EPYC 7F32 Last

AMD EPYC 7F32 8-Core testing with a Supermicro H11DSi-NT v2.00 (2.1 BIOS) and llvmpipe on Ubuntu 20.04 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2012274-HA-EPYC7F32L08.

EPYC 7F32 LastProcessorMotherboardChipsetMemoryDiskGraphicsMonitorOSKernelDesktopDisplay ServerDisplay DriverOpenGLCompilerFile-SystemScreen ResolutionRun 1Run 2Run 3Run 4AMD EPYC 7F32 8-Core @ 3.70GHz (8 Cores / 16 Threads)Supermicro H11DSi-NT v2.00 (2.1 BIOS)AMD Starship/Matisse64GB280GB INTEL SSDPE21D280GAllvmpipeVE228Ubuntu 20.045.8.0-050800rc6daily20200721-generic (x86_64) 20200720GNOME Shell 3.36.1X Server 1.20.8modesetting 1.20.83.3 Mesa 20.0.4 (LLVM 9.0.1 128 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,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: 4096Processor Details- Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0x8301034 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 IBRS_FW STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

EPYC 7F32 Lastunpack-linux: linux-4.15.tar.xzclomp: Static OMP Speeduponednn: 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 - CPUbuild2: Time To Compilebuild-eigen: Time To Compileencode-ape: WAV To APEencode-ogg: WAV To Oggencode-opus: WAV To Opus Encodencnn: 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 WavPackunpack-firefox: firefox-84.0.source.tar.xzRun 1Run 2Run 3Run 45.97429.83.549396.221162.791400.7889634.980644.944096.424209.667577.200005.582983604.401708.293429.541711.391.164393417.911704.973.59741112.07882.88312.50720.5747.97219.946.876.669.616.1410.583.3115.6532.4511.527.5823.0227.0624.8632.0713.73120.3725.97229.63.550936.151552.789760.7955904.923374.968236.421969.623557.218885.579863436.431708.223438.991718.141.158683441.931715.653.59581112.77882.95112.51220.5747.97319.816.846.649.635.9410.553.3415.5232.4111.577.6022.9626.7124.4832.1913.73120.2736.01629.03.559676.125602.790030.7970204.954494.957936.423119.466197.222775.578603431.501711.143436.781716.531.159473441.201712.853.59103112.67383.06912.48920.5837.96919.896.856.629.605.9710.463.315.4832.3211.487.6022.8926.4024.4632.3513.73020.2215.85229.73.559386.179372.792870.7880434.928984.936906.417769.595297.220085.587633417.311711.873427.261711.281.161573421.951714.223.59799112.45782.99412.49320.5557.96619.886.836.609.606.0210.483.3116.3832.3111.577.5923.0427.1025.3132.0313.73220.210OpenBenchmarking.org

Unpacking The Linux Kernel

linux-4.15.tar.xz

OpenBenchmarking.orgSeconds, Fewer Is BetterUnpacking The Linux Kernellinux-4.15.tar.xzRun 1Run 2Run 3Run 4246810SE +/- 0.046, N = 4SE +/- 0.075, N = 5SE +/- 0.030, N = 4SE +/- 0.066, N = 45.9745.9726.0165.852

CLOMP

Static OMP Speedup

OpenBenchmarking.orgSpeedup, More Is BetterCLOMP 1.2Static OMP SpeedupRun 1Run 2Run 3Run 4714212835SE +/- 0.03, N = 3SE +/- 0.09, N = 3SE +/- 0.43, N = 4SE +/- 0.20, N = 329.829.629.029.71. (CC) gcc options: -fopenmp -O3 -lm

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 1Run 2Run 3Run 40.80091.60182.40273.20364.0045SE +/- 0.01364, N = 3SE +/- 0.00496, N = 3SE +/- 0.00416, N = 3SE +/- 0.00543, N = 33.549393.550933.559673.55938MIN: 3.43MIN: 3.42MIN: 3.43MIN: 3.441. (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 1Run 2Run 3Run 4246810SE +/- 0.07572, N = 5SE +/- 0.02019, N = 3SE +/- 0.00438, N = 3SE +/- 0.01738, N = 36.221166.151556.125606.17937MIN: 5.83MIN: 5.98MIN: 5.96MIN: 5.991. (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 1Run 2Run 3Run 40.62841.25681.88522.51363.142SE +/- 0.00493, N = 3SE +/- 0.00373, N = 3SE +/- 0.00303, N = 3SE +/- 0.00526, N = 32.791402.789762.790032.79287MIN: 2.74MIN: 2.75MIN: 2.73MIN: 2.751. (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 1Run 2Run 3Run 40.17930.35860.53790.71720.8965SE +/- 0.010611, N = 3SE +/- 0.002909, N = 3SE +/- 0.004078, N = 3SE +/- 0.005391, N = 30.7889630.7955900.7970200.788043MIN: 0.74MIN: 0.74MIN: 0.74MIN: 0.741. (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 2Run 3Run 41.12062.24123.36184.48245.603SE +/- 0.03423, N = 3SE +/- 0.01299, N = 3SE +/- 0.00727, N = 3SE +/- 0.02121, N = 34.980644.923374.954494.92898MIN: 4.85MIN: 4.84MIN: 4.85MIN: 4.841. (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 1Run 2Run 3Run 41.11792.23583.35374.47165.5895SE +/- 0.02948, N = 3SE +/- 0.03713, N = 3SE +/- 0.02466, N = 3SE +/- 0.02701, N = 34.944094.968234.957934.93690MIN: 4.83MIN: 4.84MIN: 4.83MIN: 4.841. (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 1Run 2Run 3Run 4246810SE +/- 0.00261, N = 3SE +/- 0.00463, N = 3SE +/- 0.00067, N = 3SE +/- 0.00380, N = 36.424206.421966.423116.41776MIN: 6.37MIN: 6.38MIN: 6.38MIN: 6.381. (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 1Run 2Run 3Run 43691215SE +/- 0.11376, N = 3SE +/- 0.10697, N = 3SE +/- 0.03907, N = 3SE +/- 0.15046, N = 39.667579.623559.466199.59529MIN: 8.92MIN: 8.91MIN: 8.89MIN: 8.941. (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 1Run 2Run 3Run 4246810SE +/- 0.02807, N = 3SE +/- 0.03613, N = 3SE +/- 0.01281, N = 3SE +/- 0.01934, N = 37.200007.218887.222777.22008MIN: 6.99MIN: 6.99MIN: 6.95MIN: 7.021. (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 1Run 2Run 3Run 41.25722.51443.77165.02886.286SE +/- 0.00232, N = 3SE +/- 0.00050, N = 3SE +/- 0.00444, N = 3SE +/- 0.00320, N = 35.582985.579865.578605.58763MIN: 5.53MIN: 5.53MIN: 5.54MIN: 5.531. (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 1Run 2Run 3Run 48001600240032004000SE +/- 121.83, N = 15SE +/- 1.74, N = 3SE +/- 5.38, N = 3SE +/- 1.19, N = 33604.403436.433431.503417.31MIN: 3398.06MIN: 3416.4MIN: 3412.54MIN: 3402.751. (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 3Run 4400800120016002000SE +/- 2.12, N = 3SE +/- 1.85, N = 3SE +/- 2.87, N = 3SE +/- 3.16, N = 31708.291708.221711.141711.87MIN: 1692.22MIN: 1693.22MIN: 1695.84MIN: 1697.111. (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 3Run 47001400210028003500SE +/- 4.12, N = 3SE +/- 1.62, N = 3SE +/- 1.55, N = 3SE +/- 0.62, N = 33429.543438.993436.783427.26MIN: 3403.74MIN: 3421.47MIN: 3417.66MIN: 3408.141. (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 2Run 3Run 4400800120016002000SE +/- 1.39, N = 3SE +/- 0.28, N = 3SE +/- 0.71, N = 3SE +/- 1.34, N = 31711.391718.141716.531711.28MIN: 1698.74MIN: 1705.47MIN: 1705.92MIN: 1700.321. (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 1Run 2Run 3Run 40.2620.5240.7861.0481.31SE +/- 0.00362, N = 3SE +/- 0.00251, N = 3SE +/- 0.00183, N = 3SE +/- 0.00127, N = 31.164391.158681.159471.16157MIN: 1.13MIN: 1.13MIN: 1.13MIN: 1.141. (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 3Run 47001400210028003500SE +/- 5.02, N = 3SE +/- 2.14, N = 3SE +/- 4.25, N = 3SE +/- 4.16, N = 33417.913441.933441.203421.95MIN: 3393.28MIN: 3416.43MIN: 3419.28MIN: 3400.561. (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 1Run 2Run 3Run 4400800120016002000SE +/- 2.72, N = 3SE +/- 0.67, N = 3SE +/- 3.55, N = 3SE +/- 4.21, N = 31704.971715.651712.851714.22MIN: 1692.31MIN: 1699.62MIN: 1698.24MIN: 1701.351. (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 1Run 2Run 3Run 40.80951.6192.42853.2384.0475SE +/- 0.00436, N = 3SE +/- 0.00105, N = 3SE +/- 0.00094, N = 3SE +/- 0.00461, N = 33.597413.595813.591033.59799MIN: 3.52MIN: 3.52MIN: 3.53MIN: 3.531. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

Build2

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterBuild2 0.13Time To CompileRun 1Run 2Run 3Run 4306090120150SE +/- 0.41, N = 3SE +/- 0.31, N = 3SE +/- 0.88, N = 3SE +/- 0.42, N = 3112.08112.78112.67112.46

Timed Eigen Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Eigen Compilation 3.3.9Time To CompileRun 1Run 2Run 3Run 420406080100SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 382.8882.9583.0782.99

Monkey Audio Encoding

WAV To APE

OpenBenchmarking.orgSeconds, Fewer Is BetterMonkey Audio Encoding 3.99.6WAV To APERun 1Run 2Run 3Run 43691215SE +/- 0.02, N = 5SE +/- 0.01, N = 5SE +/- 0.01, N = 5SE +/- 0.01, N = 512.5112.5112.4912.491. (CXX) g++ options: -O3 -pedantic -rdynamic -lrt

Ogg Audio Encoding

WAV To Ogg

OpenBenchmarking.orgSeconds, Fewer Is BetterOgg Audio Encoding 1.3.4WAV To OggRun 1Run 2Run 3Run 4510152025SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 320.5720.5720.5820.561. (CC) gcc options: -O2 -ffast-math -fsigned-char

Opus Codec Encoding

WAV To Opus Encode

OpenBenchmarking.orgSeconds, Fewer Is BetterOpus Codec Encoding 1.3.1WAV To Opus EncodeRun 1Run 2Run 3Run 4246810SE +/- 0.006, N = 5SE +/- 0.004, N = 5SE +/- 0.003, N = 5SE +/- 0.004, N = 57.9727.9737.9697.9661. (CXX) g++ options: -fvisibility=hidden -logg -lm

NCNN

Target: CPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: mobilenetRun 1Run 2Run 3Run 4510152025SE +/- 0.08, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 319.9419.8119.8919.88MIN: 19.41 / MAX: 35.06MIN: 19.49 / MAX: 21.97MIN: 19.44 / MAX: 23.59MIN: 19.31 / MAX: 21.581. (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 2Run 3Run 4246810SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 36.876.846.856.83MIN: 6.58 / MAX: 10.87MIN: 6.59 / MAX: 9.23MIN: 6.55 / MAX: 10MIN: 6.59 / MAX: 9.341. (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 2Run 3Run 4246810SE +/- 0.05, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 36.666.646.626.60MIN: 6.41 / MAX: 41.46MIN: 6.46 / MAX: 9.61MIN: 6.46 / MAX: 9.56MIN: 6.44 / MAX: 9.531. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: shufflenet-v2Run 1Run 2Run 3Run 43691215SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 39.619.639.609.60MIN: 9.48 / MAX: 12.56MIN: 9.46 / MAX: 12.11MIN: 9.47 / MAX: 11.88MIN: 9.49 / MAX: 11.951. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: mnasnetRun 1Run 2Run 3Run 4246810SE +/- 0.20, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.10, N = 36.145.945.976.02MIN: 5.8 / MAX: 6.7MIN: 5.8 / MAX: 6.68MIN: 5.77 / MAX: 6.68MIN: 5.77 / MAX: 28.611. (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 3Run 43691215SE +/- 0.12, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 310.5810.5510.4610.48MIN: 10.27 / MAX: 68.23MIN: 10.36 / MAX: 11.1MIN: 10.28 / MAX: 12.58MIN: 10.32 / MAX: 10.671. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: blazefaceRun 1Run 2Run 3Run 40.75151.5032.25453.0063.7575SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 33.313.343.303.31MIN: 3.21 / MAX: 3.54MIN: 3.22 / MAX: 3.58MIN: 3.24 / MAX: 3.48MIN: 3.18 / MAX: 3.491. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: googlenetRun 1Run 2Run 3Run 448121620SE +/- 0.14, N = 3SE +/- 0.17, N = 3SE +/- 0.03, N = 3SE +/- 0.48, N = 315.6515.5215.4816.38MIN: 15.06 / MAX: 18.04MIN: 15 / MAX: 17.92MIN: 15.01 / MAX: 16.98MIN: 15.06 / MAX: 17.411. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: vgg16Run 1Run 2Run 3Run 4816243240SE +/- 0.12, N = 3SE +/- 0.12, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 332.4532.4132.3232.31MIN: 32.07 / MAX: 33.99MIN: 32.09 / MAX: 92.65MIN: 32.09 / MAX: 33.9MIN: 32.04 / MAX: 33.231. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: resnet18Run 1Run 2Run 3Run 43691215SE +/- 0.06, N = 3SE +/- 0.05, N = 3SE +/- 0.01, N = 3SE +/- 0.07, N = 311.5211.5711.4811.57MIN: 11.24 / MAX: 12.11MIN: 11.32 / MAX: 27.4MIN: 11.3 / MAX: 12.02MIN: 11.31 / MAX: 12.341. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: alexnetRun 1Run 2Run 3Run 4246810SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 37.587.607.607.59MIN: 7.45 / MAX: 8.3MIN: 7.47 / MAX: 9.72MIN: 7.49 / MAX: 8.32MIN: 7.47 / MAX: 10.361. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: resnet50Run 1Run 2Run 3Run 4612182430SE +/- 0.07, N = 3SE +/- 0.05, N = 3SE +/- 0.05, N = 3SE +/- 0.06, N = 323.0222.9622.8923.04MIN: 22.64 / MAX: 24.07MIN: 22.62 / MAX: 25.08MIN: 22.6 / MAX: 24.13MIN: 22.6 / MAX: 25.321. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: yolov4-tinyRun 1Run 2Run 3Run 4612182430SE +/- 0.43, N = 3SE +/- 0.33, N = 3SE +/- 0.02, N = 3SE +/- 0.24, N = 327.0626.7126.4027.10MIN: 25.93 / MAX: 29.4MIN: 26.02 / MAX: 29.99MIN: 25.98 / MAX: 38.47MIN: 26.06 / MAX: 74.451. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: squeezenet_ssd

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: squeezenet_ssdRun 1Run 2Run 3Run 4612182430SE +/- 0.38, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.42, N = 324.8624.4824.4625.31MIN: 23.86 / MAX: 26.49MIN: 23.9 / MAX: 25.96MIN: 23.88 / MAX: 25.94MIN: 23.93 / MAX: 26.271. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: regnety_400m

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: regnety_400mRun 1Run 2Run 3Run 4816243240SE +/- 0.36, N = 3SE +/- 0.17, N = 3SE +/- 0.09, N = 3SE +/- 0.31, N = 332.0732.1932.3532.03MIN: 30.83 / MAX: 33.73MIN: 31.55 / MAX: 81.79MIN: 31.73 / MAX: 34.27MIN: 31.01 / MAX: 79.481. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

WavPack Audio Encoding

WAV To WavPack

OpenBenchmarking.orgSeconds, Fewer Is BetterWavPack Audio Encoding 5.3WAV To WavPackRun 1Run 2Run 3Run 448121620SE +/- 0.00, N = 5SE +/- 0.00, N = 5SE +/- 0.00, N = 5SE +/- 0.00, N = 513.7313.7313.7313.731. (CXX) g++ options: -rdynamic

Unpacking Firefox

Extracting: firefox-84.0.source.tar.xz

OpenBenchmarking.orgSeconds, Fewer Is BetterUnpacking Firefox 84.0Extracting: firefox-84.0.source.tar.xzRun 1Run 2Run 3Run 4510152025SE +/- 0.05, N = 4SE +/- 0.06, N = 4SE +/- 0.07, N = 4SE +/- 0.05, N = 420.3720.2720.2220.21

Phoronix Test Suite v10.8.4