9900k-wiesn

Intel Core i9-9900K testing with a ASRock Z390M Pro4 (P4.20 BIOS) and Intel UHD 630 3GB 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 2009261-FI-9900KWIES08
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
Show Result Confidence Charts

Limit displaying results to tests within:

BLAS (Basic Linear Algebra Sub-Routine) Tests 2 Tests
C/C++ Compiler Tests 2 Tests
CPU Massive 2 Tests
Creator Workloads 5 Tests
Database Test Suite 2 Tests
Fortran Tests 3 Tests
HPC - High Performance Computing 10 Tests
Imaging 3 Tests
Machine Learning 6 Tests
Molecular Dynamics 2 Tests
MPI Benchmarks 4 Tests
Multi-Core 2 Tests
NVIDIA GPU Compute 3 Tests
OpenMPI Tests 4 Tests
Python Tests 3 Tests
Scientific Computing 4 Tests
Server 2 Tests
Single-Threaded 2 Tests
Vulkan Compute 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
1
September 26 2020
  2 Hours, 4 Minutes
2
September 26 2020
  8 Hours, 16 Minutes
3
September 26 2020
  2 Hours, 2 Minutes
3a
September 26 2020
  7 Hours, 44 Minutes
Invert Hiding All Results Option
  5 Hours, 2 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):


9900k-wiesn ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLOpenCLCompilerFile-SystemScreen Resolution1233aIntel Core i9-9900K @ 5.00GHz (8 Cores / 16 Threads)ASRock Z390M Pro4 (P4.20 BIOS)Intel Cannon Lake PCH16GB240GB Corsair Force MP510Intel UHD 630 3GB (1200MHz)Realtek ALC892G237HLIntel I219-VUbuntu 20.045.9.0-050900rc1daily20200819-generic (x86_64) 20200818GNOME Shell 3.36.4X Server 1.20.8modesetting 1.20.84.6 Mesa 20.0.4OpenCL 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,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: 0xd6Python Details- Python 2.7.18rc1 + Python 3.8.2Security Details- itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Not affected + mds: Vulnerable; SMT vulnerable + meltdown: Not affected + spec_store_bypass: Vulnerable + spectre_v1: Vulnerable: __user pointer sanitization and usercopy barriers only; no swapgs barriers + spectre_v2: Vulnerable IBPB: disabled STIBP: disabled + srbds: Vulnerable + tsx_async_abort: Vulnerable

1233aResult OverviewPhoronix Test Suite100%101%103%104%105%GLmark2LibRawWebP Image EncodeMonte Carlo Simulations of Ionised NebulaeIncompact3DLAMMPS Molecular Dynamics SimulatorRealSR-NCNN

9900k-wiesn realsr-ncnn: 4x - Noglmark2: 1920 x 1080incompact3d: Cylindermocassin: Dust 2D tau100.0lammps: 20k Atomslammps: Rhodopsin Proteinwebp: Defaultwebp: Quality 100webp: Quality 100, Losslesswebp: Quality 100, Highest Compressionwebp: Quality 100, Lossless, Highest Compressionlibraw: Post-Processing Benchmarkaom-av1: Speed 0 Two-Passlczero: BLASlczero: Eigenlczero: OpenCLdcraw: RAW To PPM Image Conversionespeak: Text-To-Speech Synthesissystem-decompress-gzip: couchdb: 100 - 1000 - 24gpaw: Carbon Nanotubemnn: SqueezeNetV1.0mnn: resnet-v2-50mnn: MobileNetV2_224mnn: mobilenet-v1-1.0mnn: inception-v3ncnn: CPU - squeezenetncnn: 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: Vulkan GPU - squeezenetncnn: 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 - alexnetncnn: Vulkan GPU - resnet50ncnn: Vulkan GPU - yolov4-tinytnn: CPU - MobileNet v2tnn: CPU - SqueezeNet v1.1ai-benchmark: Device Inference Scoreai-benchmark: Device Training Scoreai-benchmark: Device AI Scoreopencv: Features 2Dopencv: Object Detectionopencv: DNN - Deep Neural Networkinfluxdb: 4 - 10000 - 2,5000,1 - 10000influxdb: 64 - 10000 - 2,5000,1 - 10000influxdb: 1024 - 10000 - 2,5000,1 - 100001233a253.485754367.8928631926.1346.8501.3662.11315.5376.32233.01238.820.33253.416744367.0392661916.1496.8561.3562.11015.5556.32533.04039.2086078632733.29024.9952.56675.749343.0045.79534.6342.9666.35037.70415.5017.784.993.982.903.786.221.5415.3466.0014.8015.8027.3426.4139.5234.7611.3012.647.9511.7823.601.9832.35185.1128.5046.7768.6970.98285.030268.09211811139232010997537985249601623050.51631004.71635245.9253.359762365.9540911916.1326.8311.3502.10915.2566.34632.93939.21253.444781365.6853531916.1436.8491.3642.11115.4236.32632.65038.990.3385978432133.27824.9952.56873.534343.6475.81734.8132.9676.32037.87515.4517.794.983.982.873.766.281.6015.3366.0714.6615.7327.0126.4439.5734.5111.2912.647.9511.7723.581.9432.34184.8728.5146.0268.7170.65288.317268.22211831143232611040637334177341623988.51633876.81635905.7OpenBenchmarking.org

RealSR-NCNN

RealSR-NCNN is an NCNN neural network implementation of the RealSR project and accelerated using the Vulkan API. RealSR is the Real-World Super Resolution via Kernel Estimation and Noise Injection. NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. This test profile times how long it takes to increase the resolution of a sample image by a scale of 4x with Vulkan. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRealSR-NCNN 20200818Scale: 4x - TAA: No3a32160120180240300SE +/- 0.05, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 3253.44253.36253.42253.49

GLmark2

This is a test of Linaro's glmark2 port, currently using the X11 OpenGL 2.0 target. GLmark2 is a basic OpenGL benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterGLmark2 2020.04Resolution: 1920 x 10803a3212004006008001000781762744754

Incompact3D

Incompact3d is a Fortran-MPI based, finite difference high-performance code for solving the incompressible Navier-Stokes equation and as many as you need scalar transport equations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterIncompact3D 2020-09-17Input: Cylinder3a32180160240320400SE +/- 2.62, N = 3SE +/- 1.96, N = 3SE +/- 2.28, N = 3SE +/- 0.57, N = 3365.69365.95367.04367.891. (F9X) gfortran options: -cpp -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi

Monte Carlo Simulations of Ionised Nebulae

Mocassin is the Monte Carlo Simulations of Ionised Nebulae. MOCASSIN is a fully 3D or 2D photoionisation and dust radiative transfer code which employs a Monte Carlo approach to the transfer of radiation through media of arbitrary geometry and density distribution. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterMonte Carlo Simulations of Ionised Nebulae 2019-03-24Input: Dust 2D tau100.03a3214080120160200SE +/- 0.67, N = 3SE +/- 0.58, N = 31911911911921. (F9X) gfortran options: -cpp -Jsource/ -ffree-line-length-0 -lm -std=legacy -O3 -O2 -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi

LAMMPS Molecular Dynamics Simulator

LAMMPS is a classical molecular dynamics code, and an acronym for Large-scale Atomic/Molecular Massively Parallel Simulator. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgns/day, More Is BetterLAMMPS Molecular Dynamics Simulator 24Aug2020Model: 20k Atoms3a321246810SE +/- 0.021, N = 3SE +/- 0.010, N = 3SE +/- 0.015, N = 3SE +/- 0.022, N = 36.1436.1326.1496.1341. (CXX) g++ options: -O3 -pthread -lm

OpenBenchmarking.orgns/day, More Is BetterLAMMPS Molecular Dynamics Simulator 24Aug2020Model: Rhodopsin Protein3a321246810SE +/- 0.020, N = 3SE +/- 0.047, N = 14SE +/- 0.005, N = 3SE +/- 0.021, N = 36.8496.8316.8566.8501. (CXX) g++ options: -O3 -pthread -lm

WebP Image Encode

This is a test of Google's libwebp with the cwebp image encode utility and using a sample 6000x4000 pixel JPEG image as the input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Default3a3210.30740.61480.92221.22961.537SE +/- 0.015, N = 3SE +/- 0.001, N = 3SE +/- 0.005, N = 3SE +/- 0.015, N = 31.3641.3501.3561.3661. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff

OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 1003a3210.47540.95081.42621.90162.377SE +/- 0.001, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.001, N = 32.1112.1092.1102.1131. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff

OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100, Lossless3a32148121620SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 315.4215.2615.5615.541. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff

OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100, Highest Compression3a321246810SE +/- 0.008, N = 3SE +/- 0.039, N = 3SE +/- 0.010, N = 3SE +/- 0.006, N = 36.3266.3466.3256.3221. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff

OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100, Lossless, Highest Compression3a321816243240SE +/- 0.10, N = 3SE +/- 0.16, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 332.6532.9433.0433.011. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff

LibRaw

LibRaw is a RAW image decoder for digital camera photos. This test profile runs LibRaw's post-processing benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMpix/sec, More Is BetterLibRaw 0.20Post-Processing Benchmark3a321918273645SE +/- 0.13, N = 3SE +/- 0.08, N = 3SE +/- 0.02, N = 3SE +/- 0.10, N = 338.9939.2139.2038.821. (CXX) g++ options: -O2 -fopenmp -ljpeg -lz -lm

AOM AV1

This is a simple test of the AOMedia AV1 encoder run on the CPU with a sample video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 2.0Encoder Mode: Speed 0 Two-Pass3a10.07430.14860.22290.29720.3715SE +/- 0.00, N = 3SE +/- 0.00, N = 30.330.331. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

LeelaChessZero

LeelaChessZero (lc0 / lczero) is a chess engine automated vian neural networks. This test profile can be used for OpenCL, CUDA + cuDNN, and BLAS (CPU-based) benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.26Backend: BLAS3a22004006008001000SE +/- 5.51, N = 3SE +/- 4.91, N = 38598601. (CXX) g++ options: -flto -pthread

OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.26Backend: Eigen3a22004006008001000SE +/- 2.31, N = 3SE +/- 2.67, N = 37847861. (CXX) g++ options: -flto -pthread

OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.26Backend: OpenCL3a270140210280350SE +/- 3.28, N = 3SE +/- 2.08, N = 33213271. (CXX) g++ options: -flto -pthread

dcraw

This test times how long it takes to convert several high-resolution RAW NEF image files to PPM image format using dcraw. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterdcrawRAW To PPM Image Conversion3a2816243240SE +/- 0.05, N = 3SE +/- 0.11, N = 333.2833.291. (CC) gcc options: -lm

eSpeak-NG Speech Engine

This test times how long it takes the eSpeak speech synthesizer to read Project Gutenberg's The Outline of Science and output to a WAV file. This test profile is now tracking the eSpeak-NG version of eSpeak. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BettereSpeak-NG Speech Engine 20200907Text-To-Speech Synthesis3a2612182430SE +/- 0.11, N = 4SE +/- 0.31, N = 525.0025.001. (CC) gcc options: -O2 -std=c99

System GZIP Decompression

This simple test measures the time to decompress a gzipped tarball (the Qt5 toolkit source package). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSystem GZIP Decompression3a20.57781.15561.73342.31122.889SE +/- 0.019, N = 3SE +/- 0.018, N = 32.5682.566

Apache CouchDB

OpenBenchmarking.orgSeconds, Fewer Is BetterApache CouchDB 3.1.1Bulk Size: 100 - Inserts: 1000 - Rounds: 243a220406080100SE +/- 0.64, N = 3SE +/- 0.88, N = 673.5375.751. (CXX) g++ options: -std=c++14 -lmozjs-68 -lm -lerl_interface -lei -fPIC -MMD

GPAW

GPAW is a density-functional theory (DFT) Python code based on the projector-augmented wave (PAW) method and the atomic simulation environment (ASE). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGPAW 20.1Input: Carbon Nanotube3a270140210280350SE +/- 0.63, N = 3SE +/- 0.64, N = 3343.65343.001. (CC) gcc options: -pthread -shared -fwrapv -O2 -lxc -lblas -lmpi

Mobile Neural Network

MNN is the Mobile Neural Network as a highly efficient, lightweight deep learning framework developed by ALibaba. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2020-09-17Model: SqueezeNetV1.03a21.30882.61763.92645.23526.544SE +/- 0.037, N = 3SE +/- 0.010, N = 35.8175.795MIN: 4.84 / MAX: 7.67MIN: 4.83 / MAX: 8.791. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2020-09-17Model: resnet-v2-503a2816243240SE +/- 0.14, N = 3SE +/- 0.04, N = 334.8134.63MIN: 34.32 / MAX: 47.37MIN: 34.27 / MAX: 46.391. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2020-09-17Model: MobileNetV2_2243a20.66761.33522.00282.67043.338SE +/- 0.015, N = 3SE +/- 0.014, N = 32.9672.966MIN: 2.8 / MAX: 5.23MIN: 2.8 / MAX: 4.261. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2020-09-17Model: mobilenet-v1-1.03a2246810SE +/- 0.006, N = 3SE +/- 0.011, N = 36.3206.350MIN: 6.11 / MAX: 18.61MIN: 6.12 / MAX: 18.431. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2020-09-17Model: inception-v33a2918273645SE +/- 0.24, N = 3SE +/- 0.17, N = 337.8837.70MIN: 37.33 / MAX: 50.76MIN: 37.16 / MAX: 50.831. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

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 20200916Target: CPU - Model: squeezenet3a248121620SE +/- 0.10, N = 3SE +/- 0.07, N = 315.4515.50MIN: 15.24 / MAX: 17.65MIN: 15.25 / MAX: 15.881. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: mobilenet3a248121620SE +/- 0.09, N = 3SE +/- 0.06, N = 317.7917.78MIN: 17.55 / MAX: 18.16MIN: 17.4 / MAX: 27.551. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU-v2-v2 - Model: mobilenet-v23a21.12282.24563.36844.49125.614SE +/- 0.01, N = 3SE +/- 0.00, N = 34.984.99MIN: 4.84 / MAX: 6.09MIN: 4.89 / MAX: 6.061. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU-v3-v3 - Model: mobilenet-v33a20.89551.7912.68653.5824.4775SE +/- 0.02, N = 3SE +/- 0.01, N = 33.983.98MIN: 3.89 / MAX: 5.31MIN: 3.94 / MAX: 5.331. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: shufflenet-v23a20.65251.3051.95752.613.2625SE +/- 0.01, N = 3SE +/- 0.01, N = 32.872.90MIN: 2.83 / MAX: 4.99MIN: 2.86 / MAX: 3.811. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: mnasnet3a20.85051.7012.55153.4024.2525SE +/- 0.01, N = 3SE +/- 0.01, N = 33.763.78MIN: 3.71 / MAX: 4.81MIN: 3.74 / MAX: 5.841. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: efficientnet-b03a2246810SE +/- 0.06, N = 3SE +/- 0.00, N = 36.286.22MIN: 6.18 / MAX: 7.41MIN: 6.1 / MAX: 7.571. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: blazeface3a20.360.721.081.441.8SE +/- 0.08, N = 3SE +/- 0.03, N = 31.601.54MIN: 1.41 / MAX: 1.79MIN: 1.47 / MAX: 1.611. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: googlenet3a248121620SE +/- 0.55, N = 3SE +/- 0.05, N = 315.3315.34MIN: 14.36 / MAX: 17MIN: 15.08 / MAX: 17.871. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: vgg163a21530456075SE +/- 0.12, N = 3SE +/- 0.12, N = 366.0766.00MIN: 65.79 / MAX: 75.74MIN: 65.76 / MAX: 67.31. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: resnet183a248121620SE +/- 0.43, N = 3SE +/- 0.14, N = 314.6614.80MIN: 13.92 / MAX: 15.7MIN: 13.9 / MAX: 17.221. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: alexnet3a248121620SE +/- 0.10, N = 3SE +/- 0.03, N = 315.7315.80MIN: 15.51 / MAX: 17.29MIN: 15.51 / MAX: 17.171. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: resnet503a2612182430SE +/- 0.44, N = 3SE +/- 0.32, N = 327.0127.34MIN: 25.53 / MAX: 36.96MIN: 26.56 / MAX: 28.641. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: yolov4-tiny3a2612182430SE +/- 0.10, N = 3SE +/- 0.09, N = 326.4426.41MIN: 26.12 / MAX: 27.6MIN: 26.01 / MAX: 33.841. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: squeezenet3a2918273645SE +/- 0.06, N = 3SE +/- 0.02, N = 339.5739.52MIN: 39.18 / MAX: 41.55MIN: 39.13 / MAX: 39.751. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: mobilenet3a2816243240SE +/- 0.19, N = 3SE +/- 0.01, N = 334.5134.76MIN: 32.42 / MAX: 40.99MIN: 34.52 / MAX: 36.461. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU-v2-v2 - Model: mobilenet-v23a23691215SE +/- 0.01, N = 3SE +/- 0.00, N = 311.2911.30MIN: 10.74 / MAX: 11.56MIN: 11.05 / MAX: 11.531. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU-v3-v3 - Model: mobilenet-v33a23691215SE +/- 0.01, N = 3SE +/- 0.01, N = 312.6412.64MIN: 12.41 / MAX: 13.06MIN: 12.43 / MAX: 12.851. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: shufflenet-v23a2246810SE +/- 0.03, N = 3SE +/- 0.02, N = 37.957.95MIN: 7.07 / MAX: 8.31MIN: 6.98 / MAX: 8.331. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: mnasnet3a23691215SE +/- 0.01, N = 3SE +/- 0.01, N = 311.7711.78MIN: 11.72 / MAX: 11.93MIN: 11.17 / MAX: 11.961. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: efficientnet-b03a2612182430SE +/- 0.01, N = 3SE +/- 0.02, N = 323.5823.60MIN: 23.23 / MAX: 23.65MIN: 23.24 / MAX: 23.691. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: blazeface3a20.44550.8911.33651.7822.2275SE +/- 0.00, N = 3SE +/- 0.02, N = 31.941.98MIN: 1.92 / MAX: 2.09MIN: 1.92 / MAX: 2.141. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: googlenet3a2816243240SE +/- 0.02, N = 3SE +/- 0.02, N = 332.3432.35MIN: 31.91 / MAX: 32.6MIN: 31.8 / MAX: 32.721. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: vgg163a24080120160200SE +/- 0.05, N = 3SE +/- 0.08, N = 3184.87185.11MIN: 182.78 / MAX: 186.8MIN: 183.53 / MAX: 187.241. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: resnet183a2714212835SE +/- 0.02, N = 3SE +/- 0.01, N = 328.5128.50MIN: 27.98 / MAX: 28.66MIN: 27.98 / MAX: 28.881. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: alexnet3a21122334455SE +/- 0.93, N = 3SE +/- 0.09, N = 346.0246.77MIN: 42.37 / MAX: 50.33MIN: 44.26 / MAX: 49.731. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: resnet503a21530456075SE +/- 0.00, N = 3SE +/- 0.02, N = 368.7168.69MIN: 68.1 / MAX: 68.95MIN: 67.71 / MAX: 69.231. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: yolov4-tiny3a21632486480SE +/- 0.38, N = 3SE +/- 0.06, N = 370.6570.98MIN: 64.15 / MAX: 74MIN: 65.18 / MAX: 91.011. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

TNN

TNN is an open-source deep learning reasoning framework developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.2.3Target: CPU - Model: MobileNet v23a260120180240300SE +/- 0.91, N = 3SE +/- 0.24, N = 3288.32285.03MIN: 286.2 / MAX: 293.83MIN: 283.65 / MAX: 286.481. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -O3 -rdynamic -ldl

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.2.3Target: CPU - Model: SqueezeNet v1.13a260120180240300SE +/- 0.08, N = 3SE +/- 0.02, N = 3268.22268.09MIN: 267.71 / MAX: 269.21MIN: 267.46 / MAX: 270.331. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -O3 -rdynamic -ldl

AI Benchmark Alpha

AI Benchmark Alpha is a Python library for evaluating artificial intelligence (AI) performance on diverse hardware platforms and relies upon the TensorFlow machine learning library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterAI Benchmark Alpha 0.1.2Device Inference Score3a23006009001200150011831181

OpenBenchmarking.orgScore, More Is BetterAI Benchmark Alpha 0.1.2Device Training Score3a2200400600800100011431139

OpenBenchmarking.orgScore, More Is BetterAI Benchmark Alpha 0.1.2Device AI Score3a2500100015002000250023262320

OpenCV

This is a benchmark of the OpenCV (Computer Vision) library's built-in performance tests. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenCV 4.4Test: Features 2D3a220K40K60K80K100KSE +/- 807.78, N = 3SE +/- 869.68, N = 151104061099751. (CXX) g++ options: -fsigned-char -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -msse -msse2 -msse3 -fvisibility=hidden -O3 -ldl -lm -lpthread -lrt

OpenBenchmarking.orgms, Fewer Is BetterOpenCV 4.4Test: Object Detection3a28K16K24K32K40KSE +/- 754.41, N = 15SE +/- 401.74, N = 737334379851. (CXX) g++ options: -fsigned-char -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -msse -msse2 -msse3 -fvisibility=hidden -O3 -ldl -lm -lpthread -lrt

OpenBenchmarking.orgms, Fewer Is BetterOpenCV 4.4Test: DNN - Deep Neural Network3a25K10K15K20K25KSE +/- 161.00, N = 3SE +/- 7385.79, N = 1517734249601. (CXX) g++ options: -fsigned-char -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -msse -msse2 -msse3 -fvisibility=hidden -O3 -ldl -lm -lpthread -lrt

InfluxDB

This is a benchmark of the InfluxDB open-source time-series database optimized for fast, high-availability storage for IoT and other use-cases. The InfluxDB test profile makes use of InfluxDB Inch for facilitating the benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgval/sec, More Is BetterInfluxDB 1.8.2Concurrent Streams: 4 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 100003a2300K600K900K1200K1500KSE +/- 1945.61, N = 3SE +/- 6010.29, N = 31623988.51623050.5

OpenBenchmarking.orgval/sec, More Is BetterInfluxDB 1.8.2Concurrent Streams: 64 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 100003a2300K600K900K1200K1500KSE +/- 3347.24, N = 3SE +/- 8331.21, N = 31633876.81631004.7

OpenBenchmarking.orgval/sec, More Is BetterInfluxDB 1.8.2Concurrent Streams: 1024 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 100003a2400K800K1200K1600K2000KSE +/- 6241.14, N = 3SE +/- 6268.22, N = 31635905.71635245.9

65 Results Shown

RealSR-NCNN
GLmark2
Incompact3D
Monte Carlo Simulations of Ionised Nebulae
LAMMPS Molecular Dynamics Simulator:
  20k Atoms
  Rhodopsin Protein
WebP Image Encode:
  Default
  Quality 100
  Quality 100, Lossless
  Quality 100, Highest Compression
  Quality 100, Lossless, Highest Compression
LibRaw
AOM AV1
LeelaChessZero:
  BLAS
  Eigen
  OpenCL
dcraw
eSpeak-NG Speech Engine
System GZIP Decompression
Apache CouchDB
GPAW
Mobile Neural Network:
  SqueezeNetV1.0
  resnet-v2-50
  MobileNetV2_224
  mobilenet-v1-1.0
  inception-v3
NCNN:
  CPU - squeezenet
  CPU - mobilenet
  CPU-v2-v2 - mobilenet-v2
  CPU-v3-v3 - mobilenet-v3
  CPU - shufflenet-v2
  CPU - mnasnet
  CPU - efficientnet-b0
  CPU - blazeface
  CPU - googlenet
  CPU - vgg16
  CPU - resnet18
  CPU - alexnet
  CPU - resnet50
  CPU - yolov4-tiny
  Vulkan GPU - squeezenet
  Vulkan GPU - mobilenet
  Vulkan GPU-v2-v2 - mobilenet-v2
  Vulkan GPU-v3-v3 - mobilenet-v3
  Vulkan GPU - shufflenet-v2
  Vulkan GPU - mnasnet
  Vulkan GPU - efficientnet-b0
  Vulkan GPU - blazeface
  Vulkan GPU - googlenet
  Vulkan GPU - vgg16
  Vulkan GPU - resnet18
  Vulkan GPU - alexnet
  Vulkan GPU - resnet50
  Vulkan GPU - yolov4-tiny
TNN:
  CPU - MobileNet v2
  CPU - SqueezeNet v1.1
AI Benchmark Alpha:
  Device Inference Score
  Device Training Score
  Device AI Score
OpenCV:
  Features 2D
  Object Detection
  DNN - Deep Neural Network
InfluxDB:
  4 - 10000 - 2,5000,1 - 10000
  64 - 10000 - 2,5000,1 - 10000
  1024 - 10000 - 2,5000,1 - 10000