apple m2 compilers

Apple M2 compiler benchmarks for a future article by Michael Larabel.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2208168-NE-APPLEM2CO23
Jump To Table - Results

View

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

Limit displaying results to tests within:

Audio Encoding 4 Tests
AV1 2 Tests
Bioinformatics 2 Tests
C/C++ Compiler Tests 16 Tests
CPU Massive 15 Tests
Creator Workloads 18 Tests
Cryptography 6 Tests
Encoding 6 Tests
Game Development 3 Tests
HPC - High Performance Computing 5 Tests
Imaging 4 Tests
Common Kernel Benchmarks 2 Tests
Machine Learning 2 Tests
MPI Benchmarks 2 Tests
Multi-Core 10 Tests
OpenMPI Tests 2 Tests
Programmer / Developer System Benchmarks 3 Tests
Raytracing 2 Tests
Renderers 3 Tests
Scientific Computing 3 Tests
Server 3 Tests
Server CPU Tests 7 Tests
Single-Threaded 8 Tests
Texture Compression 2 Tests
Video Encoding 2 Tests

Statistics

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

Graph Settings

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

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs
Condense Test Profiles With Multiple Version Results Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
Clang
August 14 2022
  22 Hours, 41 Minutes
GCC
August 15 2022
  11 Hours, 28 Minutes
Invert Hiding All Results Option
  17 Hours, 4 Minutes
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):


apple m2 compilersOpenBenchmarking.orgPhoronix Test SuiteApple M2 @ 2.42GHz (4 Cores / 8 Threads)Apple MacBook Air (13 h M2 2022)8GB251GB APPLE SSD AP0256Z + 2 x 0GB APPLE SSD AP0256ZllvmpipeBroadcom Device 4433 + Broadcom Device 5f71Arch rolling5.19.0-rc7-asahi-2-1-ARCH (aarch64)KDE Plasma 5.25.4X Server 1.21.1.44.5 Mesa 22.1.6 (LLVM 14.0.6 128 bits)Clang 14.0.6GCC 12.1.0 + Clang 14.0.6ext42560x1600ProcessorMotherboardMemoryDiskGraphicsNetworkOSKernelDesktopDisplay ServerOpenGLCompilersFile-SystemScreen ResolutionApple M2 Compilers PerformanceSystem Logs- CFLAGS=-O3- Scaling Governor: apple-cpufreq schedutil- Python 3.10.5- itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Not affected + srbds: Not affected + tsx_async_abort: Not affected - GCC: --build=aarch64-unknown-linux-gnu --disable-libssp --disable-libstdcxx-pch --disable-multilib --disable-werror --enable-__cxa_atexit --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-default-ssp --enable-fix-cortex-a53-835769 --enable-fix-cortex-a53-843419 --enable-gnu-indirect-function --enable-gnu-unique-object --enable-languages=c,c++,fortran,go,lto,objc,obj-c++ --enable-lto --enable-plugin --enable-shared --enable-threads=posix --host=aarch64-unknown-linux-gnu --mandir=/usr/share/man --with-arch=armv8-a --with-linker-hash-style=gnu

Clang vs. GCC ComparisonPhoronix Test SuiteBaseline+29.2%+29.2%+58.4%+58.4%+87.6%+87.6%116.6%96.6%96%88.4%71.5%70.6%64%63.8%63%62.8%60.7%57.9%57.7%54.8%47.7%46.2%43.3%41.7%39.5%39.1%37.6%35.5%33.4%30.3%25.9%22.6%20.9%19.9%14.8%14.5%13.9%13.8%13.7%12.8%12.8%12.4%11.5%10.3%10%9.6%9.6%9.1%9%8.6%8.4%6.8%6.2%5.2%5.2%5%4.3%4%3.7%3.6%3.5%3.5%3.3%3%2.6%2.6%2.1%CPU - FastestDetCPU - regnety_400mCPU - regnety_400mCPU - resnet50CPU - efficientnet-b0PNG - 571.2%CPU - efficientnet-b0Unkeyed AlgorithmsCPU-v2-v2 - mobilenet-v2CPU - shufflenet-v2CPU - mnasnetCPU-v3-v3 - mobilenet-v3CPU - shufflenet-v2CPU-v2-v2 - mobilenet-v2CPU - mnasnetCPU-v3-v3 - mobilenet-v3Keyed AlgorithmsHWB Color SpaceCPU - DenseNetCPU - yolov4-tinyCPU - MobileNet v2CPU - yolov4-tinyNoise-GaussianD.L.M.F34.8%PNG - 734.2%WAV To MP3CPU - squeezenet_ssdC267030.1%CPU - resnet1827.3%2 - 256 - 5727%1 - 256 - 5726.9%4 - 256 - 5726.7%CPU - mobilenetP.P.A24.8%CPU - blazefaceTotal Time - 4.1.R.P.PT.T.S.SCPU - resnet1819.3%C755217.8%CPU - googlenet17.5%Composite17%19 - D.S2048 x 2048 - Total TimeCPU - googlenet14.1%CPU - squeezenet_ssd13.9%CPU - vgg1613.9%8 - 256 - 5713.9%3 - D.SCoreMark Size 666 - I.P.SResizing13.7%8 - D.SJPEG - 512.9%8, Long Mode - D.S3, Long Mode - D.SJPEG - 712.6%F.F.TWAV To FLACP.P.S11.4%KASUMI11.3%I.E.C.P.K.A11%EnhancedCPU - blazeface19, Long Mode - D.SSummer Nature 4KKASUMI - Decrypt9.2%S.M.M9.1%UASTC Level 0CPU - mobilenetCPU - vision_transformerETC1SCPU - alexnet8.3%Monero - 1M8.2%ThroughputCPU - SqueezeNet v2DistinctUserID6.2%SHA2566.1%Wownero - 1M5.3%C.1.1.b5.2%SharpenUASTC Level 2Blowfish5.1%CPU - vgg16CPU - alexnet5%Blowfish - Decrypt5%19, Long Mode - Compression SpeedTopTweet4.2%ChaCha20Poly1305 - Decrypt4.2%PartialTweets4.1%LargeRandRhodopsin Protein3.8%D.TChaCha20Poly13053.7%8, Long Mode - Compression SpeedSwirlChimera 1080p3.5%19 - Compression Speed1e12Monte CarloTwofish2.9%Trace Time2.8%3, Long Mode - Compression Speed2.6%CPU - SqueezeNet v1.1WAV To Opus EncodeWAV To WavPack2.5%CPU - resnet50NCNNNCNNNCNNNCNNNCNNJPEG XL libjxlNCNNCrypto++NCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNCrypto++GraphicsMagickTNNNCNNTNNNCNNGraphicsMagickSciMarkJPEG XL libjxlLAME MP3 EncodingNCNNNgspiceNCNNLiquid-DSPLiquid-DSPLiquid-DSPNCNNTimed MrBayes AnalysisNCNNC-RayeSpeak-NG Speech EngineNCNNNgspiceNCNNSciMarkZstd CompressionAOBenchNCNNNCNNNCNNLiquid-DSPZstd CompressionCoremarkGraphicsMagickZstd CompressionJPEG XL libjxlZstd CompressionZstd CompressionJPEG XL libjxlSciMarkFLAC Audio EncodingHimeno BenchmarkBotanCrypto++GraphicsMagickNCNNZstd Compressiondav1dBotanSciMarkBasis UniversalNCNNNCNNBasis UniversalNCNNXmrigSockperfTNNsimdjsonOpenSSLXmriglibgav1GraphicsMagickBasis UniversalBotanNCNNNCNNBotanZstd CompressionsimdjsonBotansimdjsonsimdjsonLAMMPS Molecular Dynamics Simulatorlibjpeg-turbo tjbenchBotanZstd CompressionGraphicsMagicklibgav1Zstd CompressionPrimesieveSciMarkBotanPOV-RayZstd CompressionTNNOpus Codec EncodingWavPack Audio EncodingNCNNClangGCC

apple m2 compilersaobench: 2048 x 2048 - Total Timebasis: ETC1Sbasis: UASTC Level 0basis: UASTC Level 2basis: UASTC Level 3botan: KASUMIbotan: KASUMI - Decryptbotan: Twofishbotan: Twofish - Decryptbotan: Blowfishbotan: Blowfish - Decryptbotan: CAST-256botan: CAST-256 - Decryptbotan: ChaCha20Poly1305botan: ChaCha20Poly1305 - Decryptc-ray: Total Time - 4K, 16 Rays Per Pixelcoremark: CoreMark Size 666 - Iterations Per Secondcryptopp: Keyed Algorithmscryptopp: Unkeyed Algorithmscryptopp: Integer + Elliptic Curve Public Key Algorithmsdav1d: Chimera 1080pdav1d: Summer Nature 4Kdav1d: Summer Nature 1080pdav1d: Chimera 1080p 10-bitespeak: Text-To-Speech Synthesisencode-flac: WAV To FLACgcrypt: gnupg: 2.7GB Sample File Encryptiondraco: Liondraco: Church Facadegraphics-magick: Swirlgraphics-magick: Rotategraphics-magick: Sharpengraphics-magick: Enhancedgraphics-magick: Resizinggraphics-magick: Noise-Gaussiangraphics-magick: HWB Color Spacehimeno: Poisson Pressure Solverjpegxl: PNG - 5jpegxl: PNG - 7jpegxl: JPEG - 5jpegxl: JPEG - 7jpegxl: JPEG - 8encode-mp3: WAV To MP3lammps: Rhodopsin Proteinlibgav1: Chimera 1080plibgav1: Summer Nature 4Klibgav1: Summer Nature 1080plibgav1: Chimera 1080p 10-bittjbench: Decompression Throughputliquid-dsp: 1 - 256 - 57liquid-dsp: 2 - 256 - 57liquid-dsp: 4 - 256 - 57liquid-dsp: 8 - 256 - 57luajit: Compositeluajit: Monte Carloluajit: Fast Fourier Transformluajit: Sparse Matrix Multiplyluajit: Dense LU Matrix Factorizationluajit: Jacobi Successive Over-Relaxationncnn: CPU - mobilenetncnn: CPU-v2-v2 - mobilenet-v2ncnn: CPU-v3-v3 - mobilenet-v3ncnn: CPU - shufflenet-v2ncnn: CPU - efficientnet-b0ncnn: CPU - blazefacencnn: CPU - googlenetncnn: CPU - vgg16ncnn: CPU - resnet18ncnn: CPU - alexnetncnn: CPU - resnet50ncnn: CPU - yolov4-tinyncnn: CPU - squeezenet_ssdncnn: CPU - regnety_400mncnn: CPU - mnasnetncnn: CPU - mobilenetncnn: CPU-v2-v2 - mobilenet-v2ncnn: CPU-v3-v3 - mobilenet-v3ncnn: CPU - shufflenet-v2ncnn: CPU - mnasnetncnn: CPU - efficientnet-b0ncnn: CPU - blazefacencnn: CPU - googlenetncnn: CPU - vgg16ncnn: CPU - resnet18ncnn: CPU - alexnetncnn: CPU - resnet50ncnn: CPU - yolov4-tinyncnn: CPU - squeezenet_ssdncnn: CPU - regnety_400mncnn: CPU - vision_transformerncnn: CPU - FastestDetngspice: C2670ngspice: C7552openjpeg: NASA Curiosity Panorama M34openssl: SHA256openssl: RSA4096openssl: RSA4096encode-opus: WAV To Opus Encodepovray: Trace Timeprimesieve: 1e12scimark2: Compositescimark2: Monte Carloscimark2: Fast Fourier Transformscimark2: Sparse Matrix Multiplyscimark2: Dense LU Matrix Factorizationscimark2: Jacobi Successive Over-Relaxationsimdjson: Kostyasimdjson: TopTweetsimdjson: LargeRandsimdjson: PartialTweetssimdjson: DistinctUserIDsockperf: Throughputsqlite-speedtest: Timed Time - Size 1,000mrbayes: Primate Phylogeny Analysistnn: CPU - DenseNettnn: CPU - MobileNet v2tnn: CPU - SqueezeNet v2tnn: CPU - SqueezeNet v1.1encode-wavpack: WAV To WavPackxmrig: Monero - 1Mxmrig: Wownero - 1Mcompress-zstd: 3 - Compression Speedcompress-zstd: 3 - Decompression Speedcompress-zstd: 8 - Compression Speedcompress-zstd: 8 - Decompression Speedcompress-zstd: 19 - Compression Speedcompress-zstd: 19 - Decompression Speedcompress-zstd: 3, Long Mode - Compression Speedcompress-zstd: 3, Long Mode - Decompression Speedcompress-zstd: 8, Long Mode - Compression Speedcompress-zstd: 8, Long Mode - Decompression Speedcompress-zstd: 19, Long Mode - Compression Speedcompress-zstd: 19, Long Mode - Decompression SpeedClangGCC29.47526.1636.54835.88170.15693.79491.826351.494347.604436.062436.816136.758136.985578.630570.92195.542175753.764225404.764881360.1759632161.313491376.77105.09527.87283.7020.29741.519255.91343.850343350443111571971556131219508507.40742135.5813.12114.37114.9838.657.5733.440161.8455.66133.1681.34214.69863838463333768953331533866671905446671387.75424.27560.451902.443157.76893.8115.033.473.313.136.552.2811.0329.596.1611.1515.6920.1812.6410.383.6313.073.623.253.003.535.562.0910.8334.445.9011.8028.7120.2412.0910.17544.384.0576.92656.0974872490582297201529.5107954.214.66588.92640.3662870.78450.23500.914508.826907.381986.563.034.431.004.354.4579318545.453192.7537411.322426.55756.613330.08917.9782520.62676.23525.24234.8880.24385.725.93932.4272.44647.8691.94854.721.04146.625.75124.1306.00334.12370.00184.29784.114341.749348.144415.066416.060136.749137.213558.134547.81779.027199947.689206591.620305590.7156971947.622786375.87115.13534.01280.9816.93337.251258.39343.89134765080322158610217153916413617634.59103420.789.78101.26102.1338.165.6783.315156.3255.13131.3577.30222.66638030318000605346671211066671673533331386.16429.71560.211890.853156.17893.8411.942.202.061.923.821.8612.5933.707.8412.0815.3614.6714.405.282.2311.992.212.201.902.283.261.9012.7232.807.0412.3915.2414.519.285.19501.171.87100.08466.0614882985348118071520.3106464.414.29891.45639.0952454.22463.86563.134132.955124.151987.033.054.251.044.184.1984733944.635240.5665229.211306.61453.284321.82518.4202329.92541.93526.64821.4866.14986.026.84513.1265.45241.1716.95478.321.94543.4OpenBenchmarking.org

AOBench

AOBench is a lightweight ambient occlusion renderer, written in C. The test profile is using a size of 2048 x 2048. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterAOBenchSize: 2048 x 2048 - Total TimeClangGCC714212835SE +/- 0.04, N = 3SE +/- 0.03, N = 329.4825.751. (CC) gcc options: -lm -O3

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: ETC1SClangGCC612182430SE +/- 0.20, N = 3SE +/- 0.11, N = 326.1624.131. (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 0ClangGCC246810SE +/- 0.012, N = 3SE +/- 0.007, N = 36.5486.0031. (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 2ClangGCC816243240SE +/- 0.24, N = 3SE +/- 0.14, N = 335.8834.121. (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 3ClangGCC1632486480SE +/- 0.68, N = 3SE +/- 0.74, N = 370.1670.001. (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: KASUMIClangGCC20406080100SE +/- 0.01, N = 3SE +/- 0.01, N = 393.7984.301. (CXX) g++ options: -fstack-protector -pthread -lbotan-2 -ldl -lrt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: KASUMI - DecryptClangGCC20406080100SE +/- 0.00, N = 3SE +/- 0.00, N = 391.8384.111. (CXX) g++ options: -fstack-protector -pthread -lbotan-2 -ldl -lrt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: TwofishClangGCC80160240320400SE +/- 0.04, N = 3SE +/- 0.11, N = 3351.49341.751. (CXX) g++ options: -fstack-protector -pthread -lbotan-2 -ldl -lrt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: Twofish - DecryptClangGCC80160240320400SE +/- 0.00, N = 3SE +/- 0.03, N = 3347.60348.141. (CXX) g++ options: -fstack-protector -pthread -lbotan-2 -ldl -lrt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: BlowfishClangGCC90180270360450SE +/- 0.13, N = 3SE +/- 0.06, N = 3436.06415.071. (CXX) g++ options: -fstack-protector -pthread -lbotan-2 -ldl -lrt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: Blowfish - DecryptClangGCC90180270360450SE +/- 0.01, N = 3SE +/- 0.06, N = 3436.82416.061. (CXX) g++ options: -fstack-protector -pthread -lbotan-2 -ldl -lrt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: CAST-256ClangGCC306090120150SE +/- 0.03, N = 3SE +/- 0.03, N = 3136.76136.751. (CXX) g++ options: -fstack-protector -pthread -lbotan-2 -ldl -lrt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: CAST-256 - DecryptClangGCC306090120150SE +/- 0.01, N = 3SE +/- 0.02, N = 3136.99137.211. (CXX) g++ options: -fstack-protector -pthread -lbotan-2 -ldl -lrt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: ChaCha20Poly1305ClangGCC130260390520650SE +/- 0.13, N = 3SE +/- 0.08, N = 3578.63558.131. (CXX) g++ options: -fstack-protector -pthread -lbotan-2 -ldl -lrt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: ChaCha20Poly1305 - DecryptClangGCC120240360480600SE +/- 0.16, N = 3SE +/- 0.29, N = 3570.92547.821. (CXX) g++ options: -fstack-protector -pthread -lbotan-2 -ldl -lrt

C-Ray

This is a test of C-Ray, a simple raytracer designed to test the floating-point CPU performance. This test is multi-threaded (16 threads per core), will shoot 8 rays per pixel for anti-aliasing, and will generate a 1600 x 1200 image. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total Time - 4K, 16 Rays Per PixelClangGCC20406080100SE +/- 1.77, N = 15SE +/- 0.60, N = 1595.5479.031. (CC) gcc options: -lm -lpthread -O3

Coremark

This is a test of EEMBC CoreMark processor benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations/Sec, More Is BetterCoremark 1.0CoreMark Size 666 - Iterations Per SecondClangGCC40K80K120K160K200KSE +/- 188.51, N = 3SE +/- 212.74, N = 3175753.76199947.691. (CC) gcc options: -O2 -O3 -lrt" -lrt

Crypto++

Crypto++ is a C++ class library of cryptographic algorithms. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/second, More Is BetterCrypto++ 8.2Test: Keyed AlgorithmsClangGCC130260390520650SE +/- 0.04, N = 3SE +/- 0.03, N = 3404.76591.621. (CXX) g++ options: -g2 -O3 -fPIC -pthread -pipe

OpenBenchmarking.orgMiB/second, More Is BetterCrypto++ 8.2Test: Unkeyed AlgorithmsClangGCC130260390520650SE +/- 0.02, N = 3SE +/- 0.08, N = 3360.18590.721. (CXX) g++ options: -g2 -O3 -fPIC -pthread -pipe

OpenBenchmarking.orgMiB/second, More Is BetterCrypto++ 8.2Test: Integer + Elliptic Curve Public Key AlgorithmsClangGCC5001000150020002500SE +/- 0.40, N = 3SE +/- 0.86, N = 32161.311947.621. (CXX) g++ options: -g2 -O3 -fPIC -pthread -pipe

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 1.0Video Input: Chimera 1080pClangGCC80160240320400SE +/- 5.38, N = 3SE +/- 4.00, N = 3376.77375.871. (CC) gcc options: -O3 -pthread -lm

OpenBenchmarking.orgFPS, More Is Betterdav1d 1.0Video Input: Summer Nature 4KClangGCC306090120150SE +/- 2.69, N = 15SE +/- 1.12, N = 3105.09115.131. (CC) gcc options: -O3 -pthread -lm

OpenBenchmarking.orgFPS, More Is Betterdav1d 1.0Video Input: Summer Nature 1080pClangGCC120240360480600SE +/- 2.72, N = 3SE +/- 0.68, N = 3527.87534.011. (CC) gcc options: -O3 -pthread -lm

OpenBenchmarking.orgFPS, More Is Betterdav1d 1.0Video Input: Chimera 1080p 10-bitClangGCC60120180240300SE +/- 4.07, N = 3SE +/- 2.29, N = 9283.70280.981. (CC) gcc options: -O3 -pthread -lm

eSpeak-NG Speech Engine

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

OpenBenchmarking.orgSeconds, Fewer Is BettereSpeak-NG Speech Engine 20200907Text-To-Speech SynthesisClangGCC510152025SE +/- 0.02, N = 4SE +/- 0.03, N = 420.3016.931. (CC) gcc options: -O3 -std=c99 -lpthread -lm

FLAC Audio Encoding

This test times how long it takes to encode a sample WAV file to FLAC format ten times. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterFLAC Audio Encoding 1.3.3WAV To FLACClangGCC918273645SE +/- 0.06, N = 5SE +/- 0.05, N = 541.5237.25-fvisibility=hidden1. (CXX) g++ options: -logg -lm

Gcrypt Library

Libgcrypt is a general purpose cryptographic library developed as part of the GnuPG project. This is a benchmark of libgcrypt's integrated benchmark and is measuring the time to run the benchmark command with a cipher/mac/hash repetition count set for 50 times as simple, high level look at the overall crypto performance of the system under test. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGcrypt Library 1.9ClangGCC60120180240300SE +/- 0.53, N = 3SE +/- 0.56, N = 3255.91258.391. (CC) gcc options: -O3 -fvisibility=hidden -lgpg-error

GnuPG

This test times how long it takes to encrypt a sample file using GnuPG. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGnuPG 2.2.272.7GB Sample File EncryptionClangGCC1020304050SE +/- 0.20, N = 3SE +/- 0.26, N = 343.8543.891. (CC) gcc options: -O3

Google Draco

Draco is a library developed by Google for compressing/decompressing 3D geometric meshes and point clouds. This test profile uses some Artec3D PLY models as the sample 3D model input formats for Draco compression/decompression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterGoogle Draco 1.5.0Model: LionClangGCC7001400210028003500SE +/- 2.67, N = 3SE +/- 8.25, N = 3343334761. (CXX) g++ options: -O3

OpenBenchmarking.orgms, Fewer Is BetterGoogle Draco 1.5.0Model: Church FacadeClangGCC11002200330044005500SE +/- 3.71, N = 3SE +/- 4.58, N = 3504450801. (CXX) g++ options: -O3

GraphicsMagick

This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample 6000x4000 pixel JPEG image. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: SwirlClangGCC70140210280350SE +/- 6.11, N = 15SE +/- 4.72, N = 153113221. (CC) gcc options: -fopenmp -O3 -lwebp -lwebpmux -llcms2 -ltiff -lfreetype -ljasper -ljpeg -lwmflite -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lzstd -lm -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: RotateClangGCC30060090012001500SE +/- 11.02, N = 3SE +/- 2.60, N = 3157115861. (CC) gcc options: -fopenmp -O3 -lwebp -lwebpmux -llcms2 -ltiff -lfreetype -ljasper -ljpeg -lwmflite -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lzstd -lm -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: SharpenClangGCC20406080100SE +/- 1.14, N = 15SE +/- 1.24, N = 15971021. (CC) gcc options: -fopenmp -O3 -lwebp -lwebpmux -llcms2 -ltiff -lfreetype -ljasper -ljpeg -lwmflite -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lzstd -lm -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: EnhancedClangGCC4080120160200SE +/- 1.66, N = 15SE +/- 1.86, N = 31551711. (CC) gcc options: -fopenmp -O3 -lwebp -lwebpmux -llcms2 -ltiff -lfreetype -ljasper -ljpeg -lwmflite -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lzstd -lm -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: ResizingClangGCC130260390520650SE +/- 6.24, N = 3SE +/- 4.56, N = 156135391. (CC) gcc options: -fopenmp -O3 -lwebp -lwebpmux -llcms2 -ltiff -lfreetype -ljasper -ljpeg -lwmflite -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lzstd -lm -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: Noise-GaussianClangGCC4080120160200SE +/- 1.33, N = 15SE +/- 2.09, N = 151211641. (CC) gcc options: -fopenmp -O3 -lwebp -lwebpmux -llcms2 -ltiff -lfreetype -ljasper -ljpeg -lwmflite -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lzstd -lm -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: HWB Color SpaceClangGCC30060090012001500SE +/- 12.49, N = 15SE +/- 18.02, N = 395013611. (CC) gcc options: -fopenmp -O3 -lwebp -lwebpmux -llcms2 -ltiff -lfreetype -ljasper -ljpeg -lwmflite -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lzstd -lm -lpthread

Himeno Benchmark

The Himeno benchmark is a linear solver of pressure Poisson using a point-Jacobi method. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMFLOPS, More Is BetterHimeno Benchmark 3.0Poisson Pressure SolverClangGCC2K4K6K8K10KSE +/- 3.70, N = 3SE +/- 2.90, N = 38507.417634.591. (CC) gcc options: -O3

JPEG XL libjxl

The JPEG XL Image Coding System is designed to provide next-generation JPEG image capabilities with JPEG XL offering better image quality and compression over legacy JPEG. This test profile is currently focused on the multi-threaded JPEG XL image encode performance using the reference libjxl library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMP/s, More Is BetterJPEG XL libjxl 0.6.1Input: PNG - Encode Speed: 5ClangGCC816243240SE +/- 0.36, N = 15SE +/- 0.20, N = 1535.5820.78-Xclang -mrelax-all1. (CXX) g++ options: -funwind-tables -O3 -O2 -fPIE -pie

OpenBenchmarking.orgMP/s, More Is BetterJPEG XL libjxl 0.6.1Input: PNG - Encode Speed: 7ClangGCC3691215SE +/- 0.03, N = 3SE +/- 0.02, N = 313.129.78-Xclang -mrelax-all1. (CXX) g++ options: -funwind-tables -O3 -O2 -fPIE -pie

OpenBenchmarking.orgMP/s, More Is BetterJPEG XL libjxl 0.6.1Input: JPEG - Encode Speed: 5ClangGCC306090120150SE +/- 0.68, N = 3SE +/- 0.28, N = 3114.37101.26-Xclang -mrelax-all1. (CXX) g++ options: -funwind-tables -O3 -O2 -fPIE -pie

OpenBenchmarking.orgMP/s, More Is BetterJPEG XL libjxl 0.6.1Input: JPEG - Encode Speed: 7ClangGCC306090120150SE +/- 0.49, N = 3SE +/- 0.55, N = 3114.98102.13-Xclang -mrelax-all1. (CXX) g++ options: -funwind-tables -O3 -O2 -fPIE -pie

OpenBenchmarking.orgMP/s, More Is BetterJPEG XL libjxl 0.6.1Input: JPEG - Encode Speed: 8ClangGCC918273645SE +/- 0.24, N = 3SE +/- 0.19, N = 338.6538.16-Xclang -mrelax-all1. (CXX) g++ options: -funwind-tables -O3 -O2 -fPIE -pie

LAME MP3 Encoding

LAME is an MP3 encoder licensed under the LGPL. This test measures the time required to encode a WAV file to MP3 format. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterLAME MP3 Encoding 3.100WAV To MP3ClangGCC246810SE +/- 0.007, N = 3SE +/- 0.013, N = 37.5735.678-ffast-math -funroll-loops -fschedule-insns2 -fbranch-count-reg -fforce-addr1. (CC) gcc options: -O3 -pipe -lncurses -lm

LAMMPS Molecular Dynamics Simulator

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

OpenBenchmarking.orgns/day, More Is BetterLAMMPS Molecular Dynamics Simulator 23Jun2022Model: Rhodopsin ProteinClangGCC0.7741.5482.3223.0963.87SE +/- 0.035, N = 3SE +/- 0.038, N = 43.4403.3151. (CXX) g++ options: -O3 -ldl

libgav1

Libgav1 is an AV1 decoder developed by Google for AV1 profile 0/1 compliance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is Betterlibgav1 0.17Video Input: Chimera 1080pClangGCC4080120160200SE +/- 0.29, N = 3SE +/- 1.36, N = 3161.84156.321. (CXX) g++ options: -O3 -lrt

OpenBenchmarking.orgFPS, More Is Betterlibgav1 0.17Video Input: Summer Nature 4KClangGCC1326395265SE +/- 0.16, N = 3SE +/- 0.21, N = 355.6655.131. (CXX) g++ options: -O3 -lrt

OpenBenchmarking.orgFPS, More Is Betterlibgav1 0.17Video Input: Summer Nature 1080pClangGCC306090120150SE +/- 1.30, N = 3SE +/- 0.29, N = 3133.16131.351. (CXX) g++ options: -O3 -lrt

OpenBenchmarking.orgFPS, More Is Betterlibgav1 0.17Video Input: Chimera 1080p 10-bitClangGCC20406080100SE +/- 0.49, N = 3SE +/- 1.03, N = 381.3477.301. (CXX) g++ options: -O3 -lrt

libjpeg-turbo tjbench

tjbench is a JPEG decompression/compression benchmark that is part of libjpeg-turbo, a JPEG image codec library optimized for SIMD instructions on modern CPU architectures. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMegapixels/sec, More Is Betterlibjpeg-turbo tjbench 2.1.0Test: Decompression ThroughputClangGCC50100150200250SE +/- 0.04, N = 3SE +/- 0.03, N = 3214.70222.67-lm1. (CC) gcc options: -O3 -rdynamic

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: 1 - Buffer Length: 256 - Filter Length: 57ClangGCC8M16M24M32M40MSE +/- 4977.73, N = 3SE +/- 3511.88, N = 338463333303180001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 2 - Buffer Length: 256 - Filter Length: 57ClangGCC16M32M48M64M80MSE +/- 2403.70, N = 3SE +/- 4910.31, N = 376895333605346671. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 4 - Buffer Length: 256 - Filter Length: 57ClangGCC30M60M90M120M150MSE +/- 133832.40, N = 3SE +/- 8819.17, N = 31533866671211066671. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 8 - Buffer Length: 256 - Filter Length: 57ClangGCC40M80M120M160M200MSE +/- 1293649.64, N = 15SE +/- 521674.65, N = 31905446671673533331. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

LuaJIT

This test profile is a collection of Lua scripts/benchmarks run against a locally-built copy of LuaJIT upstream. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterLuaJIT 2.1-gitTest: CompositeClangGCC30060090012001500SE +/- 0.49, N = 3SE +/- 3.74, N = 31387.751386.161. (CC) gcc options: -lm -ldl -O2 -fomit-frame-pointer -O3 -U_FORTIFY_SOURCE -fno-stack-protector

OpenBenchmarking.orgMflops, More Is BetterLuaJIT 2.1-gitTest: Monte CarloClangGCC90180270360450SE +/- 0.17, N = 3SE +/- 2.66, N = 3424.27429.711. (CC) gcc options: -lm -ldl -O2 -fomit-frame-pointer -O3 -U_FORTIFY_SOURCE -fno-stack-protector

OpenBenchmarking.orgMflops, More Is BetterLuaJIT 2.1-gitTest: Fast Fourier TransformClangGCC120240360480600SE +/- 0.91, N = 3SE +/- 0.16, N = 3560.45560.211. (CC) gcc options: -lm -ldl -O2 -fomit-frame-pointer -O3 -U_FORTIFY_SOURCE -fno-stack-protector

OpenBenchmarking.orgMflops, More Is BetterLuaJIT 2.1-gitTest: Sparse Matrix MultiplyClangGCC400800120016002000SE +/- 1.66, N = 3SE +/- 13.70, N = 31902.441890.851. (CC) gcc options: -lm -ldl -O2 -fomit-frame-pointer -O3 -U_FORTIFY_SOURCE -fno-stack-protector

OpenBenchmarking.orgMflops, More Is BetterLuaJIT 2.1-gitTest: Dense LU Matrix FactorizationClangGCC7001400210028003500SE +/- 0.85, N = 3SE +/- 7.46, N = 33157.763156.171. (CC) gcc options: -lm -ldl -O2 -fomit-frame-pointer -O3 -U_FORTIFY_SOURCE -fno-stack-protector

OpenBenchmarking.orgMflops, More Is BetterLuaJIT 2.1-gitTest: Jacobi Successive Over-RelaxationClangGCC2004006008001000SE +/- 0.04, N = 3SE +/- 0.02, N = 3893.81893.841. (CC) gcc options: -lm -ldl -O2 -fomit-frame-pointer -O3 -U_FORTIFY_SOURCE -fno-stack-protector

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: mobilenetClangGCC48121620SE +/- 1.12, N = 13SE +/- 0.15, N = 415.0311.94-lomp - MIN: 10.47 / MAX: 34.45-lgomp - MIN: 8.2 / MAX: 27.451. (CXX) g++ options: -O3 -rdynamic -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU-v2-v2 - Model: mobilenet-v2ClangGCC0.78081.56162.34243.12323.904SE +/- 0.06, N = 13SE +/- 0.01, N = 43.472.20-lomp - MIN: 3.08 / MAX: 5.31-lgomp - MIN: 2.17 / MAX: 2.41. (CXX) g++ options: -O3 -rdynamic -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU-v3-v3 - Model: mobilenet-v3ClangGCC0.74481.48962.23442.97923.724SE +/- 0.08, N = 13SE +/- 0.01, N = 43.312.06-lomp - MIN: 2.56 / MAX: 7.12-lgomp - MIN: 2.03 / MAX: 2.171. (CXX) g++ options: -O3 -rdynamic -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: shufflenet-v2ClangGCC0.70431.40862.11292.81723.5215SE +/- 0.07, N = 13SE +/- 0.00, N = 43.131.92-lomp - MIN: 2.48 / MAX: 4.66-lgomp - MIN: 1.9 / MAX: 2.281. (CXX) g++ options: -O3 -rdynamic -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: efficientnet-b0ClangGCC246810SE +/- 0.15, N = 13SE +/- 0.20, N = 46.553.82-lomp - MIN: 5.13 / MAX: 7.99-lgomp - MIN: 3.55 / MAX: 25.761. (CXX) g++ options: -O3 -rdynamic -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: blazefaceClangGCC0.5131.0261.5392.0522.565SE +/- 0.12, N = 13SE +/- 0.04, N = 42.281.86-lomp - MIN: 1.38 / MAX: 5.9-lgomp - MIN: 1.02 / MAX: 8.51. (CXX) g++ options: -O3 -rdynamic -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: googlenetClangGCC3691215SE +/- 0.26, N = 13SE +/- 0.06, N = 411.0312.59-lomp - MIN: 9.1 / MAX: 21.81-lgomp - MIN: 8.3 / MAX: 21.521. (CXX) g++ options: -O3 -rdynamic -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: vgg16ClangGCC816243240SE +/- 0.34, N = 13SE +/- 0.10, N = 429.5933.70-lomp - MIN: 27.88 / MAX: 48.18-lgomp - MIN: 28.28 / MAX: 51.281. (CXX) g++ options: -O3 -rdynamic -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: resnet18ClangGCC246810SE +/- 0.07, N = 13SE +/- 0.12, N = 46.167.84-lomp - MIN: 5.6 / MAX: 7.49-lgomp - MIN: 5.48 / MAX: 21.031. (CXX) g++ options: -O3 -rdynamic -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: alexnetClangGCC3691215SE +/- 0.31, N = 13SE +/- 0.11, N = 411.1512.08-lomp - MIN: 10.07 / MAX: 22.61-lgomp - MIN: 9.11 / MAX: 22.771. (CXX) g++ options: -O3 -rdynamic -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: resnet50ClangGCC48121620SE +/- 0.48, N = 13SE +/- 0.12, N = 415.6915.36-lomp - MIN: 13.48 / MAX: 29.95-lgomp - MIN: 13.43 / MAX: 24.891. (CXX) g++ options: -O3 -rdynamic -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: yolov4-tinyClangGCC510152025SE +/- 0.57, N = 13SE +/- 0.31, N = 420.1814.67-lomp - MIN: 15.44 / MAX: 33.23-lgomp - MIN: 12.77 / MAX: 26.021. (CXX) g++ options: -O3 -rdynamic -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: squeezenet_ssdClangGCC48121620SE +/- 0.17, N = 13SE +/- 0.06, N = 412.6414.40-lomp - MIN: 9.67 / MAX: 27.34-lgomp - MIN: 9.79 / MAX: 29.221. (CXX) g++ options: -O3 -rdynamic -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: regnety_400mClangGCC3691215SE +/- 0.26, N = 13SE +/- 0.04, N = 410.385.28-lomp - MIN: 8.02 / MAX: 15.57-lgomp - MIN: 5.16 / MAX: 5.431. (CXX) g++ options: -O3 -rdynamic -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: mnasnetClangGCC0.81681.63362.45043.26724.084SE +/- 0.08, N = 133.632.23-lomp - MIN: 2.94 / MAX: 4.76-lgomp - MIN: 2.22 / MAX: 2.331. (CXX) g++ options: -O3 -rdynamic -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: mobilenetClangGCC3691215SE +/- 0.34, N = 12SE +/- 0.15, N = 313.0711.99-lomp - MIN: 9.68 / MAX: 25.4-lgomp - MIN: 8.33 / MAX: 23.041. (CXX) g++ options: -O3 -rdynamic -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU-v2-v2 - Model: mobilenet-v2ClangGCC0.81451.6292.44353.2584.0725SE +/- 0.27, N = 12SE +/- 0.08, N = 33.622.21-lomp - MIN: 2.9 / MAX: 8.87-lgomp - MIN: 2.09 / MAX: 5.321. (CXX) g++ options: -O3 -rdynamic -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU-v3-v3 - Model: mobilenet-v3ClangGCC0.73131.46262.19392.92523.6565SE +/- 0.11, N = 12SE +/- 0.03, N = 33.252.20-lomp - MIN: 2.49 / MAX: 9.1-lgomp - MIN: 2.08 / MAX: 5.171. (CXX) g++ options: -O3 -rdynamic -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: shufflenet-v2ClangGCC0.6751.352.0252.73.375SE +/- 0.07, N = 12SE +/- 0.05, N = 33.001.90-lomp - MIN: 2.11 / MAX: 12.45-lgomp - MIN: 1.82 / MAX: 5.071. (CXX) g++ options: -O3 -rdynamic -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: mnasnetClangGCC0.79431.58862.38293.17723.9715SE +/- 0.07, N = 12SE +/- 0.09, N = 33.532.28-lomp - MIN: 2.72 / MAX: 7.36-lgomp - MIN: 2.11 / MAX: 5.511. (CXX) g++ options: -O3 -rdynamic -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: efficientnet-b0ClangGCC1.2512.5023.7535.0046.255SE +/- 0.11, N = 12SE +/- 0.02, N = 35.563.26-lomp - MIN: 4.41 / MAX: 15.78-lgomp - MIN: 3.21 / MAX: 12.851. (CXX) g++ options: -O3 -rdynamic -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: blazefaceClangGCC0.47030.94061.41091.88122.3515SE +/- 0.06, N = 12SE +/- 0.05, N = 32.091.90-lomp - MIN: 1.37 / MAX: 3.21-lgomp - MIN: 0.98 / MAX: 7.721. (CXX) g++ options: -O3 -rdynamic -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: googlenetClangGCC3691215SE +/- 0.19, N = 12SE +/- 0.07, N = 310.8312.72-lomp - MIN: 8.82 / MAX: 22.43-lgomp - MIN: 8.11 / MAX: 27.991. (CXX) g++ options: -O3 -rdynamic -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: vgg16ClangGCC816243240SE +/- 1.89, N = 12SE +/- 0.02, N = 334.4432.80-lomp - MIN: 27.08 / MAX: 74.43-lgomp - MIN: 27.43 / MAX: 42.651. (CXX) g++ options: -O3 -rdynamic -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: resnet18ClangGCC246810SE +/- 0.05, N = 12SE +/- 0.18, N = 35.907.04-lomp - MIN: 5.32 / MAX: 7.13-lgomp - MIN: 5.13 / MAX: 19.311. (CXX) g++ options: -O3 -rdynamic -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: alexnetClangGCC3691215SE +/- 0.48, N = 12SE +/- 0.12, N = 311.8012.39-lomp - MIN: 9.79 / MAX: 24.49-lgomp - MIN: 8.84 / MAX: 22.791. (CXX) g++ options: -O3 -rdynamic -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: resnet50ClangGCC714212835SE +/- 3.28, N = 12SE +/- 0.03, N = 328.7115.24-lomp - MIN: 13.32 / MAX: 216.5-lgomp - MIN: 13.38 / MAX: 25.591. (CXX) g++ options: -O3 -rdynamic -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: yolov4-tinyClangGCC510152025SE +/- 1.95, N = 12SE +/- 0.07, N = 320.2414.51-lomp - MIN: 13.87 / MAX: 70.08-lgomp - MIN: 12.49 / MAX: 23.481. (CXX) g++ options: -O3 -rdynamic -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: squeezenet_ssdClangGCC3691215SE +/- 1.64, N = 12SE +/- 0.10, N = 312.099.28-lomp - MIN: 7.83 / MAX: 31.07-lgomp - MIN: 7.07 / MAX: 20.521. (CXX) g++ options: -O3 -rdynamic -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: regnety_400mClangGCC3691215SE +/- 0.41, N = 12SE +/- 0.03, N = 310.175.19-lomp - MIN: 7.32 / MAX: 18.84-lgomp - MIN: 5.13 / MAX: 9.151. (CXX) g++ options: -O3 -rdynamic -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: vision_transformerClangGCC120240360480600SE +/- 10.55, N = 12SE +/- 0.71, N = 3544.38501.17-lomp - MIN: 375.2 / MAX: 1425.41-lgomp - MIN: 475.83 / MAX: 544.851. (CXX) g++ options: -O3 -rdynamic -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: FastestDetClangGCC0.91131.82262.73393.64524.5565SE +/- 0.40, N = 11SE +/- 0.11, N = 34.051.87-lomp - MIN: 2.43 / MAX: 8.08-lgomp - MIN: 1.69 / MAX: 12.731. (CXX) g++ options: -O3 -rdynamic -lpthread

Ngspice

Ngspice is an open-source SPICE circuit simulator. Ngspice was originally based on the Berkeley SPICE electronic circuit simulator. Ngspice supports basic threading using OpenMP. This test profile is making use of the ISCAS 85 benchmark circuits. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterNgspice 34Circuit: C2670ClangGCC20406080100SE +/- 0.28, N = 3SE +/- 3.54, N = 1576.93100.081. (CC) gcc options: -O3 -fopenmp -lm -lstdc++ -lfftw3 -lXaw -lXmu -lXt -lXext -lX11 -lXft -lfontconfig -lXrender -lfreetype -lSM -lICE

OpenBenchmarking.orgSeconds, Fewer Is BetterNgspice 34Circuit: C7552ClangGCC1530456075SE +/- 0.24, N = 3SE +/- 1.02, N = 1556.1066.061. (CC) gcc options: -O3 -fopenmp -lm -lstdc++ -lfftw3 -lXaw -lXmu -lXt -lXext -lX11 -lXft -lfontconfig -lXrender -lfreetype -lSM -lICE

OpenJPEG

OpenJPEG is an open-source JPEG 2000 codec written in the C programming language. The default input for this test profile is the NASA/JPL-Caltech/MSSS Curiosity panorama 717MB TIFF image file converting to JPEG2000 format. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenJPEG 2.4Encode: NASA Curiosity Panorama M34ClangGCC10K20K30K40K50KSE +/- 90.00, N = 3SE +/- 145.89, N = 348724488291. (CXX) g++ options: -rdynamic

OpenSSL

OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test profile makes use of the built-in "openssl speed" benchmarking capabilities. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.0Algorithm: SHA256ClangGCC2000M4000M6000M8000M10000MSE +/- 10759857.48, N = 3SE +/- 13180414.49, N = 390582297208534811807-Qunused-arguments1. (CC) gcc options: -pthread -O3 -lssl -lcrypto -ldl

OpenBenchmarking.orgsign/s, More Is BetterOpenSSL 3.0Algorithm: RSA4096ClangGCC30060090012001500SE +/- 10.91, N = 3SE +/- 15.18, N = 31529.51520.3-Qunused-arguments1. (CC) gcc options: -pthread -O3 -lssl -lcrypto -ldl

OpenBenchmarking.orgverify/s, More Is BetterOpenSSL 3.0Algorithm: RSA4096ClangGCC20K40K60K80K100KSE +/- 712.36, N = 3SE +/- 1045.44, N = 3107954.2106464.4-Qunused-arguments1. (CC) gcc options: -pthread -O3 -lssl -lcrypto -ldl

Opus Codec Encoding

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

OpenBenchmarking.orgSeconds, Fewer Is BetterOpus Codec Encoding 1.3.1WAV To Opus EncodeClangGCC48121620SE +/- 0.01, N = 5SE +/- 0.02, N = 514.6714.30-fvisibility=hidden1. (CXX) g++ options: -logg -lm

POV-Ray

This is a test of POV-Ray, the Persistence of Vision Raytracer. POV-Ray is used to create 3D graphics using ray-tracing. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPOV-Ray 3.7.0.7Trace TimeClangGCC20406080100SE +/- 0.91, N = 4SE +/- 1.04, N = 488.9391.46-R/usr/lib1. (CXX) g++ options: -pipe -O3 -ffast-math -lSDL -lXpm -lSM -lICE -lX11 -ltiff -ljpeg -lpng -lz -lrt -lm -lboost_thread -lboost_system

Primesieve

Primesieve generates prime numbers using a highly optimized sieve of Eratosthenes implementation. Primesieve primarily benchmarks the CPU's L1/L2 cache performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPrimesieve 8.0Length: 1e12ClangGCC918273645SE +/- 0.79, N = 15SE +/- 0.78, N = 1540.3739.101. (CXX) g++ options: -O3

SciMark

This test runs the ANSI C version of SciMark 2.0, which is a benchmark for scientific and numerical computing developed by programmers at the National Institute of Standards and Technology. This test is made up of Fast Foruier Transform, Jacobi Successive Over-relaxation, Monte Carlo, Sparse Matrix Multiply, and dense LU matrix factorization benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: CompositeClangGCC6001200180024003000SE +/- 3.27, N = 3SE +/- 3.41, N = 32870.782454.221. (CC) gcc options: -O3 -lm

OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Monte CarloClangGCC100200300400500SE +/- 0.00, N = 3SE +/- 0.00, N = 3450.23463.861. (CC) gcc options: -O3 -lm

OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Fast Fourier TransformClangGCC120240360480600SE +/- 0.71, N = 3SE +/- 0.57, N = 3500.91563.131. (CC) gcc options: -O3 -lm

OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Sparse Matrix MultiplyClangGCC10002000300040005000SE +/- 16.69, N = 3SE +/- 23.87, N = 34508.824132.951. (CC) gcc options: -O3 -lm

OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Dense LU Matrix FactorizationClangGCC15003000450060007500SE +/- 8.30, N = 3SE +/- 6.68, N = 36907.385124.151. (CC) gcc options: -O3 -lm

OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Jacobi Successive Over-RelaxationClangGCC400800120016002000SE +/- 0.12, N = 3SE +/- 0.43, N = 31986.561987.031. (CC) gcc options: -O3 -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 2.0Throughput Test: KostyaClangGCC0.68631.37262.05892.74523.4315SE +/- 0.00, N = 3SE +/- 0.00, N = 33.033.051. (CXX) g++ options: -O3

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 2.0Throughput Test: TopTweetClangGCC0.99681.99362.99043.98724.984SE +/- 0.00, N = 3SE +/- 0.00, N = 34.434.251. (CXX) g++ options: -O3

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 2.0Throughput Test: LargeRandomClangGCC0.2340.4680.7020.9361.17SE +/- 0.00, N = 3SE +/- 0.00, N = 31.001.041. (CXX) g++ options: -O3

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 2.0Throughput Test: PartialTweetsClangGCC0.97881.95762.93643.91524.894SE +/- 0.00, N = 3SE +/- 0.00, N = 34.354.181. (CXX) g++ options: -O3

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 2.0Throughput Test: DistinctUserIDClangGCC1.00132.00263.00394.00525.0065SE +/- 0.00, N = 3SE +/- 0.00, N = 34.454.191. (CXX) g++ options: -O3

Sockperf

This is a network socket API performance benchmark developed by Mellanox. This test profile runs both the client and server on the local host for evaluating individual system performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMessages Per Second, More Is BetterSockperf 3.7Test: ThroughputClangGCC200K400K600K800K1000KSE +/- 6642.87, N = 5SE +/- 3804.35, N = 57931858473391. (CXX) g++ options: --param -O3 -rdynamic

SQLite Speedtest

This is a benchmark of SQLite's speedtest1 benchmark program with an increased problem size of 1,000. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSQLite Speedtest 3.30Timed Time - Size 1,000ClangGCC1020304050SE +/- 0.05, N = 3SE +/- 0.07, N = 345.4544.641. (CC) gcc options: -O3 -lz

Timed MrBayes Analysis

This test performs a bayesian analysis of a set of primate genome sequences in order to estimate their phylogeny. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MrBayes Analysis 3.2.7Primate Phylogeny AnalysisClangGCC50100150200250SE +/- 1.35, N = 12SE +/- 3.68, N = 9192.75240.571. (CC) gcc options: -O3 -std=c99 -pedantic -lm -lreadline

TNN

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

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: DenseNetClangGCC16003200480064008000SE +/- 63.12, N = 8SE +/- 2.99, N = 37411.325229.21-fopenmp=libomp - MIN: 5728.98 / MAX: 13889.4-fopenmp - MIN: 5076.63 / MAX: 5318.221. (CXX) g++ options: -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: MobileNet v2ClangGCC90180270360450SE +/- 3.88, N = 7SE +/- 0.23, N = 3426.56306.61-fopenmp=libomp - MIN: 350.24 / MAX: 452.86-fopenmp - MIN: 296.56 / MAX: 311.251. (CXX) g++ options: -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: SqueezeNet v2ClangGCC1326395265SE +/- 0.03, N = 3SE +/- 0.00, N = 356.6153.28-fopenmp=libomp - MIN: 56.51 / MAX: 56.7-fopenmp - MIN: 53.24 / MAX: 53.391. (CXX) g++ options: -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: SqueezeNet v1.1ClangGCC70140210280350SE +/- 0.02, N = 3SE +/- 0.06, N = 3330.09321.83-fopenmp=libomp - MIN: 329.96 / MAX: 330.29-fopenmp - MIN: 321.48 / MAX: 322.341. (CXX) g++ options: -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

WavPack Audio Encoding

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

OpenBenchmarking.orgSeconds, Fewer Is BetterWavPack Audio Encoding 5.3WAV To WavPackClangGCC510152025SE +/- 0.00, N = 5SE +/- 0.00, N = 517.9818.421. (CXX) g++ options: -rdynamic

Xmrig

Xmrig is an open-source cross-platform CPU/GPU miner for RandomX, KawPow, CryptoNight and AstroBWT. This test profile is setup to measure the Xmlrig CPU mining performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.12.1Variant: Monero - Hash Count: 1MClangGCC5001000150020002500SE +/- 20.43, N = 3SE +/- 44.51, N = 72520.62329.9-funroll-loops-static-libgcc -static-libstdc++1. (CXX) g++ options: -fexceptions -fno-rtti -O3 -Ofast -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.12.1Variant: Wownero - Hash Count: 1MClangGCC6001200180024003000SE +/- 38.43, N = 3SE +/- 20.64, N = 32676.22541.9-funroll-loops-static-libgcc -static-libstdc++1. (CXX) g++ options: -fexceptions -fno-rtti -O3 -Ofast -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc

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 1.5.0Compression Level: 3 - Compression SpeedClangGCC8001600240032004000SE +/- 29.67, N = 3SE +/- 7.65, N = 33525.23526.61. (CC) gcc options: -O3 -pthread -lz -llzma -llz4

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 3 - Decompression SpeedClangGCC10002000300040005000SE +/- 3.94, N = 3SE +/- 0.42, N = 34234.84821.41. (CC) gcc options: -O3 -pthread -lz -llzma -llz4

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 8 - Compression SpeedClangGCC2004006008001000SE +/- 10.66, N = 3SE +/- 6.29, N = 3880.2866.11. (CC) gcc options: -O3 -pthread -lz -llzma -llz4

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 8 - Decompression SpeedClangGCC11002200330044005500SE +/- 0.60, N = 3SE +/- 14.08, N = 34385.74986.01. (CC) gcc options: -O3 -pthread -lz -llzma -llz4

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19 - Compression SpeedClangGCC612182430SE +/- 0.20, N = 3SE +/- 0.17, N = 325.926.81. (CC) gcc options: -O3 -pthread -lz -llzma -llz4

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19 - Decompression SpeedClangGCC10002000300040005000SE +/- 3.23, N = 3SE +/- 6.68, N = 33932.44513.11. (CC) gcc options: -O3 -pthread -lz -llzma -llz4

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 3, Long Mode - Compression SpeedClangGCC60120180240300SE +/- 3.71, N = 3SE +/- 2.09, N = 3272.4265.41. (CC) gcc options: -O3 -pthread -lz -llzma -llz4

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 3, Long Mode - Decompression SpeedClangGCC11002200330044005500SE +/- 0.98, N = 3SE +/- 5.93, N = 34647.85241.11. (CC) gcc options: -O3 -pthread -lz -llzma -llz4

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 8, Long Mode - Compression SpeedClangGCC150300450600750SE +/- 10.06, N = 15SE +/- 4.40, N = 15691.9716.91. (CC) gcc options: -O3 -pthread -lz -llzma -llz4

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 8, Long Mode - Decompression SpeedClangGCC12002400360048006000SE +/- 1.01, N = 15SE +/- 1.43, N = 154854.75478.31. (CC) gcc options: -O3 -pthread -lz -llzma -llz4

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19, Long Mode - Compression SpeedClangGCC510152025SE +/- 0.26, N = 3SE +/- 0.29, N = 321.021.91. (CC) gcc options: -O3 -pthread -lz -llzma -llz4

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19, Long Mode - Decompression SpeedClangGCC10002000300040005000SE +/- 4.49, N = 3SE +/- 2.75, N = 34146.64543.41. (CC) gcc options: -O3 -pthread -lz -llzma -llz4

134 Results Shown

AOBench
Basis Universal:
  ETC1S
  UASTC Level 0
  UASTC Level 2
  UASTC Level 3
Botan:
  KASUMI
  KASUMI - Decrypt
  Twofish
  Twofish - Decrypt
  Blowfish
  Blowfish - Decrypt
  CAST-256
  CAST-256 - Decrypt
  ChaCha20Poly1305
  ChaCha20Poly1305 - Decrypt
C-Ray
Coremark
Crypto++:
  Keyed Algorithms
  Unkeyed Algorithms
  Integer + Elliptic Curve Public Key Algorithms
dav1d:
  Chimera 1080p
  Summer Nature 4K
  Summer Nature 1080p
  Chimera 1080p 10-bit
eSpeak-NG Speech Engine
FLAC Audio Encoding
Gcrypt Library
GnuPG
Google Draco:
  Lion
  Church Facade
GraphicsMagick:
  Swirl
  Rotate
  Sharpen
  Enhanced
  Resizing
  Noise-Gaussian
  HWB Color Space
Himeno Benchmark
JPEG XL libjxl:
  PNG - 5
  PNG - 7
  JPEG - 5
  JPEG - 7
  JPEG - 8
LAME MP3 Encoding
LAMMPS Molecular Dynamics Simulator
libgav1:
  Chimera 1080p
  Summer Nature 4K
  Summer Nature 1080p
  Chimera 1080p 10-bit
libjpeg-turbo tjbench
Liquid-DSP:
  1 - 256 - 57
  2 - 256 - 57
  4 - 256 - 57
  8 - 256 - 57
LuaJIT:
  Composite
  Monte Carlo
  Fast Fourier Transform
  Sparse Matrix Multiply
  Dense LU Matrix Factorization
  Jacobi Successive Over-Relaxation
NCNN:
  CPU - mobilenet
  CPU-v2-v2 - mobilenet-v2
  CPU-v3-v3 - mobilenet-v3
  CPU - shufflenet-v2
  CPU - efficientnet-b0
  CPU - blazeface
  CPU - googlenet
  CPU - vgg16
  CPU - resnet18
  CPU - alexnet
  CPU - resnet50
  CPU - yolov4-tiny
  CPU - squeezenet_ssd
  CPU - regnety_400m
  CPU - mnasnet
NCNN:
  CPU - mobilenet
  CPU-v2-v2 - mobilenet-v2
  CPU-v3-v3 - mobilenet-v3
  CPU - shufflenet-v2
  CPU - mnasnet
  CPU - efficientnet-b0
  CPU - blazeface
  CPU - googlenet
  CPU - vgg16
  CPU - resnet18
  CPU - alexnet
  CPU - resnet50
  CPU - yolov4-tiny
  CPU - squeezenet_ssd
  CPU - regnety_400m
  CPU - vision_transformer
  CPU - FastestDet
Ngspice:
  C2670
  C7552
OpenJPEG
OpenSSL:
  SHA256
  RSA4096
  RSA4096
Opus Codec Encoding
POV-Ray
Primesieve
SciMark:
  Composite
  Monte Carlo
  Fast Fourier Transform
  Sparse Matrix Multiply
  Dense LU Matrix Factorization
  Jacobi Successive Over-Relaxation
simdjson:
  Kostya
  TopTweet
  LargeRand
  PartialTweets
  DistinctUserID
Sockperf
SQLite Speedtest
Timed MrBayes Analysis
TNN:
  CPU - DenseNet
  CPU - MobileNet v2
  CPU - SqueezeNet v2
  CPU - SqueezeNet v1.1
WavPack Audio Encoding
Xmrig:
  Monero - 1M
  Wownero - 1M
Zstd Compression:
  3 - Compression Speed
  3 - Decompression Speed
  8 - Compression Speed
  8 - Decompression Speed
  19 - Compression Speed
  19 - Decompression Speed
  3, Long Mode - Compression Speed
  3, Long Mode - Decompression Speed
  8, Long Mode - Compression Speed
  8, Long Mode - Decompression Speed
  19, Long Mode - Compression Speed
  19, Long Mode - Decompression Speed