Intel 10980XE  GCC Compiler Benchmarks

Intel Core i9-10980XE GCC compiler benchmarking by Michael Larabel for a future article.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2107032-IB-10980XECO53
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 4 Tests
Bioinformatics 3 Tests
C/C++ Compiler Tests 21 Tests
Compression Tests 3 Tests
CPU Massive 20 Tests
Creator Workloads 24 Tests
Cryptography 5 Tests
Encoding 13 Tests
Finance 2 Tests
HPC - High Performance Computing 7 Tests
Imaging 3 Tests
Machine Learning 4 Tests
Multi-Core 18 Tests
NVIDIA GPU Compute 3 Tests
OpenMPI Tests 2 Tests
Programmer / Developer System Benchmarks 3 Tests
Raytracing 2 Tests
Renderers 3 Tests
Scientific Computing 3 Tests
Server CPU Tests 12 Tests
Single-Threaded 6 Tests
Speech 2 Tests
Telephony 3 Tests
Video Encoding 9 Tests
Common Workstation Benchmarks 2 Tests

Statistics

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

Graph Settings

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

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
GCC 8.5
July 03 2021
  6 Hours, 30 Minutes
GCC 9.4
July 02 2021
  9 Hours, 31 Minutes
GCC 10.3
July 02 2021
  6 Hours, 12 Minutes
GCC 11.1
July 02 2021
  6 Hours, 7 Minutes
GCC 12.0.0 20210701
July 01 2021
  7 Hours, 40 Minutes
Invert Hiding All Results Option
  7 Hours, 12 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):


Intel 10980XE  GCC Compiler BenchmarksOpenBenchmarking.orgPhoronix Test SuiteIntel Core i9-10980XE @ 4.80GHz (18 Cores / 36 Threads)ASRock X299 Steel Legend (P1.30 BIOS)Intel Sky Lake-E DMI3 Registers32GBSamsung SSD 970 PRO 512GBNVIDIA NV132 11GBRealtek ALC1220ASUS VP28UIntel I219-V + Intel I211Ubuntu 21.045.11.0-22-generic (x86_64)GNOME Shell 3.38.4X Server + Waylandnouveau4.3 Mesa 21.0.11.0.2GCC 8.5.0GCC 9.4.0GCC 10.3.0GCC 11.1.0GCC 12.0.0 20210701ext42560x1600ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLVulkanCompilersFile-SystemScreen ResolutionIntel 10980XE  GCC Compiler Benchmarks PerformanceSystem Logs- Transparent Huge Pages: madvise- CXXFLAGS="-O3 -march=native" CFLAGS="-O3 -march=native"- --disable-multilib --enable-checking=release --enable-languages=c,c++- Scaling Governor: intel_cpufreq schedutil - CPU Microcode: 0x5003102- Python 3.9.5- itlb_multihit: KVM: Mitigation of VMX disabled + 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: Not affected + tsx_async_abort: Mitigation of TSX disabled

GCC 8.5GCC 9.4GCC 10.3GCC 11.1GCC 12.0.0 20210701Result OverviewPhoronix Test Suite100%108%115%123%eSpeak-NG Speech EngineSmallptGraphicsMagickTimed MrBayes AnalysisQuantLibBotanCoremarkGcrypt LibraryTNNStockfishVP9 libvpx EncodingZstd CompressiononeDNNx265Liquid-DSPWebP Image EncodeOpus Codec EncodingViennaCLTachyonSVT-VP9Timed HMMer SearchMobile Neural NetworkLAME MP3 Encoding7-Zip CompressionCrypto++EtcpakC-RayVOSK Speech Recognition ToolkitHimeno BenchmarkSecureMarkNCNNC-Bloscdav1dFLAC Audio EncodingSQLite Speedtestlibjpeg-turbo tjbenchNgspiceSVT-AV1PJSIPAOM AV1GnuPGKvazaarSVT-HEVCWavPack Audio EncodingFinanceBench

Intel 10980XE  GCC Compiler Benchmarkscompress-7zip: Compress Speed Testaom-av1: Speed 6 Realtime - Bosphorus 4Kaom-av1: Speed 6 Two-Pass - Bosphorus 4Kaom-av1: Speed 8 Realtime - Bosphorus 4Kaom-av1: Speed 9 Realtime - Bosphorus 4Kbotan: KASUMIbotan: KASUMI - Decryptbotan: AES-256botan: AES-256 - Decryptbotan: Twofishbotan: Twofish - Decryptbotan: Blowfishbotan: Blowfish - Decryptbotan: CAST-256botan: CAST-256 - Decryptbotan: ChaCha20Poly1305botan: ChaCha20Poly1305 - Decryptblosc: blosclzc-ray: Total Time - 4K, 16 Rays Per Pixelcoremark: CoreMark Size 666 - Iterations Per Secondcryptopp: Keyed Algorithmscryptopp: Unkeyed Algorithmscryptopp: Integer + Elliptic Curve Public Key Algorithmsdav1d: Summer Nature 4Kdav1d: Chimera 1080p 10-bitespeak: Text-To-Speech Synthesisetcpak: DXT1etcpak: ETC2etcpak: ETC1 + Ditheringfinancebench: Repo OpenMPfinancebench: Bonds OpenMPencode-flac: WAV To FLACgcrypt: gnupg: 2.7GB Sample File Encryptiongraphics-magick: Swirlgraphics-magick: Rotategraphics-magick: Sharpengraphics-magick: Enhancedgraphics-magick: Resizinggraphics-magick: Noise-Gaussiangraphics-magick: HWB Color Spacehimeno: Poisson Pressure Solverkvazaar: Bosphorus 4K - Very Fastkvazaar: Bosphorus 4K - Ultra Fastencode-mp3: WAV To MP3libgav1: Summer Nature 4Klibgav1: Chimera 1080p 10-bittjbench: Decompression Throughputliquid-dsp: 32 - 256 - 57liquid-dsp: 36 - 256 - 57mnn: mobilenetV3mnn: squeezenetv1.1mnn: resnet-v2-50mnn: SqueezeNetV1.0mnn: MobileNetV2_224mnn: mobilenet-v1-1.0mnn: inception-v3ncnn: 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_400mngspice: C2670ngspice: C7552onednn: IP Shapes 1D - u8s8f32 - CPUonednn: IP Shapes 3D - u8s8f32 - CPUonednn: IP Shapes 1D - bf16bf16bf16 - CPUonednn: IP Shapes 3D - bf16bf16bf16 - CPUonednn: Convolution Batch Shapes Auto - u8s8f32 - CPUonednn: Deconvolution Batch shapes_1d - u8s8f32 - CPUonednn: Deconvolution Batch shapes_3d - u8s8f32 - CPUonednn: Recurrent Neural Network Training - u8s8f32 - CPUonednn: Convolution Batch Shapes Auto - bf16bf16bf16 - CPUonednn: Deconvolution Batch shapes_1d - bf16bf16bf16 - CPUonednn: Deconvolution Batch shapes_3d - bf16bf16bf16 - CPUonednn: Recurrent Neural Network Inference - u8s8f32 - CPUonednn: Recurrent Neural Network Training - bf16bf16bf16 - CPUonednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPUonednn: Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPUonednn: Matrix Multiply Batch Shapes Transformer - bf16bf16bf16 - CPUencode-opus: WAV To Opus Encodepjsip: INVITEpjsip: OPTIONS, Statefulpjsip: OPTIONS, Statelessquantlib: securemark: SecureMark-TLSsmallpt: Global Illumination Renderer; 128 Samplessqlite-speedtest: Timed Time - Size 1,000stockfish: Total Timesvt-av1: Preset 4 - Bosphorus 4Ksvt-av1: Preset 8 - Bosphorus 4Ksvt-hevc: 1 - Bosphorus 1080psvt-hevc: 7 - Bosphorus 1080psvt-hevc: 10 - Bosphorus 1080psvt-vp9: VMAF Optimized - Bosphorus 1080psvt-vp9: PSNR/SSIM Optimized - Bosphorus 1080psvt-vp9: Visual Quality Optimized - Bosphorus 1080ptachyon: Total Timehmmer: Pfam Database Searchmrbayes: Primate Phylogeny Analysistnn: CPU - DenseNettnn: CPU - MobileNet v2tnn: CPU - SqueezeNet v2tnn: CPU - SqueezeNet v1.1viennacl: CPU BLAS - sCOPYviennacl: CPU BLAS - sAXPYviennacl: CPU BLAS - sDOTviennacl: CPU BLAS - dCOPYviennacl: CPU BLAS - dAXPYviennacl: CPU BLAS - dDOTviennacl: CPU BLAS - dGEMV-Nviennacl: CPU BLAS - dGEMV-Tviennacl: CPU BLAS - dGEMM-NNviennacl: CPU BLAS - dGEMM-NTviennacl: CPU BLAS - dGEMM-TNviennacl: CPU BLAS - dGEMM-TTvosk: vpxenc: Speed 0 - Bosphorus 4Kvpxenc: Speed 5 - Bosphorus 4Kencode-wavpack: WAV To WavPackwebp: Quality 100, Losslesswebp: Quality 100, Highest Compressionwebp: Quality 100, Lossless, Highest Compressionx265: Bosphorus 4Kcompress-zstd: 8 - Compression Speedcompress-zstd: 8 - Decompression Speedcompress-zstd: 19 - Compression Speedcompress-zstd: 19 - 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 SpeedGCC 8.5GCC 9.4GCC 10.3GCC 11.1GCC 12.0.0 20210701997117.514.4619.4027.1899.71697.6443998.6273991.201416.184420.366491.138482.780152.235152.429984.019977.16511800.729.818618050.830009714.487669377.7809025519.144212197.46215.1626.8361445.235198.109329.12842354.89843774820.1875008.436194.12164.23979280919742414443909034522.73117021.3540.138.716218.8135819246300009167900002.4034.56427.2975.5943.7042.43330.15414.165.364.725.054.826.692.5612.7336.2010.549.0518.3320.8415.6313.77134.346126.2000.5284161.232395.540622.949039.347660.4614590.6794821573.037.890329.8285811.0180937.6071573.18939.9230.4415001.763088.283330758011353022586.32598695.28657.606511400131.34011.92512.88190.03374.62306.08310.79247.4548.1611126.204146.0963505.931321.38770.124289.96345.968.877.038.157.163.669.579.955.554.756.055.220.7214.758.2213.35517.2026.64237.69521.53425.73361.760.32676.8335.53547.443.32819.2982987.434.4419.3427.24100.41198.5573987.0803993.890414.445411.573486.315475.408150.585150.879951.152945.44911802.630.035650499.474888719.762484375.2314925538.547039199.89219.6928.1071450.560199.097336.10642795.05338576452.7786468.500193.97364.22875277626542416173878644609.39856321.2040.168.525220.6177879302366679216700002.2974.42031.4525.5403.5942.45532.41213.945.104.574.974.736.572.5412.4436.0110.589.1517.5921.3515.0813.87134.222127.6880.5267981.279915.595332.860089.554550.4594560.8288661636.968.100389.7918510.9596960.1281639.78961.3830.4675941.791508.241325257291359032568.82634576.04557.034506225521.35512.02112.91190.62376.89295.07302.25243.4847.8849126.506157.3323527.682347.43673.938296.14247.171.278.038.157.463.771.879.756.154.156.254.920.9934.878.6113.37516.8236.56036.86921.64429.43436.860.22802.7375.63628.443.53017.6974267.384.4819.2827.8698.20096.8793999.2483998.479404.157411.522486.288474.804151.184151.248788.573780.12311713.430.430630485.588510717.165559372.5830415503.078606195.15222.2732.6721484.230197.629329.48635458.66276149799.1158858.369193.41164.42476176531742715854038644538.66196121.0940.648.730219.5427999397166679406600002.3414.27128.2555.6123.6692.46730.80413.815.124.645.024.806.622.6113.0636.3511.169.1817.8721.2615.2613.63133.912126.8770.5260141.227035.533342.939789.350950.4604820.6805221565.417.901639.3906210.9199935.9621566.75938.2200.4269021.755208.283328157441382222529.82634726.13057.303499422761.35912.06213.04189.88372.69299.97306.89246.7547.9045126.687154.6293508.290311.60469.297286.21546.470.377.438.357.354.771.679.658.756.458.957.120.7534.848.5913.34017.2516.86637.86921.84424.03285.560.12701.9370.13479.043.92876.9981497.514.3319.6428.07100.69797.0013985.2663995.232367.677373.562442.670439.555141.031140.850779.376774.64511926.829.960597455.160812692.986399360.4141925593.130439192.95223.0635.0861468.968194.759327.32934558.22395848802.7552088.411208.34364.20492485231943215714039164592.94740121.0140.318.732218.6181629511700009545366672.4124.60928.4455.7233.7542.47731.27513.795.064.665.054.726.562.5512.8436.5610.979.0817.7721.3715.2313.93134.711129.3960.5281331.230125.545442.934289.355500.4599560.6970801563.057.904779.4134610.9199938.0431566.25936.8800.4306761.762648.456324057691364442749.12595656.20157.411522069631.34712.09012.96191.02375.65297.32305.72244.0547.8659126.616142.9343508.390314.56169.802288.91046.770.777.638.357.463.771.779.351.049.851.950.520.8944.878.6313.35316.8036.78036.47121.16419.53351.961.02642.2469.43553.244.32775.7984937.494.4019.6728.10100.60996.6103972.0203993.173366.648374.707442.265442.410140.309140.480781.383775.48811889.429.973601830.263292714.205269374.6407955532.467940194.06221.9427.2811419.365197.128325.27834223.30338648317.5794278.379196.22264.61390379431942916074038844580.18807321.1540.208.59928.2421.32217.4258169444333339375533332.3724.28328.2725.5063.7292.47730.79713.814.894.544.984.586.272.5412.2136.7010.938.9917.7422.8315.2813.48135.428128.3200.5279391.224965.536722.946709.342060.4596600.6786261567.417.912589.5945210.9330936.4911564.71935.3780.4256751.744718.186330457631379662773.62645145.99156.715507345711.34811.96612.94191.33375.32293.71303.54244.5649.3237129.454145.1743524.746318.05669.231287.49046.470.177.138.257.263.771.479.551.249.851.951.520.5744.928.6513.33116.8926.54837.16121.08432.73332.760.82773.9385.53531.443.92782.7OpenBenchmarking.org

7-Zip Compression

This is a test of 7-Zip using p7zip with its integrated benchmark feature or upstream 7-Zip for the Windows x64 build. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 16.02Compress Speed TestGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.420K40K60K80K100KSE +/- 46.23, N = 3SE +/- 304.44, N = 3SE +/- 228.39, N = 3SE +/- 69.57, N = 3SE +/- 343.09, N = 397426981499849399711982981. (CXX) g++ options: -pipe -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 3.1Encoder Mode: Speed 6 Realtime - Input: Bosphorus 4KGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.4246810SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.08, N = 12SE +/- 0.05, N = 3SE +/- 0.08, N = 157.387.517.497.517.431. (CXX) g++ options: -O3 -march=native -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.1Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 4KGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.41.0082.0163.0244.0325.04SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 10SE +/- 0.06, N = 3SE +/- 0.05, N = 34.484.334.404.464.441. (CXX) g++ options: -O3 -march=native -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.1Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4KGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.4510152025SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.09, N = 3SE +/- 0.04, N = 3SE +/- 0.06, N = 319.2819.6419.6719.4019.341. (CXX) g++ options: -O3 -march=native -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.1Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4KGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.4714212835SE +/- 0.15, N = 3SE +/- 0.08, N = 3SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.07, N = 327.8628.0728.1027.1827.241. (CXX) g++ options: -O3 -march=native -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: KASUMIGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.420406080100SE +/- 0.06, N = 3SE +/- 0.07, N = 3SE +/- 0.25, N = 3SE +/- 0.01, N = 3SE +/- 0.12, N = 398.20100.70100.6199.72100.411. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: KASUMI - DecryptGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.420406080100SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.07, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 396.8897.0096.6197.6498.561. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: AES-256GCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.49001800270036004500SE +/- 4.08, N = 3SE +/- 2.67, N = 3SE +/- 7.30, N = 3SE +/- 0.87, N = 3SE +/- 0.82, N = 33999.253985.273972.023998.633987.081. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: AES-256 - DecryptGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.49001800270036004500SE +/- 0.87, N = 3SE +/- 0.79, N = 3SE +/- 4.17, N = 3SE +/- 1.28, N = 3SE +/- 0.39, N = 33998.483995.233993.173991.203993.891. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: TwofishGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.490180270360450SE +/- 0.23, N = 3SE +/- 1.13, N = 3SE +/- 0.30, N = 3SE +/- 0.33, N = 3SE +/- 0.12, N = 3404.16367.68366.65416.18414.451. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: Twofish - DecryptGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.490180270360450SE +/- 0.26, N = 3SE +/- 0.56, N = 3SE +/- 0.17, N = 3SE +/- 0.07, N = 3SE +/- 0.05, N = 3411.52373.56374.71420.37411.571. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: BlowfishGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.4110220330440550SE +/- 0.22, N = 3SE +/- 0.12, N = 3SE +/- 0.07, N = 3SE +/- 0.01, N = 3SE +/- 0.29, N = 3486.29442.67442.27491.14486.321. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: Blowfish - DecryptGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.4100200300400500SE +/- 0.30, N = 3SE +/- 0.13, N = 3SE +/- 0.07, N = 3SE +/- 0.04, N = 3SE +/- 0.21, N = 3474.80439.56442.41482.78475.411. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: CAST-256GCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.4306090120150SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.30, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3151.18141.03140.31152.24150.591. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: CAST-256 - DecryptGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.4306090120150SE +/- 0.06, N = 3SE +/- 0.50, N = 3SE +/- 0.28, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3151.25140.85140.48152.43150.881. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: ChaCha20Poly1305GCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.42004006008001000SE +/- 0.15, N = 3SE +/- 1.05, N = 3SE +/- 0.73, N = 3SE +/- 2.79, N = 3SE +/- 1.36, N = 3788.57779.38781.38984.02951.151. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: ChaCha20Poly1305 - DecryptGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.42004006008001000SE +/- 0.79, N = 3SE +/- 0.89, N = 3SE +/- 0.47, N = 3SE +/- 2.38, N = 3SE +/- 0.08, N = 3780.12774.65775.49977.17945.451. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

C-Blosc

A simple, compressed, fast and persistent data store library for C. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterC-Blosc 2.0Compressor: blosclzGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.43K6K9K12K15KSE +/- 21.15, N = 3SE +/- 69.56, N = 3SE +/- 37.20, N = 3SE +/- 11.42, N = 3SE +/- 18.15, N = 311713.411926.811889.411800.711802.61. (CC) gcc options: -std=gnu99 -O3 -pthread -lrt -lm

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 PixelGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.4714212835SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 330.4329.9629.9729.8230.041. (CC) gcc options: -lm -lpthread -O3 -march=native

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 SecondGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.4140K280K420K560K700KSE +/- 2003.80, N = 3SE +/- 1267.23, N = 3SE +/- 2406.19, N = 3SE +/- 3624.80, N = 3SE +/- 1621.16, N = 3630485.59597455.16601830.26618050.83650499.471. (CC) gcc options: -O2 -O3 -march=native -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 AlgorithmsGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.4160320480640800SE +/- 0.48, N = 3SE +/- 0.20, N = 3SE +/- 0.24, N = 3SE +/- 0.10, N = 3SE +/- 0.35, N = 3717.17692.99714.21714.49719.761. (CXX) g++ options: -O3 -march=native -fPIC -pthread -pipe

OpenBenchmarking.orgMiB/second, More Is BetterCrypto++ 8.2Test: Unkeyed AlgorithmsGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.480160240320400SE +/- 0.17, N = 3SE +/- 0.04, N = 3SE +/- 0.68, N = 3SE +/- 0.02, N = 3SE +/- 0.65, N = 3372.58360.41374.64377.78375.231. (CXX) g++ options: -O3 -march=native -fPIC -pthread -pipe

OpenBenchmarking.orgMiB/second, More Is BetterCrypto++ 8.2Test: Integer + Elliptic Curve Public Key AlgorithmsGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.412002400360048006000SE +/- 1.85, N = 3SE +/- 1.99, N = 3SE +/- 5.19, N = 3SE +/- 1.33, N = 3SE +/- 6.16, N = 35503.085593.135532.475519.145538.551. (CXX) g++ options: -O3 -march=native -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 0.9.0Video Input: Summer Nature 4KGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.44080120160200SE +/- 2.16, N = 3SE +/- 1.13, N = 3SE +/- 1.97, N = 6SE +/- 0.89, N = 3SE +/- 1.65, N = 3195.15192.95194.06197.46199.89MIN: 149.2 / MAX: 222.59MIN: 132.83 / MAX: 217.9MIN: 131.48 / MAX: 225.93-lm - MIN: 150.4 / MAX: 226.05-lm - MIN: 143.79 / MAX: 228.441. (CC) gcc options: -O3 -march=native -pthread

OpenBenchmarking.orgFPS, More Is Betterdav1d 0.9.0Video Input: Chimera 1080p 10-bitGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.450100150200250SE +/- 0.50, N = 3SE +/- 1.18, N = 3SE +/- 0.48, N = 3SE +/- 0.39, N = 3SE +/- 0.34, N = 3222.27223.06221.94215.16219.69MIN: 157.09 / MAX: 436.51MIN: 157.45 / MAX: 397.96MIN: 157.38 / MAX: 404.98-lm - MIN: 151.62 / MAX: 411.26-lm - MIN: 156.35 / MAX: 406.231. (CC) gcc options: -O3 -march=native -pthread

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 SynthesisGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.4816243240SE +/- 0.09, N = 4SE +/- 0.16, N = 4SE +/- 0.18, N = 4SE +/- 0.19, N = 4SE +/- 0.23, N = 432.6735.0927.2826.8428.111. (CC) gcc options: -O3 -march=native -std=c99

Etcpak

Etcpack is the self-proclaimed "fastest ETC compressor on the planet" with focused on providing open-source, very fast ETC and S3 texture compression support. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMpx/s, More Is BetterEtcpak 0.7Configuration: DXT1GCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.430060090012001500SE +/- 0.37, N = 3SE +/- 0.47, N = 3SE +/- 1.30, N = 3SE +/- 1.51, N = 3SE +/- 0.45, N = 31484.231468.971419.371445.241450.561. (CXX) g++ options: -O3 -march=native -std=c++11 -lpthread

OpenBenchmarking.orgMpx/s, More Is BetterEtcpak 0.7Configuration: ETC2GCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.44080120160200SE +/- 0.08, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3197.63194.76197.13198.11199.101. (CXX) g++ options: -O3 -march=native -std=c++11 -lpthread

OpenBenchmarking.orgMpx/s, More Is BetterEtcpak 0.7Configuration: ETC1 + DitheringGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.470140210280350SE +/- 0.38, N = 3SE +/- 0.20, N = 3SE +/- 0.05, N = 3SE +/- 2.72, N = 3SE +/- 0.09, N = 3329.49327.33325.28329.13336.111. (CXX) g++ options: -O3 -march=native -std=c++11 -lpthread

FinanceBench

FinanceBench is a collection of financial program benchmarks with support for benchmarking on the GPU via OpenCL and CPU benchmarking with OpenMP. The FinanceBench test cases are focused on Black-Sholes-Merton Process with Analytic European Option engine, QMC (Sobol) Monte-Carlo method (Equity Option Example), Bonds Fixed-rate bond with flat forward curve, and Repo Securities repurchase agreement. FinanceBench was originally written by the Cavazos Lab at University of Delaware. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterFinanceBench 2016-07-25Benchmark: Repo OpenMPGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.49K18K27K36K45KSE +/- 120.35, N = 3SE +/- 43.71, N = 3SE +/- 22.03, N = 3SE +/- 34.41, N = 3SE +/- 10.60, N = 335458.6634558.2234223.3042354.9042795.051. (CXX) g++ options: -O3 -march=native -fopenmp

OpenBenchmarking.orgms, Fewer Is BetterFinanceBench 2016-07-25Benchmark: Bonds OpenMPGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.416K32K48K64K80KSE +/- 11.94, N = 3SE +/- 36.89, N = 3SE +/- 48.36, N = 3SE +/- 5.53, N = 3SE +/- 1061.39, N = 349799.1248802.7648317.5874820.1976452.781. (CXX) g++ options: -O3 -march=native -fopenmp

FLAC Audio Encoding

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

OpenBenchmarking.orgSeconds, Fewer Is BetterFLAC Audio Encoding 1.3.2WAV To FLACGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.4246810SE +/- 0.004, N = 5SE +/- 0.009, N = 5SE +/- 0.014, N = 5SE +/- 0.012, N = 5SE +/- 0.006, N = 58.3698.4118.3798.4368.5001. (CXX) g++ options: -O3 -march=native -fvisibility=hidden -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 1.9GCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.450100150200250SE +/- 0.44, N = 3SE +/- 0.18, N = 3SE +/- 0.33, N = 3SE +/- 0.27, N = 3SE +/- 0.21, N = 3193.41208.34196.22194.12193.971. (CC) gcc options: -O3 -march=native -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 EncryptionGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.41428425670SE +/- 0.36, N = 3SE +/- 0.23, N = 3SE +/- 0.56, N = 3SE +/- 0.17, N = 3SE +/- 0.19, N = 364.4264.2064.6164.2464.231. (CC) gcc options: -O3 -march=native

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: SwirlGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.42004006008001000SE +/- 0.33, N = 3SE +/- 1.20, N = 3SE +/- 0.33, N = 37619249037927521. (CC) gcc options: -fopenmp -O3 -march=native -pthread -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lz -lm -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: RotateGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.42004006008001000SE +/- 5.24, N = 3SE +/- 2.52, N = 3SE +/- 7.25, N = 15SE +/- 7.07, N = 15SE +/- 3.51, N = 37658527948097761. (CC) gcc options: -fopenmp -O3 -march=native -pthread -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lz -lm -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: SharpenGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.470140210280350SE +/- 0.33, N = 33173193191972651. (CC) gcc options: -fopenmp -O3 -march=native -pthread -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lz -lm -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: EnhancedGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.4901802703604504274324294244241. (CC) gcc options: -fopenmp -O3 -march=native -pthread -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lz -lm -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: ResizingGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.430060090012001500SE +/- 8.67, N = 3SE +/- 3.51, N = 3SE +/- 7.21, N = 3SE +/- 2.91, N = 3SE +/- 4.93, N = 3158515711607144416171. (CC) gcc options: -fopenmp -O3 -march=native -pthread -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lz -lm -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: Noise-GaussianGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.490180270360450SE +/- 0.67, N = 3SE +/- 0.33, N = 3SE +/- 0.58, N = 3SE +/- 0.33, N = 34034034033903871. (CC) gcc options: -fopenmp -O3 -march=native -pthread -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lz -lm -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: HWB Color SpaceGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.42004006008001000SE +/- 0.88, N = 3SE +/- 1.15, N = 3SE +/- 1.33, N = 38649168849038641. (CC) gcc options: -fopenmp -O3 -march=native -pthread -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lz -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 SolverGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.410002000300040005000SE +/- 13.08, N = 3SE +/- 0.64, N = 3SE +/- 2.82, N = 3SE +/- 0.61, N = 3SE +/- 5.70, N = 34538.664592.954580.194522.734609.401. (CC) gcc options: -O3 -march=native -mavx2

Kvazaar

This is a test of Kvazaar as a CPU-based H.265 video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 4K - Video Preset: Very FastGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.4510152025SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 321.0921.0121.1521.3521.201. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O3 -march=native -lpthread -lm -lrt

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 4K - Video Preset: Ultra FastGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.4918273645SE +/- 0.15, N = 3SE +/- 0.11, N = 3SE +/- 0.08, N = 3SE +/- 0.07, N = 3SE +/- 0.07, N = 340.6440.3140.2040.1340.161. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O3 -march=native -lpthread -lm -lrt

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 MP3GCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.4246810SE +/- 0.004, N = 3SE +/- 0.005, N = 3SE +/- 0.003, N = 3SE +/- 0.002, N = 3SE +/- 0.011, N = 38.7308.7328.5998.7168.5251. (CC) gcc options: -O3 -ffast-math -funroll-loops -fschedule-insns2 -fbranch-count-reg -fforce-addr -pipe -march=native -lm

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 0.16.3Video Input: Summer Nature 4KGCC 12.0.0 20210701714212835SE +/- 0.01, N = 328.241. (CXX) g++ options: -O3 -march=native -lpthread -lrt

OpenBenchmarking.orgFPS, More Is Betterlibgav1 0.16.3Video Input: Chimera 1080p 10-bitGCC 12.0.0 20210701510152025SE +/- 0.01, N = 321.321. (CXX) g++ options: -O3 -march=native -lpthread -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 ThroughputGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.450100150200250SE +/- 0.30, N = 3SE +/- 0.47, N = 3SE +/- 0.26, N = 3SE +/- 0.03, N = 3SE +/- 0.84, N = 3219.54218.62217.43218.81220.621. (CC) gcc options: -O3 -march=native -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: 32 - Buffer Length: 256 - Filter Length: 57GCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.4200M400M600M800M1000MSE +/- 2904171.33, N = 3SE +/- 4781007.56, N = 3SE +/- 4623189.13, N = 3SE +/- 353836.12, N = 3SE +/- 539269.05, N = 39397166679511700009444333339246300009302366671. (CC) gcc options: -O3 -march=native -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 36 - Buffer Length: 256 - Filter Length: 57GCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.4200M400M600M800M1000MSE +/- 272213.15, N = 3SE +/- 1013283.99, N = 3SE +/- 1056729.76, N = 3SE +/- 120554.28, N = 3SE +/- 588132.64, N = 39406600009545366679375533339167900009216700001. (CC) gcc options: -O3 -march=native -pthread -lm -lc -lliquid

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 1.2Model: mobilenetV3GCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.40.54271.08541.62812.17082.7135SE +/- 0.011, N = 3SE +/- 0.032, N = 3SE +/- 0.011, N = 3SE +/- 0.012, N = 3SE +/- 0.015, N = 152.3412.4122.3722.4032.297MIN: 2.16 / MAX: 2.53MIN: 2.23 / MAX: 2.61MIN: 2.25 / MAX: 2.5MIN: 2.28 / MAX: 2.54MIN: 1.96 / MAX: 2.531. (CXX) g++ options: -O3 -march=native -std=c++11 -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 1.2Model: squeezenetv1.1GCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.41.0372.0743.1114.1485.185SE +/- 0.162, N = 3SE +/- 0.007, N = 3SE +/- 0.149, N = 3SE +/- 0.036, N = 3SE +/- 0.061, N = 154.2714.6094.2834.5644.420MIN: 3.97 / MAX: 4.72MIN: 4.51 / MAX: 4.78MIN: 3.97 / MAX: 4.71MIN: 4.42 / MAX: 4.75MIN: 3.98 / MAX: 4.761. (CXX) g++ options: -O3 -march=native -std=c++11 -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 1.2Model: resnet-v2-50GCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.4714212835SE +/- 0.24, N = 3SE +/- 0.06, N = 3SE +/- 0.19, N = 3SE +/- 0.10, N = 3SE +/- 0.47, N = 1528.2628.4528.2727.3031.45MIN: 27.6 / MAX: 28.76MIN: 27.77 / MAX: 28.83MIN: 27.7 / MAX: 28.91MIN: 26.86 / MAX: 27.93MIN: 24.41 / MAX: 36.241. (CXX) g++ options: -O3 -march=native -std=c++11 -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 1.2Model: SqueezeNetV1.0GCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.41.28772.57543.86315.15086.4385SE +/- 0.083, N = 3SE +/- 0.020, N = 3SE +/- 0.079, N = 3SE +/- 0.056, N = 3SE +/- 0.039, N = 155.6125.7235.5065.5945.540MIN: 5.24 / MAX: 6.01MIN: 5.47 / MAX: 6.72MIN: 5.22 / MAX: 5.91MIN: 5.4 / MAX: 5.85MIN: 5.06 / MAX: 6.721. (CXX) g++ options: -O3 -march=native -std=c++11 -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 1.2Model: MobileNetV2_224GCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.40.84471.68942.53413.37884.2235SE +/- 0.090, N = 3SE +/- 0.018, N = 3SE +/- 0.058, N = 3SE +/- 0.069, N = 3SE +/- 0.040, N = 153.6693.7543.7293.7043.594MIN: 3.42 / MAX: 4.19MIN: 3.47 / MAX: 3.95MIN: 3.41 / MAX: 3.94MIN: 3.31 / MAX: 3.95MIN: 3.07 / MAX: 4.081. (CXX) g++ options: -O3 -march=native -std=c++11 -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 1.2Model: mobilenet-v1-1.0GCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.40.55731.11461.67192.22922.7865SE +/- 0.025, N = 3SE +/- 0.024, N = 3SE +/- 0.029, N = 3SE +/- 0.025, N = 3SE +/- 0.012, N = 152.4672.4772.4772.4332.455MIN: 2.32 / MAX: 2.68MIN: 2.3 / MAX: 2.65MIN: 2.3 / MAX: 2.74MIN: 2.32 / MAX: 2.62MIN: 2.23 / MAX: 3.161. (CXX) g++ options: -O3 -march=native -std=c++11 -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 1.2Model: inception-v3GCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.4816243240SE +/- 0.42, N = 3SE +/- 0.42, N = 3SE +/- 0.43, N = 3SE +/- 0.10, N = 3SE +/- 0.28, N = 1530.8031.2830.8030.1532.41MIN: 30.12 / MAX: 31.88MIN: 30.28 / MAX: 31.97MIN: 30.14 / MAX: 31.87MIN: 29.77 / MAX: 30.53MIN: 29.17 / MAX: 33.891. (CXX) g++ options: -O3 -march=native -std=c++11 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: mobilenetGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.448121620SE +/- 0.06, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 313.8113.7913.8114.1613.94MIN: 13.51 / MAX: 20.36MIN: 13.61 / MAX: 14.23MIN: 13.64 / MAX: 14.54MIN: 13.93 / MAX: 14.76MIN: 13.68 / MAX: 22.271. (CXX) g++ options: -O3 -march=native -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU-v2-v2 - Model: mobilenet-v2GCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.41.2062.4123.6184.8246.03SE +/- 0.01, N = 3SE +/- 0.10, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 35.125.064.895.365.10MIN: 4.76 / MAX: 8.89MIN: 4.72 / MAX: 10.01MIN: 4.72 / MAX: 10.07MIN: 4.96 / MAX: 8.4MIN: 4.73 / MAX: 10.41. (CXX) g++ options: -O3 -march=native -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU-v3-v3 - Model: mobilenet-v3GCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.41.0622.1243.1864.2485.31SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 34.644.664.544.724.57MIN: 4.36 / MAX: 10.01MIN: 4.46 / MAX: 12.92MIN: 4.37 / MAX: 11.47MIN: 4.49 / MAX: 7.39MIN: 4.37 / MAX: 9.051. (CXX) g++ options: -O3 -march=native -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: shufflenet-v2GCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.41.13632.27263.40894.54525.6815SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 35.025.054.985.054.97MIN: 4.83 / MAX: 15.94MIN: 4.88 / MAX: 9.37MIN: 4.88 / MAX: 8.6MIN: 4.83 / MAX: 14.14MIN: 4.8 / MAX: 8.91. (CXX) g++ options: -O3 -march=native -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: mnasnetGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.41.08452.1693.25354.3385.4225SE +/- 0.10, N = 3SE +/- 0.03, N = 3SE +/- 0.05, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 34.804.724.584.824.73MIN: 4.42 / MAX: 16.22MIN: 4.46 / MAX: 10.72MIN: 4.39 / MAX: 10.87MIN: 4.55 / MAX: 12.4MIN: 4.44 / MAX: 11.541. (CXX) g++ options: -O3 -march=native -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: efficientnet-b0GCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.4246810SE +/- 0.11, N = 3SE +/- 0.02, N = 3SE +/- 0.09, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 36.626.566.276.696.57MIN: 6.24 / MAX: 24.41MIN: 6.27 / MAX: 11.76MIN: 6.05 / MAX: 14.37MIN: 6.33 / MAX: 10.85MIN: 6.28 / MAX: 14.641. (CXX) g++ options: -O3 -march=native -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: blazefaceGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.40.58731.17461.76192.34922.9365SE +/- 0.07, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 32.612.552.542.562.54MIN: 2.47 / MAX: 3.3MIN: 2.47 / MAX: 3.17MIN: 2.46 / MAX: 3.12MIN: 2.5 / MAX: 3.31MIN: 2.45 / MAX: 3.321. (CXX) g++ options: -O3 -march=native -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: googlenetGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.43691215SE +/- 0.08, N = 3SE +/- 0.02, N = 3SE +/- 0.31, N = 3SE +/- 0.23, N = 3SE +/- 0.28, N = 313.0612.8412.2112.7312.44MIN: 12.84 / MAX: 14.29MIN: 12.68 / MAX: 16.73MIN: 11.77 / MAX: 13.02MIN: 12.1 / MAX: 19.86MIN: 12 / MAX: 13.221. (CXX) g++ options: -O3 -march=native -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: vgg16GCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.4816243240SE +/- 0.47, N = 3SE +/- 0.52, N = 3SE +/- 0.53, N = 3SE +/- 0.37, N = 3SE +/- 0.49, N = 336.3536.5636.7036.2036.01MIN: 35.3 / MAX: 37.7MIN: 35.42 / MAX: 58.41MIN: 35.5 / MAX: 41.99MIN: 35.36 / MAX: 47.25MIN: 35.37 / MAX: 37.681. (CXX) g++ options: -O3 -march=native -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: resnet18GCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.43691215SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.23, N = 3SE +/- 0.28, N = 311.1610.9710.9310.5410.58MIN: 11.03 / MAX: 11.45MIN: 10.84 / MAX: 20.49MIN: 10.84 / MAX: 11.27MIN: 10.19 / MAX: 17.98MIN: 10.2 / MAX: 11.571. (CXX) g++ options: -O3 -march=native -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: alexnetGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.43691215SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.09, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 39.189.088.999.059.15MIN: 9.11 / MAX: 9.74MIN: 9 / MAX: 11.81MIN: 8.73 / MAX: 9.39MIN: 8.96 / MAX: 19.48MIN: 9.08 / MAX: 9.591. (CXX) g++ options: -O3 -march=native -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: resnet50GCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.4510152025SE +/- 0.29, N = 3SE +/- 0.24, N = 3SE +/- 0.24, N = 3SE +/- 0.30, N = 3SE +/- 0.29, N = 317.8717.7717.7418.3317.59MIN: 17.16 / MAX: 18.62MIN: 17.07 / MAX: 28.68MIN: 17.09 / MAX: 18.96MIN: 17.58 / MAX: 24.57MIN: 17.07 / MAX: 18.691. (CXX) g++ options: -O3 -march=native -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: yolov4-tinyGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.4510152025SE +/- 0.17, N = 3SE +/- 0.10, N = 3SE +/- 1.86, N = 3SE +/- 0.25, N = 3SE +/- 0.19, N = 321.2621.3722.8320.8421.35MIN: 20 / MAX: 24.4MIN: 20.44 / MAX: 22.72MIN: 20.18 / MAX: 937.4MIN: 19.92 / MAX: 24.91MIN: 20.42 / MAX: 33.91. (CXX) g++ options: -O3 -march=native -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: squeezenet_ssdGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.448121620SE +/- 0.05, N = 3SE +/- 0.08, N = 3SE +/- 0.13, N = 3SE +/- 0.36, N = 3SE +/- 0.06, N = 315.2615.2315.2815.6315.08MIN: 14.97 / MAX: 18.92MIN: 14.88 / MAX: 17.07MIN: 14.89 / MAX: 16.1MIN: 15.02 / MAX: 16.85MIN: 14.88 / MAX: 21.621. (CXX) g++ options: -O3 -march=native -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210525Target: CPU - Model: regnety_400mGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.448121620SE +/- 0.14, N = 3SE +/- 0.11, N = 3SE +/- 0.05, N = 3SE +/- 0.14, N = 3SE +/- 0.21, N = 313.6313.9313.4813.7713.87MIN: 13.01 / MAX: 14.57MIN: 13.17 / MAX: 14.48MIN: 13.11 / MAX: 14.04MIN: 12.93 / MAX: 14.62MIN: 13.18 / MAX: 15.011. (CXX) g++ options: -O3 -march=native -rdynamic -lgomp -lpthread -pthread

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: C2670GCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.4306090120150SE +/- 1.13, N = 3SE +/- 0.92, N = 3SE +/- 0.83, N = 3SE +/- 0.81, N = 3SE +/- 0.71, N = 3133.91134.71135.43134.35134.221. (CC) gcc options: -O3 -march=native -fopenmp -lm -lfftw3 -lXaw -lXmu -lXt -lXext -lX11 -lSM -lICE

OpenBenchmarking.orgSeconds, Fewer Is BetterNgspice 34Circuit: C7552GCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.4306090120150SE +/- 1.51, N = 3SE +/- 0.26, N = 3SE +/- 1.05, N = 3SE +/- 1.35, N = 3SE +/- 1.54, N = 3126.88129.40128.32126.20127.691. (CC) gcc options: -O3 -march=native -fopenmp -lm -lfftw3 -lXaw -lXmu -lXt -lXext -lX11 -lSM -lICE

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: u8s8f32 - Engine: CPUGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.40.11890.23780.35670.47560.5945SE +/- 0.003324, N = 3SE +/- 0.003036, N = 3SE +/- 0.003225, N = 3SE +/- 0.003001, N = 3SE +/- 0.003361, N = 30.5260140.5281330.5279390.5284160.526798MIN: 0.5MIN: 0.5MIN: 0.5MIN: 0.5MIN: 0.51. (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: CPUGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.40.2880.5760.8641.1521.44SE +/- 0.00554, N = 3SE +/- 0.00400, N = 3SE +/- 0.00255, N = 3SE +/- 0.00683, N = 3SE +/- 0.00348, N = 31.227031.230121.224961.232391.27991MIN: 1.18MIN: 1.19MIN: 1.18MIN: 1.18MIN: 1.231. (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: bf16bf16bf16 - Engine: CPUGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.41.25892.51783.77675.03566.2945SE +/- 0.01959, N = 3SE +/- 0.02335, N = 3SE +/- 0.02089, N = 3SE +/- 0.02371, N = 3SE +/- 0.02285, N = 35.533345.545445.536725.540625.59533MIN: 5.38MIN: 5.4MIN: 5.38MIN: 5.4MIN: 5.451. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPUGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.40.66351.3271.99052.6543.3175SE +/- 0.01261, N = 3SE +/- 0.01584, N = 3SE +/- 0.01797, N = 3SE +/- 0.01360, N = 3SE +/- 0.01601, N = 32.939782.934282.946702.949032.86008MIN: 2.83MIN: 2.83MIN: 2.84MIN: 2.85MIN: 2.771. (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: CPUGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.43691215SE +/- 0.01276, N = 3SE +/- 0.01164, N = 3SE +/- 0.00808, N = 3SE +/- 0.01311, N = 3SE +/- 0.01517, N = 39.350959.355509.342069.347669.55455MIN: 9.29MIN: 9.29MIN: 9.28MIN: 9.29MIN: 9.51. (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: CPUGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.40.10380.20760.31140.41520.519SE +/- 0.001585, N = 3SE +/- 0.000687, N = 3SE +/- 0.001427, N = 3SE +/- 0.000631, N = 3SE +/- 0.001062, N = 30.4604820.4599560.4596600.4614590.459456MIN: 0.45MIN: 0.45MIN: 0.45MIN: 0.45MIN: 0.451. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPUGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.40.18650.3730.55950.7460.9325SE +/- 0.005954, N = 8SE +/- 0.005568, N = 3SE +/- 0.008934, N = 3SE +/- 0.003298, N = 3SE +/- 0.008442, N = 150.6805220.6970800.6786260.6794820.828866MIN: 0.63MIN: 0.67MIN: 0.65MIN: 0.66MIN: 0.741. (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: CPUGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.4400800120016002000SE +/- 0.93, N = 3SE +/- 2.29, N = 3SE +/- 0.75, N = 3SE +/- 1.09, N = 3SE +/- 2.09, N = 31565.411563.051567.411573.031636.96MIN: 1559.12MIN: 1555.64MIN: 1561.17MIN: 1566.77MIN: 1629.181. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPUGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.4246810SE +/- 0.03159, N = 3SE +/- 0.03513, N = 3SE +/- 0.03413, N = 3SE +/- 0.02602, N = 3SE +/- 0.17046, N = 147.901637.904777.912587.890328.10038MIN: 7.61MIN: 7.56MIN: 7.63MIN: 7.58MIN: 7.581. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPUGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.43691215SE +/- 0.02137, N = 3SE +/- 0.01742, N = 3SE +/- 0.02038, N = 3SE +/- 0.02091, N = 3SE +/- 0.00795, N = 39.390629.413469.594529.828589.79185MIN: 9.29MIN: 9.27MIN: 9.4MIN: 9.53MIN: 9.621. (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: bf16bf16bf16 - Engine: CPUGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.43691215SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 310.9210.9210.9311.0210.96MIN: 10.74MIN: 10.74MIN: 10.77MIN: 10.79MIN: 10.741. (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: CPUGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.42004006008001000SE +/- 0.69, N = 3SE +/- 0.60, N = 3SE +/- 0.46, N = 3SE +/- 0.50, N = 3SE +/- 0.63, N = 3935.96938.04936.49937.61960.13MIN: 930.6MIN: 933.04MIN: 932.18MIN: 932.91MIN: 955.071. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPUGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.4400800120016002000SE +/- 1.06, N = 3SE +/- 3.72, N = 3SE +/- 1.54, N = 3SE +/- 0.81, N = 3SE +/- 1.53, N = 31566.751566.251564.711573.181639.78MIN: 1558.77MIN: 1553.36MIN: 1557.51MIN: 1566.72MIN: 1630.861. (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 Inference - Data Type: bf16bf16bf16 - Engine: CPUGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.42004006008001000SE +/- 0.16, N = 3SE +/- 0.70, N = 3SE +/- 0.15, N = 3SE +/- 1.32, N = 3SE +/- 1.46, N = 3938.22936.88935.38939.92961.38MIN: 930.52MIN: 931.54MIN: 931.25MIN: 933.27MIN: 955.171. (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: CPUGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.40.10520.21040.31560.42080.526SE +/- 0.004576, N = 4SE +/- 0.004665, N = 3SE +/- 0.000391, N = 3SE +/- 0.003487, N = 3SE +/- 0.002588, N = 30.4269020.4306760.4256750.4415000.467594MIN: 0.4MIN: 0.41MIN: 0.41MIN: 0.41MIN: 0.441. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Matrix Multiply Batch Shapes Transformer - Data Type: bf16bf16bf16 - Engine: CPUGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.40.40310.80621.20931.61242.0155SE +/- 0.00494, N = 3SE +/- 0.00508, N = 3SE +/- 0.00613, N = 3SE +/- 0.00719, N = 3SE +/- 0.00782, N = 31.755201.762641.744711.763081.79150MIN: 1.69MIN: 1.69MIN: 1.66MIN: 1.7MIN: 1.741. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -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 EncodeGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.4246810SE +/- 0.031, N = 5SE +/- 0.013, N = 5SE +/- 0.011, N = 5SE +/- 0.011, N = 5SE +/- 0.021, N = 58.2838.4568.1868.2838.2411. (CXX) g++ options: -O3 -march=native -fvisibility=hidden -logg -lm

PJSIP

PJSIP is a free and open source multimedia communication library written in C language implementing standard based protocols such as SIP, SDP, RTP, STUN, TURN, and ICE. It combines signaling protocol (SIP) with rich multimedia framework and NAT traversal functionality into high level API that is portable and suitable for almost any type of systems ranging from desktops, embedded systems, to mobile handsets. This test profile is making use of pjsip-perf with both the client/server on teh system. More details on the PJSIP benchmark at https://www.pjsip.org/high-performance-sip.htm Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgResponses Per Second, More Is BetterPJSIP 2.11Method: INVITEGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.47001400210028003500SE +/- 6.36, N = 3SE +/- 7.22, N = 3SE +/- 25.40, N = 15SE +/- 25.16, N = 15SE +/- 27.02, N = 3328132403304330732521. (CC) gcc options: -lstdc++ -lssl -lcrypto -lm -lrt -lpthread -O3 -march=native

OpenBenchmarking.orgResponses Per Second, More Is BetterPJSIP 2.11Method: OPTIONS, StatefulGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.412002400360048006000SE +/- 8.67, N = 3SE +/- 53.69, N = 3SE +/- 23.13, N = 3SE +/- 16.26, N = 3SE +/- 24.67, N = 3574457695763580157291. (CC) gcc options: -lstdc++ -lssl -lcrypto -lm -lrt -lpthread -O3 -march=native

OpenBenchmarking.orgResponses Per Second, More Is BetterPJSIP 2.11Method: OPTIONS, StatelessGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.430K60K90K120K150KSE +/- 1006.09, N = 3SE +/- 946.90, N = 3SE +/- 734.59, N = 3SE +/- 578.10, N = 3SE +/- 1635.40, N = 41382221364441379661353021359031. (CC) gcc options: -lstdc++ -lssl -lcrypto -lm -lrt -lpthread -O3 -march=native

QuantLib

QuantLib is an open-source library/framework around quantitative finance for modeling, trading and risk management scenarios. QuantLib is written in C++ with Boost and its built-in benchmark used reports the QuantLib Benchmark Index benchmark score. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMFLOPS, More Is BetterQuantLib 1.21GCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.46001200180024003000SE +/- 18.68, N = 3SE +/- 33.86, N = 4SE +/- 0.85, N = 3SE +/- 19.67, N = 3SE +/- 35.29, N = 32529.82749.12773.62586.32568.81. (CXX) g++ options: -O3 -march=native -rdynamic

SecureMark

SecureMark is an objective, standardized benchmarking framework for measuring the efficiency of cryptographic processing solutions developed by EEMBC. SecureMark-TLS is benchmarking Transport Layer Security performance with a focus on IoT/edge computing. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgmarks, More Is BetterSecureMark 1.0.4Benchmark: SecureMark-TLSGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.460K120K180K240K300KSE +/- 95.66, N = 3SE +/- 68.80, N = 3SE +/- 101.43, N = 3SE +/- 106.27, N = 3SE +/- 247.29, N = 32634722595652645142598692634571. (CC) gcc options: -pedantic -O3

Smallpt

Smallpt is a C++ global illumination renderer written in less than 100 lines of code. Global illumination is done via unbiased Monte Carlo path tracing and there is multi-threading support via the OpenMP library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSmallpt 1.0Global Illumination Renderer; 128 SamplesGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.4246810SE +/- 0.033, N = 3SE +/- 0.004, N = 3SE +/- 0.017, N = 3SE +/- 0.007, N = 3SE +/- 0.011, N = 36.1306.2015.9915.2866.0451. (CXX) g++ options: -fopenmp -O3 -march=native

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 1,000GCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.41326395265SE +/- 0.19, N = 3SE +/- 0.10, N = 3SE +/- 0.11, N = 3SE +/- 0.22, N = 3SE +/- 0.09, N = 357.3057.4156.7257.6157.031. (CC) gcc options: -O3 -march=native -ldl -lz -lpthread

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 TimeGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.411M22M33M44M55MSE +/- 623930.99, N = 3SE +/- 211973.29, N = 3SE +/- 432778.20, N = 8SE +/- 562135.06, N = 15SE +/- 508293.85, N = 1549942276522069635073457151140013506225521. (CXX) g++ options: -lgcov -m64 -lpthread -O3 -march=native -fno-exceptions -std=c++17 -pedantic -msse -msse3 -mpopcnt -mavx2 -mavx512f -mavx512bw -mavx512vnni -mavx512dq -mavx512vl -msse4.1 -mssse3 -msse2 -mbmi2 -flto -fprofile-use -fno-peel-loops -fno-tracer -flto=jobserver

SVT-AV1

This is a benchmark of the SVT-AV1 open-source video encoder/decoder. SVT-AV1 was originally developed by Intel as part of their Open Visual Cloud / Scalable Video Technology (SVT). Development of SVT-AV1 has since moved to the Alliance for Open Media as part of upstream AV1 development. SVT-AV1 is a CPU-based multi-threaded video encoder for the AV1 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8.7Encoder Mode: Preset 4 - Input: Bosphorus 4KGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.40.30580.61160.91741.22321.529SE +/- 0.003, N = 3SE +/- 0.003, N = 3SE +/- 0.002, N = 3SE +/- 0.005, N = 3SE +/- 0.001, N = 31.3591.3471.3481.3401.3551. (CXX) g++ options: -O3 -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8.7Encoder Mode: Preset 8 - Input: Bosphorus 4KGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.43691215SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.08, N = 312.0612.0911.9711.9312.021. (CXX) g++ options: -O3 -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie

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 1080pGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.43691215SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 313.0412.9612.9412.8812.911. (CC) gcc options: -O3 -march=native -fPIE -fPIC -O2 -pie -rdynamic -lpthread -lrt

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 7 - Input: Bosphorus 1080pGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.44080120160200SE +/- 0.44, N = 3SE +/- 0.31, N = 3SE +/- 0.32, N = 3SE +/- 0.58, N = 3SE +/- 0.18, N = 3189.88191.02191.33190.03190.621. (CC) gcc options: -O3 -march=native -fPIE -fPIC -O2 -pie -rdynamic -lpthread -lrt

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 10 - Input: Bosphorus 1080pGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.480160240320400SE +/- 1.74, N = 3SE +/- 1.99, N = 3SE +/- 0.75, N = 3SE +/- 0.95, N = 3SE +/- 0.96, N = 3372.69375.65375.32374.62376.891. (CC) gcc options: -O3 -march=native -fPIE -fPIC -O2 -pie -rdynamic -lpthread -lrt

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: VMAF Optimized - Input: Bosphorus 1080pGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.470140210280350SE +/- 1.76, N = 14SE +/- 2.83, N = 6SE +/- 3.01, N = 5SE +/- 2.56, N = 13SE +/- 4.16, N = 3299.97297.32293.71306.08295.071. (CC) gcc options: -O3 -fcommon -march=native -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080pGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.470140210280350SE +/- 1.79, N = 3SE +/- 2.35, N = 3SE +/- 0.68, N = 3SE +/- 0.21, N = 3SE +/- 1.42, N = 3306.89305.72303.54310.79302.251. (CC) gcc options: -O3 -fcommon -march=native -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: Visual Quality Optimized - Input: Bosphorus 1080pGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.450100150200250SE +/- 3.33, N = 3SE +/- 3.10, N = 3SE +/- 1.58, N = 3SE +/- 1.34, N = 3SE +/- 1.22, N = 3246.75244.05244.56247.45243.481. (CC) gcc options: -O3 -fcommon -march=native -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

Tachyon

This is a test of the threaded Tachyon, a parallel ray-tracing system, measuring the time to ray-trace a sample scene. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTachyon 0.99b6Total TimeGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.41122334455SE +/- 0.08, N = 3SE +/- 0.26, N = 3SE +/- 0.18, N = 3SE +/- 0.08, N = 3SE +/- 0.08, N = 347.9047.8749.3248.1647.881. (CC) gcc options: -m64 -O3 -fomit-frame-pointer -ffast-math -ltachyon -lm -lpthread

Timed HMMer Search

This test searches through the Pfam database of profile hidden markov models. The search finds the domain structure of Drosophila Sevenless protein. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed HMMer Search 3.3.2Pfam Database SearchGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.4306090120150SE +/- 0.32, N = 3SE +/- 0.11, N = 3SE +/- 0.10, N = 3SE +/- 0.06, N = 3SE +/- 0.10, N = 3126.69126.62129.45126.20126.511. (CC) gcc options: -O3 -march=native -pthread -lhmmer -leasel -lm -lmpi

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 AnalysisGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.4306090120150SE +/- 0.58, N = 3SE +/- 0.32, N = 3SE +/- 1.02, N = 3SE +/- 0.45, N = 3SE +/- 1.65, N = 12154.63142.93145.17146.10157.331. (CC) gcc options: -mmmx -msse -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -maes -mavx -mfma -mavx2 -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mrdrnd -mbmi -mbmi2 -madx -mmpx -mabm -O3 -std=c99 -pedantic -march=native -lm

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: DenseNetGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.48001600240032004000SE +/- 0.59, N = 3SE +/- 0.77, N = 3SE +/- 0.21, N = 3SE +/- 0.16, N = 3SE +/- 2.55, N = 33508.293508.393524.753505.933527.68MIN: 3489.27 / MAX: 3603.98MIN: 3486.98 / MAX: 3606.8MIN: 3509.67 / MAX: 3548.51MIN: 3487.54 / MAX: 3535.34MIN: 3508.67 / MAX: 3981.671. (CXX) g++ options: -O3 -march=native -fopenmp -pthread -fvisibility=hidden -fvisibility=default -rdynamic -ldl

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: MobileNet v2GCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.480160240320400SE +/- 0.31, N = 3SE +/- 0.19, N = 3SE +/- 0.17, N = 3SE +/- 0.29, N = 3SE +/- 0.34, N = 3311.60314.56318.06321.39347.44MIN: 309.73 / MAX: 322.67MIN: 312.66 / MAX: 328.44MIN: 316.44 / MAX: 326.16MIN: 319.29 / MAX: 341.28MIN: 345.68 / MAX: 356.591. (CXX) g++ options: -O3 -march=native -fopenmp -pthread -fvisibility=hidden -fvisibility=default -rdynamic -ldl

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: SqueezeNet v2GCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.41632486480SE +/- 0.07, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 1.05, N = 369.3069.8069.2370.1273.94MIN: 68.65 / MAX: 70.61MIN: 69.16 / MAX: 70.99MIN: 68.59 / MAX: 70.34MIN: 69.44 / MAX: 71.63MIN: 72.33 / MAX: 77.081. (CXX) g++ options: -O3 -march=native -fopenmp -pthread -fvisibility=hidden -fvisibility=default -rdynamic -ldl

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: SqueezeNet v1.1GCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.460120180240300SE +/- 0.10, N = 3SE +/- 0.63, N = 3SE +/- 0.19, N = 3SE +/- 0.07, N = 3SE +/- 0.07, N = 3286.22288.91287.49289.96296.14MIN: 285.02 / MAX: 287.82MIN: 286.05 / MAX: 294.45MIN: 285.88 / MAX: 299.62MIN: 288.43 / MAX: 291.61MIN: 294.66 / MAX: 298.561. (CXX) g++ options: -O3 -march=native -fopenmp -pthread -fvisibility=hidden -fvisibility=default -rdynamic -ldl

ViennaCL

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

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - sCOPYGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.41122334455SE +/- 0.12, N = 3SE +/- 0.07, N = 3SE +/- 0.09, N = 3SE +/- 0.27, N = 3SE +/- 0.17, N = 346.446.746.445.947.11. (CXX) g++ options: -O3 -march=native -fopenmp -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - sAXPYGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.41632486480SE +/- 0.30, N = 3SE +/- 0.31, N = 3SE +/- 0.35, N = 3SE +/- 1.48, N = 3SE +/- 0.12, N = 370.370.770.168.871.21. (CXX) g++ options: -O3 -march=native -fopenmp -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - sDOTGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.420406080100SE +/- 0.33, N = 3SE +/- 0.43, N = 3SE +/- 0.49, N = 3SE +/- 0.42, N = 3SE +/- 0.26, N = 377.477.677.177.078.01. (CXX) g++ options: -O3 -march=native -fopenmp -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dCOPYGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.4918273645SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.15, N = 338.338.338.238.138.11. (CXX) g++ options: -O3 -march=native -fopenmp -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dAXPYGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.41326395265SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.12, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 357.357.457.257.157.41. (CXX) g++ options: -O3 -march=native -fopenmp -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dDOTGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.41428425670SE +/- 9.10, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 354.763.763.763.663.71. (CXX) g++ options: -O3 -march=native -fopenmp -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMV-NGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.41632486480SE +/- 0.03, N = 3SE +/- 0.09, N = 3SE +/- 0.31, N = 3SE +/- 0.12, N = 3SE +/- 0.07, N = 371.671.771.469.571.81. (CXX) g++ options: -O3 -march=native -fopenmp -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMV-TGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.420406080100SE +/- 0.07, N = 3SE +/- 0.38, N = 3SE +/- 0.09, N = 3SE +/- 0.25, N = 3SE +/- 0.10, N = 379.679.379.579.979.71. (CXX) g++ options: -O3 -march=native -fopenmp -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMM-NNGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.41326395265SE +/- 0.63, N = 3SE +/- 0.15, N = 3SE +/- 0.44, N = 3SE +/- 0.75, N = 3SE +/- 0.13, N = 358.751.051.255.556.11. (CXX) g++ options: -O3 -march=native -fopenmp -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMM-NTGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.41326395265SE +/- 0.48, N = 3SE +/- 0.15, N = 3SE +/- 0.37, N = 3SE +/- 0.25, N = 3SE +/- 0.27, N = 356.449.849.854.754.11. (CXX) g++ options: -O3 -march=native -fopenmp -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMM-TNGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.41326395265SE +/- 1.17, N = 3SE +/- 0.10, N = 3SE +/- 0.10, N = 3SE +/- 1.55, N = 2SE +/- 0.36, N = 358.951.951.956.056.21. (CXX) g++ options: -O3 -march=native -fopenmp -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMM-TTGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.41326395265SE +/- 0.70, N = 2SE +/- 0.20, N = 3SE +/- 0.09, N = 3SE +/- 0.32, N = 3SE +/- 0.07, N = 357.150.551.555.254.91. (CXX) g++ options: -O3 -march=native -fopenmp -rdynamic -lOpenCL

VOSK Speech Recognition Toolkit

VOSK is an open-source offline speech recognition API/toolkit. VOSK supports speech recognition in 17 languages and has a variety of models available and interfaces for different programming languages. This test profile times the speech-to-text process for a roughly three minute audio recording. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterVOSK Speech Recognition Toolkit 0.3.21GCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.4510152025SE +/- 0.12, N = 3SE +/- 0.26, N = 3SE +/- 0.07, N = 3SE +/- 0.15, N = 3SE +/- 0.13, N = 320.7520.8920.5720.7220.99

VP9 libvpx Encoding

This is a standard video encoding performance test of Google's libvpx library and the vpxenc command for the VP9 video format. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.10.0Speed: Speed 0 - Input: Bosphorus 4KGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.41.1072.2143.3214.4285.535SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 34.844.874.924.754.871. (CXX) g++ options: -m64 -lm -lpthread -O3 -march=native -fPIC -U_FORTIFY_SOURCE -std=gnu++11

OpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.10.0Speed: Speed 5 - Input: Bosphorus 4KGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.4246810SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 38.598.638.658.228.611. (CXX) g++ options: -m64 -lm -lpthread -O3 -march=native -fPIC -U_FORTIFY_SOURCE -std=gnu++11

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 WavPackGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.43691215SE +/- 0.02, N = 5SE +/- 0.00, N = 5SE +/- 0.00, N = 5SE +/- 0.00, N = 5SE +/- 0.00, N = 513.3413.3513.3313.3613.381. (CXX) g++ options: -O3 -march=native -rdynamic

WebP Image Encode

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

OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100, LosslessGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.448121620SE +/- 0.06, N = 3SE +/- 0.05, N = 3SE +/- 0.01, N = 3SE +/- 0.06, N = 3SE +/- 0.02, N = 317.2516.8016.8917.2016.821. (CC) gcc options: -fvisibility=hidden -O3 -march=native -pthread -lm -ljpeg -lpng16

OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100, Highest CompressionGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.4246810SE +/- 0.003, N = 3SE +/- 0.002, N = 3SE +/- 0.043, N = 3SE +/- 0.007, N = 3SE +/- 0.007, N = 36.8666.7806.5486.6426.5601. (CC) gcc options: -fvisibility=hidden -O3 -march=native -pthread -lm -ljpeg -lpng16

OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100, Lossless, Highest CompressionGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.4918273645SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.11, N = 3SE +/- 0.13, N = 337.8736.4737.1637.7036.871. (CC) gcc options: -fvisibility=hidden -O3 -march=native -pthread -lm -ljpeg -lpng16

x265

This is a simple test of the x265 encoder run on the CPU with 1080p and 4K options for H.265 video encode performance with x265. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.4Video Input: Bosphorus 4KGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.4510152025SE +/- 0.13, N = 3SE +/- 0.11, N = 3SE +/- 0.11, N = 3SE +/- 0.10, N = 3SE +/- 0.12, N = 321.8421.1621.0821.5321.641. (CXX) g++ options: -O3 -march=native -rdynamic -lpthread -lrt -ldl -lnuma

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: 8 - Compression SpeedGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.490180270360450SE +/- 4.87, N = 3SE +/- 5.64, N = 3SE +/- 5.56, N = 3SE +/- 4.99, N = 3SE +/- 4.23, N = 5424.0419.5432.7425.7429.41. (CC) gcc options: -O3 -march=native -pthread -lz

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 8 - Decompression SpeedGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.47001400210028003500SE +/- 3.06, N = 3SE +/- 5.37, N = 3SE +/- 2.91, N = 3SE +/- 2.28, N = 3SE +/- 2.27, N = 53285.53351.93332.73361.73436.81. (CC) gcc options: -O3 -march=native -pthread -lz

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19 - Compression SpeedGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.41428425670SE +/- 0.56, N = 3SE +/- 0.50, N = 9SE +/- 0.47, N = 3SE +/- 0.19, N = 3SE +/- 0.50, N = 360.161.060.860.360.21. (CC) gcc options: -O3 -march=native -pthread -lz

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19 - Decompression SpeedGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.46001200180024003000SE +/- 9.76, N = 3SE +/- 7.69, N = 9SE +/- 16.86, N = 3SE +/- 3.24, N = 3SE +/- 14.28, N = 32701.92642.22773.92676.82802.71. (CC) gcc options: -O3 -march=native -pthread -lz

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 8, Long Mode - Compression SpeedGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.4100200300400500SE +/- 3.28, N = 15SE +/- 3.45, N = 3SE +/- 3.88, N = 15SE +/- 3.63, N = 3SE +/- 2.56, N = 13370.1469.4385.5335.5375.61. (CC) gcc options: -O3 -march=native -pthread -lz

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 8, Long Mode - Decompression SpeedGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.48001600240032004000SE +/- 3.49, N = 15SE +/- 3.35, N = 3SE +/- 3.04, N = 15SE +/- 5.55, N = 3SE +/- 2.52, N = 133479.03553.23531.43547.43628.41. (CC) gcc options: -O3 -march=native -pthread -lz

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19, Long Mode - Compression SpeedGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.41020304050SE +/- 0.19, N = 3SE +/- 0.07, N = 3SE +/- 0.15, N = 3SE +/- 0.15, N = 3SE +/- 0.13, N = 343.944.343.943.343.51. (CC) gcc options: -O3 -march=native -pthread -lz

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19, Long Mode - Decompression SpeedGCC 10.3GCC 11.1GCC 12.0.0 20210701GCC 8.5GCC 9.46001200180024003000SE +/- 2.75, N = 3SE +/- 14.84, N = 3SE +/- 2.25, N = 3SE +/- 10.70, N = 3SE +/- 4.29, N = 32876.92775.72782.72819.23017.61. (CC) gcc options: -O3 -march=native -pthread -lz

142 Results Shown

7-Zip Compression
AOM AV1:
  Speed 6 Realtime - Bosphorus 4K
  Speed 6 Two-Pass - Bosphorus 4K
  Speed 8 Realtime - Bosphorus 4K
  Speed 9 Realtime - Bosphorus 4K
Botan:
  KASUMI
  KASUMI - Decrypt
  AES-256
  AES-256 - Decrypt
  Twofish
  Twofish - Decrypt
  Blowfish
  Blowfish - Decrypt
  CAST-256
  CAST-256 - Decrypt
  ChaCha20Poly1305
  ChaCha20Poly1305 - Decrypt
C-Blosc
C-Ray
Coremark
Crypto++:
  Keyed Algorithms
  Unkeyed Algorithms
  Integer + Elliptic Curve Public Key Algorithms
dav1d:
  Summer Nature 4K
  Chimera 1080p 10-bit
eSpeak-NG Speech Engine
Etcpak:
  DXT1
  ETC2
  ETC1 + Dithering
FinanceBench:
  Repo OpenMP
  Bonds OpenMP
FLAC Audio Encoding
Gcrypt Library
GnuPG
GraphicsMagick:
  Swirl
  Rotate
  Sharpen
  Enhanced
  Resizing
  Noise-Gaussian
  HWB Color Space
Himeno Benchmark
Kvazaar:
  Bosphorus 4K - Very Fast
  Bosphorus 4K - Ultra Fast
LAME MP3 Encoding
libgav1:
  Summer Nature 4K
  Chimera 1080p 10-bit
libjpeg-turbo tjbench
Liquid-DSP:
  32 - 256 - 57
  36 - 256 - 57
Mobile Neural Network:
  mobilenetV3
  squeezenetv1.1
  resnet-v2-50
  SqueezeNetV1.0
  MobileNetV2_224
  mobilenet-v1-1.0
  inception-v3
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
Ngspice:
  C2670
  C7552
oneDNN:
  IP Shapes 1D - u8s8f32 - CPU
  IP Shapes 3D - u8s8f32 - CPU
  IP Shapes 1D - bf16bf16bf16 - CPU
  IP Shapes 3D - bf16bf16bf16 - CPU
  Convolution Batch Shapes Auto - u8s8f32 - CPU
  Deconvolution Batch shapes_1d - u8s8f32 - CPU
  Deconvolution Batch shapes_3d - u8s8f32 - CPU
  Recurrent Neural Network Training - u8s8f32 - CPU
  Convolution Batch Shapes Auto - bf16bf16bf16 - CPU
  Deconvolution Batch shapes_1d - bf16bf16bf16 - CPU
  Deconvolution Batch shapes_3d - bf16bf16bf16 - CPU
  Recurrent Neural Network Inference - u8s8f32 - CPU
  Recurrent Neural Network Training - bf16bf16bf16 - CPU
  Recurrent Neural Network Inference - bf16bf16bf16 - CPU
  Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPU
  Matrix Multiply Batch Shapes Transformer - bf16bf16bf16 - CPU
Opus Codec Encoding
PJSIP:
  INVITE
  OPTIONS, Stateful
  OPTIONS, Stateless
QuantLib
SecureMark
Smallpt
SQLite Speedtest
Stockfish
SVT-AV1:
  Preset 4 - Bosphorus 4K
  Preset 8 - Bosphorus 4K
SVT-HEVC:
  1 - Bosphorus 1080p
  7 - Bosphorus 1080p
  10 - Bosphorus 1080p
SVT-VP9:
  VMAF Optimized - Bosphorus 1080p
  PSNR/SSIM Optimized - Bosphorus 1080p
  Visual Quality Optimized - Bosphorus 1080p
Tachyon
Timed HMMer Search
Timed MrBayes Analysis
TNN:
  CPU - DenseNet
  CPU - MobileNet v2
  CPU - SqueezeNet v2
  CPU - SqueezeNet v1.1
ViennaCL:
  CPU BLAS - sCOPY
  CPU BLAS - sAXPY
  CPU BLAS - sDOT
  CPU BLAS - dCOPY
  CPU BLAS - dAXPY
  CPU BLAS - dDOT
  CPU BLAS - dGEMV-N
  CPU BLAS - dGEMV-T
  CPU BLAS - dGEMM-NN
  CPU BLAS - dGEMM-NT
  CPU BLAS - dGEMM-TN
  CPU BLAS - dGEMM-TT
VOSK Speech Recognition Toolkit
VP9 libvpx Encoding:
  Speed 0 - Bosphorus 4K
  Speed 5 - Bosphorus 4K
WavPack Audio Encoding
WebP Image Encode:
  Quality 100, Lossless
  Quality 100, Highest Compression
  Quality 100, Lossless, Highest Compression
x265
Zstd Compression:
  8 - Compression Speed
  8 - Decompression Speed
  19 - Compression Speed
  19 - Decompression Speed
  8, Long Mode - Compression Speed
  8, Long Mode - Decompression Speed
  19, Long Mode - Compression Speed
  19, Long Mode - Decompression Speed