new t

Intel Core i7-8700K testing with a ASUS TUF Z370-PLUS GAMING (2001 BIOS) and ASUS Intel UHD 630 3GB on Ubuntu 20.04 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2012227-HA-NEWT8131768&sor&grw.

new tProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLOpenCLCompilerFile-SystemScreen Resolution123Intel Core i7-8700K @ 4.70GHz (6 Cores / 12 Threads)ASUS TUF Z370-PLUS GAMING (2001 BIOS)Intel 8th Gen Core16GB128GB THNSN5128GPU7 TOSHIBAASUS Intel UHD 630 3GB (1200MHz)Realtek ALC887-VDVA2431Intel I219-VUbuntu 20.045.9.0-050900rc6daily20200923-generic (x86_64) 20200922GNOME Shell 3.36.4X Server 1.20.8modesetting 1.20.84.6 Mesa 20.0.8OpenCL 2.1GCC 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: intel_pstate powersave - CPU Microcode: 0xde - Thermald 1.9.1 Security Details- itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Mitigation of PTE Inversion; VMX: conditional cache flushes SMT vulnerable + mds: Mitigation of Clear buffers; SMT vulnerable + meltdown: Mitigation of PTI + 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 generic retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling + srbds: Mitigation of Microcode + tsx_async_abort: Mitigation of Clear buffers; SMT vulnerable

new tclomp: Static OMP Speedupencode-opus: WAV To Opus Encodevkmark: 1920 x 1080vkmark: 1280 x 1024encode-ape: WAV To APEencode-wavpack: WAV To WavPackncnn: 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_400mncnn: Vulkan GPU - mobilenetncnn: Vulkan GPU-v2-v2 - mobilenet-v2ncnn: Vulkan GPU-v3-v3 - mobilenet-v3ncnn: Vulkan GPU - shufflenet-v2ncnn: Vulkan GPU - mnasnetncnn: Vulkan GPU - efficientnet-b0ncnn: Vulkan GPU - blazefacencnn: Vulkan GPU - googlenetncnn: Vulkan GPU - vgg16ncnn: Vulkan GPU - resnet18ncnn: Vulkan GPU - resnet50vkmark: 1024 x 768ncnn: Vulkan GPU - alexnetncnn: Vulkan GPU - yolov4-tinyncnn: Vulkan GPU - squeezenet_ssdncnn: Vulkan GPU - regnety_400monednn: IP Shapes 1D - f32 - CPUonednn: IP Shapes 3D - f32 - CPUonednn: IP Shapes 1D - u8s8f32 - CPUonednn: IP Shapes 3D - u8s8f32 - 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 - CPUbuild-eigen: Time To Compilevkmark: 800 x 600onednn: Convolution Batch Shapes Auto - f32 - CPU1232.68.172748123810.47713.84019.415.574.505.894.457.321.8615.6264.8816.0113.5631.3028.4920.6314.2219.415.574.475.874.417.301.8515.7464.9115.9731.32233213.5928.4820.6914.194.604909.386102.150932.366316.341739.0311015.97966.844314.248734026.062261.964024.582261.733.874234023.722400.843.9532371.065359117.06702.68.163743121810.42513.83719.505.534.445.874.457.301.8515.6164.9315.9813.5531.3628.5120.6914.1919.455.544.485.854.437.291.8615.5964.8516.0131.36235013.5628.5120.6314.074.598369.408312.152892.367406.366309.0218215.99596.909044.253924020.252262.714022.062261.383.861304028.042261.233.9535171.291355917.05942.68.156743119310.44813.84219.475.544.475.884.457.301.8515.6564.8415.9813.5631.2928.5320.6714.1719.555.544.455.884.457.291.8515.6064.8615.9931.39238513.5828.6920.7914.124.597939.379522.150512.352046.348829.0086715.99106.867864.255714022.242261.154021.822265.163.879044031.072262.483.9550371.098358017.0617OpenBenchmarking.org

CLOMP

Static OMP Speedup

OpenBenchmarking.orgSpeedup, More Is BetterCLOMP 1.2Static OMP Speedup3210.5851.171.7552.342.925SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 32.62.62.61. (CC) gcc options: -fopenmp -O3 -lm

Opus Codec Encoding

WAV To Opus Encode

OpenBenchmarking.orgSeconds, Fewer Is BetterOpus Codec Encoding 1.3.1WAV To Opus Encode321246810SE +/- 0.001, N = 5SE +/- 0.002, N = 5SE +/- 0.003, N = 58.1568.1638.1721. (CXX) g++ options: -fvisibility=hidden -logg -lm

VKMark

Resolution: 1920 x 1080

OpenBenchmarking.orgVKMark Score, More Is BetterVKMark 2020-05-21Resolution: 1920 x 1080132160320480640800SE +/- 3.53, N = 3SE +/- 1.76, N = 37487437431. (CXX) g++ options: -pthread -ldl -pipe -std=c++14 -MD -MQ -MF

VKMark

Resolution: 1280 x 1024

OpenBenchmarking.orgVKMark Score, More Is BetterVKMark 2020-05-21Resolution: 1280 x 102412330060090012001500SE +/- 4.91, N = 3SE +/- 7.97, N = 3SE +/- 6.23, N = 31238121811931. (CXX) g++ options: -pthread -ldl -pipe -std=c++14 -MD -MQ -MF

Monkey Audio Encoding

WAV To APE

OpenBenchmarking.orgSeconds, Fewer Is BetterMonkey Audio Encoding 3.99.6WAV To APE2313691215SE +/- 0.03, N = 5SE +/- 0.03, N = 5SE +/- 0.03, N = 510.4310.4510.481. (CXX) g++ options: -O3 -pedantic -rdynamic -lrt

WavPack Audio Encoding

WAV To WavPack

OpenBenchmarking.orgSeconds, Fewer Is BetterWavPack Audio Encoding 5.3WAV To WavPack21348121620SE +/- 0.00, N = 5SE +/- 0.00, N = 5SE +/- 0.00, N = 513.8413.8413.841. (CXX) g++ options: -rdynamic

NCNN

Target: CPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: mobilenet132510152025SE +/- 0.01, N = 3SE +/- 0.07, N = 3SE +/- 0.04, N = 319.4119.4719.50MIN: 19.33 / MAX: 21.12MIN: 19.34 / MAX: 30.05MIN: 19.36 / MAX: 29.781. (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-v22311.25332.50663.75995.01326.2665SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 35.535.545.57MIN: 5.44 / MAX: 6.77MIN: 5.47 / MAX: 6.69MIN: 5.47 / MAX: 6.731. (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-v32311.01252.0253.03754.055.0625SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 34.444.474.50MIN: 4.36 / MAX: 5.56MIN: 4.37 / MAX: 5.59MIN: 4.43 / MAX: 5.591. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: shufflenet-v22311.32532.65063.97595.30126.6265SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 35.875.885.89MIN: 5.81 / MAX: 7.06MIN: 5.82 / MAX: 7.05MIN: 5.85 / MAX: 6.981. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: mnasnet1231.00132.00263.00394.00525.0065SE +/- 0.04, N = 2SE +/- 0.01, N = 3SE +/- 0.03, N = 34.454.454.45MIN: 4.39 / MAX: 5.44MIN: 4.39 / MAX: 5.77MIN: 4.39 / MAX: 5.871. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: efficientnet-b0231246810SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 37.307.307.32MIN: 7.23 / MAX: 8.35MIN: 7.24 / MAX: 8.39MIN: 7.24 / MAX: 11.311. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: blazeface2310.41850.8371.25551.6742.0925SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 31.851.851.86MIN: 1.83 / MAX: 1.91MIN: 1.83 / MAX: 1.89MIN: 1.84 / MAX: 1.91. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: googlenet21348121620SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 315.6115.6215.65MIN: 15.5 / MAX: 16.33MIN: 15.5 / MAX: 16.32MIN: 15.47 / MAX: 25.841. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: vgg163121428425670SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 364.8464.8864.93MIN: 64.7 / MAX: 74.34MIN: 64.74 / MAX: 75.06MIN: 64.8 / MAX: 74.131. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: resnet1823148121620SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 315.9815.9816.01MIN: 15.9 / MAX: 17.59MIN: 15.9 / MAX: 17.36MIN: 15.89 / MAX: 24.31. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: alexnet2133691215SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 313.5513.5613.56MIN: 13.48 / MAX: 15.65MIN: 13.51 / MAX: 14.05MIN: 13.5 / MAX: 151. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: resnet50312714212835SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 331.2931.3031.36MIN: 31.1 / MAX: 31.97MIN: 31.06 / MAX: 33.71MIN: 31.14 / MAX: 32.111. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: yolov4-tiny123714212835SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 328.4928.5128.53MIN: 28.36 / MAX: 38.25MIN: 28.41 / MAX: 29.9MIN: 28.43 / MAX: 30.161. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: squeezenet_ssd

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: squeezenet_ssd132510152025SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 320.6320.6720.69MIN: 20.55 / MAX: 21.36MIN: 20.59 / MAX: 22.28MIN: 20.58 / MAX: 22.071. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: regnety_400m

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: regnety_400m32148121620SE +/- 0.07, N = 3SE +/- 0.04, N = 3SE +/- 0.05, N = 314.1714.1914.22MIN: 14.03 / MAX: 16.48MIN: 14.1 / MAX: 24.51MIN: 14.1 / MAX: 15.631. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: mobilenet123510152025SE +/- 0.01, N = 3SE +/- 0.05, N = 3SE +/- 0.11, N = 319.4119.4519.55MIN: 19.34 / MAX: 19.89MIN: 19.32 / MAX: 21.72MIN: 19.33 / MAX: 20.031. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU-v2-v2 - Model: mobilenet-v22311.25332.50663.75995.01326.2665SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 35.545.545.57MIN: 5.43 / MAX: 7.1MIN: 5.45 / MAX: 6.64MIN: 5.46 / MAX: 9.221. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU-v3-v3 - Model: mobilenet-v33121.0082.0163.0244.0325.04SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 34.454.474.48MIN: 4.4 / MAX: 5.46MIN: 4.42 / MAX: 5.58MIN: 4.42 / MAX: 13.31. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: shufflenet-v22131.3232.6463.9695.2926.615SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 35.855.875.88MIN: 5.81 / MAX: 7.06MIN: 5.83 / MAX: 7.24MIN: 5.81 / MAX: 7.291. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: mnasnet1231.00132.00263.00394.00525.0065SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 34.414.434.45MIN: 4.35 / MAX: 5.8MIN: 4.39 / MAX: 5.56MIN: 4.4 / MAX: 5.711. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: efficientnet-b0231246810SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 37.297.297.30MIN: 7.24 / MAX: 8.94MIN: 7.24 / MAX: 8.39MIN: 7.23 / MAX: 8.591. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: blazeface1320.41850.8371.25551.6742.0925SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 31.851.851.86MIN: 1.83 / MAX: 1.89MIN: 1.83 / MAX: 1.92MIN: 1.83 / MAX: 1.951. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: googlenet23148121620SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.10, N = 315.5915.6015.74MIN: 15.48 / MAX: 16.36MIN: 15.47 / MAX: 17.79MIN: 15.5 / MAX: 36.761. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: vgg162311428425670SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 364.8564.8664.91MIN: 64.7 / MAX: 66.78MIN: 64.76 / MAX: 66.89MIN: 64.74 / MAX: 75.241. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: resnet1813248121620SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 315.9715.9916.01MIN: 15.89 / MAX: 16.15MIN: 15.89 / MAX: 16.08MIN: 15.85 / MAX: 25.671. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: resnet50123714212835SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.06, N = 331.3231.3631.39MIN: 31.08 / MAX: 33.75MIN: 31.14 / MAX: 52.21MIN: 31.18 / MAX: 32.911. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

VKMark

Resolution: 1024 x 768

OpenBenchmarking.orgVKMark Score, More Is BetterVKMark 2020-05-21Resolution: 1024 x 7683215001000150020002500SE +/- 8.33, N = 3SE +/- 14.95, N = 3SE +/- 23.90, N = 32385235023321. (CXX) g++ options: -pthread -ldl -pipe -std=c++14 -MD -MQ -MF

NCNN

Target: Vulkan GPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: alexnet2313691215SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 313.5613.5813.59MIN: 13.48 / MAX: 14.36MIN: 13.5 / MAX: 23.17MIN: 13.52 / MAX: 21.891. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: yolov4-tiny123714212835SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.20, N = 328.4828.5128.69MIN: 28.39 / MAX: 29.93MIN: 28.4 / MAX: 37.47MIN: 28.42 / MAX: 39.581. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: squeezenet_ssd

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: squeezenet_ssd213510152025SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.12, N = 320.6320.6920.79MIN: 20.56 / MAX: 21.21MIN: 20.55 / MAX: 30.08MIN: 20.56 / MAX: 22.371. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: regnety_400m

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: regnety_400m23148121620SE +/- 0.01, N = 3SE +/- 0.05, N = 3SE +/- 0.04, N = 314.0714.1214.19MIN: 14.01 / MAX: 17.02MIN: 13.98 / MAX: 15.8MIN: 14.09 / MAX: 15.751. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU3211.03612.07223.10834.14445.1805SE +/- 0.00504, N = 3SE +/- 0.01045, N = 3SE +/- 0.00744, N = 34.597934.598364.60490MIN: 4.51MIN: 4.51MIN: 4.521. (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: CPU3123691215SE +/- 0.01451, N = 3SE +/- 0.01206, N = 3SE +/- 0.02209, N = 39.379529.386109.40831MIN: 9.22MIN: 9.24MIN: 9.231. (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: CPU3120.48440.96881.45321.93762.422SE +/- 0.00121, N = 3SE +/- 0.00269, N = 3SE +/- 0.00195, N = 32.150512.150932.15289MIN: 2.13MIN: 2.13MIN: 2.131. (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: CPU3120.53271.06541.59812.13082.6635SE +/- 0.00226, N = 3SE +/- 0.00412, N = 3SE +/- 0.00682, N = 32.352042.366312.36740MIN: 2.21MIN: 2.23MIN: 2.241. (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: CPU132246810SE +/- 0.01002, N = 3SE +/- 0.02342, N = 3SE +/- 0.01859, N = 36.341736.348826.36630MIN: 6.28MIN: 6.27MIN: 6.291. (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: CPU3213691215SE +/- 0.00799, N = 3SE +/- 0.00457, N = 3SE +/- 0.00790, N = 39.008679.021829.03110MIN: 8.97MIN: 8.99MIN: 8.981. (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: CPU13248121620SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 315.9815.9916.00MIN: 15.85MIN: 15.78MIN: 15.671. (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: CPU132246810SE +/- 0.06695, N = 3SE +/- 0.05900, N = 3SE +/- 0.07138, N = 36.844316.867866.90904MIN: 6.72MIN: 6.71MIN: 6.731. (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: CPU1230.95751.9152.87253.834.7875SE +/- 0.00274, N = 3SE +/- 0.00115, N = 3SE +/- 0.00558, N = 34.248734.253924.25571MIN: 4.22MIN: 4.23MIN: 4.221. (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: CPU2319001800270036004500SE +/- 1.12, N = 3SE +/- 0.74, N = 3SE +/- 0.86, N = 34020.254022.244026.06MIN: 4015.7MIN: 4018.93MIN: 4022.771. (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: CPU3125001000150020002500SE +/- 0.99, N = 3SE +/- 1.46, N = 3SE +/- 0.88, N = 32261.152261.962262.71MIN: 2257.27MIN: 2257.28MIN: 2258.311. (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: CPU3219001800270036004500SE +/- 1.47, N = 3SE +/- 1.69, N = 3SE +/- 1.01, N = 34021.824022.064024.58MIN: 4017.01MIN: 4016.14MIN: 4018.491. (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: CPU2135001000150020002500SE +/- 0.66, N = 3SE +/- 0.73, N = 3SE +/- 4.47, N = 32261.382261.732265.16MIN: 2258.78MIN: 2258.19MIN: 2257.921. (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: CPU2130.87281.74562.61843.49124.364SE +/- 0.00368, N = 3SE +/- 0.00722, N = 3SE +/- 0.00389, N = 33.861303.874233.87904MIN: 3.81MIN: 3.81MIN: 3.811. (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: CPU1239001800270036004500SE +/- 2.06, N = 3SE +/- 2.40, N = 3SE +/- 9.41, N = 34023.724028.044031.07MIN: 4016.98MIN: 4022.9MIN: 4017.541. (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: CPU2315001000150020002500SE +/- 0.91, N = 3SE +/- 2.17, N = 3SE +/- 137.85, N = 152261.232262.482400.84MIN: 2257.77MIN: 2257.12MIN: 2256.891. (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: CPU1230.88991.77982.66973.55964.4495SE +/- 0.00482, N = 3SE +/- 0.00528, N = 3SE +/- 0.00118, N = 33.953233.953513.95503MIN: 3.92MIN: 3.92MIN: 3.921. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

Timed Eigen Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Eigen Compilation 3.3.9Time To Compile1321632486480SE +/- 0.16, N = 3SE +/- 0.06, N = 3SE +/- 0.00, N = 371.0771.1071.29

VKMark

Resolution: 800 x 600

OpenBenchmarking.orgVKMark Score, More Is BetterVKMark 2020-05-21Resolution: 800 x 6001328001600240032004000SE +/- 5.36, N = 3SE +/- 3.61, N = 3SE +/- 7.31, N = 33591358035591. (CXX) g++ options: -pthread -ldl -pipe -std=c++14 -MD -MQ -MF

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: CPU23148121620SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 317.0617.0617.07MIN: 16.98MIN: 16.97MIN: 16.991. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

Phoronix Test Suite v10.8.4