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.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2012274-HA-EPYC7F32L08
Jump To Table - Results

View

Do Not Show Noisy Results
Do Not Show Results With Incomplete Data
Do Not Show Results With Little Change/Spread
List Notable Results

Limit displaying results to tests within:

Audio Encoding 4 Tests
Timed Code Compilation 2 Tests
CPU Massive 2 Tests
Creator Workloads 5 Tests
Encoding 4 Tests
HPC - High Performance Computing 2 Tests
Machine Learning 2 Tests
Multi-Core 3 Tests
Programmer / Developer System Benchmarks 2 Tests

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
Show Geometric Means Per-Suite/Category
Show Wins / Losses Counts (Pie Chart)
Normalize Results
Remove Outliers Before Calculating Averages

Graph Settings

Force Line Graphs Where Applicable
Convert To Scalar Where Applicable
Prefer Vertical Bar Graphs

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
Run 1
December 26 2020
  1 Hour, 54 Minutes
Run 2
December 26 2020
  1 Hour, 37 Minutes
Run 3
December 27 2020
  1 Hour, 38 Minutes
Run 4
December 27 2020
  1 Hour, 37 Minutes
Invert Hiding All Results Option
  1 Hour, 42 Minutes

Only show results where is faster than
Only show results matching title/arguments (delimit multiple options with a comma):
Do not show results matching title/arguments (delimit multiple options with a comma):

Run 1

Compiler Notes: --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 Notes: NONE / errors=remount-ro,relatime,rw / Block Size: 4096
Processor Notes: Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0x8301034
Security Notes: 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

Run 2

Run 3

Run 4

Processor: AMD EPYC 7F32 8-Core @ 3.70GHz (8 Cores / 16 Threads), Motherboard: Supermicro H11DSi-NT v2.00 (2.1 BIOS), Chipset: AMD Starship/Matisse, Memory: 64GB, Disk: 280GB INTEL SSDPE21D280GA, Graphics: llvmpipe, Monitor: VE228

OS: Ubuntu 20.04, Kernel: 5.8.0-050800rc6daily20200721-generic (x86_64) 20200720, Desktop: GNOME Shell 3.36.1, Display Server: X Server 1.20.8, Display Driver: modesetting 1.20.8, OpenGL: 3.3 Mesa 20.0.4 (LLVM 9.0.1 128 bits), Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 1920x1080

EPYC 7F32 LastOpenBenchmarking.orgPhoronix Test SuiteAMD 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 9.3.0ext41920x1080ProcessorMotherboardChipsetMemoryDiskGraphicsMonitorOSKernelDesktopDisplay ServerDisplay DriverOpenGLCompilerFile-SystemScreen ResolutionEPYC 7F32 Last BenchmarksSystem Logs- --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 - NONE / errors=remount-ro,relatime,rw / Block Size: 4096- Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0x8301034 - 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

Run 1Run 2Run 3Run 4Result OverviewPhoronix Test Suite100%101%101%102%Unpacking The Linux KernelCLOMPNCNNUnpacking FirefoxBuild2oneDNNTimed Eigen CompilationMonkey Audio EncodingOgg Audio EncodingOpus Codec EncodingWavPack Audio Encoding

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

This test measures how long it takes to extract the .tar.xz Linux kernel package. Learn more via the OpenBenchmarking.org test page.

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
OpenBenchmarking.orgSeconds, Fewer Is BetterUnpacking The Linux Kernellinux-4.15.tar.xzRun 1Run 2Run 3Run 4246810Min: 5.87 / Avg: 5.97 / Max: 6.08Min: 5.81 / Avg: 5.97 / Max: 6.18Min: 5.97 / Avg: 6.02 / Max: 6.1Min: 5.69 / Avg: 5.85 / Max: 6.02

CLOMP

CLOMP is the C version of the Livermore OpenMP benchmark developed to measure OpenMP overheads and other performance impacts due to threading in order to influence future system designs. This particular test profile configuration is currently set to look at the OpenMP static schedule speed-up across all available CPU cores using the recommended test configuration. Learn more via the OpenBenchmarking.org test page.

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
OpenBenchmarking.orgSpeedup, More Is BetterCLOMP 1.2Static OMP SpeedupRun 1Run 2Run 3Run 4714212835Min: 29.7 / Avg: 29.77 / Max: 29.8Min: 29.4 / Avg: 29.57 / Max: 29.7Min: 27.8 / Avg: 28.98 / Max: 29.7Min: 29.3 / Avg: 29.7 / Max: 29.91. (CC) gcc options: -fopenmp -O3 -lm

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

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
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: IP Shapes 1D - Data Type: f32 - Engine: CPURun 1Run 2Run 3Run 4246810Min: 3.52 / Avg: 3.55 / Max: 3.57Min: 3.54 / Avg: 3.55 / Max: 3.56Min: 3.55 / Avg: 3.56 / Max: 3.57Min: 3.55 / Avg: 3.56 / Max: 3.571. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

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
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: IP Shapes 3D - Data Type: f32 - Engine: CPURun 1Run 2Run 3Run 4246810Min: 6.13 / Avg: 6.22 / Max: 6.52Min: 6.12 / Avg: 6.15 / Max: 6.19Min: 6.12 / Avg: 6.13 / Max: 6.13Min: 6.15 / Avg: 6.18 / Max: 6.211. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

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
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPURun 1Run 2Run 3Run 4246810Min: 2.79 / Avg: 2.79 / Max: 2.8Min: 2.78 / Avg: 2.79 / Max: 2.79Min: 2.78 / Avg: 2.79 / Max: 2.79Min: 2.78 / Avg: 2.79 / Max: 2.81. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

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
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPURun 1Run 2Run 3Run 4246810Min: 0.77 / Avg: 0.79 / Max: 0.81Min: 0.79 / Avg: 0.8 / Max: 0.8Min: 0.79 / Avg: 0.8 / Max: 0.8Min: 0.78 / Avg: 0.79 / Max: 0.81. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

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
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPURun 1Run 2Run 3Run 4246810Min: 4.93 / Avg: 4.98 / Max: 5.05Min: 4.9 / Avg: 4.92 / Max: 4.95Min: 4.94 / Avg: 4.95 / Max: 4.96Min: 4.89 / Avg: 4.93 / Max: 4.961. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

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
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPURun 1Run 2Run 3Run 4246810Min: 4.9 / Avg: 4.94 / Max: 5Min: 4.92 / Avg: 4.97 / Max: 5.04Min: 4.93 / Avg: 4.96 / Max: 5.01Min: 4.89 / Avg: 4.94 / Max: 4.991. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

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
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPURun 1Run 2Run 3Run 43691215Min: 6.42 / Avg: 6.42 / Max: 6.43Min: 6.41 / Avg: 6.42 / Max: 6.43Min: 6.42 / Avg: 6.42 / Max: 6.42Min: 6.41 / Avg: 6.42 / Max: 6.421. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

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
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPURun 1Run 2Run 3Run 43691215Min: 9.45 / Avg: 9.67 / Max: 9.84Min: 9.5 / Avg: 9.62 / Max: 9.84Min: 9.43 / Avg: 9.47 / Max: 9.54Min: 9.39 / Avg: 9.6 / Max: 9.891. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

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
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPURun 1Run 2Run 3Run 43691215Min: 7.14 / Avg: 7.2 / Max: 7.23Min: 7.17 / Avg: 7.22 / Max: 7.29Min: 7.21 / Avg: 7.22 / Max: 7.25Min: 7.2 / Avg: 7.22 / Max: 7.261. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

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
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPURun 1Run 2Run 3Run 4246810Min: 5.58 / Avg: 5.58 / Max: 5.59Min: 5.58 / Avg: 5.58 / Max: 5.58Min: 5.57 / Avg: 5.58 / Max: 5.59Min: 5.58 / Avg: 5.59 / Max: 5.591. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

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
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPURun 1Run 2Run 3Run 46001200180024003000Min: 3418.82 / Avg: 3604.4 / Max: 4776.46Min: 3433.92 / Avg: 3436.43 / Max: 3439.78Min: 3421.55 / Avg: 3431.5 / Max: 3440.01Min: 3414.93 / Avg: 3417.31 / Max: 3418.571. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

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
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPURun 1Run 2Run 3Run 430060090012001500Min: 1704.45 / Avg: 1708.29 / Max: 1711.76Min: 1705.77 / Avg: 1708.22 / Max: 1711.84Min: 1707.34 / Avg: 1711.14 / Max: 1716.76Min: 1706.32 / Avg: 1711.87 / Max: 1717.271. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

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
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPURun 1Run 2Run 3Run 46001200180024003000Min: 3422.83 / Avg: 3429.54 / Max: 3437.04Min: 3435.82 / Avg: 3438.99 / Max: 3441.12Min: 3433.89 / Avg: 3436.78 / Max: 3439.19Min: 3426.13 / Avg: 3427.26 / Max: 3428.261. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

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
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPURun 1Run 2Run 3Run 430060090012001500Min: 1708.72 / Avg: 1711.39 / Max: 1713.41Min: 1717.69 / Avg: 1718.14 / Max: 1718.65Min: 1715.52 / Avg: 1716.53 / Max: 1717.9Min: 1708.67 / Avg: 1711.28 / Max: 1713.071. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

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
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPURun 1Run 2Run 3Run 4246810Min: 1.16 / Avg: 1.16 / Max: 1.17Min: 1.15 / Avg: 1.16 / Max: 1.16Min: 1.16 / Avg: 1.16 / Max: 1.16Min: 1.16 / Avg: 1.16 / Max: 1.161. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

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
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPURun 1Run 2Run 3Run 46001200180024003000Min: 3412.04 / Avg: 3417.91 / Max: 3427.9Min: 3437.73 / Avg: 3441.93 / Max: 3444.73Min: 3436.04 / Avg: 3441.2 / Max: 3449.63Min: 3414.25 / Avg: 3421.95 / Max: 3428.511. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

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
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPURun 1Run 2Run 3Run 430060090012001500Min: 1700.41 / Avg: 1704.97 / Max: 1709.82Min: 1714.37 / Avg: 1715.65 / Max: 1716.62Min: 1706.24 / Avg: 1712.85 / Max: 1718.4Min: 1708.31 / Avg: 1714.22 / Max: 1722.361. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

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
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPURun 1Run 2Run 3Run 4246810Min: 3.59 / Avg: 3.6 / Max: 3.61Min: 3.59 / Avg: 3.6 / Max: 3.6Min: 3.59 / Avg: 3.59 / Max: 3.59Min: 3.59 / Avg: 3.6 / Max: 3.611. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

Build2

This test profile measures the time to bootstrap/install the build2 C++ build toolchain from source. Build2 is a cross-platform build toolchain for C/C++ code and features Cargo-like features. Learn more via the OpenBenchmarking.org test page.

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
OpenBenchmarking.orgSeconds, Fewer Is BetterBuild2 0.13Time To CompileRun 1Run 2Run 3Run 420406080100Min: 111.36 / Avg: 112.08 / Max: 112.79Min: 112.17 / Avg: 112.78 / Max: 113.19Min: 110.97 / Avg: 112.67 / Max: 113.88Min: 112 / Avg: 112.46 / Max: 113.3

Timed Eigen Compilation

This test times how long it takes to build all Eigen examples. The Eigen examples are compiled serially. Eigen is a C++ template library for linear algebra. Learn more via the OpenBenchmarking.org test page.

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
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Eigen Compilation 3.3.9Time To CompileRun 1Run 2Run 3Run 41632486480Min: 82.85 / Avg: 82.88 / Max: 82.91Min: 82.93 / Avg: 82.95 / Max: 82.97Min: 83.03 / Avg: 83.07 / Max: 83.13Min: 82.93 / Avg: 82.99 / Max: 83.06

Monkey Audio Encoding

This test times how long it takes to encode a sample WAV file to Monkey's Audio APE format. Learn more via the OpenBenchmarking.org test page.

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
OpenBenchmarking.orgSeconds, Fewer Is BetterMonkey Audio Encoding 3.99.6WAV To APERun 1Run 2Run 3Run 448121620Min: 12.48 / Avg: 12.51 / Max: 12.57Min: 12.47 / Avg: 12.51 / Max: 12.55Min: 12.47 / Avg: 12.49 / Max: 12.51Min: 12.48 / Avg: 12.49 / Max: 12.511. (CXX) g++ options: -O3 -pedantic -rdynamic -lrt

Ogg Audio Encoding

This test times how long it takes to encode a sample WAV file to Ogg format using the reference Xiph.org tools/libraries. Learn more via the OpenBenchmarking.org test page.

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
OpenBenchmarking.orgSeconds, Fewer Is BetterOgg Audio Encoding 1.3.4WAV To OggRun 1Run 2Run 3Run 4510152025Min: 20.55 / Avg: 20.57 / Max: 20.62Min: 20.54 / Avg: 20.57 / Max: 20.62Min: 20.55 / Avg: 20.58 / Max: 20.62Min: 20.52 / Avg: 20.56 / Max: 20.581. (CC) gcc options: -O2 -ffast-math -fsigned-char

Opus Codec Encoding

Opus is an open audio codec. Opus is a lossy audio compression format designed primarily for interactive real-time applications over the Internet. This test uses Opus-Tools and measures the time required to encode a WAV file to Opus. Learn more via the OpenBenchmarking.org test page.

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
OpenBenchmarking.orgSeconds, Fewer Is BetterOpus Codec Encoding 1.3.1WAV To Opus EncodeRun 1Run 2Run 3Run 43691215Min: 7.96 / Avg: 7.97 / Max: 7.99Min: 7.96 / Avg: 7.97 / Max: 7.98Min: 7.96 / Avg: 7.97 / Max: 7.97Min: 7.96 / Avg: 7.97 / Max: 7.981. (CXX) g++ options: -fvisibility=hidden -logg -lm

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

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
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: mobilenetRun 1Run 2Run 3Run 4510152025Min: 19.8 / Avg: 19.94 / Max: 20.06Min: 19.77 / Avg: 19.81 / Max: 19.87Min: 19.87 / Avg: 19.89 / Max: 19.91Min: 19.79 / Avg: 19.88 / Max: 19.961. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

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
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU-v2-v2 - Model: mobilenet-v2Run 1Run 2Run 3Run 43691215Min: 6.82 / Avg: 6.87 / Max: 6.93Min: 6.83 / Avg: 6.84 / Max: 6.84Min: 6.82 / Avg: 6.85 / Max: 6.89Min: 6.79 / Avg: 6.83 / Max: 6.881. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

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
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU-v3-v3 - Model: mobilenet-v3Run 1Run 2Run 3Run 43691215Min: 6.61 / Avg: 6.66 / Max: 6.75Min: 6.63 / Avg: 6.64 / Max: 6.66Min: 6.6 / Avg: 6.62 / Max: 6.65Min: 6.56 / Avg: 6.6 / Max: 6.661. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

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
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: shufflenet-v2Run 1Run 2Run 3Run 43691215Min: 9.56 / Avg: 9.61 / Max: 9.67Min: 9.62 / Avg: 9.63 / Max: 9.64Min: 9.58 / Avg: 9.6 / Max: 9.62Min: 9.57 / Avg: 9.6 / Max: 9.651. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

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
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: mnasnetRun 1Run 2Run 3Run 4246810Min: 5.9 / Avg: 6.14 / Max: 6.53Min: 5.92 / Avg: 5.94 / Max: 5.97Min: 5.94 / Avg: 5.97 / Max: 6.01Min: 5.9 / Avg: 6.02 / Max: 6.211. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

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
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: efficientnet-b0Run 1Run 2Run 3Run 43691215Min: 10.41 / Avg: 10.58 / Max: 10.81Min: 10.51 / Avg: 10.55 / Max: 10.57Min: 10.44 / Avg: 10.46 / Max: 10.47Min: 10.44 / Avg: 10.48 / Max: 10.51. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

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
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: blazefaceRun 1Run 2Run 3Run 4246810Min: 3.27 / Avg: 3.31 / Max: 3.37Min: 3.27 / Avg: 3.34 / Max: 3.42Min: 3.3 / Avg: 3.3 / Max: 3.3Min: 3.27 / Avg: 3.31 / Max: 3.341. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

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
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: googlenetRun 1Run 2Run 3Run 448121620Min: 15.47 / Avg: 15.65 / Max: 15.93Min: 15.35 / Avg: 15.52 / Max: 15.85Min: 15.45 / Avg: 15.48 / Max: 15.55Min: 15.43 / Avg: 16.38 / Max: 16.931. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

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
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: vgg16Run 1Run 2Run 3Run 4714212835Min: 32.28 / Avg: 32.45 / Max: 32.67Min: 32.29 / Avg: 32.41 / Max: 32.66Min: 32.25 / Avg: 32.32 / Max: 32.35Min: 32.27 / Avg: 32.31 / Max: 32.331. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

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
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: resnet18Run 1Run 2Run 3Run 43691215Min: 11.4 / Avg: 11.52 / Max: 11.59Min: 11.49 / Avg: 11.57 / Max: 11.66Min: 11.46 / Avg: 11.48 / Max: 11.5Min: 11.44 / Avg: 11.57 / Max: 11.681. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

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
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: alexnetRun 1Run 2Run 3Run 43691215Min: 7.57 / Avg: 7.58 / Max: 7.58Min: 7.57 / Avg: 7.6 / Max: 7.63Min: 7.59 / Avg: 7.6 / Max: 7.61Min: 7.58 / Avg: 7.59 / Max: 7.61. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

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
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: resnet50Run 1Run 2Run 3Run 4510152025Min: 22.91 / Avg: 23.02 / Max: 23.15Min: 22.89 / Avg: 22.96 / Max: 23.06Min: 22.8 / Avg: 22.89 / Max: 22.94Min: 22.91 / Avg: 23.04 / Max: 23.111. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

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
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: yolov4-tinyRun 1Run 2Run 3Run 4612182430Min: 26.27 / Avg: 27.06 / Max: 27.76Min: 26.37 / Avg: 26.71 / Max: 27.38Min: 26.38 / Avg: 26.4 / Max: 26.44Min: 26.62 / Avg: 27.1 / Max: 27.351. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

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
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: squeezenet_ssdRun 1Run 2Run 3Run 4612182430Min: 24.41 / Avg: 24.86 / Max: 25.61Min: 24.45 / Avg: 24.48 / Max: 24.52Min: 24.43 / Avg: 24.46 / Max: 24.48Min: 24.47 / Avg: 25.31 / Max: 25.741. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

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
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: CPU - Model: regnety_400mRun 1Run 2Run 3Run 4714212835Min: 31.37 / Avg: 32.07 / Max: 32.59Min: 31.93 / Avg: 32.19 / Max: 32.5Min: 32.18 / Avg: 32.35 / Max: 32.49Min: 31.71 / Avg: 32.03 / Max: 32.641. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

WavPack Audio Encoding

This test times how long it takes to encode a sample WAV file to WavPack format with very high quality settings. Learn more via the OpenBenchmarking.org test page.

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
OpenBenchmarking.orgSeconds, Fewer Is BetterWavPack Audio Encoding 5.3WAV To WavPackRun 1Run 2Run 3Run 448121620Min: 13.73 / Avg: 13.73 / Max: 13.74Min: 13.73 / Avg: 13.73 / Max: 13.74Min: 13.73 / Avg: 13.73 / Max: 13.73Min: 13.73 / Avg: 13.73 / Max: 13.741. (CXX) g++ options: -rdynamic

Unpacking Firefox

This simple test profile measures how long it takes to extract the .tar.xz source package of the Mozilla Firefox Web Browser. Learn more via the OpenBenchmarking.org test page.

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
OpenBenchmarking.orgSeconds, Fewer Is BetterUnpacking Firefox 84.0Extracting: firefox-84.0.source.tar.xzRun 1Run 2Run 3Run 4510152025Min: 20.23 / Avg: 20.37 / Max: 20.46Min: 20.09 / Avg: 20.27 / Max: 20.35Min: 20.05 / Avg: 20.22 / Max: 20.4Min: 20.08 / Avg: 20.21 / Max: 20.29

Run 1

Compiler Notes: --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 Notes: NONE / errors=remount-ro,relatime,rw / Block Size: 4096
Processor Notes: Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0x8301034
Security Notes: 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

Testing initiated at 26 December 2020 18:00 by user phoronix.

Run 2

Compiler Notes: --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 Notes: NONE / errors=remount-ro,relatime,rw / Block Size: 4096
Processor Notes: Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0x8301034
Security Notes: 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

Testing initiated at 26 December 2020 20:08 by user phoronix.

Run 3

Compiler Notes: --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 Notes: NONE / errors=remount-ro,relatime,rw / Block Size: 4096
Processor Notes: Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0x8301034
Security Notes: 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

Testing initiated at 27 December 2020 05:51 by user phoronix.

Run 4

Processor: AMD EPYC 7F32 8-Core @ 3.70GHz (8 Cores / 16 Threads), Motherboard: Supermicro H11DSi-NT v2.00 (2.1 BIOS), Chipset: AMD Starship/Matisse, Memory: 64GB, Disk: 280GB INTEL SSDPE21D280GA, Graphics: llvmpipe, Monitor: VE228

OS: Ubuntu 20.04, Kernel: 5.8.0-050800rc6daily20200721-generic (x86_64) 20200720, Desktop: GNOME Shell 3.36.1, Display Server: X Server 1.20.8, Display Driver: modesetting 1.20.8, OpenGL: 3.3 Mesa 20.0.4 (LLVM 9.0.1 128 bits), Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 1920x1080

Compiler Notes: --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 Notes: NONE / errors=remount-ro,relatime,rw / Block Size: 4096
Processor Notes: Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0x8301034
Security Notes: 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

Testing initiated at 27 December 2020 09:02 by user phoronix.