34.007134.018274.03281MIN: 3.65MIN: 3.67MIN: 3.671. (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.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPURun 2Run 1Run 33691215SE +/- 0.11235, N = 3SE +/- 0.10760, N = 15SE +/- 0.11809, N = 159.038939.044399.08767MIN: 6.98MIN: 6.91MIN: 6.991. (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.orgms, Fewer Is BetteroneDNN 2.0Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPURun 2Run 3Run 1612182430SE +/- 0.45, N = 12SE +/- 0.12, N = 3SE +/- 0.12, N = 322.4623.2123.30MIN: 11.33MIN: 20.94MIN: 21.631. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

oneDNN

Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPURun 3Run 1Run 21.06082.12163.18244.24325.304SE +/- 0.04344, N = 3SE +/- 0.17305, N = 15SE +/- 0.12692, N = 154.228414.602484.71473MIN: 3.96MIN: 3.92MIN: 3.931. (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.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPURun 2Run 3Run 10.9931.9862.9793.9724.965SE +/- 0.06219, N = 3SE +/- 0.06103, N = 4SE +/- 0.05240, N = 64.370974.400494.41314MIN: 4.07MIN: 4.06MIN: 4.071. (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.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPURun 3Run 1Run 22K4K6K8K10KSE +/- 184.49, N = 13SE +/- 164.15, N = 12SE +/- 128.18, N = 1210314.2210732.7310747.50MIN: 7551.61MIN: 8370.79MIN: 9600.61. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

oneDNN

Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPURun 1Run 2Run 37001400210028003500SE +/- 45.21, N = 15SE +/- 38.80, N = 15SE +/- 11.78, N = 33293.493322.683393.82MIN: 2548MIN: 2956.39MIN: 3348.851. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

oneDNN

Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPURun 1Run 2Run 32K4K6K8K10KSE +/- 206.22, N = 10SE +/- 204.17, N = 12SE +/- 330.55, N = 1210583.1010647.6010812.54MIN: 9226.33MIN: 8942.86MIN: 8507.261. (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.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPURun 1Run 3Run 27001400210028003500SE +/- 44.01, N = 15SE +/- 46.22, N = 15SE +/- 41.23, N = 63300.073327.913434.14MIN: 2751.78MIN: 2885.53MIN: 3003.061. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

oneDNN

Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPURun 3Run 1Run 20.39160.78321.17481.56641.958SE +/- 0.06598, N = 15SE +/- 0.06136, N = 15SE +/- 0.05674, N = 121.665121.712201.74056MIN: 0.98MIN: 1.12MIN: 1.111. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

oneDNN

Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPURun 1Run 2Run 32K4K6K8K10KSE +/- 258.76, N = 9SE +/- 182.83, N = 12SE +/- 137.39, N = 410689.1610915.6511077.90MIN: 9144.24MIN: 8687.22MIN: 10188.81. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

oneDNN

Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPURun 2Run 1Run 37001400210028003500SE +/- 58.86, N = 15SE +/- 31.60, N = 10SE +/- 51.82, N = 33312.303332.793405.82MIN: 2572.81MIN: 2567.62MIN: 3281.71. (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.orgms, Fewer Is BetteroneDNN 2.0Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPURun 2Run 1Run 30.40360.80721.21081.61442.018SE +/- 0.01534, N = 15SE +/- 0.01884, N = 3SE +/- 0.01875, N = 31.779531.788921.79366MIN: 1.57MIN: 1.66MIN: 1.661. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

Coremark

CoreMark Size 666 - Iterations Per Second

OpenBenchmarking.orgIterations/Sec, More Is BetterCoremark 1.0CoreMark Size 666 - Iterations Per SecondRun 1Run 2Run 3200K400K600K800K1000KSE +/- 5683.14, N = 3SE +/- 1976.60, N = 3SE +/- 2175.03, N = 3879248.02879237.12876909.951. (CC) gcc options: -O2 -lrt" -lrt

Timed FFmpeg Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed FFmpeg Compilation 4.2.2Time To CompileRun 1Run 2Run 3918273645SE +/- 0.05, N = 3SE +/- 0.09, N = 3SE +/- 0.14, N = 339.0939.1139.19

Build2

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterBuild2 0.13Time To CompileRun 1Run 3Run 220406080100SE +/- 0.36, N = 3SE +/- 0.04, N = 3SE +/- 0.14, N = 3102.30102.35102.59

Timed Eigen Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Eigen Compilation 3.3.9Time To CompileRun 2Run 1Run 3306090120150SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.17, N = 3119.98120.02120.19

Monkey Audio Encoding

WAV To APE

OpenBenchmarking.orgSeconds, Fewer Is BetterMonkey Audio Encoding 3.99.6WAV To APERun 2Run 1Run 3510152025SE +/- 0.01, N = 5SE +/- 0.01, N = 5SE +/- 0.08, N = 518.3318.3518.421. (CXX) g++ options: -O3 -pedantic -rdynamic -lrt

Opus Codec Encoding

WAV To Opus Encode

OpenBenchmarking.orgSeconds, Fewer Is BetterOpus Codec Encoding 1.3.1WAV To Opus EncodeRun 1Run 3Run 23691215SE +/- 0.00, N = 5SE +/- 0.01, N = 5SE +/- 0.01, N = 510.1910.2010.221. (CXX) g++ options: -fvisibility=hidden -logg -lm

Node.js V8 Web Tooling Benchmark

OpenBenchmarking.orgruns/s, More Is BetterNode.js V8 Web Tooling BenchmarkRun 3Run 1Run 2246810SE +/- 0.04, N = 3SE +/- 0.08, N = 3SE +/- 0.01, N = 36.856.786.741. Nodejs v10.19.0

SQLite Speedtest

Timed Time - Size 1,000

OpenBenchmarking.orgSeconds, Fewer Is BetterSQLite Speedtest 3.30Timed Time - Size 1,000Run 3Run 1Run 220406080100SE +/- 0.17, N = 3SE +/- 0.01, N = 3SE +/- 0.98, N = 390.1190.1290.321. (CC) gcc options: -O2 -ldl -lz -lpthread

NCNN

Target: CPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: mobilenetRun 2Run 1Run 31020304050SE +/- 1.10, N = 12SE +/- 1.57, N = 12SE +/- 1.07, N = 1241.8443.1043.26MIN: 35.73 / MAX: 496.11MIN: 35.09 / MAX: 501.41MIN: 34.82 / MAX: 511.891. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU-v2-v2 - Model: mobilenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU-v2-v2 - Model: mobilenet-v2Run 1Run 3Run 2510152025SE +/- 0.22, N = 12SE +/- 0.54, N = 12SE +/- 1.19, N = 1217.4218.2219.42MIN: 15.79 / MAX: 249.25MIN: 15.35 / MAX: 435.27MIN: 15.84 / MAX: 439.611. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU-v3-v3 - Model: mobilenet-v3

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU-v3-v3 - Model: mobilenet-v3Run 1Run 3Run 248121620SE +/- 0.56, N = 12SE +/- 0.59, N = 12SE +/- 0.96, N = 1216.3016.9117.48MIN: 14.83 / MAX: 444.14MIN: 14.94 / MAX: 447.34MIN: 14.75 / MAX: 525.021. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: shufflenet-v2Run 3Run 2Run 148121620SE +/- 0.13, N = 12SE +/- 0.51, N = 12SE +/- 0.42, N = 1216.9417.3517.51MIN: 16.11 / MAX: 120.46MIN: 16 / MAX: 357.5MIN: 15.95 / MAX: 355.591. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: mnasnetRun 2Run 1Run 348121620SE +/- 0.24, N = 12SE +/- 0.48, N = 12SE +/- 0.43, N = 1215.7616.1716.26MIN: 14.78 / MAX: 415.5MIN: 14.62 / MAX: 428.63MIN: 14.79 / MAX: 427.391. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: efficientnet-b0Run 1Run 2Run 3612182430SE +/- 0.37, N = 12SE +/- 0.31, N = 12SE +/- 0.56, N = 1222.1922.2423.22MIN: 20.26 / MAX: 496.03MIN: 20.84 / MAX: 524.85MIN: 20.7 / MAX: 525.921. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: blazefaceRun 1Run 2Run 3246810SE +/- 0.06, N = 12SE +/- 0.06, N = 12SE +/- 0.09, N = 127.797.897.90MIN: 7.48 / MAX: 49.5MIN: 7.55 / MAX: 80.4MIN: 7.46 / MAX: 59.211. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: googlenetRun 2Run 1Run 31122334455SE +/- 2.77, N = 12SE +/- 2.27, N = 12SE +/- 2.45, N = 1246.9948.0649.81MIN: 33.26 / MAX: 605.84MIN: 32.75 / MAX: 604.8MIN: 32.24 / MAX: 613.181. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: vgg16Run 3Run 2Run 120406080100SE +/- 3.70, N = 12SE +/- 3.64, N = 12SE +/- 5.01, N = 1288.5594.33100.72MIN: 43.77 / MAX: 279.55MIN: 47.38 / MAX: 304.01MIN: 45.51 / MAX: 338.451. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: resnet18Run 1Run 3Run 21020304050SE +/- 1.98, N = 12SE +/- 2.71, N = 12SE +/- 3.66, N = 1241.8343.6445.70MIN: 23.36 / MAX: 249.26MIN: 27.63 / MAX: 246.76MIN: 27.44 / MAX: 248.591. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: alexnetRun 2Run 3Run 1816243240SE +/- 1.11, N = 12SE +/- 1.62, N = 12SE +/- 1.65, N = 1230.1931.9233.20MIN: 16.07 / MAX: 156.27MIN: 16.26 / MAX: 163.34MIN: 18.26 / MAX: 171.511. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: resnet50Run 2Run 3Run 11428425670SE +/- 1.83, N = 12SE +/- 3.15, N = 12SE +/- 2.69, N = 1259.2459.4960.78MIN: 38.46 / MAX: 770.44MIN: 38.42 / MAX: 662.24MIN: 38.67 / MAX: 633.71. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: yolov4-tinyRun 2Run 3Run 11326395265SE +/- 0.72, N = 12SE +/- 0.57, N = 12SE +/- 1.01, N = 1255.8056.5257.99MIN: 46.04 / MAX: 269.61MIN: 44.78 / MAX: 275.31MIN: 46.53 / MAX: 296.181. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: squeezenet_ssd

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: squeezenet_ssdRun 3Run 1Run 21122334455SE +/- 1.26, N = 12SE +/- 1.46, N = 12SE +/- 1.43, N = 1244.8146.6846.89MIN: 37.3 / MAX: 531.47MIN: 37.34 / MAX: 524.93MIN: 37.8 / MAX: 531.211. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: regnety_400m

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: regnety_400mRun 1Run 3Run 2306090120150SE +/- 1.56, N = 12SE +/- 1.61, N = 12SE +/- 2.16, N = 12117.02118.48119.23MIN: 109.2 / MAX: 1631.71MIN: 109.05 / MAX: 2000.57MIN: 109.72 / MAX: 3748.321. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

WavPack Audio Encoding

WAV To WavPack

OpenBenchmarking.orgSeconds, Fewer Is BetterWavPack Audio Encoding 5.3WAV To WavPackRun 3Run 2Run 148121620SE +/- 0.00, N = 5SE +/- 0.02, N = 5SE +/- 0.02, N = 517.2917.3117.321. (CXX) g++ options: -rdynamic

Phoronix Test Suite v10.8.4