AMD EPYC 7763 Cooling Performance

AMD EPYC 7763 64-Core CPU benchmarks by Michael Larabel evaluating some heatsink fans in a 4U server.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2104096-IB-HEATSINK430
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:

AV1 2 Tests
Timed Code Compilation 6 Tests
C/C++ Compiler Tests 7 Tests
CPU Massive 10 Tests
Creator Workloads 10 Tests
Encoding 4 Tests
Game Development 2 Tests
HPC - High Performance Computing 5 Tests
Machine Learning 2 Tests
Molecular Dynamics 3 Tests
MPI Benchmarks 2 Tests
Multi-Core 17 Tests
NVIDIA GPU Compute 5 Tests
OpenMPI Tests 2 Tests
Programmer / Developer System Benchmarks 7 Tests
Python Tests 3 Tests
Renderers 3 Tests
Scientific Computing 3 Tests
Software Defined Radio 4 Tests
Server CPU Tests 8 Tests
Video Encoding 4 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
No Box Plots
On Line Graphs With Missing Data, Connect The Line Gaps

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs
Condense Test Profiles With Multiple Version Results 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
Noctua NH-U9 TR4-SP3
April 08 2021
  8 Hours, 12 Minutes
Dynatron A26
April 09 2021
  8 Hours, 45 Minutes
Dynatron A38
April 09 2021
  11 Hours, 17 Minutes
Invert Hiding All Results Option
  9 Hours, 25 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):


AMD EPYC 7763 Cooling PerformanceOpenBenchmarking.orgPhoronix Test SuiteAMD EPYC 7763 64-Core @ 2.45GHz (64 Cores / 128 Threads)Supermicro H12SSL-i v1.01 (2.0 BIOS)AMD Starship/Matisse126GB3841GB Micron_9300_MTFDHAL3T8TDPllvmpipe2 x Broadcom NetXtreme BCM5720 2-port PCIeUbuntu 20.045.12.0-051200rc6daily20210408-generic (x86_64) 20210407GNOME Shell 3.36.4X Server 1.20.83.3 Mesa 20.0.8 (LLVM 10.0.0 128 bits)GCC 9.3.0ext41024x768ProcessorMotherboardChipsetMemoryDiskGraphicsNetworkOSKernelDesktopDisplay ServerOpenGLCompilerFile-SystemScreen ResolutionAMD EPYC 7763 Cooling Performance BenchmarksSystem Logs- Transparent Huge Pages: madvise- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-HskZEa/gcc-9-9.3.0/debian/tmp-nvptx/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0xa001119 - Python 3.8.2- 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: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Noctua NH-U9 TR4-SP3Dynatron A26Dynatron A38Result OverviewPhoronix Test Suite100%101%101%102%StockfishXcompact3d Incompact3dTimed Erlang/OTP CompilationChaos Group V-RAYViennaCLOpenSCADMobile Neural NetworkTimed Node.js CompilationASTC EncoderTimed GDB GNU Debugger CompilationLuaRadioGROMACSIndigoBenchAOM AV1Timed Apache CompilationSVT-AV1Timed Linux Kernel CompilationNAMDsimdjsonsrsLTEGNU RadioSVT-HEVCLiquid-DSPGNU GMP GMPbenchTimed Mesa CompilationSVT-VP9BlenderoneDNN

AMD EPYC 7763 Cooling Performanceindigobench: CPU - Supercarindigobench: CPU - Bedroomv-ray: CPUblender: BMW27 - CPU-Onlyblender: Classroom - CPU-Onlyblender: Fishy Cat - CPU-Onlyblender: Pabellon Barcelona - CPU-Onlyblender: Barbershop - CPU-Onlybuild-linux-kernel: Time To Compilebuild-gdb: Time To Compilebuild-apache: Time To Compilebuild-mesa: Time To Compilebuild-nodejs: Time To Compilebuild-erlang: Time To Compileaom-av1: Speed 9 Realtime - Bosphorus 1080paom-av1: Speed 9 Realtime - Bosphorus 4Kaom-av1: Speed 8 Realtime - Bosphorus 1080paom-av1: Speed 8 Realtime - Bosphorus 4Kaom-av1: Speed 6 Realtime - Bosphorus 1080paom-av1: Speed 6 Realtime - Bosphorus 4Kaom-av1: Speed 6 Two-Pass - Bosphorus 1080paom-av1: Speed 6 Two-Pass - Bosphorus 4Kaom-av1: Speed 4 Two-Pass - Bosphorus 1080paom-av1: Speed 4 Two-Pass - Bosphorus 4Kaom-av1: Speed 0 Two-Pass - Bosphorus 1080paom-av1: Speed 0 Two-Pass - Bosphorus 4Ksvt-vp9: Visual Quality Optimized - Bosphorus 1080psvt-vp9: PSNR/SSIM Optimized - Bosphorus 1080psvt-vp9: VMAF Optimized - Bosphorus 1080psvt-hevc: 1 - Bosphorus 1080psvt-hevc: 7 - Bosphorus 1080psvt-hevc: 10 - Bosphorus 1080psvt-av1: Enc Mode 8 - 1080psvt-av1: Enc Mode 4 - 1080psvt-av1: Enc Mode 0 - 1080pviennacl: CPU BLAS - sCOPYviennacl: CPU BLAS - sAXPYviennacl: CPU BLAS - dCOPYviennacl: CPU BLAS - dAXPYviennacl: CPU BLAS - dDOTviennacl: CPU BLAS - dGEMV-Nviennacl: CPU BLAS - dGEMV-Tviennacl: CPU BLAS - dGEMM-NNviennacl: CPU BLAS - dGEMM-NTviennacl: CPU BLAS - dGEMM-TNviennacl: CPU BLAS - dGEMM-TTviennacl: CPU BLAS - sDOTgmpbench: Total Timeopenscad: Projector Mount Swivelopenscad: Leonardo Phone Case Slimopenscad: Pistolopenscad: Retro Caropenscad: Mini-ITX Casestockfish: Total Timeincompact3d: input.i3d 129 Cells Per Directionincompact3d: input.i3d 193 Cells Per Directionincompact3d: X3D-benchmarking input.i3donednn: Convolution Batch Shapes Auto - f32 - CPUonednn: Convolution Batch Shapes Auto - u8s8f32 - CPUonednn: Deconvolution Batch shapes_1d - f32 - CPUonednn: Deconvolution Batch shapes_1d - u8s8f32 - CPUonednn: Deconvolution Batch shapes_3d - f32 - CPUonednn: Deconvolution Batch shapes_3d - u8s8f32 - CPUonednn: IP Shapes 1D - f32 - CPUonednn: IP Shapes 1D - u8s8f32 - CPUonednn: IP Shapes 3D - f32 - CPUonednn: IP Shapes 3D - u8s8f32 - CPUonednn: Matrix Multiply Batch Shapes Transformer - f32 - CPUonednn: Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPUonednn: Recurrent Neural Network Training - f32 - CPUonednn: Recurrent Neural Network Training - u8s8f32 - CPUonednn: Recurrent Neural Network Training - bf16bf16bf16 - CPUonednn: Recurrent Neural Network Inference - f32 - CPUonednn: Recurrent Neural Network Inference - u8s8f32 - CPUonednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPUmnn: SqueezeNetV1.0mnn: resnet-v2-50mnn: MobileNetV2_224mnn: mobilenet-v1-1.0mnn: inception-v3astcenc: Mediumastcenc: Thoroughastcenc: Exhaustivesimdjson: PartialTweetssimdjson: LargeRandsimdjson: Kostyasimdjson: DistinctUserIDsrslte: OFDM_Testsrslte: PHY_DL_Testsrslte: PHY_DL_Testgnuradio: Five Back to Back FIR Filtersgnuradio: Signal Source (Cosine)gnuradio: FIR Filtergnuradio: IIR Filtergnuradio: FM Deemphasis Filtergnuradio: Hilbert Transformluaradio: Five Back to Back FIR Filtersluaradio: FM Deemphasis Filterluaradio: Hilbert Transformluaradio: Complex Phaseliquid-dsp: 16 - 256 - 57liquid-dsp: 32 - 256 - 57liquid-dsp: 64 - 256 - 57liquid-dsp: 128 - 256 - 57gromacs: water_GMX50_barenamd: ATPase Simulation - 327,506 AtomsNoctua NH-U9 TR4-SP3Dynatron A26Dynatron A3824.19011.3945791231.9280.9645.9893.59111.6126.93098.81423.59019.835110.706134.328104.5737.4586.1334.124.6116.0921.319.156.744.720.50.2345.24471.60468.7637.76324.42607.0292.8619.4730.130103562714011222111588.679388.186.192.189.76375098.8100.90218.699109.83319.06345.8411566566855.1565307222.5096487625.8123370.8800471.652207.136080.6050583.038200.7818511.177961.177583.663070.6630590.3849290.7209281373.911385.321370.82665.228664.988664.6805.78522.1303.7572.32828.1714.91767.992520.44283.640.962.834.01115633333257.494.3560.93322.2639.0608.6765.3378.21101.6344.793.5591.88033100001613766667279240000030179333335.5770.3811024.25611.3995827031.8580.8645.8093.72111.4826.87799.32623.67319.796111.318132.497101.7038.0686.5634.2924.7116.2521.479.166.714.830.500.2347.78471.09468.5937.89323.60602.5592.3479.4520.130105264014091205111682.678188.686.692.189.96405099.2100.72318.525108.61718.88645.2321601076515.1506515922.3308512667.2684940.8797521.656717.178390.6076553.024590.7834641.178631.186853.649410.6506240.3814950.7267891378.861369.981391.14666.049664.807666.4835.79722.3973.7892.34228.4514.94128.006220.61963.630.962.834.00116233333257.194.3567.73324.7641.6604.7760.3377.31110.6344.293.6591.68001900001614933333278286666730280666675.5820.3816424.36011.4045850431.9280.9246.0193.72111.5326.84499.08623.58619.800110.941133.119101.2737.4687.6334.7324.8216.1421.469.356.684.770.500.2346.82470.69467.9637.92322.43605.9793.0489.3550.130104464013991204111278.977988.286.391.989.96365089.1101.04518.734108.79418.92745.4821585120045.1505176722.7087644627.6671140.8794801.672567.180020.6036213.043520.7810601.180871.179063.617620.6403310.3852070.7215861400.191377.491381.77665.526665.265666.1305.87822.2693.7802.33228.3284.94247.989820.55913.630.962.833.98117866667255.993.7560.13303.6642.0607.0764.1376.21097.4343.493.5591.08041466671614566667279373333330281333335.5990.38215OpenBenchmarking.org

IndigoBench

This is a test of Indigo Renderer's IndigoBench benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.4Acceleration: CPU - Scene: SupercarNoctua NH-U9 TR4-SP3Dynatron A26Dynatron A38612182430SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.06, N = 324.1924.2624.36
OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.4Acceleration: CPU - Scene: SupercarNoctua NH-U9 TR4-SP3Dynatron A26Dynatron A38612182430Min: 24.13 / Avg: 24.19 / Max: 24.23Min: 24.2 / Avg: 24.26 / Max: 24.29Min: 24.24 / Avg: 24.36 / Max: 24.46

OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.4Acceleration: CPU - Scene: BedroomNoctua NH-U9 TR4-SP3Dynatron A26Dynatron A383691215SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 311.3911.4011.40
OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.4Acceleration: CPU - Scene: BedroomNoctua NH-U9 TR4-SP3Dynatron A26Dynatron A383691215Min: 11.34 / Avg: 11.39 / Max: 11.45Min: 11.35 / Avg: 11.4 / Max: 11.46Min: 11.38 / Avg: 11.4 / Max: 11.43

Chaos Group V-RAY

This is a test of Chaos Group's V-RAY benchmark. V-RAY is a commercial renderer that can integrate with various creator software products like SketchUp and 3ds Max. The V-RAY benchmark is standalone and supports CPU and NVIDIA CUDA/RTX based rendering. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgvsamples, More Is BetterChaos Group V-RAY 5Mode: CPUNoctua NH-U9 TR4-SP3Dynatron A26Dynatron A3813K26K39K52K65KSE +/- 265.36, N = 3SE +/- 814.01, N = 3SE +/- 477.68, N = 3579125827058504
OpenBenchmarking.orgvsamples, More Is BetterChaos Group V-RAY 5Mode: CPUNoctua NH-U9 TR4-SP3Dynatron A26Dynatron A3810K20K30K40K50KMin: 57435 / Avg: 57912 / Max: 58352Min: 56656 / Avg: 58270.33 / Max: 59260Min: 57791 / Avg: 58503.67 / Max: 59411

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL, NVIDIA OptiX, and NVIDIA CUDA is supported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: BMW27 - Compute: CPU-OnlyDynatron A38Noctua NH-U9 TR4-SP3Dynatron A26714212835SE +/- 0.07, N = 3SE +/- 0.10, N = 3SE +/- 0.04, N = 331.9231.9231.85
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: BMW27 - Compute: CPU-OnlyDynatron A38Noctua NH-U9 TR4-SP3Dynatron A26714212835Min: 31.8 / Avg: 31.92 / Max: 32.04Min: 31.73 / Avg: 31.92 / Max: 32.08Min: 31.78 / Avg: 31.85 / Max: 31.92

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Classroom - Compute: CPU-OnlyNoctua NH-U9 TR4-SP3Dynatron A38Dynatron A2620406080100SE +/- 0.08, N = 3SE +/- 0.08, N = 3SE +/- 0.07, N = 380.9680.9280.86
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Classroom - Compute: CPU-OnlyNoctua NH-U9 TR4-SP3Dynatron A38Dynatron A261530456075Min: 80.87 / Avg: 80.96 / Max: 81.13Min: 80.79 / Avg: 80.92 / Max: 81.07Min: 80.72 / Avg: 80.86 / Max: 80.94

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Fishy Cat - Compute: CPU-OnlyDynatron A38Noctua NH-U9 TR4-SP3Dynatron A261020304050SE +/- 0.06, N = 3SE +/- 0.08, N = 3SE +/- 0.09, N = 346.0145.9845.80
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Fishy Cat - Compute: CPU-OnlyDynatron A38Noctua NH-U9 TR4-SP3Dynatron A26918273645Min: 45.92 / Avg: 46.01 / Max: 46.13Min: 45.86 / Avg: 45.98 / Max: 46.13Min: 45.64 / Avg: 45.8 / Max: 45.96

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Pabellon Barcelona - Compute: CPU-OnlyDynatron A38Dynatron A26Noctua NH-U9 TR4-SP320406080100SE +/- 0.01, N = 3SE +/- 0.08, N = 3SE +/- 0.06, N = 393.7293.7293.59
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Pabellon Barcelona - Compute: CPU-OnlyDynatron A38Dynatron A26Noctua NH-U9 TR4-SP320406080100Min: 93.71 / Avg: 93.72 / Max: 93.73Min: 93.57 / Avg: 93.72 / Max: 93.86Min: 93.53 / Avg: 93.59 / Max: 93.7

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Barbershop - Compute: CPU-OnlyNoctua NH-U9 TR4-SP3Dynatron A38Dynatron A2620406080100SE +/- 0.05, N = 3SE +/- 0.10, N = 3SE +/- 0.08, N = 3111.61111.53111.48
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Barbershop - Compute: CPU-OnlyNoctua NH-U9 TR4-SP3Dynatron A38Dynatron A2620406080100Min: 111.56 / Avg: 111.61 / Max: 111.7Min: 111.36 / Avg: 111.53 / Max: 111.71Min: 111.4 / Avg: 111.48 / Max: 111.63

Timed Linux Kernel Compilation

This test times how long it takes to build the Linux kernel in a default configuration (defconfig) for the architecture being tested. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 5.10.20Time To CompileNoctua NH-U9 TR4-SP3Dynatron A26Dynatron A38612182430SE +/- 0.28, N = 8SE +/- 0.26, N = 9SE +/- 0.26, N = 926.9326.8826.84
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 5.10.20Time To CompileNoctua NH-U9 TR4-SP3Dynatron A26Dynatron A38612182430Min: 26.59 / Avg: 26.93 / Max: 28.91Min: 26.53 / Avg: 26.88 / Max: 28.96Min: 26.51 / Avg: 26.84 / Max: 28.88

Timed GDB GNU Debugger Compilation

This test times how long it takes to build the GNU Debugger (GDB) in a default configuration. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed GDB GNU Debugger Compilation 9.1Time To CompileDynatron A26Dynatron A38Noctua NH-U9 TR4-SP320406080100SE +/- 0.12, N = 3SE +/- 0.07, N = 3SE +/- 0.12, N = 399.3399.0998.81
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed GDB GNU Debugger Compilation 9.1Time To CompileDynatron A26Dynatron A38Noctua NH-U9 TR4-SP320406080100Min: 99.12 / Avg: 99.33 / Max: 99.55Min: 98.96 / Avg: 99.09 / Max: 99.16Min: 98.57 / Avg: 98.81 / Max: 98.95

Timed Apache Compilation

This test times how long it takes to build the Apache HTTPD web server. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Apache Compilation 2.4.41Time To CompileDynatron A26Noctua NH-U9 TR4-SP3Dynatron A38612182430SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 323.6723.5923.59
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Apache Compilation 2.4.41Time To CompileDynatron A26Noctua NH-U9 TR4-SP3Dynatron A38612182430Min: 23.65 / Avg: 23.67 / Max: 23.72Min: 23.57 / Avg: 23.59 / Max: 23.61Min: 23.57 / Avg: 23.59 / Max: 23.59

Timed Mesa Compilation

This test profile times how long it takes to compile Mesa with Meson/Ninja. For minimizing build dependencies and avoid versioning conflicts, test this is just the core Mesa build without LLVM or the extra Gallium3D/Mesa drivers enabled. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Mesa Compilation 21.0Time To CompileNoctua NH-U9 TR4-SP3Dynatron A38Dynatron A26510152025SE +/- 0.09, N = 3SE +/- 0.04, N = 3SE +/- 0.06, N = 319.8419.8019.80
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Mesa Compilation 21.0Time To CompileNoctua NH-U9 TR4-SP3Dynatron A38Dynatron A26510152025Min: 19.72 / Avg: 19.83 / Max: 20.02Min: 19.73 / Avg: 19.8 / Max: 19.87Min: 19.68 / Avg: 19.8 / Max: 19.88

Timed Node.js Compilation

This test profile times how long it takes to build/compile Node.js itself from source. Node.js is a JavaScript run-time built from the Chrome V8 JavaScript engine while itself is written in C/C++. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Node.js Compilation 15.11Time To CompileDynatron A26Dynatron A38Noctua NH-U9 TR4-SP320406080100SE +/- 0.11, N = 3SE +/- 0.30, N = 3SE +/- 0.28, N = 3111.32110.94110.71
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Node.js Compilation 15.11Time To CompileDynatron A26Dynatron A38Noctua NH-U9 TR4-SP320406080100Min: 111.1 / Avg: 111.32 / Max: 111.47Min: 110.34 / Avg: 110.94 / Max: 111.3Min: 110.15 / Avg: 110.71 / Max: 110.99

Timed Erlang/OTP Compilation

This test times how long it takes to compile Erlang/OTP. Erlang is a programming language and run-time for massively scalable soft real-time systems with high availability requirements. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Erlang/OTP Compilation 23.2Time To CompileNoctua NH-U9 TR4-SP3Dynatron A38Dynatron A26306090120150SE +/- 0.26, N = 3SE +/- 0.29, N = 3SE +/- 0.39, N = 3134.33133.12132.50
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Erlang/OTP Compilation 23.2Time To CompileNoctua NH-U9 TR4-SP3Dynatron A38Dynatron A26306090120150Min: 133.88 / Avg: 134.33 / Max: 134.77Min: 132.54 / Avg: 133.12 / Max: 133.48Min: 131.77 / Avg: 132.5 / Max: 133.08

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.0Encoder Mode: Speed 9 Realtime - Input: Bosphorus 1080pDynatron A38Dynatron A26Noctua NH-U9 TR4-SP320406080100SE +/- 0.67, N = 6SE +/- 1.09, N = 6SE +/- 1.05, N = 7101.27101.70104.571. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.0Encoder Mode: Speed 9 Realtime - Input: Bosphorus 1080pDynatron A38Dynatron A26Noctua NH-U9 TR4-SP320406080100Min: 98.05 / Avg: 101.27 / Max: 102.6Min: 98.17 / Avg: 101.7 / Max: 106.39Min: 99.71 / Avg: 104.57 / Max: 107.31. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.0Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4KNoctua NH-U9 TR4-SP3Dynatron A38Dynatron A26918273645SE +/- 0.43, N = 3SE +/- 0.48, N = 5SE +/- 0.46, N = 637.4537.4638.061. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.0Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4KNoctua NH-U9 TR4-SP3Dynatron A38Dynatron A26816243240Min: 36.62 / Avg: 37.45 / Max: 38.05Min: 36.02 / Avg: 37.46 / Max: 38.78Min: 35.8 / Avg: 38.06 / Max: 38.791. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.0Encoder Mode: Speed 8 Realtime - Input: Bosphorus 1080pNoctua NH-U9 TR4-SP3Dynatron A26Dynatron A3820406080100SE +/- 0.36, N = 6SE +/- 0.59, N = 6SE +/- 0.58, N = 686.1386.5687.631. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.0Encoder Mode: Speed 8 Realtime - Input: Bosphorus 1080pNoctua NH-U9 TR4-SP3Dynatron A26Dynatron A3820406080100Min: 85.32 / Avg: 86.13 / Max: 87.79Min: 84.83 / Avg: 86.56 / Max: 88.48Min: 86.09 / Avg: 87.63 / Max: 89.981. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.0Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4KNoctua NH-U9 TR4-SP3Dynatron A26Dynatron A38816243240SE +/- 0.07, N = 3SE +/- 0.22, N = 3SE +/- 0.28, N = 334.1034.2934.731. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.0Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4KNoctua NH-U9 TR4-SP3Dynatron A26Dynatron A38714212835Min: 34 / Avg: 34.07 / Max: 34.2Min: 33.86 / Avg: 34.29 / Max: 34.54Min: 34.18 / Avg: 34.73 / Max: 35.021. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.0Encoder Mode: Speed 6 Realtime - Input: Bosphorus 1080pNoctua NH-U9 TR4-SP3Dynatron A26Dynatron A38612182430SE +/- 0.05, N = 3SE +/- 0.18, N = 3SE +/- 0.10, N = 324.6124.7124.821. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.0Encoder Mode: Speed 6 Realtime - Input: Bosphorus 1080pNoctua NH-U9 TR4-SP3Dynatron A26Dynatron A38612182430Min: 24.54 / Avg: 24.61 / Max: 24.71Min: 24.36 / Avg: 24.71 / Max: 24.91Min: 24.64 / Avg: 24.82 / Max: 24.981. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.0Encoder Mode: Speed 6 Realtime - Input: Bosphorus 4KNoctua NH-U9 TR4-SP3Dynatron A38Dynatron A2648121620SE +/- 0.03, N = 3SE +/- 0.05, N = 3SE +/- 0.06, N = 316.0916.1416.251. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.0Encoder Mode: Speed 6 Realtime - Input: Bosphorus 4KNoctua NH-U9 TR4-SP3Dynatron A38Dynatron A2648121620Min: 16.04 / Avg: 16.09 / Max: 16.14Min: 16.07 / Avg: 16.14 / Max: 16.24Min: 16.14 / Avg: 16.25 / Max: 16.351. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.0Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 1080pNoctua NH-U9 TR4-SP3Dynatron A38Dynatron A26510152025SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.06, N = 321.3121.4621.471. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.0Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 1080pNoctua NH-U9 TR4-SP3Dynatron A38Dynatron A26510152025Min: 21.23 / Avg: 21.31 / Max: 21.38Min: 21.4 / Avg: 21.46 / Max: 21.5Min: 21.38 / Avg: 21.47 / Max: 21.581. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.0Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 4KNoctua NH-U9 TR4-SP3Dynatron A26Dynatron A383691215SE +/- 0.07, N = 3SE +/- 0.10, N = 3SE +/- 0.11, N = 69.159.169.351. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.0Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 4KNoctua NH-U9 TR4-SP3Dynatron A26Dynatron A383691215Min: 9.05 / Avg: 9.15 / Max: 9.29Min: 9.04 / Avg: 9.16 / Max: 9.36Min: 9.1 / Avg: 9.35 / Max: 9.691. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.0Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 1080pDynatron A38Dynatron A26Noctua NH-U9 TR4-SP3246810SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 36.686.716.741. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.0Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 1080pDynatron A38Dynatron A26Noctua NH-U9 TR4-SP33691215Min: 6.68 / Avg: 6.68 / Max: 6.69Min: 6.69 / Avg: 6.71 / Max: 6.72Min: 6.71 / Avg: 6.74 / Max: 6.771. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.0Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 4KNoctua NH-U9 TR4-SP3Dynatron A38Dynatron A261.08682.17363.26044.34725.434SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 34.724.774.831. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.0Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 4KNoctua NH-U9 TR4-SP3Dynatron A38Dynatron A26246810Min: 4.66 / Avg: 4.72 / Max: 4.78Min: 4.7 / Avg: 4.77 / Max: 4.82Min: 4.79 / Avg: 4.83 / Max: 4.861. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.0Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 1080pNoctua NH-U9 TR4-SP3Dynatron A26Dynatron A380.11250.2250.33750.450.5625SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.500.500.501. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.0Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 1080pNoctua NH-U9 TR4-SP3Dynatron A26Dynatron A38246810Min: 0.5 / Avg: 0.5 / Max: 0.5Min: 0.5 / Avg: 0.5 / Max: 0.51Min: 0.5 / Avg: 0.5 / Max: 0.511. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.0Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 4KNoctua NH-U9 TR4-SP3Dynatron A26Dynatron A380.0450.090.1350.180.225SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.20.20.21. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.0Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 4KNoctua NH-U9 TR4-SP3Dynatron A26Dynatron A3812345Min: 0.2 / Avg: 0.2 / Max: 0.2Min: 0.2 / Avg: 0.2 / Max: 0.2Min: 0.2 / Avg: 0.2 / Max: 0.21. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

SVT-VP9

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-VP9 CPU-based multi-threaded video encoder for the VP9 video format with a sample YUV input video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: Visual Quality Optimized - Input: Bosphorus 1080pNoctua NH-U9 TR4-SP3Dynatron A38Dynatron A2680160240320400SE +/- 5.87, N = 15SE +/- 6.16, N = 15SE +/- 6.37, N = 15345.24346.82347.781. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: Visual Quality Optimized - Input: Bosphorus 1080pNoctua NH-U9 TR4-SP3Dynatron A38Dynatron A2660120180240300Min: 264.88 / Avg: 345.24 / Max: 364.34Min: 261.19 / Avg: 346.82 / Max: 356.43Min: 259.73 / Avg: 347.78 / Max: 360.861. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080pDynatron A38Dynatron A26Noctua NH-U9 TR4-SP3100200300400500SE +/- 1.32, N = 10SE +/- 1.26, N = 10SE +/- 1.14, N = 10470.69471.09471.601. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080pDynatron A38Dynatron A26Noctua NH-U9 TR4-SP380160240320400Min: 461.98 / Avg: 470.69 / Max: 474.69Min: 466.63 / Avg: 471.09 / Max: 476.89Min: 467.1 / Avg: 471.6 / Max: 479.291. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: VMAF Optimized - Input: Bosphorus 1080pDynatron A38Dynatron A26Noctua NH-U9 TR4-SP3100200300400500SE +/- 0.90, N = 10SE +/- 1.01, N = 10SE +/- 1.02, N = 10467.96468.59468.761. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: VMAF Optimized - Input: Bosphorus 1080pDynatron A38Dynatron A26Noctua NH-U9 TR4-SP380160240320400Min: 464.22 / Avg: 467.96 / Max: 473.17Min: 463.7 / Avg: 468.59 / Max: 474.98Min: 463.63 / Avg: 468.76 / Max: 474.841. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

SVT-HEVC

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-HEVC CPU-based multi-threaded video encoder for the HEVC / H.265 video format with a sample 1080p YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 1 - Input: Bosphorus 1080pNoctua NH-U9 TR4-SP3Dynatron A26Dynatron A38918273645SE +/- 0.05, N = 4SE +/- 0.12, N = 4SE +/- 0.10, N = 437.7637.8937.921. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 1 - Input: Bosphorus 1080pNoctua NH-U9 TR4-SP3Dynatron A26Dynatron A38816243240Min: 37.63 / Avg: 37.76 / Max: 37.85Min: 37.56 / Avg: 37.89 / Max: 38.11Min: 37.77 / Avg: 37.92 / Max: 38.221. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 7 - Input: Bosphorus 1080pDynatron A38Dynatron A26Noctua NH-U9 TR4-SP370140210280350SE +/- 0.82, N = 10SE +/- 0.66, N = 10SE +/- 1.48, N = 10322.43323.60324.421. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 7 - Input: Bosphorus 1080pDynatron A38Dynatron A26Noctua NH-U9 TR4-SP360120180240300Min: 319.15 / Avg: 322.43 / Max: 325.73Min: 318.98 / Avg: 323.6 / Max: 325.91Min: 317.29 / Avg: 324.42 / Max: 333.331. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 10 - Input: Bosphorus 1080pDynatron A26Dynatron A38Noctua NH-U9 TR4-SP3130260390520650SE +/- 1.45, N = 12SE +/- 0.85, N = 12SE +/- 1.56, N = 12602.55605.97607.021. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 10 - Input: Bosphorus 1080pDynatron A26Dynatron A38Noctua NH-U9 TR4-SP3110220330440550Min: 597.01 / Avg: 602.55 / Max: 612.87Min: 601.2 / Avg: 605.97 / Max: 609.76Min: 598.21 / Avg: 607.02 / Max: 617.281. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

SVT-AV1

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-AV1 CPU-based multi-threaded video encoder for the AV1 video format with a sample 1080p YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 8 - Input: 1080pDynatron A26Noctua NH-U9 TR4-SP3Dynatron A3820406080100SE +/- 0.38, N = 6SE +/- 0.39, N = 6SE +/- 0.62, N = 692.3592.8693.051. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 8 - Input: 1080pDynatron A26Noctua NH-U9 TR4-SP3Dynatron A3820406080100Min: 91.51 / Avg: 92.35 / Max: 94.09Min: 91.35 / Avg: 92.86 / Max: 94.06Min: 91.22 / Avg: 93.05 / Max: 95.31. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 4 - Input: 1080pDynatron A38Dynatron A26Noctua NH-U9 TR4-SP33691215SE +/- 0.114, N = 6SE +/- 0.083, N = 4SE +/- 0.108, N = 49.3559.4529.4731. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 4 - Input: 1080pDynatron A38Dynatron A26Noctua NH-U9 TR4-SP33691215Min: 9.04 / Avg: 9.35 / Max: 9.81Min: 9.26 / Avg: 9.45 / Max: 9.63Min: 9.17 / Avg: 9.47 / Max: 9.671. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 0 - Input: 1080pNoctua NH-U9 TR4-SP3Dynatron A26Dynatron A380.02930.05860.08790.11720.1465SE +/- 0.001, N = 3SE +/- 0.000, N = 3SE +/- 0.001, N = 30.1300.1300.1301. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 0 - Input: 1080pNoctua NH-U9 TR4-SP3Dynatron A26Dynatron A3812345Min: 0.13 / Avg: 0.13 / Max: 0.13Min: 0.13 / Avg: 0.13 / Max: 0.13Min: 0.13 / Avg: 0.13 / Max: 0.131. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie

ViennaCL

ViennaCL is an open-source linear algebra library written in C++ and with support for OpenCL and OpenMP. This test profile makes use of ViennaCL's built-in benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - sCOPYNoctua NH-U9 TR4-SP3Dynatron A38Dynatron A262004006008001000SE +/- 30.05, N = 15SE +/- 27.57, N = 15SE +/- 28.51, N = 141035104410521. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - sCOPYNoctua NH-U9 TR4-SP3Dynatron A38Dynatron A262004006008001000Min: 810 / Avg: 1034.93 / Max: 1170Min: 815 / Avg: 1044.47 / Max: 1150Min: 778 / Avg: 1051.79 / Max: 11601. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - sAXPYNoctua NH-U9 TR4-SP3Dynatron A26Dynatron A38140280420560700SE +/- 2.32, N = 15SE +/- 2.67, N = 14SE +/- 1.86, N = 156276406401. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - sAXPYNoctua NH-U9 TR4-SP3Dynatron A26Dynatron A38110220330440550Min: 614 / Avg: 627.27 / Max: 640Min: 612 / Avg: 639.5 / Max: 655Min: 625 / Avg: 640.2 / Max: 6481. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dCOPYDynatron A38Noctua NH-U9 TR4-SP3Dynatron A2630060090012001500SE +/- 3.16, N = 15SE +/- 5.47, N = 15SE +/- 3.55, N = 141399140114091. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dCOPYDynatron A38Noctua NH-U9 TR4-SP3Dynatron A262004006008001000Min: 1370 / Avg: 1399.33 / Max: 1410Min: 1340 / Avg: 1400.67 / Max: 1430Min: 1370 / Avg: 1409.29 / Max: 14301. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dAXPYDynatron A38Dynatron A26Noctua NH-U9 TR4-SP330060090012001500SE +/- 1.31, N = 15SE +/- 2.28, N = 14SE +/- 2.23, N = 151204120512221. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dAXPYDynatron A38Dynatron A26Noctua NH-U9 TR4-SP32004006008001000Min: 1200 / Avg: 1204 / Max: 1210Min: 1190 / Avg: 1205 / Max: 1220Min: 1200 / Avg: 1222 / Max: 12301. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dDOTDynatron A38Noctua NH-U9 TR4-SP3Dynatron A262004006008001000SE +/- 2.00, N = 15SE +/- 2.15, N = 15SE +/- 1.73, N = 141112111511161. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dDOTDynatron A38Noctua NH-U9 TR4-SP3Dynatron A262004006008001000Min: 1100 / Avg: 1112 / Max: 1120Min: 1100 / Avg: 1115.33 / Max: 1130Min: 1110 / Avg: 1115.71 / Max: 11301. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMV-NDynatron A38Dynatron A26Noctua NH-U9 TR4-SP320406080100SE +/- 4.88, N = 15SE +/- 9.76, N = 14SE +/- 7.63, N = 1578.982.688.61. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMV-NDynatron A38Dynatron A26Noctua NH-U9 TR4-SP320406080100Min: 54.7 / Avg: 78.86 / Max: 113Min: 46.7 / Avg: 82.56 / Max: 148Min: 49.8 / Avg: 88.59 / Max: 1471. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMV-TDynatron A38Dynatron A26Noctua NH-U9 TR4-SP32004006008001000SE +/- 3.44, N = 15SE +/- 1.78, N = 14SE +/- 1.64, N = 157797817931. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMV-TDynatron A38Dynatron A26Noctua NH-U9 TR4-SP3140280420560700Min: 740 / Avg: 779.2 / Max: 789Min: 761 / Avg: 780.57 / Max: 788Min: 779 / Avg: 793.47 / Max: 8021. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMM-NNNoctua NH-U9 TR4-SP3Dynatron A38Dynatron A2620406080100SE +/- 0.52, N = 15SE +/- 0.34, N = 15SE +/- 0.08, N = 1488.188.288.61. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMM-NNNoctua NH-U9 TR4-SP3Dynatron A38Dynatron A2620406080100Min: 81 / Avg: 88.07 / Max: 89Min: 83.7 / Avg: 88.18 / Max: 89Min: 87.9 / Avg: 88.64 / Max: 88.91. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMM-NTNoctua NH-U9 TR4-SP3Dynatron A38Dynatron A2620406080100SE +/- 0.28, N = 15SE +/- 0.30, N = 15SE +/- 0.06, N = 1486.186.386.61. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMM-NTNoctua NH-U9 TR4-SP3Dynatron A38Dynatron A261632486480Min: 82.4 / Avg: 86.09 / Max: 86.8Min: 82.3 / Avg: 86.25 / Max: 86.8Min: 86 / Avg: 86.63 / Max: 86.81. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMM-TNDynatron A38Noctua NH-U9 TR4-SP3Dynatron A2620406080100SE +/- 0.13, N = 15SE +/- 0.04, N = 15SE +/- 0.03, N = 1491.992.192.11. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMM-TNDynatron A38Noctua NH-U9 TR4-SP3Dynatron A2620406080100Min: 90.6 / Avg: 91.89 / Max: 92.2Min: 91.7 / Avg: 92.07 / Max: 92.2Min: 91.8 / Avg: 92.11 / Max: 92.21. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMM-TTNoctua NH-U9 TR4-SP3Dynatron A26Dynatron A3820406080100SE +/- 0.13, N = 15SE +/- 0.02, N = 14SE +/- 0.05, N = 1589.789.989.91. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMM-TTNoctua NH-U9 TR4-SP3Dynatron A26Dynatron A3820406080100Min: 88.3 / Avg: 89.67 / Max: 90Min: 89.8 / Avg: 89.94 / Max: 90Min: 89.4 / Avg: 89.87 / Max: 901. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - sDOTDynatron A38Noctua NH-U9 TR4-SP3Dynatron A26140280420560700SE +/- 1.17, N = 13SE +/- 0.77, N = 14SE +/- 1.19, N = 146366376401. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - sDOTDynatron A38Noctua NH-U9 TR4-SP3Dynatron A26110220330440550Min: 628 / Avg: 635.85 / Max: 641Min: 631 / Avg: 636.93 / Max: 642Min: 634 / Avg: 640.21 / Max: 6481. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

GNU GMP GMPbench

GMPbench is a test of the GNU Multiple Precision Arithmetic (GMP) Library. GMPbench is a single-threaded integer benchmark that leverages the GMP library to stress the CPU with widening integer multiplication. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGMPbench Score, More Is BetterGNU GMP GMPbench 6.2.1Total TimeDynatron A38Noctua NH-U9 TR4-SP3Dynatron A26110022003300440055005089.15098.85099.21. (CC) gcc options: -O3 -fomit-frame-pointer -lm

OpenSCAD

OpenSCAD is a programmer-focused solid 3D CAD modeller. OpenSCAD is free software and allows creating 3D CAD objects in a script-based modelling environment. This test profile will use the system-provided OpenSCAD program otherwise and time how long it takes tn render different SCAD assets to PNG output. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenSCADRender: Projector Mount SwivelDynatron A38Noctua NH-U9 TR4-SP3Dynatron A2620406080100SE +/- 0.14, N = 3SE +/- 0.29, N = 3SE +/- 0.42, N = 3101.05100.90100.721. OpenSCAD version 2019.05
OpenBenchmarking.orgSeconds, Fewer Is BetterOpenSCADRender: Projector Mount SwivelDynatron A38Noctua NH-U9 TR4-SP3Dynatron A2620406080100Min: 100.77 / Avg: 101.05 / Max: 101.21Min: 100.57 / Avg: 100.9 / Max: 101.48Min: 100.02 / Avg: 100.72 / Max: 101.491. OpenSCAD version 2019.05

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenSCADRender: Leonardo Phone Case SlimDynatron A38Noctua NH-U9 TR4-SP3Dynatron A26510152025SE +/- 0.10, N = 3SE +/- 0.10, N = 3SE +/- 0.04, N = 318.7318.7018.531. OpenSCAD version 2019.05
OpenBenchmarking.orgSeconds, Fewer Is BetterOpenSCADRender: Leonardo Phone Case SlimDynatron A38Noctua NH-U9 TR4-SP3Dynatron A26510152025Min: 18.62 / Avg: 18.73 / Max: 18.94Min: 18.58 / Avg: 18.7 / Max: 18.9Min: 18.46 / Avg: 18.52 / Max: 18.61. OpenSCAD version 2019.05

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenSCADRender: PistolNoctua NH-U9 TR4-SP3Dynatron A38Dynatron A2620406080100SE +/- 0.20, N = 3SE +/- 0.31, N = 3SE +/- 0.10, N = 3109.83108.79108.621. OpenSCAD version 2019.05
OpenBenchmarking.orgSeconds, Fewer Is BetterOpenSCADRender: PistolNoctua NH-U9 TR4-SP3Dynatron A38Dynatron A2620406080100Min: 109.6 / Avg: 109.83 / Max: 110.24Min: 108.39 / Avg: 108.79 / Max: 109.4Min: 108.41 / Avg: 108.62 / Max: 108.731. OpenSCAD version 2019.05

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenSCADRender: Retro CarNoctua NH-U9 TR4-SP3Dynatron A38Dynatron A26510152025SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.05, N = 319.0618.9318.891. OpenSCAD version 2019.05
OpenBenchmarking.orgSeconds, Fewer Is BetterOpenSCADRender: Retro CarNoctua NH-U9 TR4-SP3Dynatron A38Dynatron A26510152025Min: 19.04 / Avg: 19.06 / Max: 19.1Min: 18.88 / Avg: 18.93 / Max: 18.99Min: 18.82 / Avg: 18.89 / Max: 18.991. OpenSCAD version 2019.05

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenSCADRender: Mini-ITX CaseNoctua NH-U9 TR4-SP3Dynatron A38Dynatron A261020304050SE +/- 0.06, N = 3SE +/- 0.17, N = 3SE +/- 0.17, N = 345.8445.4845.231. OpenSCAD version 2019.05
OpenBenchmarking.orgSeconds, Fewer Is BetterOpenSCADRender: Mini-ITX CaseNoctua NH-U9 TR4-SP3Dynatron A38Dynatron A26918273645Min: 45.75 / Avg: 45.84 / Max: 45.94Min: 45.3 / Avg: 45.48 / Max: 45.82Min: 44.98 / Avg: 45.23 / Max: 45.551. OpenSCAD version 2019.05

Stockfish

This is a test of Stockfish, an advanced open-source C++11 chess benchmark that can scale up to 512 CPU threads. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 13Total TimeNoctua NH-U9 TR4-SP3Dynatron A38Dynatron A2630M60M90M120M150MSE +/- 2161918.89, N = 4SE +/- 1246901.76, N = 3SE +/- 2061799.88, N = 151566566851585120041601076511. (CXX) g++ options: -lgcov -m64 -lpthread -fno-exceptions -std=c++17 -fprofile-use -fno-peel-loops -fno-tracer -pedantic -O3 -msse -msse3 -mpopcnt -mavx2 -msse4.1 -mssse3 -msse2 -flto -flto=jobserver
OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 13Total TimeNoctua NH-U9 TR4-SP3Dynatron A38Dynatron A2630M60M90M120M150MMin: 150550774 / Avg: 156656684.75 / Max: 160729757Min: 156877972 / Avg: 158512004 / Max: 160960506Min: 149079108 / Avg: 160107651.4 / Max: 1771379221. (CXX) g++ options: -lgcov -m64 -lpthread -fno-exceptions -std=c++17 -fprofile-use -fno-peel-loops -fno-tracer -pedantic -O3 -msse -msse3 -mpopcnt -mavx2 -msse4.1 -mssse3 -msse2 -flto -flto=jobserver

Xcompact3d Incompact3d

Xcompact3d 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 BetterXcompact3d Incompact3d 2021-03-11Input: input.i3d 129 Cells Per DirectionNoctua NH-U9 TR4-SP3Dynatron A26Dynatron A381.16022.32043.48064.64085.801SE +/- 0.01747253, N = 7SE +/- 0.02227690, N = 7SE +/- 0.02393955, N = 75.156530725.150651595.150517671. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi
OpenBenchmarking.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: input.i3d 129 Cells Per DirectionNoctua NH-U9 TR4-SP3Dynatron A26Dynatron A38246810Min: 5.09 / Avg: 5.16 / Max: 5.23Min: 5.08 / Avg: 5.15 / Max: 5.27Min: 5.02 / Avg: 5.15 / Max: 5.211. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi

OpenBenchmarking.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: input.i3d 193 Cells Per DirectionDynatron A38Noctua NH-U9 TR4-SP3Dynatron A26510152025SE +/- 0.08, N = 3SE +/- 0.04, N = 3SE +/- 0.30, N = 322.7122.5122.331. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi
OpenBenchmarking.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: input.i3d 193 Cells Per DirectionDynatron A38Noctua NH-U9 TR4-SP3Dynatron A26510152025Min: 22.6 / Avg: 22.71 / Max: 22.86Min: 22.45 / Avg: 22.51 / Max: 22.59Min: 21.73 / Avg: 22.33 / Max: 22.661. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi

OpenBenchmarking.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: X3D-benchmarking input.i3dDynatron A26Dynatron A38Noctua NH-U9 TR4-SP3140280420560700SE +/- 11.65, N = 9SE +/- 0.23, N = 3SE +/- 0.48, N = 3667.27627.67625.811. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi
OpenBenchmarking.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: X3D-benchmarking input.i3dDynatron A26Dynatron A38Noctua NH-U9 TR4-SP3120240360480600Min: 625 / Avg: 667.27 / Max: 710.12Min: 627.28 / Avg: 627.67 / Max: 628.07Min: 625.09 / Avg: 625.81 / Max: 626.721. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi

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 2.1.2Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPUNoctua NH-U9 TR4-SP3Dynatron A26Dynatron A380.1980.3960.5940.7920.99SE +/- 0.000667, N = 7SE +/- 0.000564, N = 7SE +/- 0.000819, N = 70.8800470.8797520.879480MIN: 0.84MIN: 0.84MIN: 0.841. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPUNoctua NH-U9 TR4-SP3Dynatron A26Dynatron A38246810Min: 0.88 / Avg: 0.88 / Max: 0.88Min: 0.88 / Avg: 0.88 / Max: 0.88Min: 0.88 / Avg: 0.88 / Max: 0.881. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPUDynatron A38Dynatron A26Noctua NH-U9 TR4-SP30.37630.75261.12891.50521.8815SE +/- 0.01439, N = 7SE +/- 0.00304, N = 7SE +/- 0.00301, N = 71.672561.656711.65220MIN: 1.57MIN: 1.57MIN: 1.571. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPUDynatron A38Dynatron A26Noctua NH-U9 TR4-SP3246810Min: 1.65 / Avg: 1.67 / Max: 1.76Min: 1.64 / Avg: 1.66 / Max: 1.67Min: 1.64 / Avg: 1.65 / Max: 1.661. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPUDynatron A38Dynatron A26Noctua NH-U9 TR4-SP3246810SE +/- 0.01979, N = 3SE +/- 0.02988, N = 3SE +/- 0.03799, N = 37.180027.178397.13608MIN: 6.18MIN: 6.17MIN: 6.041. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPUDynatron A38Dynatron A26Noctua NH-U9 TR4-SP33691215Min: 7.16 / Avg: 7.18 / Max: 7.22Min: 7.12 / Avg: 7.18 / Max: 7.22Min: 7.06 / Avg: 7.14 / Max: 7.191. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPUDynatron A26Noctua NH-U9 TR4-SP3Dynatron A380.13670.27340.41010.54680.6835SE +/- 0.001607, N = 3SE +/- 0.001828, N = 3SE +/- 0.000705, N = 30.6076550.6050580.603621MIN: 0.56MIN: 0.56MIN: 0.561. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPUDynatron A26Noctua NH-U9 TR4-SP3Dynatron A38246810Min: 0.61 / Avg: 0.61 / Max: 0.61Min: 0.6 / Avg: 0.61 / Max: 0.61Min: 0.6 / Avg: 0.6 / Max: 0.61. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPUDynatron A38Noctua NH-U9 TR4-SP3Dynatron A260.68481.36962.05442.73923.424SE +/- 0.00693, N = 9SE +/- 0.00904, N = 9SE +/- 0.00911, N = 93.043523.038203.02459MIN: 2.34MIN: 2.21MIN: 2.241. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPUDynatron A38Noctua NH-U9 TR4-SP3Dynatron A26246810Min: 3 / Avg: 3.04 / Max: 3.07Min: 2.99 / Avg: 3.04 / Max: 3.07Min: 2.99 / Avg: 3.02 / Max: 3.071. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPUDynatron A26Noctua NH-U9 TR4-SP3Dynatron A380.17630.35260.52890.70520.8815SE +/- 0.002597, N = 9SE +/- 0.002596, N = 9SE +/- 0.002274, N = 90.7834640.7818510.781060MIN: 0.72MIN: 0.72MIN: 0.721. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPUDynatron A26Noctua NH-U9 TR4-SP3Dynatron A38246810Min: 0.77 / Avg: 0.78 / Max: 0.8Min: 0.77 / Avg: 0.78 / Max: 0.8Min: 0.77 / Avg: 0.78 / Max: 0.81. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 1D - Data Type: f32 - Engine: CPUDynatron A38Dynatron A26Noctua NH-U9 TR4-SP30.26570.53140.79711.06281.3285SE +/- 0.00303, N = 4SE +/- 0.00176, N = 4SE +/- 0.00196, N = 41.180871.178631.17796MIN: 1.1MIN: 1.12MIN: 1.11. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 1D - Data Type: f32 - Engine: CPUDynatron A38Dynatron A26Noctua NH-U9 TR4-SP3246810Min: 1.17 / Avg: 1.18 / Max: 1.19Min: 1.18 / Avg: 1.18 / Max: 1.18Min: 1.17 / Avg: 1.18 / Max: 1.181. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPUDynatron A26Dynatron A38Noctua NH-U9 TR4-SP30.2670.5340.8011.0681.335SE +/- 0.00760, N = 4SE +/- 0.01187, N = 4SE +/- 0.00777, N = 41.186851.179061.17758MIN: 0.98MIN: 0.99MIN: 11. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPUDynatron A26Dynatron A38Noctua NH-U9 TR4-SP3246810Min: 1.17 / Avg: 1.19 / Max: 1.2Min: 1.15 / Avg: 1.18 / Max: 1.2Min: 1.16 / Avg: 1.18 / Max: 1.21. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 3D - Data Type: f32 - Engine: CPUNoctua NH-U9 TR4-SP3Dynatron A26Dynatron A380.82421.64842.47263.29684.121SE +/- 0.04102, N = 5SE +/- 0.02260, N = 5SE +/- 0.03350, N = 53.663073.649413.61762MIN: 3.37MIN: 3.4MIN: 3.361. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 3D - Data Type: f32 - Engine: CPUNoctua NH-U9 TR4-SP3Dynatron A26Dynatron A38246810Min: 3.56 / Avg: 3.66 / Max: 3.78Min: 3.61 / Avg: 3.65 / Max: 3.71Min: 3.53 / Avg: 3.62 / Max: 3.691. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPUNoctua NH-U9 TR4-SP3Dynatron A26Dynatron A380.14920.29840.44760.59680.746SE +/- 0.006455, N = 5SE +/- 0.004042, N = 5SE +/- 0.005445, N = 50.6630590.6506240.640331MIN: 0.61MIN: 0.59MIN: 0.581. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPUNoctua NH-U9 TR4-SP3Dynatron A26Dynatron A38246810Min: 0.64 / Avg: 0.66 / Max: 0.68Min: 0.64 / Avg: 0.65 / Max: 0.66Min: 0.62 / Avg: 0.64 / Max: 0.651. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPUDynatron A38Noctua NH-U9 TR4-SP3Dynatron A260.08670.17340.26010.34680.4335SE +/- 0.004169, N = 4SE +/- 0.005034, N = 4SE +/- 0.001495, N = 40.3852070.3849290.381495MIN: 0.36MIN: 0.36MIN: 0.361. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPUDynatron A38Noctua NH-U9 TR4-SP3Dynatron A2612345Min: 0.38 / Avg: 0.39 / Max: 0.4Min: 0.38 / Avg: 0.38 / Max: 0.4Min: 0.38 / Avg: 0.38 / Max: 0.391. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPUDynatron A26Dynatron A38Noctua NH-U9 TR4-SP30.16350.3270.49050.6540.8175SE +/- 0.001153, N = 4SE +/- 0.001725, N = 4SE +/- 0.002487, N = 40.7267890.7215860.720928MIN: 0.67MIN: 0.67MIN: 0.671. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPUDynatron A26Dynatron A38Noctua NH-U9 TR4-SP3246810Min: 0.72 / Avg: 0.73 / Max: 0.73Min: 0.72 / Avg: 0.72 / Max: 0.73Min: 0.72 / Avg: 0.72 / Max: 0.731. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPUDynatron A38Dynatron A26Noctua NH-U9 TR4-SP330060090012001500SE +/- 14.96, N = 3SE +/- 9.11, N = 3SE +/- 3.07, N = 31400.191378.861373.91MIN: 1335.97MIN: 1326.59MIN: 1332.451. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPUDynatron A38Dynatron A26Noctua NH-U9 TR4-SP32004006008001000Min: 1374.18 / Avg: 1400.19 / Max: 1426Min: 1364.44 / Avg: 1378.86 / Max: 1395.73Min: 1369.57 / Avg: 1373.91 / Max: 1379.841. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPUNoctua NH-U9 TR4-SP3Dynatron A38Dynatron A2630060090012001500SE +/- 3.58, N = 3SE +/- 4.57, N = 3SE +/- 3.15, N = 31385.321377.491369.98MIN: 1350.61MIN: 1335.99MIN: 1325.961. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPUNoctua NH-U9 TR4-SP3Dynatron A38Dynatron A262004006008001000Min: 1378.49 / Avg: 1385.32 / Max: 1390.6Min: 1368.39 / Avg: 1377.49 / Max: 1382.85Min: 1364.19 / Avg: 1369.98 / Max: 1375.011. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPUDynatron A26Dynatron A38Noctua NH-U9 TR4-SP330060090012001500SE +/- 4.55, N = 3SE +/- 8.30, N = 3SE +/- 8.02, N = 31391.141381.771370.82MIN: 1343.15MIN: 1330.53MIN: 1322.761. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPUDynatron A26Dynatron A38Noctua NH-U9 TR4-SP32004006008001000Min: 1382.21 / Avg: 1391.14 / Max: 1397.17Min: 1365.17 / Avg: 1381.77 / Max: 1390.53Min: 1360.41 / Avg: 1370.82 / Max: 1386.61. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPUDynatron A26Dynatron A38Noctua NH-U9 TR4-SP3140280420560700SE +/- 1.29, N = 3SE +/- 1.18, N = 3SE +/- 0.56, N = 3666.05665.53665.23MIN: 638.64MIN: 639.97MIN: 638.881. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPUDynatron A26Dynatron A38Noctua NH-U9 TR4-SP3120240360480600Min: 663.47 / Avg: 666.05 / Max: 667.37Min: 663.23 / Avg: 665.53 / Max: 667.12Min: 664.51 / Avg: 665.23 / Max: 666.321. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPUDynatron A38Noctua NH-U9 TR4-SP3Dynatron A26140280420560700SE +/- 0.96, N = 3SE +/- 1.05, N = 3SE +/- 1.25, N = 3665.27664.99664.81MIN: 637.88MIN: 636.72MIN: 637.031. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPUDynatron A38Noctua NH-U9 TR4-SP3Dynatron A26120240360480600Min: 664.02 / Avg: 665.27 / Max: 667.16Min: 663.21 / Avg: 664.99 / Max: 666.83Min: 662.32 / Avg: 664.81 / Max: 666.311. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPUDynatron A26Dynatron A38Noctua NH-U9 TR4-SP3140280420560700SE +/- 1.24, N = 3SE +/- 1.16, N = 3SE +/- 1.52, N = 3666.48666.13664.68MIN: 640.16MIN: 639.05MIN: 637.441. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPUDynatron A26Dynatron A38Noctua NH-U9 TR4-SP3120240360480600Min: 664.1 / Avg: 666.48 / Max: 668.23Min: 664.74 / Avg: 666.13 / Max: 668.43Min: 662.48 / Avg: 664.68 / Max: 667.591. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

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 1.1.3Model: SqueezeNetV1.0Dynatron A38Dynatron A26Noctua NH-U9 TR4-SP31.32262.64523.96785.29046.613SE +/- 0.015, N = 3SE +/- 0.027, N = 3SE +/- 0.039, N = 35.8785.7975.785MIN: 5.64 / MAX: 6.84MIN: 5.54 / MAX: 7.52MIN: 5.58 / MAX: 6.641. (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 1.1.3Model: SqueezeNetV1.0Dynatron A38Dynatron A26Noctua NH-U9 TR4-SP3246810Min: 5.85 / Avg: 5.88 / Max: 5.9Min: 5.76 / Avg: 5.8 / Max: 5.85Min: 5.72 / Avg: 5.78 / Max: 5.861. (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 1.1.3Model: resnet-v2-50Dynatron A26Dynatron A38Noctua NH-U9 TR4-SP3510152025SE +/- 0.09, N = 3SE +/- 0.10, N = 3SE +/- 0.07, N = 322.4022.2722.13MIN: 21.64 / MAX: 41.29MIN: 21.57 / MAX: 30.86MIN: 21.58 / MAX: 32.331. (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 1.1.3Model: resnet-v2-50Dynatron A26Dynatron A38Noctua NH-U9 TR4-SP3510152025Min: 22.3 / Avg: 22.4 / Max: 22.57Min: 22.07 / Avg: 22.27 / Max: 22.38Min: 22.02 / Avg: 22.13 / Max: 22.261. (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 1.1.3Model: MobileNetV2_224Dynatron A26Dynatron A38Noctua NH-U9 TR4-SP30.85251.7052.55753.414.2625SE +/- 0.021, N = 3SE +/- 0.016, N = 3SE +/- 0.017, N = 33.7893.7803.757MIN: 3.66 / MAX: 4.64MIN: 3.66 / MAX: 6.67MIN: 3.63 / MAX: 6.091. (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 1.1.3Model: MobileNetV2_224Dynatron A26Dynatron A38Noctua NH-U9 TR4-SP3246810Min: 3.76 / Avg: 3.79 / Max: 3.83Min: 3.75 / Avg: 3.78 / Max: 3.8Min: 3.72 / Avg: 3.76 / Max: 3.781. (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 1.1.3Model: mobilenet-v1-1.0Dynatron A26Dynatron A38Noctua NH-U9 TR4-SP30.5271.0541.5812.1082.635SE +/- 0.012, N = 3SE +/- 0.014, N = 3SE +/- 0.010, N = 32.3422.3322.328MIN: 2.29 / MAX: 2.64MIN: 2.28 / MAX: 2.65MIN: 2.28 / MAX: 2.551. (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 1.1.3Model: mobilenet-v1-1.0Dynatron A26Dynatron A38Noctua NH-U9 TR4-SP3246810Min: 2.32 / Avg: 2.34 / Max: 2.36Min: 2.31 / Avg: 2.33 / Max: 2.36Min: 2.31 / Avg: 2.33 / Max: 2.341. (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 1.1.3Model: inception-v3Dynatron A26Dynatron A38Noctua NH-U9 TR4-SP3714212835SE +/- 0.13, N = 3SE +/- 0.10, N = 3SE +/- 0.03, N = 328.4528.3328.17MIN: 27.16 / MAX: 42.86MIN: 27.14 / MAX: 44.36MIN: 27.06 / MAX: 43.231. (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 1.1.3Model: inception-v3Dynatron A26Dynatron A38Noctua NH-U9 TR4-SP3612182430Min: 28.25 / Avg: 28.45 / Max: 28.69Min: 28.18 / Avg: 28.33 / Max: 28.51Min: 28.11 / Avg: 28.17 / Max: 28.211. (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

ASTC Encoder

ASTC Encoder (astcenc) is for the Adaptive Scalable Texture Compression (ASTC) format commonly used with OpenGL, OpenGL ES, and Vulkan graphics APIs. This test profile does a coding test of both compression/decompression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.4Preset: MediumDynatron A38Dynatron A26Noctua NH-U9 TR4-SP31.1122.2243.3364.4485.56SE +/- 0.0054, N = 7SE +/- 0.0032, N = 7SE +/- 0.0039, N = 74.94244.94124.91761. (CXX) g++ options: -O3 -flto -pthread
OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.4Preset: MediumDynatron A38Dynatron A26Noctua NH-U9 TR4-SP3246810Min: 4.92 / Avg: 4.94 / Max: 4.96Min: 4.93 / Avg: 4.94 / Max: 4.96Min: 4.9 / Avg: 4.92 / Max: 4.931. (CXX) g++ options: -O3 -flto -pthread

OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.4Preset: ThoroughDynatron A26Noctua NH-U9 TR4-SP3Dynatron A38246810SE +/- 0.0081, N = 6SE +/- 0.0055, N = 6SE +/- 0.0064, N = 68.00627.99257.98981. (CXX) g++ options: -O3 -flto -pthread
OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.4Preset: ThoroughDynatron A26Noctua NH-U9 TR4-SP3Dynatron A383691215Min: 7.98 / Avg: 8.01 / Max: 8.04Min: 7.97 / Avg: 7.99 / Max: 8.01Min: 7.98 / Avg: 7.99 / Max: 8.011. (CXX) g++ options: -O3 -flto -pthread

OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.4Preset: ExhaustiveDynatron A26Dynatron A38Noctua NH-U9 TR4-SP3510152025SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 320.6220.5620.441. (CXX) g++ options: -O3 -flto -pthread
OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.4Preset: ExhaustiveDynatron A26Dynatron A38Noctua NH-U9 TR4-SP3510152025Min: 20.59 / Avg: 20.62 / Max: 20.65Min: 20.52 / Avg: 20.56 / Max: 20.58Min: 20.38 / Avg: 20.44 / Max: 20.541. (CXX) g++ options: -O3 -flto -pthread

simdjson

This is a benchmark of SIMDJSON, a high performance JSON parser. SIMDJSON aims to be the fastest JSON parser and is used by projects like Microsoft FishStore, Yandex ClickHouse, Shopify, and others. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 0.8.2Throughput Test: PartialTweetsDynatron A26Dynatron A38Noctua NH-U9 TR4-SP30.8191.6382.4573.2764.095SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 33.633.633.641. (CXX) g++ options: -O3 -pthread
OpenBenchmarking.orgGB/s, More Is Bettersimdjson 0.8.2Throughput Test: PartialTweetsDynatron A26Dynatron A38Noctua NH-U9 TR4-SP3246810Min: 3.63 / Avg: 3.63 / Max: 3.64Min: 3.63 / Avg: 3.63 / Max: 3.64Min: 3.62 / Avg: 3.64 / Max: 3.651. (CXX) g++ options: -O3 -pthread

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 0.8.2Throughput Test: LargeRandomNoctua NH-U9 TR4-SP3Dynatron A26Dynatron A380.2160.4320.6480.8641.08SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.960.960.961. (CXX) g++ options: -O3 -pthread
OpenBenchmarking.orgGB/s, More Is Bettersimdjson 0.8.2Throughput Test: LargeRandomNoctua NH-U9 TR4-SP3Dynatron A26Dynatron A38246810Min: 0.96 / Avg: 0.96 / Max: 0.96Min: 0.96 / Avg: 0.96 / Max: 0.96Min: 0.96 / Avg: 0.96 / Max: 0.961. (CXX) g++ options: -O3 -pthread

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 0.8.2Throughput Test: KostyaNoctua NH-U9 TR4-SP3Dynatron A26Dynatron A380.63681.27361.91042.54723.184SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 32.832.832.831. (CXX) g++ options: -O3 -pthread
OpenBenchmarking.orgGB/s, More Is Bettersimdjson 0.8.2Throughput Test: KostyaNoctua NH-U9 TR4-SP3Dynatron A26Dynatron A38246810Min: 2.83 / Avg: 2.83 / Max: 2.83Min: 2.83 / Avg: 2.83 / Max: 2.83Min: 2.82 / Avg: 2.83 / Max: 2.841. (CXX) g++ options: -O3 -pthread

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 0.8.2Throughput Test: DistinctUserIDDynatron A38Dynatron A26Noctua NH-U9 TR4-SP30.90231.80462.70693.60924.5115SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 33.984.004.011. (CXX) g++ options: -O3 -pthread
OpenBenchmarking.orgGB/s, More Is Bettersimdjson 0.8.2Throughput Test: DistinctUserIDDynatron A38Dynatron A26Noctua NH-U9 TR4-SP3246810Min: 3.97 / Avg: 3.98 / Max: 3.99Min: 3.98 / Avg: 4 / Max: 4.01Min: 3.99 / Avg: 4.01 / Max: 4.021. (CXX) g++ options: -O3 -pthread

srsLTE

srsLTE is an open-source LTE software radio suite created by Software Radio Systems (SRS). srsLTE can be used for building your own software defined (SDR) LTE mobile network. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSamples / Second, More Is BettersrsLTE 20.10.1Test: OFDM_TestNoctua NH-U9 TR4-SP3Dynatron A26Dynatron A3830M60M90M120M150MSE +/- 1770436.23, N = 3SE +/- 1902921.73, N = 3SE +/- 1178039.80, N = 31156333331162333331178666671. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lmbedcrypto -lconfig++ -lsctp -lbladeRF -lm -lfftw3f
OpenBenchmarking.orgSamples / Second, More Is BettersrsLTE 20.10.1Test: OFDM_TestNoctua NH-U9 TR4-SP3Dynatron A26Dynatron A3820M40M60M80M100MMin: 112400000 / Avg: 115633333.33 / Max: 118500000Min: 113300000 / Avg: 116233333.33 / Max: 119800000Min: 116100000 / Avg: 117866666.67 / Max: 1201000001. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lmbedcrypto -lconfig++ -lsctp -lbladeRF -lm -lfftw3f

OpenBenchmarking.orgeNb Mb/s, More Is BettersrsLTE 20.10.1Test: PHY_DL_TestDynatron A38Dynatron A26Noctua NH-U9 TR4-SP360120180240300SE +/- 0.84, N = 3SE +/- 0.18, N = 3SE +/- 0.22, N = 3255.9257.1257.41. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lmbedcrypto -lconfig++ -lsctp -lbladeRF -lm -lfftw3f
OpenBenchmarking.orgeNb Mb/s, More Is BettersrsLTE 20.10.1Test: PHY_DL_TestDynatron A38Dynatron A26Noctua NH-U9 TR4-SP350100150200250Min: 254.4 / Avg: 255.93 / Max: 257.3Min: 256.8 / Avg: 257.13 / Max: 257.4Min: 257.1 / Avg: 257.37 / Max: 257.81. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lmbedcrypto -lconfig++ -lsctp -lbladeRF -lm -lfftw3f

OpenBenchmarking.orgUE Mb/s, More Is BettersrsLTE 20.10.1Test: PHY_DL_TestDynatron A38Noctua NH-U9 TR4-SP3Dynatron A2620406080100SE +/- 0.52, N = 3SE +/- 0.46, N = 3SE +/- 0.23, N = 393.794.394.31. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lmbedcrypto -lconfig++ -lsctp -lbladeRF -lm -lfftw3f
OpenBenchmarking.orgUE Mb/s, More Is BettersrsLTE 20.10.1Test: PHY_DL_TestDynatron A38Noctua NH-U9 TR4-SP3Dynatron A2620406080100Min: 92.7 / Avg: 93.67 / Max: 94.5Min: 93.4 / Avg: 94.3 / Max: 94.9Min: 93.9 / Avg: 94.27 / Max: 94.71. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lmbedcrypto -lconfig++ -lsctp -lbladeRF -lm -lfftw3f

GNU Radio

GNU Radio is a free software development toolkit providing signal processing blocks to implement software-defined radios (SDR) and signal processing systems. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: Five Back to Back FIR FiltersDynatron A38Noctua NH-U9 TR4-SP3Dynatron A26120240360480600SE +/- 5.99, N = 9SE +/- 8.06, N = 4SE +/- 5.98, N = 3560.1560.9567.71. 3.8.1.0
OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: Five Back to Back FIR FiltersDynatron A38Noctua NH-U9 TR4-SP3Dynatron A26100200300400500Min: 545 / Avg: 560.13 / Max: 601.6Min: 547.6 / Avg: 560.85 / Max: 580.9Min: 561.1 / Avg: 567.67 / Max: 579.61. 3.8.1.0

OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: Signal Source (Cosine)Dynatron A38Noctua NH-U9 TR4-SP3Dynatron A267001400210028003500SE +/- 17.69, N = 9SE +/- 6.28, N = 4SE +/- 26.65, N = 33303.63322.23324.71. 3.8.1.0
OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: Signal Source (Cosine)Dynatron A38Noctua NH-U9 TR4-SP3Dynatron A266001200180024003000Min: 3235.2 / Avg: 3303.58 / Max: 3399.1Min: 3306.8 / Avg: 3322.2 / Max: 3332.8Min: 3279.2 / Avg: 3324.67 / Max: 3371.51. 3.8.1.0

OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: FIR FilterNoctua NH-U9 TR4-SP3Dynatron A26Dynatron A38140280420560700SE +/- 0.72, N = 4SE +/- 1.06, N = 3SE +/- 0.99, N = 9639.0641.6642.01. 3.8.1.0
OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: FIR FilterNoctua NH-U9 TR4-SP3Dynatron A26Dynatron A38110220330440550Min: 637.6 / Avg: 638.95 / Max: 641Min: 640.3 / Avg: 641.6 / Max: 643.7Min: 637 / Avg: 642.01 / Max: 6461. 3.8.1.0

OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: IIR FilterDynatron A26Dynatron A38Noctua NH-U9 TR4-SP3130260390520650SE +/- 1.25, N = 3SE +/- 1.20, N = 9SE +/- 1.08, N = 4604.7607.0608.61. 3.8.1.0
OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: IIR FilterDynatron A26Dynatron A38Noctua NH-U9 TR4-SP3110220330440550Min: 602.2 / Avg: 604.67 / Max: 606.3Min: 600.9 / Avg: 606.97 / Max: 611.3Min: 606.2 / Avg: 608.63 / Max: 611.11. 3.8.1.0

OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: FM Deemphasis FilterDynatron A26Dynatron A38Noctua NH-U9 TR4-SP3160320480640800SE +/- 1.05, N = 3SE +/- 1.58, N = 9SE +/- 1.86, N = 4760.3764.1765.31. 3.8.1.0
OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: FM Deemphasis FilterDynatron A26Dynatron A38Noctua NH-U9 TR4-SP3130260390520650Min: 758.2 / Avg: 760.3 / Max: 761.4Min: 758.5 / Avg: 764.08 / Max: 772.4Min: 760.6 / Avg: 765.33 / Max: 769.21. 3.8.1.0

OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: Hilbert TransformDynatron A38Dynatron A26Noctua NH-U9 TR4-SP380160240320400SE +/- 0.76, N = 9SE +/- 1.82, N = 3SE +/- 1.21, N = 4376.2377.3378.21. 3.8.1.0
OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: Hilbert TransformDynatron A38Dynatron A26Noctua NH-U9 TR4-SP370140210280350Min: 372.9 / Avg: 376.23 / Max: 379.4Min: 373.8 / Avg: 377.3 / Max: 379.9Min: 376.3 / Avg: 378.15 / Max: 381.71. 3.8.1.0

LuaRadio

LuaRadio is a lightweight software-defined radio (SDR) framework built atop LuaJIT. LuaRadio provides a suite of source, sink, and processing blocks, with a simple API for defining flow graphs, running flow graphs, creating blocks, and creating data types. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterLuaRadio 0.9.1Test: Five Back to Back FIR FiltersDynatron A38Noctua NH-U9 TR4-SP3Dynatron A262004006008001000SE +/- 2.63, N = 3SE +/- 3.75, N = 3SE +/- 1.05, N = 31097.41101.61110.6
OpenBenchmarking.orgMiB/s, More Is BetterLuaRadio 0.9.1Test: Five Back to Back FIR FiltersDynatron A38Noctua NH-U9 TR4-SP3Dynatron A262004006008001000Min: 1092.8 / Avg: 1097.4 / Max: 1101.9Min: 1096.4 / Avg: 1101.63 / Max: 1108.9Min: 1109.1 / Avg: 1110.57 / Max: 1112.6

OpenBenchmarking.orgMiB/s, More Is BetterLuaRadio 0.9.1Test: FM Deemphasis FilterDynatron A38Dynatron A26Noctua NH-U9 TR4-SP370140210280350SE +/- 0.41, N = 3SE +/- 0.22, N = 3SE +/- 0.20, N = 3343.4344.2344.7
OpenBenchmarking.orgMiB/s, More Is BetterLuaRadio 0.9.1Test: FM Deemphasis FilterDynatron A38Dynatron A26Noctua NH-U9 TR4-SP360120180240300Min: 342.6 / Avg: 343.37 / Max: 344Min: 343.8 / Avg: 344.23 / Max: 344.5Min: 344.3 / Avg: 344.67 / Max: 345

OpenBenchmarking.orgMiB/s, More Is BetterLuaRadio 0.9.1Test: Hilbert TransformNoctua NH-U9 TR4-SP3Dynatron A38Dynatron A2620406080100SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 393.593.593.6
OpenBenchmarking.orgMiB/s, More Is BetterLuaRadio 0.9.1Test: Hilbert TransformNoctua NH-U9 TR4-SP3Dynatron A38Dynatron A2620406080100Min: 93.4 / Avg: 93.5 / Max: 93.6Min: 93.4 / Avg: 93.47 / Max: 93.5Min: 93.5 / Avg: 93.57 / Max: 93.6

OpenBenchmarking.orgMiB/s, More Is BetterLuaRadio 0.9.1Test: Complex PhaseDynatron A38Dynatron A26Noctua NH-U9 TR4-SP3130260390520650SE +/- 0.49, N = 3SE +/- 0.72, N = 3SE +/- 0.62, N = 3591.0591.6591.8
OpenBenchmarking.orgMiB/s, More Is BetterLuaRadio 0.9.1Test: Complex PhaseDynatron A38Dynatron A26Noctua NH-U9 TR4-SP3100200300400500Min: 590 / Avg: 590.97 / Max: 591.6Min: 590.2 / Avg: 591.63 / Max: 592.4Min: 590.9 / Avg: 591.8 / Max: 593

Liquid-DSP

LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 16 - Buffer Length: 256 - Filter Length: 57Dynatron A26Noctua NH-U9 TR4-SP3Dynatron A38200M400M600M800M1000MSE +/- 5535858.86, N = 3SE +/- 6476302.96, N = 3SE +/- 2740148.01, N = 38001900008033100008041466671. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 16 - Buffer Length: 256 - Filter Length: 57Dynatron A26Noctua NH-U9 TR4-SP3Dynatron A38140M280M420M560M700MMin: 791330000 / Avg: 800190000 / Max: 810370000Min: 790760000 / Avg: 803310000 / Max: 812360000Min: 800810000 / Avg: 804146666.67 / Max: 8095800001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 32 - Buffer Length: 256 - Filter Length: 57Noctua NH-U9 TR4-SP3Dynatron A38Dynatron A26300M600M900M1200M1500MSE +/- 3887729.99, N = 3SE +/- 2380709.51, N = 3SE +/- 3637917.60, N = 31613766667161456666716149333331. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 32 - Buffer Length: 256 - Filter Length: 57Noctua NH-U9 TR4-SP3Dynatron A38Dynatron A26300M600M900M1200M1500MMin: 1606200000 / Avg: 1613766666.67 / Max: 1619100000Min: 1611300000 / Avg: 1614566666.67 / Max: 1619200000Min: 1608700000 / Avg: 1614933333.33 / Max: 16213000001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 64 - Buffer Length: 256 - Filter Length: 57Dynatron A26Noctua NH-U9 TR4-SP3Dynatron A38600M1200M1800M2400M3000MSE +/- 3268196.92, N = 3SE +/- 5372460.64, N = 3SE +/- 3347304.06, N = 32782866667279240000027937333331. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 64 - Buffer Length: 256 - Filter Length: 57Dynatron A26Noctua NH-U9 TR4-SP3Dynatron A38500M1000M1500M2000M2500MMin: 2778300000 / Avg: 2782866666.67 / Max: 2789200000Min: 2781700000 / Avg: 2792400000 / Max: 2798600000Min: 2789000000 / Avg: 2793733333.33 / Max: 28002000001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 128 - Buffer Length: 256 - Filter Length: 57Noctua NH-U9 TR4-SP3Dynatron A26Dynatron A38600M1200M1800M2400M3000MSE +/- 2577035.33, N = 3SE +/- 448454.13, N = 3SE +/- 266666.67, N = 33017933333302806666730281333331. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 128 - Buffer Length: 256 - Filter Length: 57Noctua NH-U9 TR4-SP3Dynatron A26Dynatron A38500M1000M1500M2000M2500MMin: 3013100000 / Avg: 3017933333.33 / Max: 3021900000Min: 3027200000 / Avg: 3028066666.67 / Max: 3028700000Min: 3027600000 / Avg: 3028133333.33 / Max: 30284000001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

GROMACS

The GROMACS (GROningen MAchine for Chemical Simulations) molecular dynamics package testing on the CPU with the water_GMX50 data. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2021Input: water_GMX50_bareNoctua NH-U9 TR4-SP3Dynatron A26Dynatron A381.25982.51963.77945.03926.299SE +/- 0.003, N = 3SE +/- 0.018, N = 3SE +/- 0.010, N = 35.5775.5825.5991. (CXX) g++ options: -O3 -pthread
OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2021Input: water_GMX50_bareNoctua NH-U9 TR4-SP3Dynatron A26Dynatron A38246810Min: 5.57 / Avg: 5.58 / Max: 5.58Min: 5.55 / Avg: 5.58 / Max: 5.61Min: 5.58 / Avg: 5.6 / Max: 5.611. (CXX) g++ options: -O3 -pthread

NAMD

NAMD is a parallel molecular dynamics code designed for high-performance simulation of large biomolecular systems. NAMD was developed by the Theoretical and Computational Biophysics Group in the Beckman Institute for Advanced Science and Technology at the University of Illinois at Urbana-Champaign. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD 2.14ATPase Simulation - 327,506 AtomsDynatron A38Dynatron A26Noctua NH-U9 TR4-SP30.0860.1720.2580.3440.43SE +/- 0.00076, N = 3SE +/- 0.00041, N = 3SE +/- 0.00051, N = 30.382150.381640.38110
OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD 2.14ATPase Simulation - 327,506 AtomsDynatron A38Dynatron A26Noctua NH-U9 TR4-SP312345Min: 0.38 / Avg: 0.38 / Max: 0.38Min: 0.38 / Avg: 0.38 / Max: 0.38Min: 0.38 / Avg: 0.38 / Max: 0.38

CPU Temperature Monitor

OpenBenchmarking.orgCelsiusCPU Temperature MonitorPhoronix Test Suite System MonitoringDynatron A26Noctua NH-U9 TR4-SP3Dynatron A381530456075Min: 41 / Avg: 59.01 / Max: 79.25Min: 41.5 / Avg: 56.86 / Max: 79.5Min: 40.25 / Avg: 51.96 / Max: 70.25

107 Results Shown

IndigoBench:
  CPU - Supercar
  CPU - Bedroom
Chaos Group V-RAY
Blender:
  BMW27 - CPU-Only
  Classroom - CPU-Only
  Fishy Cat - CPU-Only
  Pabellon Barcelona - CPU-Only
  Barbershop - CPU-Only
Timed Linux Kernel Compilation
Timed GDB GNU Debugger Compilation
Timed Apache Compilation
Timed Mesa Compilation
Timed Node.js Compilation
Timed Erlang/OTP Compilation
AOM AV1:
  Speed 9 Realtime - Bosphorus 1080p
  Speed 9 Realtime - Bosphorus 4K
  Speed 8 Realtime - Bosphorus 1080p
  Speed 8 Realtime - Bosphorus 4K
  Speed 6 Realtime - Bosphorus 1080p
  Speed 6 Realtime - Bosphorus 4K
  Speed 6 Two-Pass - Bosphorus 1080p
  Speed 6 Two-Pass - Bosphorus 4K
  Speed 4 Two-Pass - Bosphorus 1080p
  Speed 4 Two-Pass - Bosphorus 4K
  Speed 0 Two-Pass - Bosphorus 1080p
  Speed 0 Two-Pass - Bosphorus 4K
SVT-VP9:
  Visual Quality Optimized - Bosphorus 1080p
  PSNR/SSIM Optimized - Bosphorus 1080p
  VMAF Optimized - Bosphorus 1080p
SVT-HEVC:
  1 - Bosphorus 1080p
  7 - Bosphorus 1080p
  10 - Bosphorus 1080p
SVT-AV1:
  Enc Mode 8 - 1080p
  Enc Mode 4 - 1080p
  Enc Mode 0 - 1080p
ViennaCL:
  CPU BLAS - sCOPY
  CPU BLAS - sAXPY
  CPU BLAS - dCOPY
  CPU BLAS - dAXPY
  CPU BLAS - dDOT
  CPU BLAS - dGEMV-N
  CPU BLAS - dGEMV-T
  CPU BLAS - dGEMM-NN
  CPU BLAS - dGEMM-NT
  CPU BLAS - dGEMM-TN
  CPU BLAS - dGEMM-TT
  CPU BLAS - sDOT
GNU GMP GMPbench
OpenSCAD:
  Projector Mount Swivel
  Leonardo Phone Case Slim
  Pistol
  Retro Car
  Mini-ITX Case
Stockfish
Xcompact3d Incompact3d:
  input.i3d 129 Cells Per Direction
  input.i3d 193 Cells Per Direction
  X3D-benchmarking input.i3d
oneDNN:
  Convolution Batch Shapes Auto - f32 - CPU
  Convolution Batch Shapes Auto - u8s8f32 - CPU
  Deconvolution Batch shapes_1d - f32 - CPU
  Deconvolution Batch shapes_1d - u8s8f32 - CPU
  Deconvolution Batch shapes_3d - f32 - CPU
  Deconvolution Batch shapes_3d - u8s8f32 - CPU
  IP Shapes 1D - f32 - CPU
  IP Shapes 1D - u8s8f32 - CPU
  IP Shapes 3D - f32 - CPU
  IP Shapes 3D - u8s8f32 - CPU
  Matrix Multiply Batch Shapes Transformer - f32 - CPU
  Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPU
  Recurrent Neural Network Training - f32 - CPU
  Recurrent Neural Network Training - u8s8f32 - CPU
  Recurrent Neural Network Training - bf16bf16bf16 - CPU
  Recurrent Neural Network Inference - f32 - CPU
  Recurrent Neural Network Inference - u8s8f32 - CPU
  Recurrent Neural Network Inference - bf16bf16bf16 - CPU
Mobile Neural Network:
  SqueezeNetV1.0
  resnet-v2-50
  MobileNetV2_224
  mobilenet-v1-1.0
  inception-v3
ASTC Encoder:
  Medium
  Thorough
  Exhaustive
simdjson:
  PartialTweets
  LargeRand
  Kostya
  DistinctUserID
srsLTE:
  OFDM_Test
  PHY_DL_Test
  PHY_DL_Test
GNU Radio:
  Five Back to Back FIR Filters
  Signal Source (Cosine)
  FIR Filter
  IIR Filter
  FM Deemphasis Filter
  Hilbert Transform
LuaRadio:
  Five Back to Back FIR Filters
  FM Deemphasis Filter
  Hilbert Transform
  Complex Phase
Liquid-DSP:
  16 - 256 - 57
  32 - 256 - 57
  64 - 256 - 57
  128 - 256 - 57
GROMACS
NAMD
CPU Temperature Monitor