GM-1000, Karbon 700, CompuLab Airtop PCs

Tests 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 2011011-FI-GM100056276
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
Allow Limiting Results To Certain Suite(s)

Statistics

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

Graph Settings

Force Line Graphs Where Applicable
Convert To Scalar Where Applicable
Prefer Vertical Bar Graphs
No Box Plots
On Line Graphs With Missing Data, Connect The Line Gaps

Additional Graphs

Show Perf Per Core/Thread Calculation Graphs Where Applicable
Show Perf Per Clock Calculation Graphs Where Applicable

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
Toggle/Hide
Result
Result
Identifier
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
Karbon 700
October 30 2020
  22 Hours, 2 Minutes
CompuLab Airtop
October 31 2020
  19 Hours, 53 Minutes
CompuLab Airtop3
October 29 2020
  12 Hours, 25 Minutes
GM-1000
October 28 2020
  18 Hours
Invert Behavior (Only Show Selected Data)
  18 Hours, 5 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):


GM-1000, Karbon 700, CompuLab Airtop PCsProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLOpenCLVulkanCompilerFile-SystemScreen ResolutionGM-1000CompuLab Airtop3Karbon 700CompuLab AirtopIntel Core i7-9700TE @ 3.80GHz (8 Cores)C OZE GM-1000 v0.0.01.001 (5.13 BIOS)Intel Cannon Lake PCH32GBCIE M8 T405 512GBNVIDIA Quadro P2000 4GB (1455/3003MHz)Realtek ALC888-VDDELL S2409WIntel I219-LM + 2 x Intel 10G X550T + Intel I210Ubuntu 20.105.8.0-25-generic (x86_64)GNOME Shell 3.38.1X Server 1.20.9NVIDIA 455.284.6.0OpenCL 1.2 CUDA 11.1.961.2.142GCC 10.2.0ext41920x1080Intel Xeon E-2288G @ 5.00GHz (8 Cores / 16 Threads)Compulab SBC-ATCFL v1.2 (ATOP3.PRD.0.29.2 BIOS)64GBSamsung SSD 970 EVO Plus 250GBNVIDIA Quadro RTX 4000 8GB (1005/6500MHz)Intel Cannon Lake PCH cAVSVE228Intel I219-LM + Intel I2105.8.0-26-generic (x86_64)Intel Xeon E-2278GEL @ 3.90GHz (8 Cores / 16 Threads)Logic Supply RXM-181 (Z01-0001A027 BIOS)16GB512GB TS512GMTE510TIntel UHD P630 3GB (1150MHz)Realtek ALC233VA2431Intel I219-LM + 2 x Intel I210modesetting 1.20.94.6 Mesa 20.2.11.2.145Intel Core i7-5775C @ 3.70GHz (4 Cores / 8 Threads)CompuLab v1.0 (ARTP-3.1.0.637.0.0 X64 BIOS)Intel Broadwell-U DMI256GB ADATA SP310eVGA NVIDIA GeForce GTX 950 2GB (1151/3304MHz)Realtek ALC886G237HLIntel I218-LM + Intel I210 + Intel 7260NVIDIA 455.284.6.0OpenCL 1.2 CUDA 11.1.961.2.142OpenBenchmarking.orgCompiler Details- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-JvwpWM/gcc-10-10.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-JvwpWM/gcc-10-10.2.0/debian/tmp-gcn/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v Disk Details- GM-1000: NONE / errors=remount-ro,relatime,rw- CompuLab Airtop3: NONE / errors=remount-ro,relatime,rw- Karbon 700: NONE / errors=remount-ro,relatime,rw- CompuLab Airtop: MQ-DEADLINE / errors=remount-ro,relatime,rwProcessor Details- GM-1000: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xd6 - Thermald 2.3- CompuLab Airtop3: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xd6 - Thermald 2.3- Karbon 700: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xd6 - Thermald 2.3- CompuLab Airtop: Scaling Governor: intel_cpufreq ondemand - CPU Microcode: 0x22 - Thermald 2.3OpenCL Details- GM-1000: GPU Compute Cores: 768- CompuLab Airtop3: GPU Compute Cores: 2304- CompuLab Airtop: GPU Compute Cores: 768Java Details- GM-1000: OpenJDK Runtime Environment (build 11.0.9+10-post-Ubuntu-0ubuntu1)- CompuLab Airtop3: OpenJDK Runtime Environment (build 11.0.9+11-Ubuntu-0ubuntu1)- Karbon 700: OpenJDK Runtime Environment (build 11.0.9+11-Ubuntu-0ubuntu1)- CompuLab Airtop: OpenJDK Runtime Environment (build 11.0.9+11-Ubuntu-0ubuntu1)Python Details- Python 3.8.6Security Details- GM-1000: 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: Mitigation of TSX disabled + tsx_async_abort: Mitigation of TSX disabled - CompuLab Airtop3: 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: Mitigation of TSX disabled + tsx_async_abort: Mitigation of TSX disabled - Karbon 700: itlb_multihit: KVM: Mitigation of VMX unsupported + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + srbds: Mitigation of TSX disabled + tsx_async_abort: Mitigation of TSX disabled - CompuLab Airtop: itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Mitigation of PTE Inversion; VMX: conditional cache flushes SMT vulnerable + mds: Mitigation of Clear buffers; SMT vulnerable + meltdown: Mitigation of PTI + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full generic retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling + srbds: Mitigation of Microcode + tsx_async_abort: Mitigation of Clear buffers; SMT vulnerable

GM-1000CompuLab Airtop3Karbon 700CompuLab AirtopLogarithmic Result OverviewPhoronix Test SuiteKripkeIORNCNNApache CassandraLAMMPS Molecular Dynamics SimulatorIncompact3DOpenVKLLeelaChessZeroFacebook RocksDBOpenSSLrays1benchTensorFlow LiteNAMDJohn The RipperKvazaarNumenta Anomaly BenchmarkYafaRayTimed Linux Kernel CompilationTimed LLVM CompilationKeyDBIntel Open Image Denoise7-Zip CompressionSVT-AV1LuxCoreRenderSVT-VP9PostgreSQL pgbenchZstd CompressionRealSR-NCNNWaifu2x-NCNN Vulkanx265OCRMyPDFdav1doneDNNTimed GDB GNU Debugger Compilationlibavif avifencTimed PHP CompilationASTC EncoderHigh Performance Conjugate GradientGROMACSFFTETimed Apache CompilationMonte Carlo Simulations of Ionised NebulaeVP9 libvpx EncodingWireGuard + Linux Networking Stack Stress TestPostMarkAI Benchmark AlphaHuginDaCapo BenchmarkRawTherapeeLevelDBeSpeak-NG Speech EngineC-BloscMlpack BenchmarkNumpy BenchmarklibrsvgTimed MAFFT AlignmentMobile Neural NetworkPyPerformanceJava Gradle BuildTesseract OCRDolfynRNNoiseBYTE Unix BenchmarkGitWebP Image EncodeGNU Octave BenchmarkTNNTimed HMMer SearchHierarchical INTegrationLibRawCaffe

GM-1000, Karbon 700, CompuLab Airtop PCsior: Write Testior: Read Testpostmark: Disk Transaction Performancerealsr-ncnn: 4x - Norealsr-ncnn: 4x - Yeswaifu2x-ncnn: 2x - 3 - Nowaifu2x-ncnn: 2x - 3 - Yesglmark2: 1920 x 1080wireguard: blosc: blosclzhpcg: lczero: BLASlczero: Eigennamd: ATPase Simulation - 327,506 Atomsdolfyn: Computational Fluid Dynamicsffte: N=256, 3D Complex FFT Routinehmmer: Pfam Database Searchincompact3d: Cylindermafft: Multiple Sequence Alignment - LSU RNAmocassin: Dust 2D tau100.0lammps: Rhodopsin Proteinwebp: Defaultwebp: Quality 100webp: Quality 100, Losslesswebp: Quality 100, Highest Compressionwebp: Quality 100, Lossless, Highest Compressionjava-gradle-perf: Reactordacapobench: H2dacapobench: Jythondacapobench: Tradesoapdacapobench: Tradebeansbyte: Dhrystone 2compress-zstd: 3compress-zstd: 19libraw: Post-Processing Benchmarkjohn-the-ripper: Blowfishjohn-the-ripper: MD5onednn: IP Batch 1D - f32 - CPUonednn: IP Batch All - f32 - CPUonednn: IP Batch 1D - u8s8f32 - CPUonednn: IP Batch All - u8s8f32 - CPUonednn: Convolution Batch Shapes Auto - f32 - CPUonednn: Deconvolution Batch deconv_1d - f32 - CPUonednn: Deconvolution Batch deconv_3d - f32 - CPUonednn: Convolution Batch Shapes Auto - u8s8f32 - CPUonednn: Deconvolution Batch deconv_1d - u8s8f32 - CPUonednn: Deconvolution Batch deconv_3d - u8s8f32 - CPUonednn: Recurrent Neural Network Training - f32 - CPUonednn: Recurrent Neural Network Inference - f32 - CPUonednn: Matrix Multiply Batch Shapes Transformer - f32 - CPUonednn: Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPUdav1d: Chimera 1080pdav1d: Summer Nature 4Kdav1d: Summer Nature 1080pdav1d: Chimera 1080p 10-bitkvazaar: Bosphorus 4K - Mediumkvazaar: Bosphorus 1080p - Mediumkvazaar: Bosphorus 4K - Very Fastkvazaar: Bosphorus 4K - Ultra Fastkvazaar: Bosphorus 1080p - Very Fastkvazaar: Bosphorus 1080p - Ultra Fastsvt-av1: Enc Mode 0 - 1080psvt-av1: Enc Mode 4 - 1080psvt-vp9: PSNR/SSIM Optimized - Bosphorus 1080psvt-vp9: Visual Quality Optimized - Bosphorus 1080pvpxenc: Speed 0vpxenc: Speed 5x265: Bosphorus 4Kx265: Bosphorus 1080poidn: Memorialopenvkl: vklBenchmarkluxcorerender: DLSCluxcorerender: Rainbow Colors and Prismcompress-7zip: Compress Speed Testavifenc: 0avifenc: 2avifenc: 8avifenc: 10build-apache: Time To Compilebuild-gdb: Time To Compilebuild-linux-kernel: Time To Compilebuild-llvm: Time To Compilebuild-php: Time To Compileyafaray: Total Time For Sample Scenerays1bench: Large Scenenumpy: espeak: Text-To-Speech Synthesisrnnoise: openssl: RSA 4096-bit Performanceleveldb: Hot Readleveldb: Fill Syncleveldb: Fill Syncleveldb: Overwriteleveldb: Overwriteleveldb: Rand Fillleveldb: Rand Fillleveldb: Rand Readleveldb: Seek Randleveldb: Rand Deleteleveldb: Seq Fillleveldb: Seq Fillkeydb: gromacs: Water Benchmarktensorflow-lite: SqueezeNettensorflow-lite: Inception V4tensorflow-lite: NASNet Mobiletensorflow-lite: Mobilenet Floattensorflow-lite: Mobilenet Quanttensorflow-lite: Inception ResNet V2pgbench: 1 - 1 - Read Onlypgbench: 1 - 1 - Read Only - Average Latencypgbench: 1 - 1 - Read Writepgbench: 1 - 1 - Read Write - Average Latencypgbench: 1 - 50 - Read Onlypgbench: 1 - 50 - Read Only - Average Latencypgbench: 1 - 50 - Read Writepgbench: 1 - 50 - Read Write - Average Latencyastcenc: Fastastcenc: Mediumastcenc: Thoroughastcenc: Exhaustivehugin: Panorama Photo Assistant + Stitching Timeocrmypdf: Processing 60 Page PDF Documentoctave-benchmark: rawtherapee: Total Benchmark Timersvg: SVG Files To PNGcaffe: AlexNet - CPU - 100caffe: AlexNet - CPU - 200caffe: GoogleNet - CPU - 100caffe: GoogleNet - CPU - 200mnn: SqueezeNetV1.0mnn: resnet-v2-50mnn: inception-v3ncnn: CPU - squeezenetncnn: CPU - mobilenetncnn: CPU-v2-v2 - mobilenet-v2ncnn: CPU - googlenetncnn: CPU - vgg16ncnn: CPU - resnet18ncnn: CPU - alexnetncnn: CPU - resnet50ncnn: CPU - yolov4-tinyncnn: Vulkan GPU - squeezenetncnn: Vulkan GPU - mobilenetncnn: Vulkan GPU-v2-v2 - mobilenet-v2ncnn: Vulkan GPU-v3-v3 - mobilenet-v3ncnn: Vulkan GPU - shufflenet-v2ncnn: Vulkan GPU - mnasnetncnn: Vulkan GPU - efficientnet-b0ncnn: Vulkan GPU - blazefacencnn: Vulkan GPU - googlenetncnn: Vulkan GPU - vgg16ncnn: Vulkan GPU - resnet18ncnn: Vulkan GPU - alexnetncnn: Vulkan GPU - resnet50ncnn: Vulkan GPU - yolov4-tinytnn: CPU - MobileNet v2tnn: CPU - SqueezeNet v1.1cassandra: Writesrocksdb: Rand Fillrocksdb: Rand Readrocksdb: Seq Fillrocksdb: Rand Fill Syncrocksdb: Read While Writingpyperformance: gopyperformance: 2to3pyperformance: chaospyperformance: floatpyperformance: nbodypyperformance: pathlibpyperformance: raytracepyperformance: json_loadspyperformance: crypto_pyaespyperformance: regex_compilepyperformance: python_startuppyperformance: django_templatepyperformance: pickle_pure_pythonnumenta-nab: Relative Entropynumenta-nab: Windowed Gaussiannumenta-nab: Earthgecko Skylinenumenta-nab: Bayesian Changepointhint: FLOATai-benchmark: Device Inference Scoreai-benchmark: Device Training Scoreai-benchmark: Device AI Scoregit: Time To Complete Common Git Commandsmlpack: scikit_icamlpack: scikit_qdamlpack: scikit_svmmlpack: scikit_linearridgeregressiontesseract-ocr: Time To OCR 7 Imageskripke: brl-cad: VGR Performance MetricGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop461.45476.15657837.875276.6243.21416.8683442269.9328600.43.708317847584.1786822.14530890.906674731131.248706.78615311.2683444.8701.7592.78021.1978.57246.982271.428333948336680362136200967.73601.723.327.2676544308349.53324114.2914.8400567.765416.622410.809218.8837116.123612.82036.69517670.341231.3864.385025.91239354.5192.95344.0776.171.999.015.6210.3823.5444.450.0741.446107.7980.065.0919.656.5331.423.7080.390.670.7524110190.816110.7376.6726.28332.115155.395212.6481604.059114.796374.75419.74322.0733.37729.1001492.74.8540.42260.14630.828.73331.128.4594.7485.92826.18732.527.204458524.510.53340636960111803212462783932795245441300248620.0405031.9881283730.39072668.8967.939.9176.98631.6975.78839.6088.00795.48124.631442458942412614025531911.11751.88763.68225.5430.336.6123.9983.0723.5622.5347.3343.0810.279.313.003.392.383.105.231.047.8433.335.808.1713.2216.28369.908362.1302073263473924616331981091347380873627035211712213819.350528.41161869.0152.346249.50226.115300.54497.135360309999.31612640732137260.37264.7287.8128.933.1427.1082088958343138253.171052.00833312.62681.5255.601160.38710397.84.090168407651.9601016.67830993.635188678100.192378.5799158.6282026.7861.3132.08216.0226.38034.796196.073292836893692279148614938.02955.525.733.35152728364544.4973867.69051.8898927.745717.02485.046736.6564016.52365.642153.31356322.594143.8883.964932.56113644.69157.41582.07114.584.2619.0212.0522.2147.2191.460.1342.943169.12131.837.7728.6112.3654.917.53141.931.411.534875299.60959.4125.0864.80520.91091.59198.509769.66264.689177.73146.11420.2923.70521.5822539.96.8360.36472.06248.336.68749.036.1837.6638.93733.73852.833.545751370.010.81922651232606971997081536451564962946127335540.034342.3722965450.16959783.7315.538.5233.23274.4945.83921.6876.48560.83318.22039309795821028692066226.58142.58144.44416.2019.005.1515.0066.2815.1914.2328.5129.063.634.591.431.661.31.482.640.613.228.311.682.113.758.50283.960269.275678208717384346559613215662344192337320026485.989.910314.337621.485.91386.8238.933922.21512.454132.85443.079471438878.8102311281108223644.96742.1462.6822.432.4720.27121264093100566652.88517.186944223.4621764.69010.77279.335524207.6926843.62.314993353062.8099221.02517775.746492801131.201512.73032612.4452655.1161.6732.64719.9728.13343.025256.350326748815172395638072622.21609.012.527.12112275941056.27342108.9432.5556441.127532.00326.618037.8867130.88417.720484.63495539.076251.0127.045873.62375450.53100.79432.2787.553.0313.818.6116.0034.6967.530.1042.115112.7196.136.3522.879.0041.445.2798.391.051.1533135134.32577.8146.3545.99926.428117.552134.6691051.60083.925246.29631.93334.9931.67527.4631931.610.1801.41309.96832.955.25033.154.60710.22913.67344.01340.543.656570969.820.51729828343719772620072020552051263952660265440.0389411.1452266750.22175667.1687.236.2046.09384.6658.57328.1908.56985.42922.564547331112501463792942389.17059.98362.30823.5027.577.8222.40118.1224.1723.8743.4942.3627.5826.198.1710.1910.109.2616.472.4123.54151.4623.8525.9250.2265.87369.086343.221501245263583153797210335419175152245925533210911413118.247927.11091788.5249.343429.87016.805192.61671.556371786567.42537745685143056.44960.81130.5327.253.9425.651574190477.35232.45500047.270405.7743.29219.9273718255.8156601.62.710617847374.4411222.54919794.106635888117.8671024.4666312.3153312.4881.8232.80421.0258.44945.709251.688345654277803494436078067.22511.423.728.3262333996928.64328116.9785.6232173.582820.398710.293017.536719.580113.237611.2904605.870167.4794.323195.48320307.3482.58277.9763.511.988.635.339.7421.5539.000.0681.29080.9163.994.5217.216.1027.913.5053.750.670.7322673203.068120.4618.9838.25936.064173.464217.4081666.606118.944391.49620.17276.2437.78625.3311048.44.1560.110317.68220.443.32620.443.3854.1525.47943.79519.844.663346852.160.46654273278362073883193670363551857087053210920.0473013.3201119150.447319156.8668.6811.1472.57597.5075.99042.8328.60199.21926.7195759611534214721129427610.77554.82063.20423.0527.067.0320.3981.9224.2423.7546.6038.9012.3510.743.183.732.593.325.7018.4833.746.178.7014.0920.01301.682292.585201044644591862504355730262486406627937512113614023.053828.012519610.255.248951.01327.591282.79682.884370080894.79875615736135159.82960.1076.4621.424.4727.892371669444869OpenBenchmarking.org

IOR

IOR is a parallel I/O storage benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterIOR 3.2.1Write TestGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop140280420560700SE +/- 32.44, N = 15SE +/- 0.83, N = 13SE +/- 6.43, N = 15SE +/- 0.19, N = 11461.45253.17652.8877.35MIN: 18.41 / MAX: 691.92MIN: 74.4 / MAX: 323.5MIN: 125.89 / MAX: 1003.71MIN: 37.51 / MAX: 96.261. (CC) gcc options: -O2 -lm -pthread -lmpi

OpenBenchmarking.orgMB/s, More Is BetterIOR 3.2.1Read TestGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop2004006008001000SE +/- 4.42, N = 15SE +/- 4.11, N = 13SE +/- 0.53, N = 15SE +/- 0.82, N = 11476.151052.00517.18232.45MIN: 10.65 / MAX: 548.82MIN: 53.05 / MAX: 1439MIN: 142.77 / MAX: 594.11MIN: 207.97 / MAX: 242.211. (CC) gcc options: -O2 -lm -pthread -lmpi

PostMark

This is a test of NetApp's PostMark benchmark designed to simulate small-file testing similar to the tasks endured by web and mail servers. This test profile will set PostMark to perform 25,000 transactions with 500 files simultaneously with the file sizes ranging between 5 and 512 kilobytes. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTPS, More Is BetterPostMark 1.51Disk Transaction PerformanceGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop2K4K6K8K10K65788333694450001. (CC) gcc options: -O3

RealSR-NCNN

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

OpenBenchmarking.orgSeconds, Fewer Is BetterRealSR-NCNN 20200818Scale: 4x - TAA: NoGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop50100150200250SE +/- 0.02, N = 3SE +/- 0.03, N = 4SE +/- 0.02, N = 3SE +/- 0.09, N = 337.8812.63223.4647.27

OpenBenchmarking.orgSeconds, Fewer Is BetterRealSR-NCNN 20200818Scale: 4x - TAA: YesGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop400800120016002000SE +/- 0.07, N = 3SE +/- 0.44, N = 3SE +/- 0.20, N = 3SE +/- 6.42, N = 9276.6281.531764.69405.77

Waifu2x-NCNN Vulkan

Waifu2x-NCNN is an NCNN neural network implementation of the Waifu2x converter project and accelerated using the Vulkan API. NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. This test profile times how long it takes to increase the resolution of a sample image with Vulkan. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterWaifu2x-NCNN Vulkan 20200818Scale: 2x - Denoise: 3 - TAA: NoGM-1000Karbon 700CompuLab Airtop3691215SE +/- 0.007, N = 9SE +/- 0.003, N = 5SE +/- 0.030, N = 103.21410.7723.292

OpenBenchmarking.orgSeconds, Fewer Is BetterWaifu2x-NCNN Vulkan 20200818Scale: 2x - Denoise: 3 - TAA: YesGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop20406080100SE +/- 0.010, N = 3SE +/- 0.012, N = 7SE +/- 0.027, N = 3SE +/- 0.167, N = 316.8685.60179.33519.927

GLmark2

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

OpenBenchmarking.orgScore, More Is BetterGLmark2 2020.04Resolution: 1920 x 1080GM-1000Karbon 700CompuLab Airtop800160024003200400034425243718

WireGuard + Linux Networking Stack Stress Test

This is a benchmark of the WireGuard secure VPN tunnel and Linux networking stack stress test. The test runs on the local host but does require root permissions to run. The way it works is it creates three namespaces. ns0 has a loopback device. ns1 and ns2 each have wireguard devices. Those two wireguard devices send traffic through the loopback device of ns0. The end result of this is that tests wind up testing encryption and decryption at the same time -- a pretty CPU and scheduler-heavy workflow. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterWireGuard + Linux Networking Stack Stress TestGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop60120180240300SE +/- 2.25, N = 3SE +/- 0.53, N = 3SE +/- 0.72, N = 3SE +/- 0.60, N = 3269.93160.39207.69255.82

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 2.0 Beta 5Compressor: blosclzGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop2K4K6K8K10KSE +/- 11.16, N = 4SE +/- 6.83, N = 3SE +/- 13.18, N = 3SE +/- 27.03, N = 38600.410397.86843.66601.61. (CXX) g++ options: -rdynamic

High Performance Conjugate Gradient

HPCG is the High Performance Conjugate Gradient and is a new scientific benchmark from Sandia National Lans focused for super-computer testing with modern real-world workloads compared to HPCC. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOP/s, More Is BetterHigh Performance Conjugate Gradient 3.1GM-1000CompuLab Airtop3Karbon 700CompuLab Airtop0.92031.84062.76093.68124.6015SE +/- 0.00058, N = 3SE +/- 0.00092, N = 3SE +/- 0.00031, N = 3SE +/- 0.00891, N = 33.708314.090162.314992.710611. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -pthread -lmpi_cxx -lmpi

LeelaChessZero

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

OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.26Backend: BLASGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop2004006008001000SE +/- 6.44, N = 3SE +/- 8.54, N = 3SE +/- 10.93, N = 37848403357841. (CXX) g++ options: -flto -pthread

OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.26Backend: EigenGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop160320480640800SE +/- 2.52, N = 3SE +/- 7.36, N = 3SE +/- 4.33, N = 3SE +/- 3.38, N = 37587653067371. (CXX) g++ options: -flto -pthread

NAMD

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

OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD 2.14ATPase Simulation - 327,506 AtomsGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop0.99931.99862.99793.99724.9965SE +/- 0.00286, N = 3SE +/- 0.00439, N = 3SE +/- 0.00379, N = 3SE +/- 0.00395, N = 34.178681.960102.809924.44112

Dolfyn

Dolfyn is a Computational Fluid Dynamics (CFD) code of modern numerical simulation techniques. The Dolfyn test profile measures the execution time of the bundled computational fluid dynamics demos that are bundled with Dolfyn. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterDolfyn 0.527Computational Fluid DynamicsGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop510152025SE +/- 0.08, N = 3SE +/- 0.02, N = 3SE +/- 0.13, N = 3SE +/- 0.08, N = 322.1516.6821.0322.55

FFTE

FFTE is a package by Daisuke Takahashi to compute Discrete Fourier Transforms of 1-, 2- and 3- dimensional sequences of length (2^p)*(3^q)*(5^r). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMFLOPS, More Is BetterFFTE 7.0N=256, 3D Complex FFT RoutineGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop7K14K21K28K35KSE +/- 47.47, N = 11SE +/- 76.97, N = 11SE +/- 18.12, N = 9SE +/- 59.46, N = 930890.9130993.6417775.7519794.111. (F9X) gfortran options: -O3 -fomit-frame-pointer -fopenmp

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 3.3.1Pfam Database SearchGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop306090120150SE +/- 0.02, N = 3SE +/- 0.10, N = 3SE +/- 0.08, N = 3SE +/- 0.07, N = 3131.25100.19131.20117.871. (CC) gcc options: -O3 -pthread -lhmmer -leasel -lm

Incompact3D

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

OpenBenchmarking.orgSeconds, Fewer Is BetterIncompact3D 2020-09-17Input: CylinderGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop2004006008001000SE +/- 1.81, N = 3SE +/- 1.24, N = 3SE +/- 1.81, N = 3SE +/- 4.69, N = 3706.79378.58512.731024.471. (F9X) gfortran options: -cpp -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent -levent_pthreads -lutil -lm -lrt -lz

Timed MAFFT Alignment

This test performs an alignment of 100 pyruvate decarboxylase sequences. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MAFFT Alignment 7.471Multiple Sequence Alignment - LSU RNAGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop3691215SE +/- 0.101, N = 11SE +/- 0.018, N = 5SE +/- 0.024, N = 4SE +/- 0.091, N = 411.2688.62812.44512.3151. (CC) gcc options: -std=c99 -O3 -lm -lpthread

Monte Carlo Simulations of Ionised Nebulae

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

OpenBenchmarking.orgSeconds, Fewer Is BetterMonte Carlo Simulations of Ionised Nebulae 2019-03-24Input: Dust 2D tau100.0GM-1000CompuLab Airtop3Karbon 700CompuLab Airtop70140210280350SE +/- 1.33, N = 3SE +/- 0.58, N = 3SE +/- 0.67, N = 3SE +/- 3.84, N = 33442022653311. (F9X) gfortran options: -cpp -Jsource/ -ffree-line-length-0 -lm -std=legacy -O3 -O2 -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent -levent_pthreads -lutil -lrt -lz

LAMMPS Molecular Dynamics Simulator

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

OpenBenchmarking.orgns/day, More Is BetterLAMMPS Molecular Dynamics Simulator 24Aug2020Model: Rhodopsin ProteinGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop246810SE +/- 0.047, N = 15SE +/- 0.062, N = 10SE +/- 0.006, N = 8SE +/- 0.061, N = 154.8706.7865.1162.4881. (CXX) g++ options: -O3 -pthread -lm

WebP Image Encode

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

OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: DefaultGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop0.41020.82041.23061.64082.051SE +/- 0.003, N = 11SE +/- 0.000, N = 12SE +/- 0.002, N = 13SE +/- 0.001, N = 111.7591.3131.6731.8231. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff

OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100GM-1000CompuLab Airtop3Karbon 700CompuLab Airtop0.63091.26181.89272.52363.1545SE +/- 0.001, N = 9SE +/- 0.002, N = 10SE +/- 0.001, N = 10SE +/- 0.002, N = 92.7802.0822.6472.8041. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff

OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100, LosslessGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop510152025SE +/- 0.01, N = 3SE +/- 0.00, N = 4SE +/- 0.01, N = 3SE +/- 0.00, N = 321.2016.0219.9721.031. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff

OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100, Highest CompressionGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop246810SE +/- 0.007, N = 5SE +/- 0.006, N = 6SE +/- 0.014, N = 6SE +/- 0.011, N = 58.5726.3808.1338.4491. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff

OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100, Lossless, Highest CompressionGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop1122334455SE +/- 0.09, N = 3SE +/- 0.10, N = 3SE +/- 0.13, N = 3SE +/- 0.05, N = 346.9834.8043.0345.711. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff

Java Gradle Build

This test runs Java software project builds using the Gradle build system. It is intended to give developers an idea as to the build performance for development activities and build servers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterJava Gradle BuildGradle Build: ReactorGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop60120180240300SE +/- 3.29, N = 3SE +/- 2.24, N = 12SE +/- 3.91, N = 9SE +/- 3.19, N = 9271.43196.07256.35251.69

DaCapo Benchmark

This test runs the DaCapo Benchmarks written in Java and intended to test system/CPU performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: H2GM-1000CompuLab Airtop3Karbon 700CompuLab Airtop7001400210028003500SE +/- 39.15, N = 20SE +/- 28.32, N = 20SE +/- 41.03, N = 20SE +/- 26.08, N = 203339292832673456

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: JythonGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop12002400360048006000SE +/- 23.71, N = 6SE +/- 38.10, N = 7SE +/- 54.95, N = 7SE +/- 44.43, N = 64833368948815427

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: TradesoapGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop2K4K6K8K10KSE +/- 85.52, N = 20SE +/- 30.62, N = 13SE +/- 43.34, N = 4SE +/- 48.38, N = 46680369251727803

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: TradebeansGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop11002200330044005500SE +/- 30.71, N = 5SE +/- 42.33, N = 20SE +/- 92.26, N = 16SE +/- 64.08, N = 53621279139564944

BYTE Unix Benchmark

This is a test of BYTE. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgLPS, More Is BetterBYTE Unix Benchmark 3.6Computational Test: Dhrystone 2GM-1000CompuLab Airtop3Karbon 700CompuLab Airtop10M20M30M40M50MSE +/- 15338.08, N = 3SE +/- 180310.11, N = 3SE +/- 87756.94, N = 3SE +/- 360329.39, N = 336200967.748614938.038072622.236078067.2

Zstd Compression

This test measures the time needed to compress a sample file (an Ubuntu ISO) using Zstd compression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.5Compression Level: 3GM-1000CompuLab Airtop3Karbon 700CompuLab Airtop8001600240032004000SE +/- 4.91, N = 3SE +/- 2.03, N = 3SE +/- 3.71, N = 3SE +/- 2.72, N = 33601.72955.51609.02511.41. (CC) gcc options: -O3 -pthread -lz -llzma

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.5Compression Level: 19GM-1000CompuLab Airtop3Karbon 700CompuLab Airtop612182430SE +/- 0.25, N = 3SE +/- 0.09, N = 3SE +/- 0.00, N = 3SE +/- 0.23, N = 323.325.712.523.71. (CC) gcc options: -O3 -pthread -lz -llzma

LibRaw

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

OpenBenchmarking.orgMpix/sec, More Is BetterLibRaw 0.20Post-Processing BenchmarkGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop816243240SE +/- 0.32, N = 3SE +/- 0.10, N = 3SE +/- 0.08, N = 3SE +/- 0.10, N = 327.2633.3527.1228.321. (CXX) g++ options: -O2 -fopenmp -ljpeg -lz -lm

John The Ripper

This is a benchmark of John The Ripper, which is a password cracker. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 1.9.0-jumbo-1Test: BlowfishGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop3K6K9K12K15KSE +/- 60.95, N = 13SE +/- 227.62, N = 4SE +/- 103.18, N = 10765415272112276233-lbz21. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -pthread -lm -lz -ldl -lcrypt

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 1.9.0-jumbo-1Test: MD5GM-1000CompuLab Airtop3Karbon 700CompuLab Airtop200K400K600K800K1000KSE +/- 3391.63, N = 15SE +/- 10984.38, N = 4SE +/- 6589.74, N = 7SE +/- 115.39, N = 3430834836454594105399692-lbz21. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -pthread -lm -lz -ldl -lcrypt

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 oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: IP Batch 1D - Data Type: f32 - Engine: CPUGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop3691215SE +/- 0.22450, N = 15SE +/- 0.04455, N = 15SE +/- 0.04542, N = 15SE +/- 0.05158, N = 49.533244.497386.273428.64328MIN: 6.67MIN: 3.82MIN: 5.45MIN: 8.211. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: IP Batch All - Data Type: f32 - Engine: CPUGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop306090120150SE +/- 0.53, N = 3SE +/- 0.12, N = 3SE +/- 0.10, N = 3SE +/- 0.45, N = 3114.2967.69108.94116.98MIN: 99.97MIN: 65.58MIN: 99.88MIN: 114.081. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: IP Batch 1D - Data Type: u8s8f32 - Engine: CPUGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop1.26522.53043.79565.06086.326SE +/- 0.10124, N = 15SE +/- 0.00614, N = 4SE +/- 0.03957, N = 15SE +/- 0.01843, N = 44.840051.889892.555645.62321MIN: 3.33MIN: 1.55MIN: 1.92MIN: 5.551. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: IP Batch All - Data Type: u8s8f32 - Engine: CPUGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop1632486480SE +/- 0.33, N = 3SE +/- 0.06, N = 3SE +/- 0.05, N = 3SE +/- 0.24, N = 367.7727.7541.1373.58MIN: 59.54MIN: 25.65MIN: 35.58MIN: 72.881. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPUGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop714212835SE +/- 0.05, N = 7SE +/- 0.02, N = 7SE +/- 0.03, N = 6SE +/- 0.02, N = 616.6217.0232.0020.40MIN: 16.36MIN: 16.91MIN: 31.82MIN: 20.061. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Deconvolution Batch deconv_1d - Data Type: f32 - Engine: CPUGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop3691215SE +/- 0.15350, N = 13SE +/- 0.06779, N = 4SE +/- 0.14132, N = 12SE +/- 0.06708, N = 310.809215.046736.6180310.29300MIN: 6.79MIN: 4.56MIN: 4.86MIN: 10.021. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Deconvolution Batch deconv_3d - Data Type: f32 - Engine: CPUGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop48121620SE +/- 0.08092, N = 15SE +/- 0.02344, N = 9SE +/- 0.02235, N = 9SE +/- 0.04063, N = 98.883716.656407.8867117.53670MIN: 8.11MIN: 6.4MIN: 7.8MIN: 17.191. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPUGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop714212835SE +/- 0.02, N = 6SE +/- 0.05, N = 7SE +/- 0.01, N = 6SE +/- 0.05, N = 616.1216.5230.8819.58MIN: 15.9MIN: 16.37MIN: 30.58MIN: 17.981. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Deconvolution Batch deconv_1d - Data Type: u8s8f32 - Engine: CPUGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop3691215SE +/- 0.13560, N = 12SE +/- 0.02496, N = 3SE +/- 0.11012, N = 12SE +/- 0.09759, N = 312.820305.642157.7204813.23760MIN: 8.95MIN: 4.78MIN: 6.41MIN: 12.921. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Deconvolution Batch deconv_3d - Data Type: u8s8f32 - Engine: CPUGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop3691215SE +/- 0.01402, N = 9SE +/- 0.02023, N = 9SE +/- 0.00916, N = 9SE +/- 0.00833, N = 96.695173.313564.6349511.29040MIN: 6.49MIN: 3.15MIN: 4.53MIN: 11.221. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPUGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop140280420560700SE +/- 8.43, N = 3SE +/- 2.57, N = 3SE +/- 2.70, N = 3SE +/- 6.00, N = 9670.34322.59539.08605.87MIN: 612.85MIN: 310.92MIN: 524.69MIN: 563.771. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPUGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop50100150200250SE +/- 0.93, N = 3SE +/- 0.47, N = 3SE +/- 0.50, N = 3SE +/- 2.10, N = 3231.39143.89251.01167.48MIN: 223.49MIN: 141.15MIN: 247.27MIN: 163.71. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPUGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop246810SE +/- 0.04995, N = 4SE +/- 0.00566, N = 4SE +/- 0.01697, N = 4SE +/- 0.01480, N = 44.385023.964937.045874.32319MIN: 4.02MIN: 3.9MIN: 6.9MIN: 3.981. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPUGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop1.33032.66063.99095.32126.6515SE +/- 0.05068, N = 15SE +/- 0.00686, N = 4SE +/- 0.03701, N = 15SE +/- 0.02910, N = 45.912392.561133.623755.48320MIN: 4.17MIN: 2.22MIN: 2.86MIN: 5.231. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

dav1d

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

OpenBenchmarking.orgFPS, More Is Betterdav1d 0.7.0Video Input: Chimera 1080pGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop140280420560700SE +/- 2.32, N = 3SE +/- 2.55, N = 3SE +/- 1.11, N = 3SE +/- 1.02, N = 3354.51644.69450.53307.34MIN: 226.96 / MAX: 562.8MIN: 479.82 / MAX: 947.65MIN: 341.02 / MAX: 685.68MIN: 221.1 / MAX: 501.291. (CC) gcc options: -pthread

OpenBenchmarking.orgFPS, More Is Betterdav1d 0.7.0Video Input: Summer Nature 4KGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop306090120150SE +/- 1.39, N = 4SE +/- 1.02, N = 3SE +/- 0.28, N = 3SE +/- 0.31, N = 392.95157.41100.7982.58MIN: 77.22 / MAX: 122.95MIN: 139.25 / MAX: 172.94MIN: 89.28 / MAX: 105.54MIN: 76.45 / MAX: 95.481. (CC) gcc options: -pthread

OpenBenchmarking.orgFPS, More Is Betterdav1d 0.7.0Video Input: Summer Nature 1080pGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop130260390520650SE +/- 0.50, N = 3SE +/- 1.68, N = 3SE +/- 1.38, N = 3SE +/- 1.58, N = 3344.07582.07432.27277.97MIN: 298.25 / MAX: 380.67MIN: 481.99 / MAX: 638.3MIN: 364.27 / MAX: 468.57MIN: 249.54 / MAX: 307.951. (CC) gcc options: -pthread

OpenBenchmarking.orgFPS, More Is Betterdav1d 0.7.0Video Input: Chimera 1080p 10-bitGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop306090120150SE +/- 0.61, N = 3SE +/- 0.05, N = 3SE +/- 0.06, N = 3SE +/- 0.07, N = 376.17114.5887.5563.51MIN: 47.76 / MAX: 187.8MIN: 72.92 / MAX: 273.76MIN: 56.85 / MAX: 197.5MIN: 42.21 / MAX: 145.151. (CC) gcc options: -pthread

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: MediumGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop0.95851.9172.87553.8344.7925SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 31.994.263.031.981. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 1080p - Video Preset: MediumGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop510152025SE +/- 0.15, N = 3SE +/- 0.12, N = 3SE +/- 0.23, N = 3SE +/- 0.00, N = 39.0119.0213.818.631. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 4K - Video Preset: Very FastGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop3691215SE +/- 0.06, N = 3SE +/- 0.07, N = 3SE +/- 0.10, N = 3SE +/- 0.01, N = 35.6212.058.615.331. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 4K - Video Preset: Ultra FastGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop510152025SE +/- 0.15, N = 4SE +/- 0.12, N = 3SE +/- 0.24, N = 4SE +/- 0.00, N = 310.3822.2116.009.741. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 1080p - Video Preset: Very FastGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop1122334455SE +/- 0.24, N = 14SE +/- 0.46, N = 4SE +/- 0.34, N = 14SE +/- 0.01, N = 323.5447.2134.6921.551. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 1080p - Video Preset: Ultra FastGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop20406080100SE +/- 0.87, N = 15SE +/- 1.01, N = 7SE +/- 0.80, N = 15SE +/- 0.02, N = 444.4591.4667.5339.001. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

SVT-AV1

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

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 0 - Input: 1080pGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop0.03020.06040.09060.12080.151SE +/- 0.000, N = 3SE +/- 0.001, N = 3SE +/- 0.000, N = 3SE +/- 0.001, N = 30.0740.1340.1040.0681. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 4 - Input: 1080pGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop0.66221.32441.98662.64883.311SE +/- 0.025, N = 3SE +/- 0.013, N = 3SE +/- 0.028, N = 3SE +/- 0.002, N = 31.4462.9432.1151.2901. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie

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 1080p YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.1Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080pGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop4080120160200SE +/- 1.68, N = 15SE +/- 0.26, N = 8SE +/- 0.71, N = 7SE +/- 0.88, N = 7107.79169.12112.7180.911. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.1Tuning: Visual Quality Optimized - Input: Bosphorus 1080pGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop306090120150SE +/- 1.58, N = 15SE +/- 0.95, N = 8SE +/- 0.08, N = 6SE +/- 0.12, N = 580.06131.8396.1363.991. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

VP9 libvpx Encoding

This is a standard video encoding performance test of Google's libvpx library and the vpxenc command for the VP9/WebM format using a sample 1080p video. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.8.2Speed: Speed 0GM-1000CompuLab Airtop3Karbon 700CompuLab Airtop246810SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 35.097.776.354.521. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=c++11

OpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.8.2Speed: Speed 5GM-1000CompuLab Airtop3Karbon 700CompuLab Airtop714212835SE +/- 0.20, N = 8SE +/- 0.15, N = 3SE +/- 0.09, N = 3SE +/- 0.10, N = 319.6528.6122.8717.211. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=c++11

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 4KGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop3691215SE +/- 0.05, N = 3SE +/- 0.11, N = 3SE +/- 0.11, N = 3SE +/- 0.03, N = 36.5312.369.006.101. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.4Video Input: Bosphorus 1080pGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop1224364860SE +/- 0.37, N = 13SE +/- 0.30, N = 5SE +/- 0.41, N = 8SE +/- 0.09, N = 331.4254.9141.4427.911. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

Intel Open Image Denoise

Open Image Denoise is a denoising library for ray-tracing and part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 1.2.0Scene: MemorialGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop246810SE +/- 0.04, N = 6SE +/- 0.10, N = 3SE +/- 0.09, N = 3SE +/- 0.01, N = 33.707.535.273.50

OpenVKL

OpenVKL is the Intel Open Volume Kernel Library that offers high-performance volume computation kernels and part of the Intel oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgItems / Sec, More Is BetterOpenVKL 0.9Benchmark: vklBenchmarkGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop306090120150SE +/- 0.39, N = 3SE +/- 0.98, N = 3SE +/- 0.29, N = 3SE +/- 0.05, N = 380.39141.9398.3953.75MIN: 1 / MAX: 345MIN: 1 / MAX: 580MIN: 1 / MAX: 378MIN: 1 / MAX: 212

LuxCoreRender

LuxCoreRender is an open-source physically based renderer. This test profile is focused on running LuxCoreRender on the CPU as opposed to the OpenCL version. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.3Scene: DLSCGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop0.31730.63460.95191.26921.5865SE +/- 0.01, N = 15SE +/- 0.02, N = 3SE +/- 0.01, N = 9SE +/- 0.00, N = 30.671.411.050.67MIN: 0.59 / MAX: 0.97MIN: 1.31 / MAX: 1.69MIN: 0.95 / MAX: 1.29MIN: 0.65 / MAX: 0.68

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.3Scene: Rainbow Colors and PrismGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop0.34430.68861.03291.37721.7215SE +/- 0.01, N = 12SE +/- 0.01, N = 3SE +/- 0.02, N = 4SE +/- 0.00, N = 30.751.531.150.73MIN: 0.65 / MAX: 1.15MIN: 1.48 / MAX: 1.81MIN: 1.06 / MAX: 1.42MIN: 0.7 / MAX: 0.8

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 TestGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop10K20K30K40K50KSE +/- 339.20, N = 4SE +/- 370.06, N = 3SE +/- 59.48, N = 3SE +/- 77.43, N = 3241104875233135226731. (CXX) g++ options: -pipe -lpthread

libavif avifenc

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

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.7.3Encoder Speed: 0GM-1000CompuLab Airtop3Karbon 700CompuLab Airtop4080120160200SE +/- 0.11, N = 3SE +/- 0.27, N = 3SE +/- 0.22, N = 3SE +/- 0.73, N = 3190.8299.61134.33203.071. (CXX) g++ options: -O3 -fPIC

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.7.3Encoder Speed: 2GM-1000CompuLab Airtop3Karbon 700CompuLab Airtop306090120150SE +/- 1.76, N = 3SE +/- 0.11, N = 3SE +/- 0.57, N = 3SE +/- 0.45, N = 3110.7459.4177.81120.461. (CXX) g++ options: -O3 -fPIC

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.7.3Encoder Speed: 8GM-1000CompuLab Airtop3Karbon 700CompuLab Airtop3691215SE +/- 0.014, N = 6SE +/- 0.006, N = 7SE +/- 0.013, N = 6SE +/- 0.014, N = 56.6725.0866.3548.9831. (CXX) g++ options: -O3 -fPIC

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.7.3Encoder Speed: 10GM-1000CompuLab Airtop3Karbon 700CompuLab Airtop246810SE +/- 0.007, N = 7SE +/- 0.001, N = 8SE +/- 0.006, N = 7SE +/- 0.010, N = 66.2834.8055.9998.2591. (CXX) g++ options: -O3 -fPIC

Timed Apache Compilation

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Apache Compilation 2.4.41Time To CompileGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop816243240SE +/- 0.35, N = 7SE +/- 0.03, N = 3SE +/- 0.08, N = 3SE +/- 0.03, N = 332.1220.9126.4336.06

Timed GDB GNU Debugger Compilation

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed GDB GNU Debugger Compilation 9.1Time To CompileGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop4080120160200SE +/- 0.70, N = 3SE +/- 0.08, N = 3SE +/- 0.35, N = 3SE +/- 0.28, N = 3155.4091.59117.55173.46

Timed Linux Kernel Compilation

This test times how long it takes to build the Linux kernel in a default configuration. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 5.4Time To CompileGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop50100150200250SE +/- 0.47, N = 3SE +/- 0.13, N = 3SE +/- 0.65, N = 3SE +/- 0.72, N = 3212.6598.51134.67217.41

Timed LLVM Compilation

This test times how long it takes to build the LLVM compiler. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 10.0Time To CompileGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop400800120016002000SE +/- 1.30, N = 3SE +/- 4.62, N = 3SE +/- 0.57, N = 3SE +/- 9.03, N = 31604.06769.661051.601666.61

Timed PHP Compilation

This test times how long it takes to build PHP 7. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed PHP Compilation 7.4.2Time To CompileGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop306090120150SE +/- 0.58, N = 3SE +/- 0.33, N = 3SE +/- 0.36, N = 3SE +/- 0.08, N = 3114.8064.6983.93118.94

YafaRay

YafaRay is an open-source physically based montecarlo ray-tracing engine. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterYafaRay 3.4.1Total Time For Sample SceneGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop80160240320400SE +/- 2.21, N = 3SE +/- 0.40, N = 3SE +/- 0.75, N = 3SE +/- 0.14, N = 3374.75177.73246.30391.501. (CXX) g++ options: -std=c++11 -O3 -ffast-math -rdynamic -ldl -lImath -lIlmImf -lIex -lHalf -lz -lIlmThread -lxml2 -lfreetype -lpthread

rays1bench

This is a test of rays1bench, a simple path-tracer / ray-tracing that supports SSE and AVX instructions, multi-threading, and other features. This test profile is measuring the performance of the "large scene" in rays1bench. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgmrays/s, More Is Betterrays1bench 2020-01-09Large SceneGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop1020304050SE +/- 0.19, N = 3SE +/- 0.09, N = 3SE +/- 0.30, N = 13SE +/- 0.01, N = 319.7446.1131.9320.17

Numpy Benchmark

This is a test to obtain the general Numpy performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterNumpy BenchmarkGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop90180270360450SE +/- 0.61, N = 3SE +/- 0.95, N = 3SE +/- 1.03, N = 3SE +/- 0.36, N = 3322.07420.29334.99276.24

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 SynthesisGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop918273645SE +/- 0.19, N = 4SE +/- 0.13, N = 4SE +/- 0.46, N = 20SE +/- 0.36, N = 933.3823.7131.6837.791. (CC) gcc options: -O2 -std=c99

RNNoise

RNNoise is a recurrent neural network for audio noise reduction developed by Mozilla and Xiph.Org. This test profile is a single-threaded test measuring the time to denoise a sample 26 minute long 16-bit RAW audio file using this recurrent neural network noise suppression library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRNNoise 2020-06-28GM-1000CompuLab Airtop3Karbon 700CompuLab Airtop714212835SE +/- 0.17, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.15, N = 329.1021.5827.4625.331. (CC) gcc options: -O2 -pedantic -fvisibility=hidden

OpenSSL

OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test measures the RSA 4096-bit performance of OpenSSL. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSigns Per Second, More Is BetterOpenSSL 1.1.1RSA 4096-bit PerformanceGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop5001000150020002500SE +/- 29.90, N = 15SE +/- 21.92, N = 14SE +/- 13.61, N = 15SE +/- 3.09, N = 31492.72539.91931.61048.41. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

LevelDB

LevelDB is a key-value storage library developed by Google that supports making use of Snappy for data compression and has other modern features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Hot ReadGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop3691215SE +/- 0.045, N = 15SE +/- 0.037, N = 6SE +/- 0.133, N = 5SE +/- 0.008, N = 84.8546.83610.1804.1561. (CXX) g++ options: -O3 -lsnappy -lpthread

OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: Fill SyncGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop0.3150.630.9451.261.575SE +/- 0.00, N = 10SE +/- 0.00, N = 6SE +/- 0.08, N = 15SE +/- 0.00, N = 50.40.31.40.11. (CXX) g++ options: -O3 -lsnappy -lpthread

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Fill SyncGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop2K4K6K8K10KSE +/- 8.65, N = 10SE +/- 6.82, N = 6SE +/- 74.53, N = 15SE +/- 23.53, N = 52260.156472.061309.9710317.681. (CXX) g++ options: -O3 -lsnappy -lpthread

OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: OverwriteGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop1122334455SE +/- 0.26, N = 15SE +/- 0.41, N = 15SE +/- 1.32, N = 15SE +/- 0.04, N = 830.848.332.920.41. (CXX) g++ options: -O3 -lsnappy -lpthread

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: OverwriteGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop1224364860SE +/- 0.24, N = 15SE +/- 0.31, N = 15SE +/- 2.50, N = 15SE +/- 0.10, N = 828.7336.6955.2543.331. (CXX) g++ options: -O3 -lsnappy -lpthread

OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: Random FillGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop1122334455SE +/- 0.32, N = 15SE +/- 0.44, N = 15SE +/- 1.18, N = 15SE +/- 0.03, N = 831.149.033.120.41. (CXX) g++ options: -O3 -lsnappy -lpthread

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Random FillGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop1224364860SE +/- 0.30, N = 15SE +/- 0.33, N = 15SE +/- 2.43, N = 15SE +/- 0.06, N = 828.4636.1854.6143.391. (CXX) g++ options: -O3 -lsnappy -lpthread

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Random ReadGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop3691215SE +/- 0.022, N = 8SE +/- 0.090, N = 15SE +/- 0.166, N = 15SE +/- 0.011, N = 84.7487.66310.2294.1521. (CXX) g++ options: -O3 -lsnappy -lpthread

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Seek RandomGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop48121620SE +/- 0.070, N = 15SE +/- 0.183, N = 15SE +/- 0.156, N = 15SE +/- 0.024, N = 75.9288.93713.6735.4791. (CXX) g++ options: -O3 -lsnappy -lpthread

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Random DeleteGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop1020304050SE +/- 0.34, N = 4SE +/- 0.21, N = 3SE +/- 0.14, N = 3SE +/- 0.02, N = 326.1933.7444.0143.801. (CXX) g++ options: -O3 -lsnappy -lpthread

OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: Sequential FillGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop1224364860SE +/- 0.41, N = 5SE +/- 0.78, N = 3SE +/- 0.15, N = 3SE +/- 0.07, N = 332.552.840.519.81. (CXX) g++ options: -O3 -lsnappy -lpthread

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Sequential FillGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop1020304050SE +/- 0.33, N = 5SE +/- 0.49, N = 3SE +/- 0.15, N = 3SE +/- 0.18, N = 327.2033.5543.6644.661. (CXX) g++ options: -O3 -lsnappy -lpthread

KeyDB

A benchmark of KeyDB as a multi-threaded fork of the Redis server. The KeyDB benchmark is conducted using memtier-benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOps/sec, More Is BetterKeyDB 6.0.16GM-1000CompuLab Airtop3Karbon 700CompuLab Airtop160K320K480K640K800KSE +/- 3781.40, N = 3SE +/- 4773.08, N = 3SE +/- 6113.88, N = 3SE +/- 4325.50, N = 3458524.51751370.01570969.82346852.161. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

GROMACS

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

OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2020.3Water BenchmarkGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop0.18430.36860.55290.73720.9215SE +/- 0.001, N = 3SE +/- 0.002, N = 3SE +/- 0.001, N = 3SE +/- 0.006, N = 30.5330.8190.5170.4661. (CXX) g++ options: -O3 -pthread -lrt -lpthread -lm

TensorFlow Lite

This is a benchmark of the TensorFlow Lite implementation. The current Linux support is limited to running on CPUs. This test profile is measuring the average inference time. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: SqueezeNetGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop120K240K360K480K600KSE +/- 5447.42, N = 4SE +/- 69.61, N = 3SE +/- 3356.24, N = 3SE +/- 9.24, N = 3406369226512298283542732

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception V4GM-1000CompuLab Airtop3Karbon 700CompuLab Airtop2M4M6M8M10MSE +/- 34182.46, N = 3SE +/- 1363.50, N = 3SE +/- 20514.24, N = 3SE +/- 604.55, N = 36011180326069743719777836207

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: NASNet MobileGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop80K160K240K320K400KSE +/- 4505.57, N = 4SE +/- 758.89, N = 3SE +/- 2829.30, N = 3SE +/- 14.01, N = 3321246199708262007388319

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet FloatGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop80K160K240K320K400KSE +/- 4495.68, N = 3SE +/- 175.70, N = 3SE +/- 2261.01, N = 3SE +/- 22.91, N = 3278393153645202055367036

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet QuantGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop80K160K240K320K400KSE +/- 4770.18, N = 3SE +/- 67.72, N = 3SE +/- 2286.50, N = 3SE +/- 116.90, N = 3279524156496205126355185

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception ResNet V2GM-1000CompuLab Airtop3Karbon 700CompuLab Airtop1.5M3M4.5M6M7.5MSE +/- 40177.63, N = 3SE +/- 1078.35, N = 3SE +/- 17665.88, N = 3SE +/- 615.40, N = 35441300294612739526607087053

PostgreSQL pgbench

This is a benchmark of PostgreSQL using pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 13.0Scaling Factor: 1 - Clients: 1 - Mode: Read OnlyGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop7K14K21K28K35KSE +/- 159.81, N = 3SE +/- 56.86, N = 3SE +/- 116.17, N = 3SE +/- 191.07, N = 15248623355426544210921. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 1 - Clients: 1 - Mode: Read Only - Average LatencyGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop0.01060.02120.03180.04240.053SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 150.0400.0300.0380.0471. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 13.0Scaling Factor: 1 - Clients: 1 - Mode: Read WriteGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop2004006008001000SE +/- 4.74, N = 3SE +/- 20.79, N = 12SE +/- 59.06, N = 15SE +/- 3.58, N = 65034349413011. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 1 - Clients: 1 - Mode: Read Write - Average LatencyGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop0.7471.4942.2412.9883.735SE +/- 0.018, N = 3SE +/- 0.125, N = 12SE +/- 0.096, N = 15SE +/- 0.040, N = 61.9882.3721.1453.3201. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 13.0Scaling Factor: 1 - Clients: 50 - Mode: Read OnlyGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop60K120K180K240K300KSE +/- 1251.67, N = 15SE +/- 2332.06, N = 3SE +/- 470.82, N = 3SE +/- 1589.17, N = 31283732965452266751119151. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 1 - Clients: 50 - Mode: Read Only - Average LatencyGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop0.10060.20120.30180.40240.503SE +/- 0.003, N = 15SE +/- 0.001, N = 3SE +/- 0.000, N = 3SE +/- 0.006, N = 30.3900.1690.2210.4471. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 13.0Scaling Factor: 1 - Clients: 50 - Mode: Read WriteGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop160320480640800SE +/- 3.31, N = 3SE +/- 1.80, N = 3SE +/- 23.33, N = 15SE +/- 0.26, N = 37265977563191. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 1 - Clients: 50 - Mode: Read Write - Average LatencyGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop306090120150SE +/- 0.31, N = 3SE +/- 0.25, N = 3SE +/- 2.36, N = 15SE +/- 0.13, N = 368.9083.7367.17156.871. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

ASTC Encoder

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

OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.0Preset: FastGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop246810SE +/- 0.01, N = 6SE +/- 0.00, N = 7SE +/- 0.03, N = 6SE +/- 0.01, N = 57.935.537.238.681. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread

OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.0Preset: MediumGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop3691215SE +/- 0.16, N = 15SE +/- 0.00, N = 5SE +/- 0.00, N = 5SE +/- 0.01, N = 49.918.526.2011.141. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread

OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.0Preset: ThoroughGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop20406080100SE +/- 1.07, N = 3SE +/- 0.49, N = 3SE +/- 0.72, N = 3SE +/- 0.01, N = 376.9833.2346.0972.571. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread

OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.0Preset: ExhaustiveGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop140280420560700SE +/- 0.59, N = 3SE +/- 0.82, N = 3SE +/- 0.17, N = 3SE +/- 4.46, N = 3631.69274.49384.66597.501. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread

Hugin

Hugin is an open-source, cross-platform panorama photo stitcher software package. This test profile times how long it takes to run the assistant and panorama photo stitching on a set of images. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterHuginPanorama Photo Assistant + Stitching TimeGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop20406080100SE +/- 0.89, N = 3SE +/- 0.49, N = 3SE +/- 0.35, N = 3SE +/- 0.60, N = 375.7945.8458.5775.99

OCRMyPDF

OCRMyPDF is an optical character recognition (OCR) text layer to scanned PDF files, producing new PDFs with the text now selectable/searchable/copy-paste capable. OCRMyPDF leverages the Tesseract OCR engine and is written in Python. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOCRMyPDF 10.3.1+dfsgProcessing 60 Page PDF DocumentGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop1020304050SE +/- 0.48, N = 6SE +/- 0.07, N = 3SE +/- 0.34, N = 6SE +/- 0.31, N = 339.6121.6928.1942.83

GNU Octave Benchmark

This test profile measures how long it takes to complete several reference GNU Octave files via octave-benchmark. GNU Octave is used for numerical computations and is an open-source alternative to MATLAB. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGNU Octave Benchmark 5.2.0GM-1000CompuLab Airtop3Karbon 700CompuLab Airtop246810SE +/- 0.022, N = 6SE +/- 0.020, N = 6SE +/- 0.027, N = 5SE +/- 0.032, N = 58.0076.4858.5698.601

RawTherapee

RawTherapee is a cross-platform, open-source multi-threaded RAW image processing program. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRawTherapeeTotal Benchmark TimeGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop20406080100SE +/- 1.25, N = 3SE +/- 0.51, N = 3SE +/- 0.32, N = 3SE +/- 0.03, N = 395.4860.8385.4399.221. RawTherapee, version 5.8, command line.

librsvg

RSVG/librsvg is an SVG vector graphics library. This test profile times how long it takes to complete various operations by rsvg-convert. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterlibrsvgOperation: SVG Files To PNGGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop612182430SE +/- 0.42, N = 3SE +/- 0.06, N = 3SE +/- 0.13, N = 3SE +/- 0.26, N = 324.6318.2222.5626.721. rsvg-convert version 2.50.1

Caffe

This is a benchmark of the Caffe deep learning framework and currently supports the AlexNet and Googlenet model and execution on both CPUs and NVIDIA GPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: AlexNet - Acceleration: CPU - Iterations: 100GM-1000CompuLab Airtop3Karbon 700CompuLab Airtop12K24K36K48K60KSE +/- 486.77, N = 7SE +/- 402.90, N = 3SE +/- 777.23, N = 4SE +/- 90.44, N = 3442453930954733575961. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: AlexNet - Acceleration: CPU - Iterations: 200GM-1000CompuLab Airtop3Karbon 700CompuLab Airtop20K40K60K80K100KSE +/- 906.54, N = 3SE +/- 476.82, N = 3SE +/- 595.64, N = 3SE +/- 108.07, N = 389424795821112501153421. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: GoogleNet - Acceleration: CPU - Iterations: 100GM-1000CompuLab Airtop3Karbon 700CompuLab Airtop30K60K90K120K150KSE +/- 87.22, N = 3SE +/- 164.54, N = 3SE +/- 614.60, N = 3SE +/- 192.70, N = 31261401028691463791472111. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: GoogleNet - Acceleration: CPU - Iterations: 200GM-1000CompuLab Airtop3Karbon 700CompuLab Airtop60K120K180K240K300KSE +/- 2728.74, N = 3SE +/- 196.94, N = 3SE +/- 572.20, N = 3SE +/- 117.62, N = 32553192066222942382942761. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

Mobile Neural Network

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

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2020-09-17Model: SqueezeNetV1.0GM-1000CompuLab Airtop3Karbon 700CompuLab Airtop3691215SE +/- 0.024, N = 3SE +/- 0.007, N = 3SE +/- 0.008, N = 3SE +/- 0.028, N = 311.1176.5819.17010.775MIN: 9.82 / MAX: 23.66MIN: 6.13 / MAX: 44.44MIN: 8.87 / MAX: 21.4MIN: 10.62 / MAX: 12.651. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2020-09-17Model: resnet-v2-50GM-1000CompuLab Airtop3Karbon 700CompuLab Airtop1326395265SE +/- 0.24, N = 3SE +/- 0.04, N = 3SE +/- 0.05, N = 3SE +/- 0.06, N = 351.8942.5859.9854.82MIN: 48.29 / MAX: 64.91MIN: 42.1 / MAX: 110.22MIN: 57.88 / MAX: 70.26MIN: 49.62 / MAX: 90.531. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2020-09-17Model: inception-v3GM-1000CompuLab Airtop3Karbon 700CompuLab Airtop1428425670SE +/- 0.28, N = 3SE +/- 0.09, N = 3SE +/- 0.53, N = 3SE +/- 0.36, N = 363.6844.4462.3163.20MIN: 58.94 / MAX: 77.62MIN: 43.87 / MAX: 110.57MIN: 50.28 / MAX: 75.48MIN: 60.21 / MAX: 126.581. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: squeezenetGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop612182430SE +/- 0.12, N = 3SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.05, N = 325.5416.2023.5023.05MIN: 24.15 / MAX: 35.43MIN: 15.74 / MAX: 23.82MIN: 23.31 / MAX: 24.17MIN: 22.62 / MAX: 24.771. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: mobilenetGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop714212835SE +/- 0.17, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 330.3319.0027.5727.06MIN: 28.89 / MAX: 41.86MIN: 18.81 / MAX: 19.51MIN: 27.32 / MAX: 28.23MIN: 26.9 / MAX: 28.181. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU-v2-v2 - Model: mobilenet-v2GM-1000CompuLab Airtop3Karbon 700CompuLab Airtop246810SE +/- 0.22, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 36.615.157.827.03MIN: 5.61 / MAX: 9.69MIN: 5.01 / MAX: 5.7MIN: 7.64 / MAX: 8.38MIN: 6.92 / MAX: 8.491. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: googlenetGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop612182430SE +/- 0.96, N = 3SE +/- 0.32, N = 3SE +/- 0.30, N = 3SE +/- 0.09, N = 323.9915.0022.4020.39MIN: 17.71 / MAX: 26.79MIN: 14.19 / MAX: 15.74MIN: 21.48 / MAX: 24.2MIN: 20.14 / MAX: 21.291. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: vgg16GM-1000CompuLab Airtop3Karbon 700CompuLab Airtop306090120150SE +/- 0.13, N = 3SE +/- 0.08, N = 3SE +/- 0.06, N = 3SE +/- 0.27, N = 383.0766.28118.1281.92MIN: 81.47 / MAX: 93.06MIN: 65.89 / MAX: 74.14MIN: 117.8 / MAX: 125.35MIN: 81.13 / MAX: 85.381. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: resnet18GM-1000CompuLab Airtop3Karbon 700CompuLab Airtop612182430SE +/- 0.04, N = 3SE +/- 0.22, N = 3SE +/- 0.09, N = 3SE +/- 0.05, N = 323.5615.1924.1724.24MIN: 21.32 / MAX: 35.12MIN: 14.53 / MAX: 15.97MIN: 23.62 / MAX: 25MIN: 24 / MAX: 34.651. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: alexnetGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop612182430SE +/- 0.06, N = 3SE +/- 0.08, N = 3SE +/- 0.05, N = 3SE +/- 0.11, N = 322.5314.2323.8723.75MIN: 21.39 / MAX: 32.99MIN: 14 / MAX: 14.66MIN: 23.7 / MAX: 32.05MIN: 23.46 / MAX: 25.421. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: resnet50GM-1000CompuLab Airtop3Karbon 700CompuLab Airtop1122334455SE +/- 0.19, N = 3SE +/- 0.05, N = 3SE +/- 0.06, N = 3SE +/- 0.15, N = 347.3328.5143.4946.60MIN: 44.74 / MAX: 59.62MIN: 27.85 / MAX: 37.31MIN: 41.8 / MAX: 45.89MIN: 46.17 / MAX: 50.281. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: yolov4-tinyGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop1020304050SE +/- 0.16, N = 3SE +/- 0.19, N = 3SE +/- 0.04, N = 3SE +/- 0.15, N = 343.0829.0642.3638.90MIN: 41.28 / MAX: 53.54MIN: 28.14 / MAX: 101.73MIN: 41.91 / MAX: 50.86MIN: 38.21 / MAX: 47.131. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: squeezenetGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop612182430SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.17, N = 3SE +/- 0.02, N = 310.273.6327.5812.35MIN: 9.98 / MAX: 10.78MIN: 3.57 / MAX: 3.76MIN: 27.17 / MAX: 31.88MIN: 11.58 / MAX: 15.041. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: mobilenetGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop612182430SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.29, N = 3SE +/- 0.01, N = 39.314.5926.1910.74MIN: 9 / MAX: 10.28MIN: 4.54 / MAX: 12.63MIN: 23.7 / MAX: 35.85MIN: 9.23 / MAX: 12.041. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2GM-1000CompuLab Airtop3Karbon 700CompuLab Airtop246810SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.07, N = 3SE +/- 0.00, N = 33.001.438.173.18MIN: 2.89 / MAX: 3.84MIN: 1.4 / MAX: 9.39MIN: 7.83 / MAX: 8.44MIN: 3.11 / MAX: 4.261. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3GM-1000CompuLab Airtop3Karbon 700CompuLab Airtop3691215SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.22, N = 3SE +/- 0.00, N = 33.391.6610.193.73MIN: 3.29 / MAX: 4.22MIN: 1.65 / MAX: 1.69MIN: 9.74 / MAX: 10.79MIN: 3.65 / MAX: 4.871. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: shufflenet-v2GM-1000CompuLab Airtop3Karbon 700CompuLab Airtop3691215SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.55, N = 3SE +/- 0.00, N = 32.381.3010.102.59MIN: 2.24 / MAX: 4.75MIN: 1.29 / MAX: 1.36MIN: 7.39 / MAX: 12.25MIN: 2.52 / MAX: 4.111. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: mnasnetGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop3691215SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.69, N = 3SE +/- 0.00, N = 33.101.489.263.32MIN: 3 / MAX: 4.16MIN: 1.46 / MAX: 1.51MIN: 8.48 / MAX: 11.1MIN: 3.26 / MAX: 4.291. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: efficientnet-b0GM-1000CompuLab Airtop3Karbon 700CompuLab Airtop48121620SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.06, N = 3SE +/- 0.01, N = 35.232.6416.475.70MIN: 5.06 / MAX: 5.95MIN: 2.61 / MAX: 2.67MIN: 16.27 / MAX: 16.89MIN: 5.57 / MAX: 6.861. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: blazefaceGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop0.54231.08461.62692.16922.7115SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.31, N = 31.040.612.411.00MIN: 0.94 / MAX: 1.7MIN: 0.6 / MAX: 0.63MIN: 1.77 / MAX: 5.23MIN: 0.99 / MAX: 1.051. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: googlenetGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop612182430SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 37.843.2223.548.48MIN: 7.62 / MAX: 10.98MIN: 3.2 / MAX: 3.32MIN: 23.24 / MAX: 23.83MIN: 8.04 / MAX: 10.851. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: vgg16GM-1000CompuLab Airtop3Karbon 700CompuLab Airtop306090120150SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.07, N = 333.338.31151.4633.74MIN: 32.53 / MAX: 40.22MIN: 150.54 / MAX: 152.37MIN: 33.2 / MAX: 36.351. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: resnet18GM-1000CompuLab Airtop3Karbon 700CompuLab Airtop612182430SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 35.801.6823.856.17MIN: 5.62 / MAX: 13.86MIN: 23.55 / MAX: 24.04MIN: 6.05 / MAX: 7.991. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: alexnetGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop612182430SE +/- 0.08, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 38.172.1125.928.70MIN: 7.83 / MAX: 8.81MIN: 25.54 / MAX: 26.26MIN: 8.52 / MAX: 10.861. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: resnet50GM-1000CompuLab Airtop3Karbon 700CompuLab Airtop1122334455SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 313.223.7550.2214.09MIN: 12.84 / MAX: 29.57MIN: 49.9 / MAX: 50.44MIN: 13.67 / MAX: 16.541. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: yolov4-tinyGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop1530456075SE +/- 0.01, N = 3SE +/- 0.19, N = 3SE +/- 0.28, N = 3SE +/- 0.03, N = 316.288.5065.8720.01MIN: 15.64 / MAX: 17.64MIN: 8.02 / MAX: 9.19MIN: 50.88 / MAX: 68.67MIN: 15.5 / MAX: 21.721. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

TNN

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

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.2.3Target: CPU - Model: MobileNet v2GM-1000CompuLab Airtop3Karbon 700CompuLab Airtop80160240320400SE +/- 0.15, N = 3SE +/- 0.57, N = 3SE +/- 0.91, N = 3SE +/- 0.12, N = 3369.91283.96369.09301.68MIN: 368.82 / MAX: 373.15MIN: 282.43 / MAX: 316.3MIN: 367.26 / MAX: 372.62MIN: 300.63 / MAX: 304.861. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -O3 -rdynamic -ldl

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.2.3Target: CPU - Model: SqueezeNet v1.1GM-1000CompuLab Airtop3Karbon 700CompuLab Airtop80160240320400SE +/- 0.13, N = 3SE +/- 0.04, N = 3SE +/- 0.14, N = 3SE +/- 0.04, N = 3362.13269.28343.22292.59MIN: 361.7 / MAX: 362.7MIN: 268.32 / MAX: 274.07MIN: 342.72 / MAX: 356.39MIN: 291.2 / MAX: 293.741. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -O3 -rdynamic -ldl

Apache Cassandra

This is a benchmark of the Apache Cassandra NoSQL database management system making use of cassandra-stress. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOp/s, More Is BetterApache Cassandra 3.11.4Test: WritesGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop15K30K45K60K75KSE +/- 177.03, N = 15SE +/- 744.79, N = 3SE +/- 581.94, N = 6SE +/- 299.90, N = 420732678205012420104

Facebook RocksDB

This is a benchmark of Facebook's RocksDB as an embeddable persistent key-value store for fast storage based on Google's LevelDB. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.3.6Test: Random FillGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop200K400K600K800K1000KSE +/- 7757.34, N = 5SE +/- 7973.52, N = 3SE +/- 11711.73, N = 15SE +/- 673.55, N = 36347398717385263584644591. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread

OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.3.6Test: Random ReadGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop9M18M27M36M45MSE +/- 338773.40, N = 4SE +/- 49809.36, N = 3SE +/- 368380.75, N = 3SE +/- 86603.84, N = 3246163314346559631537972186250431. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread

OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.3.6Test: Sequential FillGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop300K600K900K1200K1500KSE +/- 13114.25, N = 15SE +/- 12373.00, N = 15SE +/- 13395.98, N = 5SE +/- 2320.66, N = 4981091132156610335415573021. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread

OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.3.6Test: Random Fill SyncGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop2K4K6K8K10KSE +/- 40.71, N = 15SE +/- 4.06, N = 3SE +/- 68.24, N = 3SE +/- 4.93, N = 33473234491756241. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread

OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.3.6Test: Read While WritingGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop400K800K1200K1600K2000KSE +/- 8029.23, N = 8SE +/- 19030.80, N = 9SE +/- 15797.71, N = 3SE +/- 1361.04, N = 3808736192337315224598640661. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread

PyPerformance

PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: goGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop60120180240300SE +/- 1.67, N = 3270200255279

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: 2to3GM-1000CompuLab Airtop3Karbon 700CompuLab Airtop80160240320400SE +/- 0.67, N = 3352264332375

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: chaosGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop306090120150SE +/- 1.00, N = 3SE +/- 0.06, N = 3117.085.9109.0121.0

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: floatGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop306090120150SE +/- 0.06, N = 3SE +/- 0.33, N = 3122.089.9114.0136.0

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: nbodyGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop306090120150SE +/- 0.33, N = 3138103131140

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: pathlibGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop612182430SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.06, N = 3SE +/- 0.09, N = 319.314.318.223.0

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: raytraceGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop120240360480600SE +/- 0.67, N = 3SE +/- 0.88, N = 3505376479538

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: json_loadsGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop714212835SE +/- 0.03, N = 3SE +/- 0.19, N = 3SE +/- 0.00, N = 3SE +/- 0.17, N = 328.421.427.128.0

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: crypto_pyaesGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop306090120150SE +/- 0.33, N = 3SE +/- 0.03, N = 3116.085.9109.0125.0

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: regex_compileGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop4080120160200SE +/- 0.58, N = 3186138178196

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: python_startupGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop3691215SE +/- 0.06, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 39.016.828.5210.20

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: django_templateGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop1224364860SE +/- 0.15, N = 3SE +/- 0.06, N = 3SE +/- 0.15, N = 3SE +/- 0.00, N = 352.338.949.355.2

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: pickle_pure_pythonGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop110220330440550SE +/- 2.73, N = 3462339434489

Numenta Anomaly Benchmark

Numenta Anomaly Benchmark (NAB) is a benchmark for evaluating algorithms for anomaly detection in streaming, real-time applications. It is comprised of over 50 labeled real-world and artificial timeseries data files plus a novel scoring mechanism designed for real-time applications. This test profile currently measures the time to run various detectors. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Relative EntropyGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop1224364860SE +/- 0.44, N = 12SE +/- 0.19, N = 15SE +/- 0.27, N = 15SE +/- 0.69, N = 449.5022.2229.8751.01

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Windowed GaussianGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop612182430SE +/- 0.28, N = 14SE +/- 0.15, N = 5SE +/- 0.20, N = 15SE +/- 0.39, N = 426.1212.4516.8127.59

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Earthgecko SkylineGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop70140210280350SE +/- 4.34, N = 3SE +/- 2.03, N = 3SE +/- 1.51, N = 3SE +/- 1.98, N = 3300.54132.85192.62282.80

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Bayesian ChangepointGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop20406080100SE +/- 1.25, N = 3SE +/- 0.49, N = 15SE +/- 0.22, N = 3SE +/- 0.85, N = 397.1443.0871.5682.88

Hierarchical INTegration

This test runs the U.S. Department of Energy's Ames Laboratory Hierarchical INTegration (HINT) benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgQUIPs, More Is BetterHierarchical INTegration 1.0Test: FLOATGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop100M200M300M400M500MSE +/- 534147.70, N = 3SE +/- 825158.10, N = 3SE +/- 666152.61, N = 3SE +/- 478845.36, N = 3360309999.32471438878.81371786567.43370080894.801. (CC) gcc options: -O3 -march=native -lm

AI Benchmark Alpha

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

OpenBenchmarking.orgScore, More Is BetterAI Benchmark Alpha 0.1.2Device Inference ScoreGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop20040060080010006401128745615

OpenBenchmarking.orgScore, More Is BetterAI Benchmark Alpha 0.1.2Device Training ScoreGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop20040060080010007321108685736

OpenBenchmarking.orgScore, More Is BetterAI Benchmark Alpha 0.1.2Device AI ScoreGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop50010001500200025001372223614301351

Git

This test measures the time needed to carry out some sample Git operations on an example, static repository that happens to be a copy of the GNOME GTK tool-kit repository. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGitTime To Complete Common Git CommandsGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop1428425670SE +/- 0.41, N = 3SE +/- 0.08, N = 3SE +/- 0.16, N = 3SE +/- 0.17, N = 360.3744.9756.4559.831. git version 2.27.0

Mlpack Benchmark

Mlpack benchmark scripts for machine learning libraries Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_icaGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop1428425670SE +/- 1.11, N = 3SE +/- 0.52, N = 3SE +/- 0.73, N = 3SE +/- 0.09, N = 364.7242.1460.8160.10

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_qdaGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop306090120150SE +/- 0.01, N = 3SE +/- 0.23, N = 3SE +/- 10.16, N = 12SE +/- 1.20, N = 1287.8162.68130.5376.46

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_svmGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop714212835SE +/- 0.20, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 328.9322.4327.2521.42

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_linearridgeregressionGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop1.00582.01163.01744.02325.029SE +/- 0.03, N = 15SE +/- 0.03, N = 15SE +/- 0.06, N = 15SE +/- 0.01, N = 33.142.473.944.47

Tesseract OCR

Tesseract-OCR is the open-source optical character recognition (OCR) engine for the conversion of text within images to raw text output. This test profile relies upon a system-supplied Tesseract installation. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTesseract OCR 4.1.1Time To OCR 7 ImagesGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop714212835SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.06, N = 327.1120.2725.6527.89

Kripke

Kripke is a simple, scalable, 3D Sn deterministic particle transport code. Its primary purpose is to research how data layout, programming paradigms and architectures effect the implementation and performance of Sn transport. Kripke is developed by LLNL. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgThroughput FoM, More Is BetterKripke 1.2.4GM-1000CompuLab Airtop3Karbon 700CompuLab Airtop5M10M15M20M25MSE +/- 42312.00, N = 3SE +/- 86477.80, N = 3SE +/- 187229.46, N = 9SE +/- 47162.72, N = 42088958321264093574190437166941. (CXX) g++ options: -O3 -fopenmp

BRL-CAD

BRL-CAD 7.28.0 is a cross-platform, open-source solid modeling system with built-in benchmark mode. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgVGR Performance Metric, More Is BetterBRL-CAD 7.30.8VGR Performance MetricGM-1000CompuLab Airtop3CompuLab Airtop20K40K60K80K100K43138100566448691. (CXX) g++ options: -std=c++11 -pipe -fno-strict-aliasing -fno-common -fexceptions -ftemplate-depth-128 -m64 -ggdb3 -O3 -fipa-pta -fstrength-reduce -finline-functions -flto -pedantic -rdynamic -lSM -lICE -lGLU -lGL -lGLdispatch -lX11 -lXext -lpthread -ldl -luuid -lm

CPU Temperature Monitor

OpenBenchmarking.orgCelsiusCPU Temperature MonitorPhoronix Test Suite System MonitoringGM-1000CompuLab Airtop3Karbon 700CompuLab Airtop20406080100Min: 49 / Avg: 67.98 / Max: 82Min: 34 / Avg: 70.36 / Max: 100Min: 38 / Avg: 60.6 / Max: 87Min: 40 / Avg: 70.91 / Max: 96

System Temperature Monitor

OpenBenchmarking.orgCelsiusSystem Temperature MonitorPhoronix Test Suite System MonitoringGM-10001530456075Min: 54 / Avg: 71.36 / Max: 76

195 Results Shown

IOR:
  Write Test
  Read Test
PostMark
RealSR-NCNN:
  4x - No
  4x - Yes
Waifu2x-NCNN Vulkan:
  2x - 3 - No
  2x - 3 - Yes
GLmark2
WireGuard + Linux Networking Stack Stress Test
C-Blosc
High Performance Conjugate Gradient
LeelaChessZero:
  BLAS
  Eigen
NAMD
Dolfyn
FFTE
Timed HMMer Search
Incompact3D
Timed MAFFT Alignment
Monte Carlo Simulations of Ionised Nebulae
LAMMPS Molecular Dynamics Simulator
WebP Image Encode:
  Default
  Quality 100
  Quality 100, Lossless
  Quality 100, Highest Compression
  Quality 100, Lossless, Highest Compression
Java Gradle Build
DaCapo Benchmark:
  H2
  Jython
  Tradesoap
  Tradebeans
BYTE Unix Benchmark
Zstd Compression:
  3
  19
LibRaw
John The Ripper:
  Blowfish
  MD5
oneDNN:
  IP Batch 1D - f32 - CPU
  IP Batch All - f32 - CPU
  IP Batch 1D - u8s8f32 - CPU
  IP Batch All - u8s8f32 - CPU
  Convolution Batch Shapes Auto - f32 - CPU
  Deconvolution Batch deconv_1d - f32 - CPU
  Deconvolution Batch deconv_3d - f32 - CPU
  Convolution Batch Shapes Auto - u8s8f32 - CPU
  Deconvolution Batch deconv_1d - u8s8f32 - CPU
  Deconvolution Batch deconv_3d - u8s8f32 - CPU
  Recurrent Neural Network Training - f32 - CPU
  Recurrent Neural Network Inference - f32 - CPU
  Matrix Multiply Batch Shapes Transformer - f32 - CPU
  Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPU
dav1d:
  Chimera 1080p
  Summer Nature 4K
  Summer Nature 1080p
  Chimera 1080p 10-bit
Kvazaar:
  Bosphorus 4K - Medium
  Bosphorus 1080p - Medium
  Bosphorus 4K - Very Fast
  Bosphorus 4K - Ultra Fast
  Bosphorus 1080p - Very Fast
  Bosphorus 1080p - Ultra Fast
SVT-AV1:
  Enc Mode 0 - 1080p
  Enc Mode 4 - 1080p
SVT-VP9:
  PSNR/SSIM Optimized - Bosphorus 1080p
  Visual Quality Optimized - Bosphorus 1080p
VP9 libvpx Encoding:
  Speed 0
  Speed 5
x265:
  Bosphorus 4K
  Bosphorus 1080p
Intel Open Image Denoise
OpenVKL
LuxCoreRender:
  DLSC
  Rainbow Colors and Prism
7-Zip Compression
libavif avifenc:
  0
  2
  8
  10
Timed Apache Compilation
Timed GDB GNU Debugger Compilation
Timed Linux Kernel Compilation
Timed LLVM Compilation
Timed PHP Compilation
YafaRay
rays1bench
Numpy Benchmark
eSpeak-NG Speech Engine
RNNoise
OpenSSL
LevelDB:
  Hot Read
  Fill Sync
  Fill Sync
  Overwrite
  Overwrite
  Rand Fill
  Rand Fill
  Rand Read
  Seek Rand
  Rand Delete
  Seq Fill
  Seq Fill
KeyDB
GROMACS
TensorFlow Lite:
  SqueezeNet
  Inception V4
  NASNet Mobile
  Mobilenet Float
  Mobilenet Quant
  Inception ResNet V2
PostgreSQL pgbench:
  1 - 1 - Read Only
  1 - 1 - Read Only - Average Latency
  1 - 1 - Read Write
  1 - 1 - Read Write - Average Latency
  1 - 50 - Read Only
  1 - 50 - Read Only - Average Latency
  1 - 50 - Read Write
  1 - 50 - Read Write - Average Latency
ASTC Encoder:
  Fast
  Medium
  Thorough
  Exhaustive
Hugin
OCRMyPDF
GNU Octave Benchmark
RawTherapee
librsvg
Caffe:
  AlexNet - CPU - 100
  AlexNet - CPU - 200
  GoogleNet - CPU - 100
  GoogleNet - CPU - 200
Mobile Neural Network:
  SqueezeNetV1.0
  resnet-v2-50
  inception-v3
NCNN:
  CPU - squeezenet
  CPU - mobilenet
  CPU-v2-v2 - mobilenet-v2
  CPU - googlenet
  CPU - vgg16
  CPU - resnet18
  CPU - alexnet
  CPU - resnet50
  CPU - yolov4-tiny
  Vulkan GPU - squeezenet
  Vulkan GPU - mobilenet
  Vulkan GPU-v2-v2 - mobilenet-v2
  Vulkan GPU-v3-v3 - mobilenet-v3
  Vulkan GPU - shufflenet-v2
  Vulkan GPU - mnasnet
  Vulkan GPU - efficientnet-b0
  Vulkan GPU - blazeface
  Vulkan GPU - googlenet
  Vulkan GPU - vgg16
  Vulkan GPU - resnet18
  Vulkan GPU - alexnet
  Vulkan GPU - resnet50
  Vulkan GPU - yolov4-tiny
TNN:
  CPU - MobileNet v2
  CPU - SqueezeNet v1.1
Apache Cassandra
Facebook RocksDB:
  Rand Fill
  Rand Read
  Seq Fill
  Rand Fill Sync
  Read While Writing
PyPerformance:
  go
  2to3
  chaos
  float
  nbody
  pathlib
  raytrace
  json_loads
  crypto_pyaes
  regex_compile
  python_startup
  django_template
  pickle_pure_python
Numenta Anomaly Benchmark:
  Relative Entropy
  Windowed Gaussian
  Earthgecko Skyline
  Bayesian Changepoint
Hierarchical INTegration
AI Benchmark Alpha:
  Device Inference Score
  Device Training Score
  Device AI Score
Git
Mlpack Benchmark:
  scikit_ica
  scikit_qda
  scikit_svm
  scikit_linearridgeregression
Tesseract OCR
Kripke
BRL-CAD
CPU Temperature Monitor:
  Phoronix Test Suite System Monitoring:
    Celsius
    Celsius