990KS March

Intel Core i9-9900KS testing with a ASUS PRIME Z390-A (1502 BIOS) and ASUS Intel UHD 630 CFL GT2 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 2104012-IB-990KSMARC41
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 3 Tests
Timed Code Compilation 4 Tests
C/C++ Compiler Tests 7 Tests
CPU Massive 9 Tests
Creator Workloads 9 Tests
Encoding 5 Tests
Game Development 2 Tests
HPC - High Performance Computing 4 Tests
Machine Learning 3 Tests
Multi-Core 13 Tests
NVIDIA GPU Compute 2 Tests
OpenCL 2 Tests
Programmer / Developer System Benchmarks 6 Tests
Python Tests 4 Tests
Software Defined Radio 4 Tests
Server CPU Tests 8 Tests
Single-Threaded 2 Tests
Texture Compression 2 Tests
Video Encoding 5 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
March 31 2021
  8 Hours, 8 Minutes
2
March 31 2021
  8 Hours, 5 Minutes
3
March 31 2021
  8 Hours, 6 Minutes
Invert Hiding All Results Option
  8 Hours, 6 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):


990KS MarchProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerOpenGLOpenCLCompilerFile-SystemScreen Resolution123Intel Core i9-9900KS @ 5.00GHz (8 Cores / 16 Threads)ASUS PRIME Z390-A (1502 BIOS)Intel Cannon Lake PCH32GB240GB Corsair Force MP510ASUS Intel UHD 630 CFL GT2 3GB (1200MHz)Realtek ALC1220G237HLIntel I219-VUbuntu 20.045.9.0-050900rc8daily20201005-generic (x86_64) 20201004GNOME Shell 3.36.2X Server 1.20.84.6 Mesa 20.2.6OpenCL 2.1GCC 9.3.0ext41920x1080OpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseCompiler 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: 0xcc - Thermald 1.9.1 Python Details- Python 2.7.18rc1 + Python 3.8.2Security Details- itlb_multihit: KVM: Mitigation of VMX unsupported + 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 Enhanced IBRS IBPB: conditional RSB filling + srbds: Mitigation of TSX disabled + tsx_async_abort: Mitigation of TSX disabled

123Result OverviewPhoronix Test Suite100%100%101%101%StockfishsrsLTEAOM AV1Mobile Neural NetworkOpenSCADSVT-VP9Zstd CompressionGNU GMP GMPbenchTimed Erlang/OTP CompilationBasis Universaldav1dSHOC Scalable HeterOgeneous ComputingSVT-HEVCSysbenchLuaRadiooneDNNXcompact3d Incompact3dASTC EncoderTimed Linux Kernel CompilationsimdjsonLiquid-DSPTimed Mesa CompilationGNU RadioViennaCLlibavif avifencBotanTimed Node.js CompilationtoyBrot Fractal GeneratorSystemd Total Boot Time

990KS Marchbuild-nodejs: Time To Compilegnuradio: Hilbert Transformgnuradio: FM Deemphasis Filtergnuradio: IIR Filtergnuradio: FIR Filtergnuradio: Signal Source (Cosine)gnuradio: Five Back to Back FIR Filtersluaradio: Complex Phaseluaradio: Hilbert Transformluaradio: FM Deemphasis Filterluaradio: Five Back to Back FIR Filtersaom-av1: Speed 4 Two-Pass - Bosphorus 4Kshoc: OpenCL - S3Daom-av1: Speed 0 Two-Pass - Bosphorus 4Kgmpbench: Total Timeaom-av1: Speed 6 Two-Pass - Bosphorus 4Kincompact3d: input.i3d 193 Cells Per Directionastcenc: Exhaustivebuild-erlang: Time To Compileopenscad: Pistolaom-av1: Speed 4 Two-Pass - Bosphorus 1080pbuild-linux-kernel: Time To Compileopenscad: Projector Mount Swivelsysbench: CPUsvt-hevc: 1 - Bosphorus 1080pdav1d: Chimera 1080p 10-bitshoc: OpenCL - Texture Read Bandwidthonednn: Recurrent Neural Network Training - bf16bf16bf16 - CPUonednn: Recurrent Neural Network Training - u8s8f32 - CPUonednn: Recurrent Neural Network Training - f32 - CPUshoc: OpenCL - Max SP Flopsonednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPUonednn: Recurrent Neural Network Inference - f32 - CPUonednn: Recurrent Neural Network Inference - u8s8f32 - CPUmnn: inception-v3mnn: mobilenet-v1-1.0mnn: MobileNetV2_224mnn: resnet-v2-50mnn: SqueezeNetV1.0avifenc: 0simdjson: DistinctUserIDsimdjson: PartialTweetsbasis: UASTC Level 3avifenc: 6, Losslesssimdjson: Kostyabuild-mesa: Time To Compileaom-av1: Speed 0 Two-Pass - Bosphorus 1080pcompress-zstd: 19, Long Mode - Decompression Speedcompress-zstd: 19, Long Mode - Compression Speedsimdjson: LargeRandcompress-zstd: 19 - Decompression Speedcompress-zstd: 19 - Compression Speedaom-av1: Speed 6 Realtime - Bosphorus 4Ktoybrot: C++ Threadstoybrot: C++ Taskstoybrot: TBBshoc: OpenCL - MD5 Hashtoybrot: OpenMPopenscad: Mini-ITX Casestockfish: Total Timesrslte: PHY_DL_Testsrslte: PHY_DL_Testaom-av1: Speed 6 Two-Pass - Bosphorus 1080pavifenc: 2srslte: OFDM_Testcompress-zstd: 8 - Decompression Speedcompress-zstd: 8 - Compression Speedcompress-zstd: 8, Long Mode - Decompression Speedcompress-zstd: 8, Long Mode - Compression Speedincompact3d: input.i3d 129 Cells Per Directioncompress-zstd: 3, Long Mode - Decompression Speedcompress-zstd: 3, Long Mode - Compression Speedviennacl: OpenCL BLAS - dGEMM-TTviennacl: OpenCL BLAS - dGEMM-TNviennacl: OpenCL BLAS - dGEMM-NTviennacl: OpenCL BLAS - dGEMM-NNviennacl: OpenCL BLAS - dGEMV-Tviennacl: OpenCL BLAS - dGEMV-Nviennacl: OpenCL BLAS - dDOTviennacl: OpenCL BLAS - dAXPYviennacl: OpenCL BLAS - dCOPYviennacl: OpenCL BLAS - sDOTviennacl: OpenCL BLAS - sAXPYviennacl: OpenCL BLAS - sCOPYcompress-zstd: 3 - Decompression Speedcompress-zstd: 3 - Compression Speedbasis: UASTC Level 2botan: AES-256 - Decryptbotan: AES-256aom-av1: Speed 9 Realtime - Bosphorus 4Kbotan: ChaCha20Poly1305 - Decryptbotan: ChaCha20Poly1305botan: Blowfish - Decryptbotan: Blowfishbotan: Twofish - Decryptbotan: Twofishbotan: CAST-256 - Decryptbotan: CAST-256botan: KASUMI - Decryptbotan: KASUMIaom-av1: Speed 6 Realtime - Bosphorus 1080pviennacl: CPU BLAS - dGEMM-TTviennacl: CPU BLAS - dGEMM-TNviennacl: CPU BLAS - dGEMM-NTviennacl: CPU BLAS - dGEMM-NNviennacl: CPU BLAS - dGEMV-Tviennacl: CPU BLAS - dGEMV-Nviennacl: CPU BLAS - dDOTviennacl: CPU BLAS - dAXPYviennacl: CPU BLAS - dCOPYviennacl: CPU BLAS - sDOTviennacl: CPU BLAS - sAXPYviennacl: CPU BLAS - sCOPYbasis: ETC1Sshoc: OpenCL - GEMM SGEMM_Nonednn: Deconvolution Batch shapes_1d - f32 - CPUonednn: Deconvolution Batch shapes_1d - u8s8f32 - CPUdav1d: Summer Nature 4Kliquid-dsp: 4 - 256 - 57liquid-dsp: 2 - 256 - 57liquid-dsp: 1 - 256 - 57liquid-dsp: 16 - 256 - 57liquid-dsp: 8 - 256 - 57astcenc: Thoroughaom-av1: Speed 8 Realtime - Bosphorus 4Kopenscad: Retro Caropenscad: Leonardo Phone Case Slimdav1d: Chimera 1080ponednn: IP Shapes 1D - f32 - CPUonednn: IP Shapes 1D - u8s8f32 - CPUavifenc: 6onednn: Matrix Multiply Batch Shapes Transformer - f32 - CPUonednn: Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPUshoc: OpenCL - Reductionaom-av1: Speed 8 Realtime - Bosphorus 1080ponednn: IP Shapes 3D - f32 - CPUonednn: IP Shapes 3D - u8s8f32 - CPUbasis: UASTC Level 0aom-av1: Speed 9 Realtime - Bosphorus 1080ponednn: Convolution Batch Shapes Auto - f32 - CPUonednn: Convolution Batch Shapes Auto - u8s8f32 - CPUshoc: OpenCL - FFT SPsvt-hevc: 7 - Bosphorus 1080pdav1d: Summer Nature 1080pastcenc: Mediumavifenc: 10, Losslesssvt-vp9: Visual Quality Optimized - Bosphorus 1080psvt-vp9: VMAF Optimized - Bosphorus 1080psvt-vp9: PSNR/SSIM Optimized - Bosphorus 1080psysbench: RAM / Memoryavifenc: 10onednn: Deconvolution Batch shapes_3d - f32 - CPUonednn: Deconvolution Batch shapes_3d - u8s8f32 - CPUsvt-hevc: 10 - Bosphorus 1080pshoc: OpenCL - Triadshoc: OpenCL - Bus Speed Readbackshoc: OpenCL - Bus Speed Downloadsystemd-boot-total: Userspacesystemd-boot-total: Firmwaresystemd-boot-total: Loadersystemd-boot-total: Kernelsystemd-boot-total: Total123477.097618.0836.7666.1822.33003.21190.2704.287.2486.81297.93.4220.99310.126250.36.34121.691170113.8873113.000100.7676.7694.71492.93119380.346.85160.9156.90993413.973414.523408.161760.701854.881852.131852.2629.4472.3292.67225.3084.89972.0744.534.3863.54362.6743.156.4150.383957.531.91.073969.034.513.164485444756440580.38614386641.90823777878112.7293.219.6837.2531267000004312.4332.64609.8395.134.33759694433.41164.015.715.816.518.934.837.93835.334.037.734.632.94186.52379.433.4614806.1024815.97247.78908.311916.108539.238543.597437.297436.078172.091171.954107.861112.98025.0635.536.534.134.846.545.544.139.326.247.942.828.223.455245.9208.838982.14490185.132508566671301833336762966750033333345271333314.920738.6817.25916.975733.643.577401.6674712.9523.154333.4400336.7934124.398.261031.832157.172141.4814.283014.033515.3682106.19648.265.79495.778136.76173.31176.2928391.473.1546.639933.97706230.2715.605329.049529.211922109156793555194124050476.801618.3837.7664.9820.03011.41195.5700.287.1487.71292.43.4120.85180.126221.86.32121.826073113.7734112.558100.9786.7394.56993.90819382.716.84164.4056.89323445.233413.023405.321761.071851.221851.141850.8229.6702.3332.65525.2544.88272.2584.554.3863.56062.3893.1056.4680.373963.931.81.073983.134.613.124477444842441350.38614385442.05323501591112.2291.819.1137.3041284666674308.9327.64601.3378.434.43972274437.71156.915.715.816.518.934.738.13835.334.137.634.633.34164.52374.533.3744811.1814814.82848.72907.952913.025539.017543.385437.288436.124172.076171.951107.764112.94324.9535.536.434.234.846.545.644.139.326.247.942.928.223.390245.8858.865012.14385184.252515766671300466676763233350026333345207333314.905937.9417.34616.941731.763.574551.6657913.0053.151573.4335936.7270122.648.146951.829107.091140.3914.303113.998815.3757105.90649.675.77575.771136.22172.24175.2728491.743.1606.646593.93198229.4215.233629.052029.164122109156793555194124050477.284620.2837.3665.0818.33011.21188.7698.187.5489.51291.83.3920.84790.126217.66.30121.742472113.8933112.484100.8136.7594.76894.96619367.306.84163.7656.91753415.353413.883405.991760.611854.401852.051851.3029.7952.3462.68325.4144.94371.7994.544.3763.59362.3963.0956.4750.383939.431.51.073981.934.613.144480544729440850.3864383842.08423832208113.4295.019.2137.3261285000004307.7327.54574.8387.234.38460034442.71177.115.715.816.418.934.837.93835.434.237.634.633.34180.32388.433.3874812.4214815.61748.78908.474914.454539.337543.951436.744434.656172.150171.958107.878112.98525.0735.536.534.134.846.545.544.139.326.247.942.828.323.367245.7838.876182.14452184.162514733331306633336759966750001666745308666714.910337.1217.36717.054732.833.565771.665512.9643.149433.4391436.7633121.968.167881.823407.089139.8214.293614.010615.3573105.78647.635.77375.787136.05172.10175.0628338.593.1706.615573.93216229.3615.251829.153129.176622109156793555194124050OpenBenchmarking.org

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 Compile312100200300400500SE +/- 0.19, N = 3SE +/- 0.32, N = 3SE +/- 0.34, N = 3477.28477.10476.80
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Node.js Compilation 15.11Time To Compile31280160240320400Min: 476.91 / Avg: 477.28 / Max: 477.48Min: 476.51 / Avg: 477.1 / Max: 477.61Min: 476.16 / Avg: 476.8 / Max: 477.3

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: Hilbert Transform123130260390520650SE +/- 1.07, N = 3SE +/- 2.62, N = 3SE +/- 1.23, N = 3618.0618.3620.21. 3.8.1.0
OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: Hilbert Transform123110220330440550Min: 616.5 / Avg: 618.03 / Max: 620.1Min: 613.1 / Avg: 618.33 / Max: 621.3Min: 618.5 / Avg: 620.23 / Max: 622.61. 3.8.1.0

OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: FM Deemphasis Filter1322004006008001000SE +/- 2.38, N = 3SE +/- 1.55, N = 3SE +/- 1.84, N = 3836.7837.3837.71. 3.8.1.0
OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: FM Deemphasis Filter132150300450600750Min: 832 / Avg: 836.73 / Max: 839.6Min: 834.2 / Avg: 837.3 / Max: 839Min: 835.4 / Avg: 837.67 / Max: 841.31. 3.8.1.0

OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: IIR Filter231140280420560700SE +/- 1.34, N = 3SE +/- 0.81, N = 3SE +/- 1.14, N = 3664.9665.0666.11. 3.8.1.0
OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: IIR Filter231120240360480600Min: 663.1 / Avg: 664.87 / Max: 667.5Min: 663.6 / Avg: 665 / Max: 666.4Min: 663.8 / Avg: 666.07 / Max: 667.41. 3.8.1.0

OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: FIR Filter3212004006008001000SE +/- 2.94, N = 3SE +/- 3.57, N = 3SE +/- 1.65, N = 3818.3820.0822.31. 3.8.1.0
OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: FIR Filter321140280420560700Min: 815.2 / Avg: 818.33 / Max: 824.2Min: 812.9 / Avg: 820.03 / Max: 824Min: 820.6 / Avg: 822.3 / Max: 825.61. 3.8.1.0

OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: Signal Source (Cosine)1326001200180024003000SE +/- 3.36, N = 3SE +/- 2.72, N = 3SE +/- 2.10, N = 33003.23011.23011.41. 3.8.1.0
OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: Signal Source (Cosine)1325001000150020002500Min: 2996.9 / Avg: 3003.17 / Max: 3008.4Min: 3006.3 / Avg: 3011.17 / Max: 3015.7Min: 3007.4 / Avg: 3011.4 / Max: 3014.51. 3.8.1.0

OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: Five Back to Back FIR Filters31230060090012001500SE +/- 15.25, N = 3SE +/- 12.45, N = 3SE +/- 9.72, N = 31188.71190.21195.51. 3.8.1.0
OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: Five Back to Back FIR Filters3122004006008001000Min: 1161 / Avg: 1188.7 / Max: 1213.6Min: 1176.7 / Avg: 1190.23 / Max: 1215.1Min: 1185.2 / Avg: 1195.47 / Max: 1214.91. 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: Complex Phase321150300450600750SE +/- 11.13, N = 3SE +/- 6.74, N = 3SE +/- 5.92, N = 3698.1700.2704.2
OpenBenchmarking.orgMiB/s, More Is BetterLuaRadio 0.9.1Test: Complex Phase321120240360480600Min: 676 / Avg: 698.1 / Max: 711.5Min: 692.2 / Avg: 700.2 / Max: 713.6Min: 692.5 / Avg: 704.17 / Max: 711.7

OpenBenchmarking.orgMiB/s, More Is BetterLuaRadio 0.9.1Test: Hilbert Transform21320406080100SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.32, N = 387.187.287.5
OpenBenchmarking.orgMiB/s, More Is BetterLuaRadio 0.9.1Test: Hilbert Transform21320406080100Min: 87 / Avg: 87.1 / Max: 87.2Min: 87.2 / Avg: 87.23 / Max: 87.3Min: 87.1 / Avg: 87.47 / Max: 88.1

OpenBenchmarking.orgMiB/s, More Is BetterLuaRadio 0.9.1Test: FM Deemphasis Filter123110220330440550SE +/- 1.86, N = 3SE +/- 1.98, N = 3SE +/- 0.27, N = 3486.8487.7489.5
OpenBenchmarking.orgMiB/s, More Is BetterLuaRadio 0.9.1Test: FM Deemphasis Filter12390180270360450Min: 483.1 / Avg: 486.8 / Max: 488.9Min: 483.7 / Avg: 487.67 / Max: 489.7Min: 489.1 / Avg: 489.47 / Max: 490

OpenBenchmarking.orgMiB/s, More Is BetterLuaRadio 0.9.1Test: Five Back to Back FIR Filters32130060090012001500SE +/- 4.98, N = 3SE +/- 3.21, N = 3SE +/- 2.64, N = 31291.81292.41297.9
OpenBenchmarking.orgMiB/s, More Is BetterLuaRadio 0.9.1Test: Five Back to Back FIR Filters3212004006008001000Min: 1282.3 / Avg: 1291.77 / Max: 1299.2Min: 1287.1 / Avg: 1292.43 / Max: 1298.2Min: 1292.8 / Avg: 1297.93 / Max: 1301.6

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 4 Two-Pass - Input: Bosphorus 4K3210.76951.5392.30853.0783.8475SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 33.393.413.421. (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 4K321246810Min: 3.38 / Avg: 3.39 / Max: 3.41Min: 3.37 / Avg: 3.41 / Max: 3.45Min: 3.39 / Avg: 3.42 / Max: 3.451. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

SHOC Scalable HeterOgeneous Computing

The CUDA and OpenCL version of Vetter's Scalable HeterOgeneous Computing benchmark suite. SHOC provides a number of different benchmark programs for evaluating the performance and stability of compute devices. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: S3D321510152025SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.04, N = 320.8520.8520.991. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi
OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: S3D321510152025Min: 20.82 / Avg: 20.85 / Max: 20.89Min: 20.79 / Avg: 20.85 / Max: 20.91Min: 20.94 / Avg: 20.99 / Max: 21.061. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

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 0 Two-Pass - Input: Bosphorus 4K1230.0270.0540.0810.1080.135SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.120.120.121. (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 4K12312345Min: 0.12 / Avg: 0.12 / Max: 0.12Min: 0.12 / Avg: 0.12 / Max: 0.12Min: 0.12 / Avg: 0.12 / Max: 0.121. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

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 Time321130026003900520065006217.66221.86250.31. (CC) gcc options: -O3 -fomit-frame-pointer -lm

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 6 Two-Pass - Input: Bosphorus 4K321246810SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 36.306.326.341. (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 4K3213691215Min: 6.28 / Avg: 6.3 / Max: 6.33Min: 6.29 / Avg: 6.32 / Max: 6.35Min: 6.33 / Avg: 6.34 / Max: 6.361. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

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 193 Cells Per Direction231306090120150SE +/- 0.03, N = 3SE +/- 0.05, N = 3SE +/- 0.01, N = 3121.83121.74121.691. (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 Direction23120406080100Min: 121.79 / Avg: 121.83 / Max: 121.89Min: 121.66 / Avg: 121.74 / Max: 121.82Min: 121.67 / Avg: 121.69 / Max: 121.711. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi

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: Exhaustive312306090120150SE +/- 0.16, N = 3SE +/- 0.12, N = 3SE +/- 0.14, N = 3113.89113.89113.771. (CXX) g++ options: -O3 -flto -pthread
OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.4Preset: Exhaustive31220406080100Min: 113.59 / Avg: 113.89 / Max: 114.14Min: 113.65 / Avg: 113.89 / Max: 114.02Min: 113.5 / Avg: 113.77 / Max: 113.991. (CXX) g++ options: -O3 -flto -pthread

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 Compile123306090120150SE +/- 0.14, N = 3SE +/- 0.40, N = 3SE +/- 0.31, N = 3113.00112.56112.48
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Erlang/OTP Compilation 23.2Time To Compile12320406080100Min: 112.71 / Avg: 113 / Max: 113.15Min: 111.94 / Avg: 112.56 / Max: 113.31Min: 111.89 / Avg: 112.48 / Max: 112.94

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: Pistol23120406080100SE +/- 0.21, N = 3SE +/- 0.09, N = 3SE +/- 0.07, N = 3100.98100.81100.771. OpenSCAD version 2019.05
OpenBenchmarking.orgSeconds, Fewer Is BetterOpenSCADRender: Pistol23120406080100Min: 100.57 / Avg: 100.98 / Max: 101.2Min: 100.65 / Avg: 100.81 / Max: 100.92Min: 100.63 / Avg: 100.77 / Max: 100.851. OpenSCAD version 2019.05

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 4 Two-Pass - Input: Bosphorus 1080p231246810SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 36.736.756.761. (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 1080p2313691215Min: 6.71 / Avg: 6.73 / Max: 6.78Min: 6.72 / Avg: 6.75 / Max: 6.77Min: 6.75 / Avg: 6.76 / Max: 6.781. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

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 Compile31220406080100SE +/- 0.47, N = 3SE +/- 0.78, N = 3SE +/- 0.60, N = 394.7794.7194.57
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 5.10.20Time To Compile31220406080100Min: 93.92 / Avg: 94.77 / Max: 95.55Min: 93.79 / Avg: 94.71 / Max: 96.27Min: 93.89 / Avg: 94.57 / Max: 95.76

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 Swivel32120406080100SE +/- 0.08, N = 3SE +/- 0.42, N = 3SE +/- 0.21, N = 394.9793.9192.931. OpenSCAD version 2019.05
OpenBenchmarking.orgSeconds, Fewer Is BetterOpenSCADRender: Projector Mount Swivel32120406080100Min: 94.85 / Avg: 94.97 / Max: 95.12Min: 93.07 / Avg: 93.91 / Max: 94.39Min: 92.52 / Avg: 92.93 / Max: 93.191. OpenSCAD version 2019.05

Sysbench

This is a benchmark of Sysbench with the built-in CPU and memory sub-tests. Sysbench is a scriptable multi-threaded benchmark tool based on LuaJIT. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgEvents Per Second, More Is BetterSysbench 1.0.20Test: CPU3124K8K12K16K20KSE +/- 16.54, N = 3SE +/- 14.24, N = 3SE +/- 20.02, N = 319367.3019380.3419382.711. (CC) gcc options: -pthread -O2 -funroll-loops -rdynamic -ldl -laio -lm
OpenBenchmarking.orgEvents Per Second, More Is BetterSysbench 1.0.20Test: CPU3123K6K9K12K15KMin: 19349.59 / Avg: 19367.3 / Max: 19400.35Min: 19363.09 / Avg: 19380.34 / Max: 19408.59Min: 19361.28 / Avg: 19382.71 / Max: 19422.721. (CC) gcc options: -pthread -O2 -funroll-loops -rdynamic -ldl -laio -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 1080p231246810SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 36.846.846.851. (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 1080p2313691215Min: 6.84 / Avg: 6.84 / Max: 6.85Min: 6.84 / Avg: 6.84 / Max: 6.85Min: 6.84 / Avg: 6.85 / Max: 6.881. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

dav1d

Dav1d is an open-source, speedy AV1 video decoder. This test profile times how long it takes to decode sample AV1 video content. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is Betterdav1d 0.8.2Video Input: Chimera 1080p 10-bit1324080120160200SE +/- 0.13, N = 3SE +/- 1.42, N = 3SE +/- 1.75, N = 3160.91163.76164.40MIN: 103.41 / MAX: 410.16MIN: 104.03 / MAX: 384.96MIN: 103.73 / MAX: 392.071. (CC) gcc options: -pthread -lm
OpenBenchmarking.orgFPS, More Is Betterdav1d 0.8.2Video Input: Chimera 1080p 10-bit132306090120150Min: 160.68 / Avg: 160.91 / Max: 161.12Min: 160.92 / Avg: 163.76 / Max: 165.28Min: 160.89 / Avg: 164.4 / Max: 166.21. (CC) gcc options: -pthread -lm

SHOC Scalable HeterOgeneous Computing

The CUDA and OpenCL version of Vetter's Scalable HeterOgeneous Computing benchmark suite. SHOC provides a number of different benchmark programs for evaluating the performance and stability of compute devices. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Texture Read Bandwidth2131326395265SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 356.8956.9156.921. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi
OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Texture Read Bandwidth2131122334455Min: 56.88 / Avg: 56.89 / Max: 56.92Min: 56.88 / Avg: 56.91 / Max: 56.93Min: 56.91 / Avg: 56.92 / Max: 56.921. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -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: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU2317001400210028003500SE +/- 26.13, N = 3SE +/- 0.66, N = 3SE +/- 2.52, N = 33445.233415.353413.97MIN: 3408.23MIN: 3409.68MIN: 3402.031. (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 Training - Data Type: bf16bf16bf16 - Engine: CPU2316001200180024003000Min: 3414.38 / Avg: 3445.23 / Max: 3497.19Min: 3414.07 / Avg: 3415.35 / Max: 3416.29Min: 3409.08 / Avg: 3413.97 / Max: 3417.431. (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: CPU1327001400210028003500SE +/- 3.64, N = 3SE +/- 0.89, N = 3SE +/- 0.58, N = 33414.523413.883413.02MIN: 3404.15MIN: 3407.32MIN: 3406.861. (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: CPU1326001200180024003000Min: 3410.04 / Avg: 3414.52 / Max: 3421.72Min: 3412.31 / Avg: 3413.88 / Max: 3415.38Min: 3411.89 / Avg: 3413.02 / Max: 3413.821. (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: CPU1327001400210028003500SE +/- 5.97, N = 3SE +/- 4.35, N = 3SE +/- 3.80, N = 33408.163405.993405.32MIN: 3391.46MIN: 3393.27MIN: 3391.391. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU1326001200180024003000Min: 3396.77 / Avg: 3408.16 / Max: 3416.94Min: 3398.22 / Avg: 3405.99 / Max: 3413.28Min: 3398.27 / Avg: 3405.32 / Max: 3411.31. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

SHOC Scalable HeterOgeneous Computing

The CUDA and OpenCL version of Vetter's Scalable HeterOgeneous Computing benchmark suite. SHOC provides a number of different benchmark programs for evaluating the performance and stability of compute devices. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Max SP Flops312400800120016002000SE +/- 0.83, N = 3SE +/- 1.38, N = 3SE +/- 0.55, N = 31760.611760.701761.071. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi
OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Max SP Flops31230060090012001500Min: 1758.95 / Avg: 1760.61 / Max: 1761.54Min: 1757.97 / Avg: 1760.7 / Max: 1762.47Min: 1759.97 / Avg: 1761.07 / Max: 1761.71. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -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: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU132400800120016002000SE +/- 3.26, N = 3SE +/- 1.53, N = 3SE +/- 1.24, N = 31854.881854.401851.22MIN: 1847.25MIN: 1846.77MIN: 1841.631. (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: CPU13230060090012001500Min: 1851.2 / Avg: 1854.88 / Max: 1861.38Min: 1852.03 / Avg: 1854.4 / Max: 1857.27Min: 1848.87 / Avg: 1851.22 / Max: 1853.061. (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: CPU132400800120016002000SE +/- 0.88, N = 3SE +/- 0.20, N = 3SE +/- 1.72, N = 31852.131852.051851.14MIN: 1846.26MIN: 1846.88MIN: 1843.951. (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: CPU13230060090012001500Min: 1850.4 / Avg: 1852.13 / Max: 1853.23Min: 1851.66 / Avg: 1852.05 / Max: 1852.26Min: 1848.53 / Avg: 1851.14 / Max: 1854.381. (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: CPU132400800120016002000SE +/- 0.58, N = 3SE +/- 1.14, N = 3SE +/- 0.16, N = 31852.261851.301850.82MIN: 1846.85MIN: 1843.57MIN: 1844.821. (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: CPU13230060090012001500Min: 1851.25 / Avg: 1852.26 / Max: 1853.25Min: 1849.02 / Avg: 1851.3 / Max: 1852.56Min: 1850.6 / Avg: 1850.82 / Max: 1851.131. (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: inception-v3321714212835SE +/- 0.16, N = 3SE +/- 0.04, N = 3SE +/- 0.08, N = 329.8029.6729.45MIN: 29.45 / MAX: 42.01MIN: 29.48 / MAX: 42.09MIN: 29.17 / MAX: 40.181. (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-v3321714212835Min: 29.56 / Avg: 29.8 / Max: 30.11Min: 29.6 / Avg: 29.67 / Max: 29.72Min: 29.32 / Avg: 29.45 / Max: 29.581. (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-v1-1.03210.52791.05581.58372.11162.6395SE +/- 0.010, N = 3SE +/- 0.006, N = 3SE +/- 0.007, N = 32.3462.3332.329MIN: 2.28 / MAX: 3.63MIN: 2.27 / MAX: 3.55MIN: 2.26 / MAX: 4.961. (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-v1-1.0321246810Min: 2.33 / Avg: 2.35 / Max: 2.36Min: 2.32 / Avg: 2.33 / Max: 2.35Min: 2.32 / 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: MobileNetV2_2243120.60371.20741.81112.41483.0185SE +/- 0.063, N = 3SE +/- 0.063, N = 3SE +/- 0.051, N = 32.6832.6722.655MIN: 2.37 / MAX: 4.91MIN: 2.34 / MAX: 4.31MIN: 2.35 / MAX: 3.811. (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_224312246810Min: 2.56 / Avg: 2.68 / Max: 2.77Min: 2.56 / Avg: 2.67 / Max: 2.78Min: 2.56 / Avg: 2.66 / Max: 2.721. (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-v2-50312612182430SE +/- 0.05, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 325.4125.3125.25MIN: 25.17 / MAX: 37.2MIN: 25.08 / MAX: 37.21MIN: 25.09 / MAX: 35.041. (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-v2-50312612182430Min: 25.32 / Avg: 25.41 / Max: 25.48Min: 25.24 / Avg: 25.31 / Max: 25.38Min: 25.23 / Avg: 25.25 / Max: 25.31. (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: SqueezeNetV1.03121.11222.22443.33664.44885.561SE +/- 0.027, N = 3SE +/- 0.029, N = 3SE +/- 0.030, N = 34.9434.8994.882MIN: 4.65 / MAX: 16.5MIN: 4.71 / MAX: 7.4MIN: 4.68 / MAX: 5.581. (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: SqueezeNetV1.0312246810Min: 4.89 / Avg: 4.94 / Max: 4.99Min: 4.86 / Avg: 4.9 / Max: 4.96Min: 4.82 / Avg: 4.88 / Max: 4.921. (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

libavif avifenc

This is a test of the AOMedia libavif library testing the encoding of a JPEG image to AV1 Image Format (AVIF). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.9.0Encoder Speed: 02131632486480SE +/- 0.25, N = 3SE +/- 0.16, N = 3SE +/- 0.26, N = 372.2672.0771.801. (CXX) g++ options: -O3 -fPIC -lm
OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.9.0Encoder Speed: 02131428425670Min: 71.77 / Avg: 72.26 / Max: 72.58Min: 71.81 / Avg: 72.07 / Max: 72.37Min: 71.41 / Avg: 71.8 / Max: 72.281. (CXX) g++ options: -O3 -fPIC -lm

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: DistinctUserID1321.02382.04763.07144.09525.119SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 34.534.544.551. (CXX) g++ options: -O3 -pthread
OpenBenchmarking.orgGB/s, More Is Bettersimdjson 0.8.2Throughput Test: DistinctUserID132246810Min: 4.53 / Avg: 4.53 / Max: 4.54Min: 4.53 / Avg: 4.54 / Max: 4.55Min: 4.54 / Avg: 4.55 / Max: 4.571. (CXX) g++ options: -O3 -pthread

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 0.8.2Throughput Test: PartialTweets3120.98551.9712.95653.9424.9275SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 34.374.384.381. (CXX) g++ options: -O3 -pthread
OpenBenchmarking.orgGB/s, More Is Bettersimdjson 0.8.2Throughput Test: PartialTweets312246810Min: 4.37 / Avg: 4.37 / Max: 4.38Min: 4.38 / Avg: 4.38 / Max: 4.39Min: 4.38 / Avg: 4.38 / Max: 4.391. (CXX) g++ options: -O3 -pthread

Basis Universal

Basis Universal is a GPU texture codec. This test times how long it takes to convert sRGB PNGs into Basis Univeral assets with various settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.13Settings: UASTC Level 33211428425670SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 363.5963.5663.541. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.13Settings: UASTC Level 33211224364860Min: 63.55 / Avg: 63.59 / Max: 63.62Min: 63.49 / Avg: 63.56 / Max: 63.61Min: 63.5 / Avg: 63.54 / Max: 63.581. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread

libavif avifenc

This is a test of the AOMedia libavif library testing the encoding of a JPEG image to AV1 Image Format (AVIF). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.9.0Encoder Speed: 6, Lossless1321428425670SE +/- 0.15, N = 3SE +/- 0.14, N = 3SE +/- 0.11, N = 362.6762.4062.391. (CXX) g++ options: -O3 -fPIC -lm
OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.9.0Encoder Speed: 6, Lossless1321224364860Min: 62.42 / Avg: 62.67 / Max: 62.95Min: 62.14 / Avg: 62.4 / Max: 62.62Min: 62.2 / Avg: 62.39 / Max: 62.571. (CXX) g++ options: -O3 -fPIC -lm

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: Kostya3120.69751.3952.09252.793.4875SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 33.093.103.101. (CXX) g++ options: -O3 -pthread
OpenBenchmarking.orgGB/s, More Is Bettersimdjson 0.8.2Throughput Test: Kostya312246810Min: 3.08 / Avg: 3.09 / Max: 3.11Min: 3.1 / Avg: 3.1 / Max: 3.1Min: 3.1 / Avg: 3.1 / Max: 3.111. (CXX) g++ options: -O3 -pthread

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 Compile3211326395265SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 356.4856.4756.42
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Mesa Compilation 21.0Time To Compile3211122334455Min: 56.43 / Avg: 56.48 / Max: 56.55Min: 56.39 / Avg: 56.47 / Max: 56.54Min: 56.37 / Avg: 56.41 / Max: 56.45

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 0 Two-Pass - Input: Bosphorus 1080p2130.08550.1710.25650.3420.4275SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.370.380.381. (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 1080p21312345Min: 0.37 / Avg: 0.37 / Max: 0.38Min: 0.38 / Avg: 0.38 / Max: 0.39Min: 0.38 / Avg: 0.38 / Max: 0.381. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

Zstd Compression

This test measures the time needed to compress/decompress a sample file (a FreeBSD disk image - FreeBSD-12.2-RELEASE-amd64-memstick.img) using Zstd compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 19, Long Mode - Decompression Speed3129001800270036004500SE +/- 5.83, N = 3SE +/- 9.00, N = 3SE +/- 0.96, N = 33939.43957.53963.91. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 19, Long Mode - Decompression Speed3127001400210028003500Min: 3927.9 / Avg: 3939.43 / Max: 3946.7Min: 3940.1 / Avg: 3957.5 / Max: 3970.2Min: 3962.2 / Avg: 3963.93 / Max: 3965.51. (CC) gcc options: -O3 -pthread -lz -llzma

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 19, Long Mode - Compression Speed321714212835SE +/- 0.07, N = 3SE +/- 0.06, N = 3SE +/- 0.12, N = 331.531.831.91. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 19, Long Mode - Compression Speed321714212835Min: 31.4 / Avg: 31.47 / Max: 31.6Min: 31.7 / Avg: 31.8 / Max: 31.9Min: 31.7 / Avg: 31.93 / Max: 32.11. (CC) gcc options: -O3 -pthread -lz -llzma

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: LargeRandom1230.24080.48160.72240.96321.204SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 31.071.071.071. (CXX) g++ options: -O3 -pthread
OpenBenchmarking.orgGB/s, More Is Bettersimdjson 0.8.2Throughput Test: LargeRandom123246810Min: 1.07 / Avg: 1.07 / Max: 1.07Min: 1.07 / Avg: 1.07 / Max: 1.07Min: 1.07 / Avg: 1.07 / Max: 1.071. (CXX) g++ options: -O3 -pthread

Zstd Compression

This test measures the time needed to compress/decompress a sample file (a FreeBSD disk image - FreeBSD-12.2-RELEASE-amd64-memstick.img) using Zstd compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 19 - Decompression Speed1329001800270036004500SE +/- 10.42, N = 3SE +/- 4.27, N = 3SE +/- 1.35, N = 33969.03981.93983.11. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 19 - Decompression Speed1327001400210028003500Min: 3958 / Avg: 3968.97 / Max: 3989.8Min: 3976.1 / Avg: 3981.87 / Max: 3990.2Min: 3981.2 / Avg: 3983.1 / Max: 3985.71. (CC) gcc options: -O3 -pthread -lz -llzma

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 19 - Compression Speed123816243240SE +/- 0.12, N = 3SE +/- 0.07, N = 3SE +/- 0.06, N = 334.534.634.61. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 19 - Compression Speed123714212835Min: 34.3 / Avg: 34.47 / Max: 34.7Min: 34.5 / Avg: 34.63 / Max: 34.7Min: 34.5 / Avg: 34.6 / Max: 34.71. (CC) gcc options: -O3 -pthread -lz -llzma

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 6 Realtime - Input: Bosphorus 4K2313691215SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 313.1213.1413.161. (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 4K23148121620Min: 13.1 / Avg: 13.12 / Max: 13.15Min: 13.12 / Avg: 13.14 / Max: 13.15Min: 13.12 / Avg: 13.16 / Max: 13.181. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

toyBrot Fractal Generator

ToyBrot is a Mandelbrot fractal generator supporting C++ threads/tasks, OpenMP, Intel Threaded Building Blocks (TBB), and other targets. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BettertoyBrot Fractal Generator 2020-11-18Implementation: C++ Threads13210K20K30K40K50KSE +/- 27.00, N = 3SE +/- 36.98, N = 3SE +/- 25.27, N = 34485444805447741. (CXX) g++ options: -O3 -lpthread
OpenBenchmarking.orgms, Fewer Is BettertoyBrot Fractal Generator 2020-11-18Implementation: C++ Threads1328K16K24K32K40KMin: 44802 / Avg: 44854.33 / Max: 44892Min: 44735 / Avg: 44804.67 / Max: 44861Min: 44728 / Avg: 44774.33 / Max: 448151. (CXX) g++ options: -O3 -lpthread

OpenBenchmarking.orgms, Fewer Is BettertoyBrot Fractal Generator 2020-11-18Implementation: C++ Tasks21310K20K30K40K50KSE +/- 118.82, N = 3SE +/- 16.42, N = 3SE +/- 38.73, N = 34484244756447291. (CXX) g++ options: -O3 -lpthread
OpenBenchmarking.orgms, Fewer Is BettertoyBrot Fractal Generator 2020-11-18Implementation: C++ Tasks2138K16K24K32K40KMin: 44672 / Avg: 44842.33 / Max: 45071Min: 44723 / Avg: 44755.67 / Max: 44775Min: 44664 / Avg: 44729 / Max: 447981. (CXX) g++ options: -O3 -lpthread

OpenBenchmarking.orgms, Fewer Is BettertoyBrot Fractal Generator 2020-11-18Implementation: TBB2319K18K27K36K45KSE +/- 72.84, N = 3SE +/- 82.93, N = 3SE +/- 59.38, N = 34413544085440581. (CXX) g++ options: -O3 -lpthread
OpenBenchmarking.orgms, Fewer Is BettertoyBrot Fractal Generator 2020-11-18Implementation: TBB2318K16K24K32K40KMin: 44005 / Avg: 44134.67 / Max: 44257Min: 43921 / Avg: 44085.33 / Max: 44187Min: 43939 / Avg: 44057.67 / Max: 441211. (CXX) g++ options: -O3 -lpthread

SHOC Scalable HeterOgeneous Computing

The CUDA and OpenCL version of Vetter's Scalable HeterOgeneous Computing benchmark suite. SHOC provides a number of different benchmark programs for evaluating the performance and stability of compute devices. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGHash/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: MD5 Hash3120.08690.17380.26070.34760.4345SE +/- 0.0000, N = 3SE +/- 0.0000, N = 3SE +/- 0.0000, N = 30.38600.38610.38611. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi
OpenBenchmarking.orgGHash/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: MD5 Hash31212345Min: 0.39 / Avg: 0.39 / Max: 0.39Min: 0.39 / Avg: 0.39 / Max: 0.39Min: 0.39 / Avg: 0.39 / Max: 0.391. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

toyBrot Fractal Generator

ToyBrot is a Mandelbrot fractal generator supporting C++ threads/tasks, OpenMP, Intel Threaded Building Blocks (TBB), and other targets. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BettertoyBrot Fractal Generator 2020-11-18Implementation: OpenMP1239K18K27K36K45KSE +/- 13.86, N = 3SE +/- 16.82, N = 3SE +/- 19.34, N = 34386643854438381. (CXX) g++ options: -O3 -lpthread
OpenBenchmarking.orgms, Fewer Is BettertoyBrot Fractal Generator 2020-11-18Implementation: OpenMP1238K16K24K32K40KMin: 43839 / Avg: 43866.33 / Max: 43884Min: 43829 / Avg: 43854 / Max: 43886Min: 43804 / Avg: 43837.67 / Max: 438711. (CXX) g++ options: -O3 -lpthread

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: Mini-ITX Case3211020304050SE +/- 0.02, N = 3SE +/- 0.12, N = 3SE +/- 0.07, N = 342.0842.0541.911. OpenSCAD version 2019.05
OpenBenchmarking.orgSeconds, Fewer Is BetterOpenSCADRender: Mini-ITX Case321918273645Min: 42.04 / Avg: 42.08 / Max: 42.11Min: 41.93 / Avg: 42.05 / Max: 42.29Min: 41.82 / Avg: 41.91 / Max: 42.051. 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 Time2135M10M15M20M25MSE +/- 299604.32, N = 3SE +/- 294389.71, N = 4SE +/- 377829.22, N = 32350159123777878238322081. (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 -mbmi2 -flto -flto=jobserver
OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 13Total Time2134M8M12M16M20MMin: 23119357 / Avg: 23501591.33 / Max: 24092347Min: 22976806 / Avg: 23777877.5 / Max: 24368176Min: 23328430 / Avg: 23832208 / Max: 245718681. (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 -mbmi2 -flto -flto=jobserver

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.orgUE Mb/s, More Is BettersrsLTE 20.10.1Test: PHY_DL_Test213306090120150SE +/- 0.13, N = 3SE +/- 0.09, N = 3SE +/- 0.12, N = 3112.2112.7113.41. (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 -lbladeRF -lm -lfftw3f -lmbedcrypto
OpenBenchmarking.orgUE Mb/s, More Is BettersrsLTE 20.10.1Test: PHY_DL_Test21320406080100Min: 111.9 / Avg: 112.17 / Max: 112.3Min: 112.6 / Avg: 112.73 / Max: 112.9Min: 113.2 / Avg: 113.37 / Max: 113.61. (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 -lbladeRF -lm -lfftw3f -lmbedcrypto

OpenBenchmarking.orgeNb Mb/s, More Is BettersrsLTE 20.10.1Test: PHY_DL_Test21360120180240300SE +/- 0.73, N = 3SE +/- 0.19, N = 3SE +/- 0.84, N = 3291.8293.2295.01. (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 -lbladeRF -lm -lfftw3f -lmbedcrypto
OpenBenchmarking.orgeNb Mb/s, More Is BettersrsLTE 20.10.1Test: PHY_DL_Test21350100150200250Min: 290.6 / Avg: 291.77 / Max: 293.1Min: 292.8 / Avg: 293.17 / Max: 293.4Min: 293.4 / Avg: 295.03 / Max: 296.21. (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 -lbladeRF -lm -lfftw3f -lmbedcrypto

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 6 Two-Pass - Input: Bosphorus 1080p231510152025SE +/- 0.08, N = 3SE +/- 0.01, N = 3SE +/- 0.17, N = 319.1119.2119.681. (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 1080p231510152025Min: 18.95 / Avg: 19.11 / Max: 19.21Min: 19.19 / Avg: 19.21 / Max: 19.24Min: 19.43 / Avg: 19.68 / Max: 201. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

libavif avifenc

This is a test of the AOMedia libavif library testing the encoding of a JPEG image to AV1 Image Format (AVIF). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.9.0Encoder Speed: 2321918273645SE +/- 0.09, N = 3SE +/- 0.11, N = 3SE +/- 0.06, N = 337.3337.3037.251. (CXX) g++ options: -O3 -fPIC -lm
OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.9.0Encoder Speed: 2321816243240Min: 37.18 / Avg: 37.33 / Max: 37.47Min: 37.11 / Avg: 37.3 / Max: 37.48Min: 37.15 / Avg: 37.25 / Max: 37.341. (CXX) g++ options: -O3 -fPIC -lm

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_Test12330M60M90M120M150MSE +/- 416333.20, N = 3SE +/- 821245.67, N = 3SE +/- 665832.81, N = 31267000001284666671285000001. (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 -lbladeRF -lm -lfftw3f -lmbedcrypto
OpenBenchmarking.orgSamples / Second, More Is BettersrsLTE 20.10.1Test: OFDM_Test12320M40M60M80M100MMin: 125900000 / Avg: 126700000 / Max: 127300000Min: 127500000 / Avg: 128466666.67 / Max: 130100000Min: 127400000 / Avg: 128500000 / Max: 1297000001. (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 -lbladeRF -lm -lfftw3f -lmbedcrypto

Zstd Compression

This test measures the time needed to compress/decompress a sample file (a FreeBSD disk image - FreeBSD-12.2-RELEASE-amd64-memstick.img) using Zstd compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 8 - Decompression Speed3219001800270036004500SE +/- 5.58, N = 3SE +/- 5.34, N = 3SE +/- 11.68, N = 34307.74308.94312.41. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 8 - Decompression Speed3217001400210028003500Min: 4296.7 / Avg: 4307.7 / Max: 4314.8Min: 4302.5 / Avg: 4308.9 / Max: 4319.5Min: 4289.2 / Avg: 4312.43 / Max: 4326.21. (CC) gcc options: -O3 -pthread -lz -llzma

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 8 - Compression Speed32170140210280350SE +/- 0.88, N = 3SE +/- 2.23, N = 3SE +/- 1.66, N = 3327.5327.6332.61. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 8 - Compression Speed32160120180240300Min: 326.2 / Avg: 327.53 / Max: 329.2Min: 323.2 / Avg: 327.6 / Max: 330.4Min: 330.6 / Avg: 332.6 / Max: 335.91. (CC) gcc options: -O3 -pthread -lz -llzma

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 8, Long Mode - Decompression Speed32110002000300040005000SE +/- 22.35, N = 3SE +/- 1.73, N = 3SE +/- 2.70, N = 34574.84601.34609.81. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 8, Long Mode - Decompression Speed3218001600240032004000Min: 4530.1 / Avg: 4574.8 / Max: 4597.3Min: 4598.3 / Avg: 4601.33 / Max: 4604.3Min: 4605.7 / Avg: 4609.8 / Max: 4614.91. (CC) gcc options: -O3 -pthread -lz -llzma

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 8, Long Mode - Compression Speed23190180270360450SE +/- 2.00, N = 3SE +/- 2.94, N = 3SE +/- 4.78, N = 3378.4387.2395.11. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 8, Long Mode - Compression Speed23170140210280350Min: 374.6 / Avg: 378.4 / Max: 381.4Min: 383.4 / Avg: 387.23 / Max: 393Min: 387.3 / Avg: 395.1 / Max: 403.81. (CC) gcc options: -O3 -pthread -lz -llzma

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 Direction231816243240SE +/- 0.34, N = 3SE +/- 0.31, N = 3SE +/- 0.35, N = 334.4434.3834.341. (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 Direction231714212835Min: 34.09 / Avg: 34.44 / Max: 35.13Min: 34.05 / Avg: 34.38 / Max: 35.01Min: 33.98 / Avg: 34.34 / Max: 35.041. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi

Zstd Compression

This test measures the time needed to compress/decompress a sample file (a FreeBSD disk image - FreeBSD-12.2-RELEASE-amd64-memstick.img) using Zstd compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 3, Long Mode - Decompression Speed12310002000300040005000SE +/- 7.93, N = 3SE +/- 5.89, N = 3SE +/- 1.29, N = 34433.44437.74442.71. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 3, Long Mode - Decompression Speed1238001600240032004000Min: 4425.4 / Avg: 4433.43 / Max: 4449.3Min: 4426.1 / Avg: 4437.73 / Max: 4445.1Min: 4440.2 / Avg: 4442.73 / Max: 4444.41. (CC) gcc options: -O3 -pthread -lz -llzma

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 3, Long Mode - Compression Speed21330060090012001500SE +/- 10.72, N = 3SE +/- 5.14, N = 3SE +/- 6.67, N = 31156.91164.01177.11. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 3, Long Mode - Compression Speed2132004006008001000Min: 1137.2 / Avg: 1156.87 / Max: 1174.1Min: 1154.3 / Avg: 1164 / Max: 1171.8Min: 1164.3 / Avg: 1177.07 / Max: 1186.81. (CC) gcc options: -O3 -pthread -lz -llzma

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.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMM-TT12348121620SE +/- 0.00, N = 2SE +/- 0.00, N = 2SE +/- 0.00, N = 215.715.715.71. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMM-TT12348121620Min: 15.7 / Avg: 15.7 / Max: 15.7Min: 15.7 / Avg: 15.7 / Max: 15.7Min: 15.7 / Avg: 15.7 / Max: 15.71. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMM-TN12348121620SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 315.815.815.81. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMM-TN12348121620Min: 15.7 / Avg: 15.77 / Max: 15.8Min: 15.7 / Avg: 15.77 / Max: 15.8Min: 15.7 / Avg: 15.77 / Max: 15.81. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMM-NT31248121620SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 316.416.516.51. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMM-NT31248121620Min: 16.4 / Avg: 16.43 / Max: 16.5Min: 16.5 / Avg: 16.5 / Max: 16.5Min: 16.4 / Avg: 16.47 / Max: 16.51. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMM-NN123510152025SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 318.918.918.91. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMM-NN123510152025Min: 18.9 / Avg: 18.9 / Max: 18.9Min: 18.9 / Avg: 18.9 / Max: 18.9Min: 18.9 / Avg: 18.9 / Max: 18.91. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMV-T213816243240SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 334.734.834.81. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMV-T213714212835Min: 34.7 / Avg: 34.73 / Max: 34.8Min: 34.8 / Avg: 34.8 / Max: 34.8Min: 34.7 / Avg: 34.77 / Max: 34.81. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMV-N132918273645SE +/- 0.00, N = 337.937.938.11. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMV-N132816243240Min: 37.9 / Avg: 37.9 / Max: 37.91. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dDOT1239182736453838381. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dAXPY123816243240SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 335.335.335.41. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dAXPY123816243240Min: 35.2 / Avg: 35.27 / Max: 35.3Min: 35.3 / Avg: 35.3 / Max: 35.3Min: 35.3 / Avg: 35.37 / Max: 35.41. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dCOPY123816243240SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 334.034.134.21. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dCOPY123714212835Min: 34 / Avg: 34.03 / Max: 34.1Min: 34.1 / Avg: 34.13 / Max: 34.2Min: 34.1 / Avg: 34.17 / Max: 34.21. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - sDOT231918273645SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.00, N = 337.637.637.71. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - sDOT231816243240Min: 37.6 / Avg: 37.63 / Max: 37.7Min: 37.6 / Avg: 37.63 / Max: 37.7Min: 37.7 / Avg: 37.7 / Max: 37.71. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - sAXPY123816243240SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 334.634.634.61. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - sAXPY123714212835Min: 34.6 / Avg: 34.6 / Max: 34.6Min: 34.6 / Avg: 34.6 / Max: 34.6Min: 34.6 / Avg: 34.6 / Max: 34.61. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - sCOPY123816243240SE +/- 0.06, N = 3SE +/- 0.10, N = 3SE +/- 0.06, N = 332.933.333.31. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - sCOPY123714212835Min: 32.8 / Avg: 32.9 / Max: 33Min: 33.1 / Avg: 33.3 / Max: 33.4Min: 33.2 / Avg: 33.3 / Max: 33.41. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

Zstd Compression

This test measures the time needed to compress/decompress a sample file (a FreeBSD disk image - FreeBSD-12.2-RELEASE-amd64-memstick.img) using Zstd compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 3 - Decompression Speed2319001800270036004500SE +/- 19.69, N = 3SE +/- 1.88, N = 3SE +/- 4.56, N = 34164.54180.34186.51. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 3 - Decompression Speed2317001400210028003500Min: 4125.2 / Avg: 4164.53 / Max: 4186Min: 4178 / Avg: 4180.27 / Max: 4184Min: 4177.7 / Avg: 4186.5 / Max: 41931. (CC) gcc options: -O3 -pthread -lz -llzma

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 3 - Compression Speed2135001000150020002500SE +/- 16.90, N = 3SE +/- 12.12, N = 3SE +/- 12.46, N = 32374.52379.42388.41. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 3 - Compression Speed213400800120016002000Min: 2340.7 / Avg: 2374.5 / Max: 2392Min: 2357.7 / Avg: 2379.37 / Max: 2399.6Min: 2363.5 / Avg: 2388.4 / Max: 2401.51. (CC) gcc options: -O3 -pthread -lz -llzma

Basis Universal

Basis Universal is a GPU texture codec. This test times how long it takes to convert sRGB PNGs into Basis Univeral assets with various settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.13Settings: UASTC Level 2132816243240SE +/- 0.02, N = 3SE +/- 0.12, N = 3SE +/- 0.10, N = 333.4633.3933.371. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.13Settings: UASTC Level 2132714212835Min: 33.42 / Avg: 33.46 / Max: 33.49Min: 33.14 / Avg: 33.39 / Max: 33.52Min: 33.17 / Avg: 33.37 / Max: 33.491. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread

Botan

Botan is a BSD-licensed cross-platform open-source C++ crypto library "cryptography toolkit" that supports most publicly known cryptographic algorithms. The project's stated goal is to be "the best option for cryptography in C++ by offering the tools necessary to implement a range of practical systems, such as TLS protocol, X.509 certificates, modern AEAD ciphers, PKCS#11 and TPM hardware support, password hashing, and post quantum crypto schemes." Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: AES-256 - Decrypt12310002000300040005000SE +/- 4.51, N = 3SE +/- 0.85, N = 3SE +/- 0.04, N = 34806.104811.184812.421. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: AES-256 - Decrypt1238001600240032004000Min: 4797.42 / Avg: 4806.1 / Max: 4812.55Min: 4809.49 / Avg: 4811.18 / Max: 4812.06Min: 4812.34 / Avg: 4812.42 / Max: 4812.481. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: AES-25623110002000300040005000SE +/- 0.54, N = 3SE +/- 0.22, N = 3SE +/- 0.17, N = 34814.834815.624815.971. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: AES-2562318001600240032004000Min: 4813.76 / Avg: 4814.83 / Max: 4815.42Min: 4815.22 / Avg: 4815.62 / Max: 4816Min: 4815.77 / Avg: 4815.97 / Max: 4816.31. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

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 4K1231122334455SE +/- 0.53, N = 15SE +/- 0.10, N = 3SE +/- 0.07, N = 347.7848.7248.781. (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 4K1231020304050Min: 44.39 / Avg: 47.78 / Max: 49.23Min: 48.6 / Avg: 48.72 / Max: 48.92Min: 48.67 / Avg: 48.78 / Max: 48.911. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

Botan

Botan is a BSD-licensed cross-platform open-source C++ crypto library "cryptography toolkit" that supports most publicly known cryptographic algorithms. The project's stated goal is to be "the best option for cryptography in C++ by offering the tools necessary to implement a range of practical systems, such as TLS protocol, X.509 certificates, modern AEAD ciphers, PKCS#11 and TPM hardware support, password hashing, and post quantum crypto schemes." Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: ChaCha20Poly1305 - Decrypt2132004006008001000SE +/- 0.82, N = 3SE +/- 0.56, N = 3SE +/- 0.54, N = 3907.95908.31908.471. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: ChaCha20Poly1305 - Decrypt213160320480640800Min: 906.36 / Avg: 907.95 / Max: 909.1Min: 907.19 / Avg: 908.31 / Max: 908.96Min: 907.39 / Avg: 908.47 / Max: 909.071. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: ChaCha20Poly13052312004006008001000SE +/- 3.02, N = 3SE +/- 1.80, N = 3SE +/- 0.12, N = 3913.03914.45916.111. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: ChaCha20Poly1305231160320480640800Min: 907.01 / Avg: 913.02 / Max: 916.47Min: 910.86 / Avg: 914.45 / Max: 916.31Min: 915.93 / Avg: 916.11 / Max: 916.341. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: Blowfish - Decrypt213120240360480600SE +/- 0.37, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 3539.02539.24539.341. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: Blowfish - Decrypt213100200300400500Min: 538.27 / Avg: 539.02 / Max: 539.4Min: 539.15 / Avg: 539.24 / Max: 539.28Min: 539.28 / Avg: 539.34 / Max: 539.391. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: Blowfish213120240360480600SE +/- 0.40, N = 3SE +/- 0.05, N = 3SE +/- 0.10, N = 3543.39543.60543.951. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: Blowfish213100200300400500Min: 542.58 / Avg: 543.39 / Max: 543.81Min: 543.51 / Avg: 543.6 / Max: 543.64Min: 543.81 / Avg: 543.95 / Max: 544.151. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: Twofish - Decrypt32190180270360450SE +/- 0.95, N = 3SE +/- 0.15, N = 3SE +/- 0.18, N = 3436.74437.29437.301. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: Twofish - Decrypt32180160240320400Min: 434.86 / Avg: 436.74 / Max: 437.79Min: 437.14 / Avg: 437.29 / Max: 437.59Min: 437.01 / Avg: 437.3 / Max: 437.631. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: Twofish31290180270360450SE +/- 1.83, N = 3SE +/- 0.16, N = 3SE +/- 0.12, N = 3434.66436.08436.121. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: Twofish31280160240320400Min: 431 / Avg: 434.66 / Max: 436.57Min: 435.89 / Avg: 436.08 / Max: 436.4Min: 436 / Avg: 436.12 / Max: 436.361. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: CAST-256 - Decrypt2134080120160200SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3172.08172.09172.151. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: CAST-256 - Decrypt213306090120150Min: 172.06 / Avg: 172.08 / Max: 172.09Min: 172.07 / Avg: 172.09 / Max: 172.11Min: 172.1 / Avg: 172.15 / Max: 172.211. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: CAST-2562134080120160200SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3171.95171.95171.961. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: CAST-256213306090120150Min: 171.95 / Avg: 171.95 / Max: 171.96Min: 171.93 / Avg: 171.95 / Max: 171.98Min: 171.95 / Avg: 171.96 / Max: 171.961. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: KASUMI - Decrypt21320406080100SE +/- 0.07, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 3107.76107.86107.881. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: KASUMI - Decrypt21320406080100Min: 107.66 / Avg: 107.76 / Max: 107.89Min: 107.8 / Avg: 107.86 / Max: 107.89Min: 107.81 / Avg: 107.88 / Max: 107.931. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: KASUMI213306090120150SE +/- 0.05, N = 3SE +/- 0.05, N = 3SE +/- 0.05, N = 3112.94112.98112.991. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: KASUMI21320406080100Min: 112.88 / Avg: 112.94 / Max: 113.04Min: 112.87 / Avg: 112.98 / Max: 113.04Min: 112.88 / Avg: 112.99 / Max: 113.041. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

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 6 Realtime - Input: Bosphorus 1080p213612182430SE +/- 0.29, N = 5SE +/- 0.24, N = 3SE +/- 0.22, N = 324.9525.0625.071. (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 1080p213612182430Min: 24.42 / Avg: 24.95 / Max: 26.08Min: 24.79 / Avg: 25.06 / Max: 25.53Min: 24.73 / Avg: 25.07 / Max: 25.481. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

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.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMM-TT123816243240SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 335.535.535.51. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMM-TT123816243240Min: 35.4 / Avg: 35.47 / Max: 35.5Min: 35.5 / Avg: 35.53 / Max: 35.6Min: 35.4 / Avg: 35.47 / Max: 35.51. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMM-TN213816243240SE +/- 0.07, N = 3SE +/- 0.03, N = 3SE +/- 0.00, N = 336.436.536.51. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMM-TN213816243240Min: 36.3 / Avg: 36.43 / Max: 36.5Min: 36.4 / Avg: 36.47 / Max: 36.5Min: 36.5 / Avg: 36.5 / Max: 36.51. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMM-NT132816243240SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.07, N = 334.134.134.21. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMM-NT132714212835Min: 34 / Avg: 34.07 / Max: 34.1Min: 34 / Avg: 34.07 / Max: 34.1Min: 34.1 / Avg: 34.23 / Max: 34.31. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMM-NN123816243240SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 334.834.834.81. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMM-NN123714212835Min: 34.8 / Avg: 34.8 / Max: 34.8Min: 34.8 / Avg: 34.8 / Max: 34.8Min: 34.8 / Avg: 34.83 / Max: 34.91. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMV-T1231122334455SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 346.546.546.51. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMV-T123918273645Min: 46.4 / Avg: 46.47 / Max: 46.5Min: 46.5 / Avg: 46.5 / Max: 46.5Min: 46.5 / Avg: 46.5 / Max: 46.51. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMV-N1321020304050SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 345.545.545.61. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMV-N132918273645Min: 45.5 / Avg: 45.5 / Max: 45.5Min: 45.5 / Avg: 45.53 / Max: 45.6Min: 45.5 / Avg: 45.57 / Max: 45.61. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dDOT1231020304050SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 344.144.144.11. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dDOT123918273645Min: 44 / Avg: 44.07 / Max: 44.1Min: 44.1 / Avg: 44.1 / Max: 44.1Min: 44.1 / Avg: 44.1 / Max: 44.11. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dAXPY123918273645SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 339.339.339.31. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dAXPY123816243240Min: 39.3 / Avg: 39.3 / Max: 39.3Min: 39.3 / Avg: 39.3 / Max: 39.3Min: 39.3 / Avg: 39.3 / Max: 39.31. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dCOPY123612182430SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 326.226.226.21. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dCOPY123612182430Min: 26.1 / Avg: 26.17 / Max: 26.2Min: 26.2 / Avg: 26.2 / Max: 26.2Min: 26.2 / Avg: 26.2 / Max: 26.21. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - sDOT1231122334455SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 347.947.947.91. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - sDOT1231020304050Min: 47.8 / Avg: 47.9 / Max: 48Min: 47.9 / Avg: 47.93 / Max: 48Min: 47.9 / Avg: 47.93 / Max: 481. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - sAXPY1321020304050SE +/- 0.03, N = 3SE +/- 0.09, N = 3SE +/- 0.07, N = 342.842.842.91. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - sAXPY132918273645Min: 42.8 / Avg: 42.83 / Max: 42.9Min: 42.7 / Avg: 42.83 / Max: 43Min: 42.8 / Avg: 42.87 / Max: 431. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - sCOPY123714212835SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 328.228.228.31. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - sCOPY123612182430Min: 28.2 / Avg: 28.23 / Max: 28.3Min: 28.2 / Avg: 28.23 / Max: 28.3Min: 28.2 / Avg: 28.27 / Max: 28.31. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

Basis Universal

Basis Universal is a GPU texture codec. This test times how long it takes to convert sRGB PNGs into Basis Univeral assets with various settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.13Settings: ETC1S123612182430SE +/- 0.03, N = 3SE +/- 0.08, N = 3SE +/- 0.05, N = 323.4623.3923.371. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.13Settings: ETC1S123510152025Min: 23.41 / Avg: 23.46 / Max: 23.5Min: 23.25 / Avg: 23.39 / Max: 23.52Min: 23.31 / Avg: 23.37 / Max: 23.461. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread

SHOC Scalable HeterOgeneous Computing

The CUDA and OpenCL version of Vetter's Scalable HeterOgeneous Computing benchmark suite. SHOC provides a number of different benchmark programs for evaluating the performance and stability of compute devices. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: GEMM SGEMM_N32150100150200250SE +/- 0.06, N = 3SE +/- 0.06, N = 3SE +/- 0.06, N = 3245.78245.89245.921. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi
OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: GEMM SGEMM_N3214080120160200Min: 245.71 / Avg: 245.78 / Max: 245.91Min: 245.79 / Avg: 245.89 / Max: 245.99Min: 245.8 / Avg: 245.92 / Max: 2461. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -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: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU321246810SE +/- 0.00592, N = 3SE +/- 0.01330, N = 3SE +/- 0.00652, N = 38.876188.865018.83898MIN: 4.77MIN: 4.67MIN: 4.681. (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: CPU3213691215Min: 8.87 / Avg: 8.88 / Max: 8.89Min: 8.84 / Avg: 8.87 / Max: 8.88Min: 8.83 / Avg: 8.84 / Max: 8.851. (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: CPU1320.48260.96521.44781.93042.413SE +/- 0.00353, N = 3SE +/- 0.00152, N = 3SE +/- 0.00224, N = 32.144902.144522.14385MIN: 1.94MIN: 1.97MIN: 1.971. (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: CPU132246810Min: 2.14 / Avg: 2.14 / Max: 2.15Min: 2.14 / Avg: 2.14 / Max: 2.15Min: 2.14 / Avg: 2.14 / Max: 2.151. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

dav1d

Dav1d is an open-source, speedy AV1 video decoder. This test profile times how long it takes to decode sample AV1 video content. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is Betterdav1d 0.8.2Video Input: Summer Nature 4K3214080120160200SE +/- 0.19, N = 3SE +/- 0.13, N = 3SE +/- 0.14, N = 3184.16184.25185.13MIN: 173.76 / MAX: 209.16MIN: 173.91 / MAX: 209.75MIN: 174.56 / MAX: 210.521. (CC) gcc options: -pthread -lm
OpenBenchmarking.orgFPS, More Is Betterdav1d 0.8.2Video Input: Summer Nature 4K321306090120150Min: 183.94 / Avg: 184.16 / Max: 184.54Min: 183.99 / Avg: 184.25 / Max: 184.39Min: 184.87 / Avg: 185.13 / Max: 185.351. (CC) gcc options: -pthread -lm

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: 4 - Buffer Length: 256 - Filter Length: 5713250M100M150M200M250MSE +/- 265476.51, N = 3SE +/- 321679.62, N = 3SE +/- 375470.08, N = 32508566672514733332515766671. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 4 - Buffer Length: 256 - Filter Length: 5713240M80M120M160M200MMin: 250440000 / Avg: 250856666.67 / Max: 251350000Min: 250830000 / Avg: 251473333.33 / Max: 251800000Min: 251070000 / Avg: 251576666.67 / Max: 2523100001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 2 - Buffer Length: 256 - Filter Length: 5721330M60M90M120M150MSE +/- 367891.89, N = 3SE +/- 40551.75, N = 3SE +/- 35276.68, N = 31300466671301833331306633331. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 2 - Buffer Length: 256 - Filter Length: 5721320M40M60M80M100MMin: 129320000 / Avg: 130046666.67 / Max: 130510000Min: 130110000 / Avg: 130183333.33 / Max: 130250000Min: 130610000 / Avg: 130663333.33 / Max: 1307300001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 1 - Buffer Length: 256 - Filter Length: 5731214M28M42M56M70MSE +/- 27834.83, N = 3SE +/- 881.92, N = 3SE +/- 1763.83, N = 36759966767629667676323331. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 1 - Buffer Length: 256 - Filter Length: 5731212M24M36M48M60MMin: 67544000 / Avg: 67599666.67 / Max: 67628000Min: 67628000 / Avg: 67629666.67 / Max: 67631000Min: 67629000 / Avg: 67632333.33 / Max: 676350001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 16 - Buffer Length: 256 - Filter Length: 57321110M220M330M440M550MSE +/- 199360.09, N = 3SE +/- 188355.46, N = 3SE +/- 324054.18, N = 35000166675002633335003333331. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 16 - Buffer Length: 256 - Filter Length: 5732190M180M270M360M450MMin: 499680000 / Avg: 500016666.67 / Max: 500370000Min: 500070000 / Avg: 500263333.33 / Max: 500640000Min: 499730000 / Avg: 500333333.33 / Max: 5008400001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 8 - Buffer Length: 256 - Filter Length: 57213100M200M300M400M500MSE +/- 514274.03, N = 3SE +/- 1523508.38, N = 3SE +/- 2209451.92, N = 34520733334527133334530866671. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 8 - Buffer Length: 256 - Filter Length: 5721380M160M240M320M400MMin: 451130000 / Avg: 452073333.33 / Max: 452900000Min: 451150000 / Avg: 452713333.33 / Max: 455760000Min: 450300000 / Avg: 453086666.67 / Max: 4574500001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

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: Thorough13248121620SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 314.9214.9114.911. (CXX) g++ options: -O3 -flto -pthread
OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.4Preset: Thorough13248121620Min: 14.9 / Avg: 14.92 / Max: 14.94Min: 14.88 / Avg: 14.91 / Max: 14.93Min: 14.86 / Avg: 14.91 / Max: 14.941. (CXX) g++ options: -O3 -flto -pthread

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 8 Realtime - Input: Bosphorus 4K321918273645SE +/- 0.51, N = 4SE +/- 0.08, N = 3SE +/- 0.05, N = 337.1237.9438.681. (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 4K321816243240Min: 35.61 / Avg: 37.12 / Max: 37.8Min: 37.81 / Avg: 37.94 / Max: 38.07Min: 38.59 / Avg: 38.68 / Max: 38.761. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

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: Retro Car32148121620SE +/- 0.02, N = 3SE +/- 0.10, N = 3SE +/- 0.02, N = 317.3717.3517.261. OpenSCAD version 2019.05
OpenBenchmarking.orgSeconds, Fewer Is BetterOpenSCADRender: Retro Car32148121620Min: 17.33 / Avg: 17.37 / Max: 17.39Min: 17.24 / Avg: 17.35 / Max: 17.55Min: 17.23 / Avg: 17.26 / Max: 17.311. OpenSCAD version 2019.05

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenSCADRender: Leonardo Phone Case Slim31248121620SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 317.0516.9816.941. OpenSCAD version 2019.05
OpenBenchmarking.orgSeconds, Fewer Is BetterOpenSCADRender: Leonardo Phone Case Slim31248121620Min: 17.04 / Avg: 17.05 / Max: 17.08Min: 16.96 / Avg: 16.98 / Max: 17Min: 16.91 / Avg: 16.94 / Max: 16.981. OpenSCAD version 2019.05

dav1d

Dav1d is an open-source, speedy AV1 video decoder. This test profile times how long it takes to decode sample AV1 video content. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is Betterdav1d 0.8.2Video Input: Chimera 1080p231160320480640800SE +/- 2.01, N = 3SE +/- 0.90, N = 3SE +/- 1.00, N = 3731.76732.83733.64MIN: 538.01 / MAX: 1138.02MIN: 537.85 / MAX: 1141.98MIN: 538.11 / MAX: 1144.181. (CC) gcc options: -pthread -lm
OpenBenchmarking.orgFPS, More Is Betterdav1d 0.8.2Video Input: Chimera 1080p231130260390520650Min: 729.06 / Avg: 731.76 / Max: 735.69Min: 731.12 / Avg: 732.83 / Max: 734.17Min: 731.86 / Avg: 733.64 / Max: 735.311. (CC) gcc options: -pthread -lm

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU1230.80491.60982.41473.21964.0245SE +/- 0.01205, N = 3SE +/- 0.00753, N = 3SE +/- 0.00251, N = 33.577403.574553.56577MIN: 3.23MIN: 3.24MIN: 3.261. (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: CPU123246810Min: 3.56 / Avg: 3.58 / Max: 3.6Min: 3.56 / Avg: 3.57 / Max: 3.59Min: 3.56 / Avg: 3.57 / Max: 3.571. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU1230.37520.75041.12561.50081.876SE +/- 0.00165, N = 3SE +/- 0.00242, N = 3SE +/- 0.00123, N = 31.667471.665791.66550MIN: 1.51MIN: 1.51MIN: 1.511. (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: CPU123246810Min: 1.66 / Avg: 1.67 / Max: 1.67Min: 1.66 / Avg: 1.67 / Max: 1.67Min: 1.66 / Avg: 1.67 / Max: 1.671. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

libavif avifenc

This is a test of the AOMedia libavif library testing the encoding of a JPEG image to AV1 Image Format (AVIF). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.9.0Encoder Speed: 62313691215SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 313.0112.9612.951. (CXX) g++ options: -O3 -fPIC -lm
OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.9.0Encoder Speed: 623148121620Min: 12.92 / Avg: 13 / Max: 13.07Min: 12.94 / Avg: 12.96 / Max: 12.98Min: 12.89 / Avg: 12.95 / Max: 131. (CXX) g++ options: -O3 -fPIC -lm

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU1230.70971.41942.12912.83883.5485SE +/- 0.00701, N = 3SE +/- 0.00442, N = 3SE +/- 0.00951, N = 33.154333.151573.14943MIN: 3.1MIN: 3.1MIN: 3.091. (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: CPU123246810Min: 3.14 / Avg: 3.15 / Max: 3.16Min: 3.14 / Avg: 3.15 / Max: 3.16Min: 3.13 / Avg: 3.15 / Max: 3.161. (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: CPU1320.7741.5482.3223.0963.87SE +/- 0.00410, N = 3SE +/- 0.00188, N = 3SE +/- 0.00274, N = 33.440033.439143.43359MIN: 3.15MIN: 3.18MIN: 3.171. (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: CPU132246810Min: 3.43 / Avg: 3.44 / Max: 3.45Min: 3.44 / Avg: 3.44 / Max: 3.44Min: 3.43 / Avg: 3.43 / Max: 3.441. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

SHOC Scalable HeterOgeneous Computing

The CUDA and OpenCL version of Vetter's Scalable HeterOgeneous Computing benchmark suite. SHOC provides a number of different benchmark programs for evaluating the performance and stability of compute devices. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Reduction231816243240SE +/- 0.07, N = 3SE +/- 0.03, N = 3SE +/- 0.05, N = 336.7336.7636.791. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi
OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Reduction231816243240Min: 36.62 / Avg: 36.73 / Max: 36.86Min: 36.71 / Avg: 36.76 / Max: 36.81Min: 36.71 / Avg: 36.79 / Max: 36.881. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

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 8 Realtime - Input: Bosphorus 1080p321306090120150SE +/- 1.32, N = 12SE +/- 1.89, N = 3SE +/- 0.42, N = 3121.96122.64124.391. (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 1080p32120406080100Min: 108.28 / Avg: 121.96 / Max: 125.56Min: 118.85 / Avg: 122.64 / Max: 124.65Min: 123.58 / Avg: 124.39 / Max: 124.981. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

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: IP Shapes 3D - Data Type: f32 - Engine: CPU132246810SE +/- 0.00549, N = 3SE +/- 0.01559, N = 3SE +/- 0.00679, N = 38.261038.167888.14695MIN: 8.14MIN: 8.03MIN: 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 3D - Data Type: f32 - Engine: CPU1323691215Min: 8.25 / Avg: 8.26 / Max: 8.27Min: 8.14 / Avg: 8.17 / Max: 8.19Min: 8.13 / Avg: 8.15 / Max: 8.161. (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: CPU1230.41220.82441.23661.64882.061SE +/- 0.00346, N = 3SE +/- 0.00543, N = 3SE +/- 0.00185, N = 31.832151.829101.82340MIN: 1.79MIN: 1.78MIN: 1.781. (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: CPU123246810Min: 1.83 / Avg: 1.83 / Max: 1.84Min: 1.82 / Avg: 1.83 / Max: 1.84Min: 1.82 / Avg: 1.82 / Max: 1.831. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

Basis Universal

Basis Universal is a GPU texture codec. This test times how long it takes to convert sRGB PNGs into Basis Univeral assets with various settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.13Settings: UASTC Level 0123246810SE +/- 0.000, N = 3SE +/- 0.003, N = 3SE +/- 0.005, N = 37.1727.0917.0891. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.13Settings: UASTC Level 01233691215Min: 7.17 / Avg: 7.17 / Max: 7.17Min: 7.09 / Avg: 7.09 / Max: 7.1Min: 7.08 / Avg: 7.09 / Max: 7.11. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread

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 1080p321306090120150SE +/- 2.02, N = 4SE +/- 0.46, N = 3SE +/- 1.63, N = 6139.82140.39141.481. (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 1080p321306090120150Min: 135.94 / Avg: 139.82 / Max: 145.36Min: 139.48 / Avg: 140.39 / Max: 140.87Min: 135.56 / Avg: 141.48 / Max: 146.41. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

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: CPU23148121620SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 314.3014.2914.28MIN: 14.2MIN: 14.2MIN: 14.21. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU23148121620Min: 14.27 / Avg: 14.3 / Max: 14.37Min: 14.27 / Avg: 14.29 / Max: 14.33Min: 14.26 / Avg: 14.28 / Max: 14.321. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU13248121620SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 314.0314.0114.00MIN: 13.92MIN: 13.88MIN: 13.91. (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: CPU13248121620Min: 14.01 / Avg: 14.03 / Max: 14.09Min: 13.98 / Avg: 14.01 / Max: 14.06Min: 13.98 / Avg: 14 / Max: 14.021. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

SHOC Scalable HeterOgeneous Computing

The CUDA and OpenCL version of Vetter's Scalable HeterOgeneous Computing benchmark suite. SHOC provides a number of different benchmark programs for evaluating the performance and stability of compute devices. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: FFT SP31248121620SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 315.3615.3715.381. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi
OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: FFT SP31248121620Min: 15.34 / Avg: 15.36 / Max: 15.38Min: 15.36 / Avg: 15.37 / Max: 15.38Min: 15.36 / Avg: 15.38 / Max: 15.391. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

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: 7 - Input: Bosphorus 1080p32120406080100SE +/- 0.10, N = 3SE +/- 0.06, N = 3SE +/- 0.13, N = 3105.78105.90106.191. (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 1080p32120406080100Min: 105.58 / Avg: 105.78 / Max: 105.91Min: 105.78 / Avg: 105.9 / Max: 105.99Min: 106.04 / Avg: 106.19 / Max: 106.461. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

dav1d

Dav1d is an open-source, speedy AV1 video decoder. This test profile times how long it takes to decode sample AV1 video content. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is Betterdav1d 0.8.2Video Input: Summer Nature 1080p312140280420560700SE +/- 0.54, N = 3SE +/- 1.42, N = 3SE +/- 0.67, N = 3647.63648.26649.67MIN: 582.84 / MAX: 717.06MIN: 589.55 / MAX: 721.08MIN: 588.3 / MAX: 717.461. (CC) gcc options: -pthread -lm
OpenBenchmarking.orgFPS, More Is Betterdav1d 0.8.2Video Input: Summer Nature 1080p312110220330440550Min: 646.71 / Avg: 647.63 / Max: 648.59Min: 645.44 / Avg: 648.26 / Max: 649.92Min: 648.54 / Avg: 649.67 / Max: 650.851. (CC) gcc options: -pthread -lm

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: Medium1231.30392.60783.91175.21566.5195SE +/- 0.0231, N = 3SE +/- 0.0051, N = 3SE +/- 0.0062, N = 35.79495.77575.77371. (CXX) g++ options: -O3 -flto -pthread
OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.4Preset: Medium123246810Min: 5.77 / Avg: 5.79 / Max: 5.84Min: 5.77 / Avg: 5.78 / Max: 5.78Min: 5.76 / Avg: 5.77 / Max: 5.791. (CXX) g++ options: -O3 -flto -pthread

libavif avifenc

This is a test of the AOMedia libavif library testing the encoding of a JPEG image to AV1 Image Format (AVIF). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.9.0Encoder Speed: 10, Lossless3121.30212.60423.90635.20846.5105SE +/- 0.012, N = 3SE +/- 0.013, N = 3SE +/- 0.013, N = 35.7875.7785.7711. (CXX) g++ options: -O3 -fPIC -lm
OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.9.0Encoder Speed: 10, Lossless312246810Min: 5.77 / Avg: 5.79 / Max: 5.81Min: 5.76 / Avg: 5.78 / Max: 5.8Min: 5.75 / Avg: 5.77 / Max: 5.791. (CXX) g++ options: -O3 -fPIC -lm

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 1080p321306090120150SE +/- 0.35, N = 3SE +/- 0.13, N = 3SE +/- 0.26, N = 3136.05136.22136.761. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: Visual Quality Optimized - Input: Bosphorus 1080p321306090120150Min: 135.37 / Avg: 136.05 / Max: 136.51Min: 135.97 / Avg: 136.22 / Max: 136.39Min: 136.33 / Avg: 136.76 / Max: 137.241. (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 1080p3214080120160200SE +/- 0.26, N = 3SE +/- 0.43, N = 3SE +/- 0.19, N = 3172.10172.24173.311. (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 1080p321306090120150Min: 171.6 / Avg: 172.1 / Max: 172.48Min: 171.53 / Avg: 172.24 / Max: 173Min: 173.03 / Avg: 173.31 / Max: 173.671. (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 1080p3214080120160200SE +/- 0.09, N = 3SE +/- 0.47, N = 3SE +/- 0.31, N = 3175.06175.27176.291. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080p321306090120150Min: 174.89 / Avg: 175.06 / Max: 175.18Min: 174.41 / Avg: 175.27 / Max: 176.04Min: 175.74 / Avg: 176.29 / Max: 176.811. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

Sysbench

This is a benchmark of Sysbench with the built-in CPU and memory sub-tests. Sysbench is a scriptable multi-threaded benchmark tool based on LuaJIT. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/sec, More Is BetterSysbench 1.0.20Test: RAM / Memory3126K12K18K24K30KSE +/- 41.95, N = 3SE +/- 98.12, N = 3SE +/- 138.44, N = 328338.5928391.4728491.741. (CC) gcc options: -pthread -O2 -funroll-loops -rdynamic -ldl -laio -lm
OpenBenchmarking.orgMiB/sec, More Is BetterSysbench 1.0.20Test: RAM / Memory3125K10K15K20K25KMin: 28274.42 / Avg: 28338.59 / Max: 28417.47Min: 28212.81 / Avg: 28391.47 / Max: 28551.12Min: 28263.5 / Avg: 28491.74 / Max: 28741.61. (CC) gcc options: -pthread -O2 -funroll-loops -rdynamic -ldl -laio -lm

libavif avifenc

This is a test of the AOMedia libavif library testing the encoding of a JPEG image to AV1 Image Format (AVIF). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.9.0Encoder Speed: 103210.71331.42662.13992.85323.5665SE +/- 0.012, N = 3SE +/- 0.010, N = 3SE +/- 0.004, N = 33.1703.1603.1541. (CXX) g++ options: -O3 -fPIC -lm
OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.9.0Encoder Speed: 10321246810Min: 3.16 / Avg: 3.17 / Max: 3.19Min: 3.15 / Avg: 3.16 / Max: 3.18Min: 3.15 / Avg: 3.15 / Max: 3.161. (CXX) g++ options: -O3 -fPIC -lm

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU213246810SE +/- 0.01698, N = 3SE +/- 0.00984, N = 3SE +/- 0.00264, N = 36.646596.639936.61557MIN: 6MIN: 6MIN: 5.991. (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: CPU2133691215Min: 6.62 / Avg: 6.65 / Max: 6.68Min: 6.62 / Avg: 6.64 / Max: 6.66Min: 6.61 / Avg: 6.62 / Max: 6.621. (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: CPU1320.89481.78962.68443.57924.474SE +/- 0.02149, N = 3SE +/- 0.01771, N = 3SE +/- 0.01212, N = 33.977063.932163.93198MIN: 3.65MIN: 3.62MIN: 3.641. (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: CPU132246810Min: 3.94 / Avg: 3.98 / Max: 4.01Min: 3.9 / Avg: 3.93 / Max: 3.96Min: 3.91 / Avg: 3.93 / Max: 3.951. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

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: 10 - Input: Bosphorus 1080p32150100150200250SE +/- 0.43, N = 3SE +/- 0.19, N = 3SE +/- 0.11, N = 3229.36229.42230.271. (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 1080p3214080120160200Min: 228.57 / Avg: 229.36 / Max: 230.06Min: 229.18 / Avg: 229.42 / Max: 229.8Min: 230.06 / Avg: 230.27 / Max: 230.411. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

SHOC Scalable HeterOgeneous Computing

The CUDA and OpenCL version of Vetter's Scalable HeterOgeneous Computing benchmark suite. SHOC provides a number of different benchmark programs for evaluating the performance and stability of compute devices. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Triad23148121620SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 315.2315.2515.611. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi
OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Triad23148121620Min: 15.21 / Avg: 15.23 / Max: 15.25Min: 15.19 / Avg: 15.25 / Max: 15.29Min: 15.55 / Avg: 15.61 / Max: 15.651. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Bus Speed Readback123714212835SE +/- 0.22, N = 3SE +/- 0.10, N = 3SE +/- 0.20, N = 329.0529.0529.151. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi
OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Bus Speed Readback123612182430Min: 28.76 / Avg: 29.05 / Max: 29.48Min: 28.94 / Avg: 29.05 / Max: 29.25Min: 28.83 / Avg: 29.15 / Max: 29.521. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Bus Speed Download231714212835SE +/- 0.05, N = 3SE +/- 0.16, N = 3SE +/- 0.10, N = 329.1629.1829.211. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi
OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Bus Speed Download231612182430Min: 29.06 / Avg: 29.16 / Max: 29.23Min: 28.89 / Avg: 29.18 / Max: 29.44Min: 29.03 / Avg: 29.21 / Max: 29.391. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

Systemd Total Boot Time

This test uses systemd-analyze to report the entire boot time. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterSystemd Total Boot TimeTest: Userspace3215K10K15K20K25K221092210922109

OpenBenchmarking.orgms, Fewer Is BetterSystemd Total Boot TimeTest: Firmware3213K6K9K12K15K156791567915679

OpenBenchmarking.orgms, Fewer Is BetterSystemd Total Boot TimeTest: Loader3218001600240032004000355535553555

OpenBenchmarking.orgms, Fewer Is BetterSystemd Total Boot TimeTest: Kernel321400800120016002000194119411941

OpenBenchmarking.orgms, Fewer Is BetterSystemd Total Boot TimeTest: Total3215K10K15K20K25K240502405024050

162 Results Shown

Timed Node.js Compilation
GNU Radio:
  Hilbert Transform
  FM Deemphasis Filter
  IIR Filter
  FIR Filter
  Signal Source (Cosine)
  Five Back to Back FIR Filters
LuaRadio:
  Complex Phase
  Hilbert Transform
  FM Deemphasis Filter
  Five Back to Back FIR Filters
AOM AV1
SHOC Scalable HeterOgeneous Computing
AOM AV1
GNU GMP GMPbench
AOM AV1
Xcompact3d Incompact3d
ASTC Encoder
Timed Erlang/OTP Compilation
OpenSCAD
AOM AV1
Timed Linux Kernel Compilation
OpenSCAD
Sysbench
SVT-HEVC
dav1d
SHOC Scalable HeterOgeneous Computing
oneDNN:
  Recurrent Neural Network Training - bf16bf16bf16 - CPU
  Recurrent Neural Network Training - u8s8f32 - CPU
  Recurrent Neural Network Training - f32 - CPU
SHOC Scalable HeterOgeneous Computing
oneDNN:
  Recurrent Neural Network Inference - bf16bf16bf16 - CPU
  Recurrent Neural Network Inference - f32 - CPU
  Recurrent Neural Network Inference - u8s8f32 - CPU
Mobile Neural Network:
  inception-v3
  mobilenet-v1-1.0
  MobileNetV2_224
  resnet-v2-50
  SqueezeNetV1.0
libavif avifenc
simdjson:
  DistinctUserID
  PartialTweets
Basis Universal
libavif avifenc
simdjson
Timed Mesa Compilation
AOM AV1
Zstd Compression:
  19, Long Mode - Decompression Speed
  19, Long Mode - Compression Speed
simdjson
Zstd Compression:
  19 - Decompression Speed
  19 - Compression Speed
AOM AV1
toyBrot Fractal Generator:
  C++ Threads
  C++ Tasks
  TBB
SHOC Scalable HeterOgeneous Computing
toyBrot Fractal Generator
OpenSCAD
Stockfish
srsLTE:
  PHY_DL_Test:
    UE Mb/s
    eNb Mb/s
AOM AV1
libavif avifenc
srsLTE
Zstd Compression:
  8 - Decompression Speed
  8 - Compression Speed
  8, Long Mode - Decompression Speed
  8, Long Mode - Compression Speed
Xcompact3d Incompact3d
Zstd Compression:
  3, Long Mode - Decompression Speed
  3, Long Mode - Compression Speed
ViennaCL:
  OpenCL BLAS - dGEMM-TT
  OpenCL BLAS - dGEMM-TN
  OpenCL BLAS - dGEMM-NT
  OpenCL BLAS - dGEMM-NN
  OpenCL BLAS - dGEMV-T
  OpenCL BLAS - dGEMV-N
  OpenCL BLAS - dDOT
  OpenCL BLAS - dAXPY
  OpenCL BLAS - dCOPY
  OpenCL BLAS - sDOT
  OpenCL BLAS - sAXPY
  OpenCL BLAS - sCOPY
Zstd Compression:
  3 - Decompression Speed
  3 - Compression Speed
Basis Universal
Botan:
  AES-256 - Decrypt
  AES-256
AOM AV1
Botan:
  ChaCha20Poly1305 - Decrypt
  ChaCha20Poly1305
  Blowfish - Decrypt
  Blowfish
  Twofish - Decrypt
  Twofish
  CAST-256 - Decrypt
  CAST-256
  KASUMI - Decrypt
  KASUMI
AOM AV1
ViennaCL:
  CPU BLAS - dGEMM-TT
  CPU BLAS - dGEMM-TN
  CPU BLAS - dGEMM-NT
  CPU BLAS - dGEMM-NN
  CPU BLAS - dGEMV-T
  CPU BLAS - dGEMV-N
  CPU BLAS - dDOT
  CPU BLAS - dAXPY
  CPU BLAS - dCOPY
  CPU BLAS - sDOT
  CPU BLAS - sAXPY
  CPU BLAS - sCOPY
Basis Universal
SHOC Scalable HeterOgeneous Computing
oneDNN:
  Deconvolution Batch shapes_1d - f32 - CPU
  Deconvolution Batch shapes_1d - u8s8f32 - CPU
dav1d
Liquid-DSP:
  4 - 256 - 57
  2 - 256 - 57
  1 - 256 - 57
  16 - 256 - 57
  8 - 256 - 57
ASTC Encoder
AOM AV1
OpenSCAD:
  Retro Car
  Leonardo Phone Case Slim
dav1d
oneDNN:
  IP Shapes 1D - f32 - CPU
  IP Shapes 1D - u8s8f32 - CPU
libavif avifenc
oneDNN:
  Matrix Multiply Batch Shapes Transformer - f32 - CPU
  Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPU
SHOC Scalable HeterOgeneous Computing
AOM AV1
oneDNN:
  IP Shapes 3D - f32 - CPU
  IP Shapes 3D - u8s8f32 - CPU
Basis Universal
AOM AV1
oneDNN:
  Convolution Batch Shapes Auto - f32 - CPU
  Convolution Batch Shapes Auto - u8s8f32 - CPU
SHOC Scalable HeterOgeneous Computing
SVT-HEVC
dav1d
ASTC Encoder
libavif avifenc
SVT-VP9:
  Visual Quality Optimized - Bosphorus 1080p
  VMAF Optimized - Bosphorus 1080p
  PSNR/SSIM Optimized - Bosphorus 1080p
Sysbench
libavif avifenc
oneDNN:
  Deconvolution Batch shapes_3d - f32 - CPU
  Deconvolution Batch shapes_3d - u8s8f32 - CPU
SVT-HEVC
SHOC Scalable HeterOgeneous Computing:
  OpenCL - Triad
  OpenCL - Bus Speed Readback
  OpenCL - Bus Speed Download
Systemd Total Boot Time:
  Userspace
  Firmware
  Loader
  Kernel
  Total