GM-1000

Intel Xeon E-2288G testing with a Compulab SBC-ATCFL v1.2 (ATOP3.PRD.0.29.2 BIOS) and NVIDIA Quadro RTX 4000 8GB on Ubuntu 20.10 via the Phoronix Test Suite.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2010308-FI-2010295FI67
Jump To Table - Results

View

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

Limit displaying results to tests within:

AV1 3 Tests
Bioinformatics 2 Tests
BLAS (Basic Linear Algebra Sub-Routine) Tests 2 Tests
C++ Boost Tests 2 Tests
Timed Code Compilation 5 Tests
C/C++ Compiler Tests 21 Tests
Compression Tests 3 Tests
CPU Massive 30 Tests
Creator Workloads 24 Tests
Cryptography 2 Tests
Database Test Suite 5 Tests
Encoding 7 Tests
Fortran Tests 6 Tests
Game Development 3 Tests
HPC - High Performance Computing 24 Tests
Imaging 6 Tests
Java 2 Tests
Common Kernel Benchmarks 6 Tests
Machine Learning 12 Tests
Molecular Dynamics 5 Tests
MPI Benchmarks 5 Tests
Multi-Core 27 Tests
NVIDIA GPU Compute 7 Tests
OCR 2 Tests
Intel oneAPI 3 Tests
OpenCV Tests 2 Tests
OpenMPI Tests 5 Tests
Productivity 2 Tests
Programmer / Developer System Benchmarks 9 Tests
Python 4 Tests
Raytracing 2 Tests
Renderers 3 Tests
Scientific Computing 11 Tests
Server 6 Tests
Server CPU Tests 17 Tests
Single-Threaded 6 Tests
Speech 2 Tests
Telephony 2 Tests
Video Encoding 7 Tests
Vulkan Compute 3 Tests
Common Workstation Benchmarks 3 Tests

Statistics

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

Graph Settings

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

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
Hide
Result
Result
Identifier
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
GM-1000
October 28 2020
  18 Hours, 39 Minutes
CompuLab Airtop3
October 29 2020
  12 Hours, 59 Minutes
Invert Hiding All Results Option
  15 Hours, 49 Minutes
Only show results matching title/arguments (delimit multiple options with a comma):
Do not show results matching title/arguments (delimit multiple options with a comma):

GM-1000

Processor: Intel Core i7-9700TE @ 3.80GHz (8 Cores), Motherboard: C OZE GM-1000 v0.0.01.001 (5.13 BIOS), Chipset: Intel Cannon Lake PCH, Memory: 32GB, Disk: CIE M8 T405 512GB, Graphics: NVIDIA Quadro P2000 4GB (1455/3003MHz), Audio: Realtek ALC888-VD, Monitor: DELL S2409W, Network: Intel I219-LM + 2 x Intel 10G X550T + Intel I210

OS: Ubuntu 20.10, Kernel: 5.8.0-25-generic (x86_64), Desktop: GNOME Shell 3.38.1, Display Server: X Server 1.20.9, Display Driver: NVIDIA 455.28, OpenGL: 4.6.0, OpenCL: OpenCL 1.2 CUDA 11.1.96, Vulkan: 1.2.142, Compiler: GCC 10.2.0, File-System: ext4, Screen Resolution: 1920x1080

Compiler Notes: --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 Notes: NONE / errors=remount-ro,relatime,rw
Processor Notes: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xd6 - Thermald 2.3
OpenCL Notes: GPU Compute Cores: 768
Java Notes: OpenJDK Runtime Environment (build 11.0.9+10-post-Ubuntu-0ubuntu1)
Python Notes: Python 3.8.6
Security Notes: 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

Processor: Intel Xeon E-2288G @ 5.00GHz (8 Cores / 16 Threads), Motherboard: Compulab SBC-ATCFL v1.2 (ATOP3.PRD.0.29.2 BIOS), Chipset: Intel Cannon Lake PCH, Memory: 64GB, Disk: Samsung SSD 970 EVO Plus 250GB, Graphics: NVIDIA Quadro RTX 4000 8GB (1005/6500MHz), Audio: Intel Cannon Lake PCH cAVS, Monitor: VE228, Network: Intel I219-LM + Intel I210

OS: Ubuntu 20.10, Kernel: 5.8.0-26-generic (x86_64), Desktop: GNOME Shell 3.38.1, Display Server: X Server 1.20.9, Display Driver: NVIDIA 455.28, OpenGL: 4.6.0, OpenCL: OpenCL 1.2 CUDA 11.1.96, Vulkan: 1.2.142, Compiler: GCC 10.2.0, File-System: ext4, Screen Resolution: 1920x1080

Compiler Notes: --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 Notes: NONE / errors=remount-ro,relatime,rw
Processor Notes: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xd6 - Thermald 2.3
OpenCL Notes: GPU Compute Cores: 2304
Java Notes: OpenJDK Runtime Environment (build 11.0.9+11-Ubuntu-0ubuntu1)
Python Notes: Python 3.8.6
Security Notes: 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

GM-1000ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLOpenCLVulkanCompilerFile-SystemScreen ResolutionGM-1000CompuLab Airtop3Intel 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)OpenBenchmarking.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- NONE / errors=remount-ro,relatime,rwProcessor Details- Scaling Governor: intel_pstate powersave - CPU Microcode: 0xd6 - Thermald 2.3OpenCL Details- GM-1000: GPU Compute Cores: 768- CompuLab Airtop3: GPU Compute Cores: 2304Java 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)Python Details- Python 3.8.6Security Details- 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

GM-1000 vs. CompuLab Airtop3 ComparisonPhoronix Test SuiteBaseline+86025%+86025%+172050%+172050%+258075%+258075%301.1%287.2%252.5%245.2%239.3%227.1%201.2%200%182.9%156.1%144.2%143.5%137.8%133.6%133.1%131.7%131%130.9%130.8%130.1%127.2%126.2%125.5%122.8%120.9%115.9%114.4%114.2%114.1%114%113.2%112%111.1%110.9%110.4%109.8%109.7%109.5%108.4%107.8%105.8%104.2%104%103.5%103.5%102.8%102.2%102.1%100.6%99.5%98.1%94.1%91.6%91.5%89.3%86.7%86.4%84.7%84.4%83.1%82.6%81.9%81.2%81.1%80.9%79.4%78.6%77.5%76.6%76.6%76.5%76.3%74.8%70.5%70.3%70.2%69.7%69.3%69.2%68.9%68.8%68.3%66%65.3%64.7%63.9%63%62.5%61.6%60.9%60.8%60.7%59.9%59.6%58.3%57.7%57.6%57%56.9%56.8%55.1%53.7%53.6%53.6%53%52.7%51.4%50.4%48.2%45.6%43.4%43.3%40.8%40.8%40.1%39.3%38.4%37.3%36.3%36.2%35.7%35.2%35%35%35%35%35%34.8%34.8%34.7%34.5%34.4%34.4%34.3%34.3%34.3%34%34%33.7%33.5%33.5%33.3%33.3%32.8%32.7%32.3%32.1%31.2%31%31%30.8%30.8%30.6%30.5%30.3%29.7%29%28.3%27.1%26.7%25.3%24%23.6%23.5%22.6%22.3%21.9%20.9%16.3%14%12.6%12.4%10.6%10.3%10.3%7.1%Vulkan GPU - vgg161920 x 1080344100%Vulkan GPU - alexnetVulkan GPU - resnet50Vulkan GPU - resnet184x - YesWrites2x - 3 - Yes4x - NoFill Sync186.4%Vulkan GPU - squeezenetIP Batch 1D - u8s8f32 - CPUIP Batch All - u8s8f32 - CPUVulkan GPU - googlenetRead While WritingLarge SceneV.P.MThorough1 - 50 - Read OnlyM.M.B.S.T - u8s8f32 - CPU1 - 50 - Read Only - Average LatencyExhaustiveD.B.d - u8s8f32 - CPUEarthgecko SkylineB.CRelative EntropyRead TestTime To CompileBosphorus 4K - Very FastD.B.d - f32 - CPUBosphorus 4K - MediumBosphorus 4K - Ultra FastATPase Simulation - 327,506 AtomsIP Batch 1D - f32 - CPUBosphorus 1080p - MediumT.T.F.S.SDLSCVulkan GPU-v2-v2 - mobilenet-v2Windowed GaussianVulkan GPU - mnasnetTime To CompileR.N.N.T - f32 - CPUBosphorus 1080p - Ultra FastVulkan GPU-v3-v3 - mobilenet-v3R.C.a.PEnc Mode 4 - 1080pMemorialVulkan GPU - mobilenetC.S.TD.B.d - u8s8f32 - CPUBosphorus 1080p - Very FastBlowfishVulkan GPU - efficientnet-b0MD5Vulkan GPU - yolov4-tinyBosphorus 4KCylinder2I.R.VInception V4Vulkan GPU - shufflenet-v2P.6.P.P.DWrite Test82.3%Chimera 1080pMobilenet FloatEnc Mode 0 - 1080pTradesoapSqueezeNetMobilenet QuantTime To CompileRand ReadvklBenchmarkCPU - mnasnetD.I.SBosphorus 1080pVulkan GPU - blazefaceDust 2D tau100.0R.4.b.PTime To CompileSummer Nature 4KS.N.1SqueezeNetV1.0IP Batch All - f32 - CPUCPU - resnet50P.P.A.S.TV.Q.O - Bosphorus 1080pDevice AI ScoreSeq FillCPU - shufflenet-v2Rand Read61.4%NASNet MobileR.N.N.I - f32 - CPUCPU-v3-v3 - mobilenet-v3CPU - googlenetCPU - mobilenetCPU - alexnetCPU - squeezenetRand FillT.B.TP.S.O - Bosphorus 1080pOverwriteCPU - resnet18Water BenchmarkTime To Compilescikit_icaCPU - efficientnet-b0Speed 0D.T.SSeek Rand50.8%C.1.1.bCPU - yolov4-tinyRand Fill Sync48.2%Speed 5Fastinception-v3Hot Read40.8%CPU - blazefaceT.T.S.Sscikit_qdaRhodopsin ProteinReactorRand Fillpickle_pure_pythonchaosfloatSVG Files To PNGcrypto_pyaesQ.1.L.H.Cgopathlib1 - 1 - Read Onlyregex_compileSeq FillCPU - SqueezeNet v1.1django_templateQ.1.H.CraytraceDhrystone 2T.T.C.C.G.CnbodyDefaultT.T.O.7.IQuality 100D.B.d - f32 - CPU2to31 - 1 - Read Only - Average LatencyFill Sync33.3%C.F.Djson_loadsQ.1.Lpython_startup8JythonP.D.SFLOAT10M.S.A - LSU RNACPU - MobileNet v2Tradebeansscikit_svmRand Delete28.8%CPU-v2-v2 - mobilenet-v2Overwrite27.7%Rand Fill27.1%scikit_linearridgeregressionD.T.PCPU - vgg16MobileNetV2_224GoogleNet - CPU - 200Seq Fill23.3%GoogleNet - CPU - 100P.P.B321.9%resnet-v2-501 - 50 - Read Write21.6%1 - 50 - Read Write - Average Latency21.5%blosclz1 - 1 - Read Write - Average Latency19.3%Medium1 - 1 - Read Write15.9%H2AlexNet - CPU - 100AlexNet - CPU - 200M.M.B.S.T - f32 - CPU19BLASC.B.S.A - u8s8f32 - CPU2.5%C.B.S.A - f32 - CPU2.4%NCNNGLmark2NCNNNCNNNCNNRealSR-NCNNApache CassandraWaifu2x-NCNN VulkanRealSR-NCNNLevelDBNCNNoneDNNoneDNNNCNNFacebook RocksDBrays1benchBRL-CADASTC EncoderPostgreSQL pgbenchoneDNNPostgreSQL pgbenchASTC EncoderoneDNNNumenta Anomaly BenchmarkNumenta Anomaly BenchmarkNumenta Anomaly BenchmarkIORTimed Linux Kernel CompilationKvazaaroneDNNKvazaarKvazaarNAMDoneDNNKvazaarYafaRayLuxCoreRenderNCNNNumenta Anomaly BenchmarkNCNNTimed LLVM CompilationoneDNNKvazaarNCNNLuxCoreRenderSVT-AV1Intel Open Image DenoiseNCNN7-Zip CompressiononeDNNKvazaarJohn The RipperNCNNJohn The Ripperlibavif avifencNCNNx265Incompact3Dlibavif avifencTensorFlow LiteTensorFlow LiteNCNNOCRMyPDFIORdav1dTensorFlow LiteSVT-AV1DaCapo BenchmarkTensorFlow LiteTensorFlow LiteTimed PHP CompilationFacebook RocksDBOpenVKLNCNNAI Benchmark Alphax265NCNNMonte Carlo Simulations of Ionised NebulaeOpenSSLTimed GDB GNU Debugger Compilationdav1ddav1dMobile Neural NetworkoneDNNWireGuard + Linux Networking Stack Stress TestNCNNHuginSVT-VP9KeyDBAI Benchmark AlphaLevelDBNCNNLevelDBTensorFlow LiteoneDNNNCNNNCNNNCNNNCNNNCNNLevelDBRawTherapeeSVT-VP9LevelDBNCNNGROMACSTimed Apache CompilationMlpack BenchmarkNCNNVP9 libvpx EncodingAI Benchmark AlphaLevelDBdav1dNCNNFacebook RocksDBVP9 libvpx EncodingASTC EncoderMobile Neural NetworkLevelDBNCNNeSpeak-NG Speech EngineMlpack BenchmarkLAMMPS Molecular Dynamics SimulatorJava Gradle BuildFacebook RocksDBPyPerformancePyPerformancePyPerformancelibrsvgPyPerformanceWebP Image EncodePyPerformancePyPerformancePostgreSQL pgbenchRNNoisePyPerformanceFacebook RocksDBTNNPyPerformanceWebP Image EncodePyPerformanceBYTE Unix BenchmarkGitPyPerformanceWebP Image EncodeTesseract OCRWebP Image EncodeoneDNNPyPerformancePostgreSQL pgbenchLevelDBDolfynPyPerformanceWebP Image EncodePyPerformancelibavif avifencDaCapo BenchmarkTimed HMMer SearchHierarchical INTegrationlibavif avifencTimed MAFFT AlignmentNumpy BenchmarkTNNDaCapo BenchmarkMlpack BenchmarkLevelDBNCNNLevelDBLevelDBMlpack BenchmarkPostMarkNCNNMobile Neural NetworkCaffeGNU Octave BenchmarkLevelDBCaffeLibRawZstd CompressionMobile Neural NetworkPostgreSQL pgbenchPostgreSQL pgbenchC-BloscPostgreSQL pgbenchASTC EncoderPostgreSQL pgbenchDaCapo BenchmarkCaffeCaffeoneDNNZstd CompressionHigh Performance Conjugate GradientLeelaChessZerooneDNNoneDNNGM-1000CompuLab Airtop3

GM-1000ncnn: Vulkan GPU - vgg16glmark2: 1920 x 1080ncnn: Vulkan GPU - alexnetncnn: Vulkan GPU - resnet50ncnn: Vulkan GPU - resnet18realsr-ncnn: 4x - Yescassandra: Writeswaifu2x-ncnn: 2x - 3 - Yesrealsr-ncnn: 4x - Noleveldb: Fill Syncncnn: Vulkan GPU - squeezenetonednn: IP Batch All - u8s8f32 - CPUncnn: Vulkan GPU - googlenetrocksdb: Read While Writingrays1bench: Large Scenebrl-cad: VGR Performance Metricastcenc: Thoroughpgbench: 1 - 50 - Read Onlyonednn: Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPUpgbench: 1 - 50 - Read Only - Average Latencyastcenc: Exhaustiveonednn: Deconvolution Batch deconv_1d - u8s8f32 - CPUnumenta-nab: Earthgecko Skylinenumenta-nab: Bayesian Changepointnumenta-nab: Relative Entropyior: Read Testbuild-linux-kernel: Time To Compilekvazaar: Bosphorus 4K - Very Fastonednn: Deconvolution Batch deconv_1d - f32 - CPUkvazaar: Bosphorus 4K - Mediumkvazaar: Bosphorus 4K - Ultra Fastnamd: ATPase Simulation - 327,506 Atomskvazaar: Bosphorus 1080p - Mediumyafaray: Total Time For Sample Sceneluxcorerender: DLSCncnn: Vulkan GPU-v2-v2 - mobilenet-v2numenta-nab: Windowed Gaussianncnn: Vulkan GPU - mnasnetbuild-llvm: Time To Compileonednn: Recurrent Neural Network Training - f32 - CPUncnn: Vulkan GPU-v3-v3 - mobilenet-v3luxcorerender: Rainbow Colors and Prismsvt-av1: Enc Mode 4 - 1080poidn: Memorialncnn: Vulkan GPU - mobilenetcompress-7zip: Compress Speed Testonednn: Deconvolution Batch deconv_3d - u8s8f32 - CPUkvazaar: Bosphorus 1080p - Very Fastjohn-the-ripper: Blowfishncnn: Vulkan GPU - efficientnet-b0john-the-ripper: MD5avifenc: 0ncnn: Vulkan GPU - yolov4-tinyx265: Bosphorus 4Kincompact3d: Cylinderavifenc: 2tensorflow-lite: Inception ResNet V2tensorflow-lite: Inception V4ncnn: Vulkan GPU - shufflenet-v2ocrmypdf: Processing 60 Page PDF Documentdav1d: Chimera 1080ptensorflow-lite: Mobilenet Floatsvt-av1: Enc Mode 0 - 1080pdacapobench: Tradesoaptensorflow-lite: SqueezeNettensorflow-lite: Mobilenet Quantbuild-php: Time To Compilerocksdb: Rand Readopenvkl: vklBenchmarkai-benchmark: Device Inference Scorex265: Bosphorus 1080pncnn: Vulkan GPU - blazefacemocassin: Dust 2D tau100.0build-gdb: Time To Compiledav1d: Summer Nature 4Kdav1d: Summer Nature 1080pmnn: SqueezeNetV1.0onednn: IP Batch All - f32 - CPUwireguard: ncnn: CPU - resnet50hugin: Panorama Photo Assistant + Stitching Timekeydb: ai-benchmark: Device AI Scoreleveldb: Seq Fillleveldb: Rand Readtensorflow-lite: NASNet Mobileonednn: Recurrent Neural Network Inference - f32 - CPUncnn: CPU - mobilenetncnn: CPU - alexnetncnn: CPU - squeezenetleveldb: Rand Fillrawtherapee: Total Benchmark Timeleveldb: Overwritencnn: CPU - resnet18gromacs: Water Benchmarkbuild-apache: Time To Compilemlpack: scikit_icavpxenc: Speed 0ai-benchmark: Device Training Scoredav1d: Chimera 1080p 10-bitncnn: CPU - yolov4-tinyrocksdb: Rand Fill Syncvpxenc: Speed 5astcenc: Fastmnn: inception-v3leveldb: Hot Readespeak: Text-To-Speech Synthesismlpack: scikit_qdalammps: Rhodopsin Proteinjava-gradle-perf: Reactorrocksdb: Rand Fillpyperformance: pickle_pure_pythonpyperformance: chaospyperformance: floatrsvg: SVG Files To PNGpyperformance: crypto_pyaeswebp: Quality 100, Lossless, Highest Compressionpyperformance: gopyperformance: pathlibpgbench: 1 - 1 - Read Onlyrnnoise: pyperformance: regex_compilerocksdb: Seq Filltnn: CPU - SqueezeNet v1.1pyperformance: django_templatewebp: Quality 100, Highest Compressionpyperformance: raytracebyte: Dhrystone 2git: Time To Complete Common Git Commandspyperformance: nbodywebp: Defaulttesseract-ocr: Time To OCR 7 Imageswebp: Quality 100onednn: Deconvolution Batch deconv_3d - f32 - CPUpyperformance: 2to3pgbench: 1 - 1 - Read Only - Average Latencyleveldb: Fill Syncdolfyn: Computational Fluid Dynamicspyperformance: json_loadswebp: Quality 100, Losslesspyperformance: python_startupavifenc: 8dacapobench: Jythonhmmer: Pfam Database Searchhint: FLOATavifenc: 10mafft: Multiple Sequence Alignment - LSU RNAnumpy: tnn: CPU - MobileNet v2mlpack: scikit_svmleveldb: Rand Deletencnn: CPU-v2-v2 - mobilenet-v2leveldb: Overwriteleveldb: Rand Fillmlpack: scikit_linearridgeregressionpostmark: Disk Transaction Performancencnn: CPU - vgg16caffe: GoogleNet - CPU - 200octave-benchmark: leveldb: Seq Fillcaffe: GoogleNet - CPU - 100libraw: Post-Processing Benchmarkcompress-zstd: 3mnn: resnet-v2-50pgbench: 1 - 50 - Read Writepgbench: 1 - 50 - Read Write - Average Latencyblosc: blosclzdacapobench: H2caffe: AlexNet - CPU - 100caffe: AlexNet - CPU - 200onednn: Matrix Multiply Batch Shapes Transformer - f32 - CPUcompress-zstd: 19hpcg: lczero: BLASonednn: Convolution Batch Shapes Auto - u8s8f32 - CPUonednn: Convolution Batch Shapes Auto - f32 - CPUkripke: lczero: Eigenffte: N=256, 3D Complex FFT Routinewaifu2x-ncnn: 2x - 3 - Noncnn: CPU - googlenetncnn: CPU - blazefacencnn: CPU - efficientnet-b0ncnn: CPU - mnasnetncnn: CPU - shufflenet-v2ncnn: CPU-v3-v3 - mobilenet-v3mnn: mobilenet-v1-1.0mnn: MobileNetV2_224astcenc: Mediumpgbench: 1 - 1 - Read Write - Average Latencypgbench: 1 - 1 - Read Writeleveldb: Seek Randopenssl: RSA 4096-bit Performancesvt-vp9: Visual Quality Optimized - Bosphorus 1080psvt-vp9: PSNR/SSIM Optimized - Bosphorus 1080pkvazaar: Bosphorus 1080p - Ultra Fastonednn: IP Batch 1D - u8s8f32 - CPUonednn: IP Batch 1D - f32 - CPUdacapobench: Tradebeansior: Write TestGM-1000CompuLab Airtop333.3334428.1713.225.80276.6242073216.86837.8752260.14610.2767.76547.8480873619.744313876.981283735.912390.390631.6912.8203300.54497.13549.502476.15212.6485.6210.809211.9910.384.178689.01374.7540.673.0026.1153.101604.059670.3413.390.751.4463.709.31241106.6951723.5476545.23430834190.81616.286.53706.786153110.737544130060111802.3839.608354.512783930.0746680406369279524114.7962461633180.3964031.421.04344155.39592.95344.0711.117114.291269.93247.3375.788458524.51137232.54.748321246231.38630.3322.5325.5431.195.48130.823.560.53332.11564.725.0973276.1743.08347319.657.9363.6824.85433.37787.814.870271.42863473946211712224.63111646.98227019.32486229.100186981091362.13052.38.57250536200967.760.3721381.75927.1082.7808.883713520.0400.422.14528.421.1979.016.6724833131.248360309999.316126.28311.268322.07369.90828.9326.1876.6128.73328.4593.14657883.072553198.00727.20412614027.263601.751.88772668.8968600.4333944245894244.3850223.33.7083178416.123616.62242088958375830890.9066747313.21423.992.0710.256.905.356.517.7834.7039.911.9885035.9281492.780.06107.7944.454.840059.533243621461.458.3112.113.751.6881.525678205.60112.6266472.0623.6327.74573.22192337346.1110056633.232965452.561130.169274.495.64215132.85443.07922.2151052.0098.50912.055.046734.2622.211.9601019.02177.7311.411.4312.4541.48769.662322.5941.661.532.9437.534.59487523.3135647.21152722.6483645499.6098.5012.36378.57991559.412294612732606971.321.687644.691536450.134369222651215649664.68943465596141.93112854.910.6120291.591157.41582.076.58167.6905160.38728.5145.839751370.01223652.87.663199708143.88819.0014.2316.2049.060.83348.315.190.81920.91042.147.771108114.5829.06234428.615.5344.4446.83623.70562.686.786196.07387173833985.989.918.22085.934.79620014.33355421.5821381321566269.27538.96.38037648614938.044.9671031.31320.2712.0826.656402640.030.316.67821.416.0226.825.0863689100.192471438878.810234.8058.628420.29283.96022.4333.7385.1536.68736.1832.47833366.282066226.48533.54510286933.352955.542.58159783.73110397.8292839309795823.9649325.74.0901684016.523617.02482126409376530993.63518867815.001.476.703.913.314.057.8493.7928.522.3724348.9372539.9131.83169.1291.461.889894.497382791253.17OpenBenchmarking.org

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: Vulkan GPU - Model: vgg16CompuLab Airtop3GM-1000816243240SE +/- 0.02, N = 3SE +/- 0.03, N = 38.3133.33MIN: 7.75 / MAX: 20.64MIN: 32.53 / MAX: 40.221. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: vgg16CompuLab Airtop3GM-1000714212835Min: 8.29 / Avg: 8.31 / Max: 8.35Min: 33.28 / Avg: 33.33 / Max: 33.361. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

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 1080CompuLab Airtop3GM-1000700140021002800350013442
MinAvgMaxCompuLab Airtop334.035.538.0GM-100055.069.472.0OpenBenchmarking.orgCelsius, Fewer Is BetterGLmark2 2020.04CPU Temperature Monitor20406080100
OpenBenchmarking.orgCelsius, Fewer Is BetterGLmark2 2020.04System Temperature MonitorGM-1000153045607527.8

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: Vulkan GPU - Model: alexnetCompuLab Airtop3GM-1000246810SE +/- 0.03, N = 3SE +/- 0.08, N = 32.118.17MIN: 1.84 / MAX: 20.31MIN: 7.83 / MAX: 8.811. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: alexnetCompuLab Airtop3GM-10003691215Min: 2.08 / Avg: 2.11 / Max: 2.17Min: 8.08 / Avg: 8.17 / Max: 8.321. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: resnet50CompuLab Airtop3GM-10003691215SE +/- 0.01, N = 3SE +/- 0.04, N = 33.7513.22MIN: 3.72 / MAX: 9.31MIN: 12.84 / MAX: 29.571. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: resnet50CompuLab Airtop3GM-100048121620Min: 3.74 / Avg: 3.75 / Max: 3.77Min: 13.15 / Avg: 13.22 / Max: 13.281. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: resnet18CompuLab Airtop3GM-10001.3052.613.9155.226.525SE +/- 0.03, N = 3SE +/- 0.01, N = 31.685.80MIN: 1.63 / MAX: 20.3MIN: 5.62 / MAX: 13.861. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: resnet18CompuLab Airtop3GM-1000246810Min: 1.64 / Avg: 1.68 / Max: 1.74Min: 5.79 / Avg: 5.8 / Max: 5.811. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

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: YesCompuLab Airtop3GM-100060120180240300SE +/- 0.44, N = 3SE +/- 0.07, N = 381.53276.62
MinAvgMaxCompuLab Airtop338.040.259.0GM-100050.052.564.0OpenBenchmarking.orgCelsius, Fewer Is BetterRealSR-NCNN 20200818CPU Temperature Monitor20406080100
MinAvgMaxGM-100054.054.165.0OpenBenchmarking.orgCelsius, Fewer Is BetterRealSR-NCNN 20200818System Temperature Monitor20406080100
OpenBenchmarking.orgSeconds, Fewer Is BetterRealSR-NCNN 20200818Scale: 4x - TAA: YesCompuLab Airtop3GM-100050100150200250Min: 80.72 / Avg: 81.53 / Max: 82.23Min: 276.49 / Avg: 276.62 / Max: 276.75

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: WritesCompuLab Airtop3GM-100015K30K45K60K75KSE +/- 744.79, N = 3SE +/- 177.03, N = 156782020732
MinAvgMaxCompuLab Airtop347.066.481.0GM-100059.068.277.0OpenBenchmarking.orgCelsius, Fewer Is BetterApache Cassandra 3.11.4CPU Temperature Monitor20406080100
OpenBenchmarking.orgCelsius, Fewer Is BetterApache Cassandra 3.11.4System Temperature MonitorGM-10001428425670Min: 64 / Avg: 72.15 / Max: 75
OpenBenchmarking.orgOp/s, More Is BetterApache Cassandra 3.11.4Test: WritesCompuLab Airtop3GM-100012K24K36K48K60KMin: 66893 / Avg: 67819.67 / Max: 69293Min: 19586 / Avg: 20732.33 / Max: 22089

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: YesCompuLab Airtop3GM-100048121620SE +/- 0.012, N = 7SE +/- 0.010, N = 35.60116.868
MinAvgMaxCompuLab Airtop337.039.353.0GM-100055.055.556.0OpenBenchmarking.orgCelsius, Fewer Is BetterWaifu2x-NCNN Vulkan 20200818CPU Temperature Monitor1632486480
OpenBenchmarking.orgCelsius, Fewer Is BetterWaifu2x-NCNN Vulkan 20200818System Temperature MonitorGM-1000153045607527.8
OpenBenchmarking.orgSeconds, Fewer Is BetterWaifu2x-NCNN Vulkan 20200818Scale: 2x - Denoise: 3 - TAA: YesCompuLab Airtop3GM-100048121620Min: 5.55 / Avg: 5.6 / Max: 5.63Min: 16.85 / Avg: 16.87 / Max: 16.89

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: NoCompuLab Airtop3GM-1000918273645SE +/- 0.03, N = 4SE +/- 0.02, N = 312.6337.88
MinAvgMaxCompuLab Airtop342.045.063.0GM-100050.051.060.0OpenBenchmarking.orgCelsius, Fewer Is BetterRealSR-NCNN 20200818CPU Temperature Monitor20406080100
OpenBenchmarking.orgCelsius, Fewer Is BetterRealSR-NCNN 20200818System Temperature MonitorGM-1000122436486027.8
OpenBenchmarking.orgSeconds, Fewer Is BetterRealSR-NCNN 20200818Scale: 4x - TAA: NoCompuLab Airtop3GM-1000816243240Min: 12.56 / Avg: 12.63 / Max: 12.72Min: 37.84 / Avg: 37.88 / Max: 37.92

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: Fill SyncCompuLab Airtop3GM-100014002800420056007000SE +/- 6.82, N = 6SE +/- 8.65, N = 106472.062260.151. (CXX) g++ options: -O3 -lsnappy -lpthread
MinAvgMaxCompuLab Airtop349.050.753.0GM-100058.058.760.0OpenBenchmarking.orgCelsius, Fewer Is BetterLevelDB 1.22CPU Temperature Monitor1632486480
OpenBenchmarking.orgCelsius, Fewer Is BetterLevelDB 1.22System Temperature MonitorGM-1000142842567027.8
OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Fill SyncCompuLab Airtop3GM-100011002200330044005500Min: 6452.65 / Avg: 6472.06 / Max: 6500.89Min: 2218.02 / Avg: 2260.15 / Max: 2294.611. (CXX) g++ options: -O3 -lsnappy -lpthread

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: Vulkan GPU - Model: squeezenetCompuLab Airtop3GM-10003691215SE +/- 0.01, N = 3SE +/- 0.00, N = 33.6310.27MIN: 3.57 / MAX: 3.76MIN: 9.98 / MAX: 10.781. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: squeezenetCompuLab Airtop3GM-10003691215Min: 3.61 / Avg: 3.63 / Max: 3.64Min: 10.26 / Avg: 10.27 / Max: 10.271. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: IP Batch All - Data Type: u8s8f32 - Engine: CPUCompuLab Airtop3GM-10001530456075SE +/- 0.06, N = 3SE +/- 0.33, N = 327.7567.77MIN: 25.65MIN: 59.541. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
MinAvgMaxCompuLab Airtop356.075.188.0GM-100061.068.677.0OpenBenchmarking.orgCelsius, Fewer Is BetteroneDNN 1.5CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.074.175.0OpenBenchmarking.orgCelsius, Fewer Is BetteroneDNN 1.5System Temperature Monitor20406080100
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: IP Batch All - Data Type: u8s8f32 - Engine: CPUCompuLab Airtop3GM-10001326395265Min: 27.68 / Avg: 27.75 / Max: 27.86Min: 67.23 / Avg: 67.77 / Max: 68.361. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -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: Vulkan GPU - Model: googlenetCompuLab Airtop3GM-1000246810SE +/- 0.00, N = 3SE +/- 0.03, N = 33.227.84MIN: 3.2 / MAX: 3.32MIN: 7.62 / MAX: 10.981. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: googlenetCompuLab Airtop3GM-10003691215Min: 3.21 / Avg: 3.22 / Max: 3.22Min: 7.79 / Avg: 7.84 / Max: 7.881. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

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: Read While WritingCompuLab Airtop3GM-1000400K800K1200K1600K2000KSE +/- 19030.80, N = 9SE +/- 8029.23, N = 819233738087361. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
MinAvgMaxCompuLab Airtop345.069.986.0GM-100055.065.774.0OpenBenchmarking.orgCelsius, Fewer Is BetterFacebook RocksDB 6.3.6CPU Temperature Monitor20406080100
MinAvgMaxGM-100054.066.075.0OpenBenchmarking.orgCelsius, Fewer Is BetterFacebook RocksDB 6.3.6System Temperature Monitor20406080100
OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.3.6Test: Read While WritingCompuLab Airtop3GM-1000300K600K900K1200K1500KMin: 1872384 / Avg: 1923372.56 / Max: 2059306Min: 780815 / Avg: 808736.38 / Max: 8403101. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -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 SceneCompuLab Airtop3GM-10001020304050SE +/- 0.09, N = 3SE +/- 0.19, N = 346.1119.74
MinAvgMaxCompuLab Airtop359.073.793.0GM-100061.069.378.0OpenBenchmarking.orgCelsius, Fewer Is Betterrays1bench 2020-01-09CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.073.475.0OpenBenchmarking.orgCelsius, Fewer Is Betterrays1bench 2020-01-09System Temperature Monitor20406080100
OpenBenchmarking.orgmrays/s, More Is Betterrays1bench 2020-01-09Large SceneCompuLab Airtop3GM-1000918273645Min: 45.93 / Avg: 46.11 / Max: 46.21Min: 19.54 / Avg: 19.74 / Max: 20.12

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 MetricCompuLab Airtop3GM-100020K40K60K80K100K100566431381. (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
MinAvgMaxCompuLab Airtop356.075.288.0GM-100062.069.180.0OpenBenchmarking.orgCelsius, Fewer Is BetterBRL-CAD 7.30.8CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.074.975.0OpenBenchmarking.orgCelsius, Fewer Is BetterBRL-CAD 7.30.8System Temperature Monitor20406080100

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: ThoroughCompuLab Airtop3GM-100020406080100SE +/- 0.49, N = 3SE +/- 1.07, N = 333.2376.981. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread
MinAvgMaxCompuLab Airtop344.066.882.0GM-100059.067.976.0OpenBenchmarking.orgCelsius, Fewer Is BetterASTC Encoder 2.0CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.074.275.0OpenBenchmarking.orgCelsius, Fewer Is BetterASTC Encoder 2.0System Temperature Monitor20406080100
OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.0Preset: ThoroughCompuLab Airtop3GM-10001530456075Min: 32.25 / Avg: 33.23 / Max: 33.75Min: 74.85 / Avg: 76.98 / Max: 78.191. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread

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: 50 - Mode: Read OnlyCompuLab Airtop3GM-100060K120K180K240K300KSE +/- 2332.06, N = 3SE +/- 1251.67, N = 152965451283731. (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 OnlyCompuLab Airtop3GM-100050K100K150K200K250KMin: 292821.58 / Avg: 296544.71 / Max: 300839.21Min: 125521.71 / Avg: 128373.27 / Max: 144975.271. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPUCompuLab Airtop3GM-10001.33032.66063.99095.32126.6515SE +/- 0.00686, N = 4SE +/- 0.05068, N = 152.561135.91239MIN: 2.22MIN: 4.171. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
MinAvgMaxCompuLab Airtop356.072.294.0GM-100061.068.979.0OpenBenchmarking.orgCelsius, Fewer Is BetteroneDNN 1.5CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.072.275.0OpenBenchmarking.orgCelsius, Fewer Is BetteroneDNN 1.5System Temperature Monitor20406080100
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPUCompuLab Airtop3GM-1000246810Min: 2.55 / Avg: 2.56 / Max: 2.58Min: 5.21 / Avg: 5.91 / Max: 5.991. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

PostgreSQL pgbench

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

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 1 - Clients: 50 - Mode: Read Only - Average LatencyCompuLab Airtop3GM-10000.08780.17560.26340.35120.439SE +/- 0.001, N = 3SE +/- 0.003, N = 150.1690.3901. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
MinAvgMaxCompuLab Airtop342.058.977.0GM-100057.065.274.0OpenBenchmarking.orgCelsius, Fewer Is BetterPostgreSQL pgbench 13.0CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.064.175.0OpenBenchmarking.orgCelsius, Fewer Is BetterPostgreSQL pgbench 13.0System Temperature Monitor20406080100
OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 1 - Clients: 50 - Mode: Read Only - Average LatencyCompuLab Airtop3GM-100012345Min: 0.17 / Avg: 0.17 / Max: 0.17Min: 0.35 / Avg: 0.39 / Max: 0.41. (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: ExhaustiveCompuLab Airtop3GM-1000140280420560700SE +/- 0.82, N = 3SE +/- 0.59, N = 3274.49631.691. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread
MinAvgMaxCompuLab Airtop347.071.590.0GM-100060.068.577.0OpenBenchmarking.orgCelsius, Fewer Is BetterASTC Encoder 2.0CPU Temperature Monitor20406080100
OpenBenchmarking.orgCelsius, Fewer Is BetterASTC Encoder 2.0System Temperature MonitorGM-10001428425670Min: 64 / Avg: 74.9 / Max: 75
OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.0Preset: ExhaustiveCompuLab Airtop3GM-1000110220330440550Min: 272.97 / Avg: 274.49 / Max: 275.76Min: 630.77 / Avg: 631.69 / Max: 632.791. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Deconvolution Batch deconv_1d - Data Type: u8s8f32 - Engine: CPUCompuLab Airtop3GM-10003691215SE +/- 0.02496, N = 3SE +/- 0.13560, N = 125.6421512.82030MIN: 4.78MIN: 8.951. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
MinAvgMaxCompuLab Airtop355.070.591.0GM-100061.068.879.0OpenBenchmarking.orgCelsius, Fewer Is BetteroneDNN 1.5CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.072.076.0OpenBenchmarking.orgCelsius, Fewer Is BetteroneDNN 1.5System Temperature Monitor20406080100
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Deconvolution Batch deconv_1d - Data Type: u8s8f32 - Engine: CPUCompuLab Airtop3GM-100048121620Min: 5.59 / Avg: 5.64 / Max: 5.67Min: 11.33 / Avg: 12.82 / Max: 131. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

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: Earthgecko SkylineCompuLab Airtop3GM-100070140210280350SE +/- 2.03, N = 3SE +/- 4.34, N = 3132.85300.54
MinAvgMaxCompuLab Airtop350.071.988.0GM-100059.069.677.0OpenBenchmarking.orgCelsius, Fewer Is BetterNumenta Anomaly Benchmark 1.1CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.074.875.0OpenBenchmarking.orgCelsius, Fewer Is BetterNumenta Anomaly Benchmark 1.1System Temperature Monitor20406080100
OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Earthgecko SkylineCompuLab Airtop3GM-100050100150200250Min: 129.43 / Avg: 132.85 / Max: 136.47Min: 293.05 / Avg: 300.54 / Max: 308.1

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Bayesian ChangepointCompuLab Airtop3GM-100020406080100SE +/- 0.49, N = 15SE +/- 1.25, N = 343.0897.14
MinAvgMaxCompuLab Airtop354.075.899.0GM-100060.069.978.0OpenBenchmarking.orgCelsius, Fewer Is BetterNumenta Anomaly Benchmark 1.1CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.074.475.0OpenBenchmarking.orgCelsius, Fewer Is BetterNumenta Anomaly Benchmark 1.1System Temperature Monitor20406080100
OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Bayesian ChangepointCompuLab Airtop3GM-100020406080100Min: 40.15 / Avg: 43.08 / Max: 45.1Min: 94.65 / Avg: 97.13 / Max: 98.61

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Relative EntropyCompuLab Airtop3GM-10001122334455SE +/- 0.19, N = 15SE +/- 0.44, N = 1222.2249.50
MinAvgMaxCompuLab Airtop340.066.082.0GM-100057.067.376.0OpenBenchmarking.orgCelsius, Fewer Is BetterNumenta Anomaly Benchmark 1.1CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.071.575.0OpenBenchmarking.orgCelsius, Fewer Is BetterNumenta Anomaly Benchmark 1.1System Temperature Monitor20406080100
OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Relative EntropyCompuLab Airtop3GM-10001020304050Min: 20.66 / Avg: 22.21 / Max: 23.35Min: 44.92 / Avg: 49.5 / Max: 50.61

IOR

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

OpenBenchmarking.orgMB/s, More Is BetterIOR 3.2.1Read TestCompuLab Airtop3GM-10002004006008001000SE +/- 4.11, N = 13SE +/- 4.42, N = 151052.00476.15MIN: 53.05 / MAX: 1439MIN: 10.65 / MAX: 548.821. (CC) gcc options: -O2 -lm -pthread -lmpi
MinAvgMaxCompuLab Airtop344.045.349.0GM-100049.049.751.0OpenBenchmarking.orgCelsius, Fewer Is BetterIOR 3.2.1CPU Temperature Monitor1530456075
OpenBenchmarking.orgCelsius, Fewer Is BetterIOR 3.2.1System Temperature MonitorGM-1000122436486027.8
OpenBenchmarking.orgMB/s, More Is BetterIOR 3.2.1Read TestCompuLab Airtop3GM-10002004006008001000Min: 1034.39 / Avg: 1052 / Max: 1069.98Min: 443.63 / Avg: 476.15 / Max: 499.021. (CC) gcc options: -O2 -lm -pthread -lmpi

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 CompileCompuLab Airtop3GM-100050100150200250SE +/- 0.13, N = 3SE +/- 0.47, N = 398.51212.65
MinAvgMaxCompuLab Airtop354.073.888.0GM-100061.068.376.0OpenBenchmarking.orgCelsius, Fewer Is BetterTimed Linux Kernel Compilation 5.4CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.074.475.0OpenBenchmarking.orgCelsius, Fewer Is BetterTimed Linux Kernel Compilation 5.4System Temperature Monitor20406080100
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 5.4Time To CompileCompuLab Airtop3GM-10004080120160200Min: 98.27 / Avg: 98.51 / Max: 98.72Min: 211.76 / Avg: 212.65 / Max: 213.35

Kvazaar

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

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 4K - Video Preset: Very FastCompuLab Airtop3GM-10003691215SE +/- 0.07, N = 3SE +/- 0.06, N = 312.055.621. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
MinAvgMaxCompuLab Airtop354.073.791.0GM-100060.068.178.0OpenBenchmarking.orgCelsius, Fewer Is BetterKvazaar 2.0CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.074.675.0OpenBenchmarking.orgCelsius, Fewer Is BetterKvazaar 2.0System Temperature Monitor20406080100
OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 4K - Video Preset: Very FastCompuLab Airtop3GM-100048121620Min: 11.95 / Avg: 12.05 / Max: 12.19Min: 5.56 / Avg: 5.62 / Max: 5.741. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

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: Deconvolution Batch deconv_1d - Data Type: f32 - Engine: CPUCompuLab Airtop3GM-10003691215SE +/- 0.06779, N = 4SE +/- 0.15350, N = 135.0467310.80921MIN: 4.56MIN: 6.791. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
MinAvgMaxCompuLab Airtop356.072.490.0GM-100061.068.478.0OpenBenchmarking.orgCelsius, Fewer Is BetteroneDNN 1.5CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.072.075.0OpenBenchmarking.orgCelsius, Fewer Is BetteroneDNN 1.5System Temperature Monitor20406080100
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Deconvolution Batch deconv_1d - Data Type: f32 - Engine: CPUCompuLab Airtop3GM-10003691215Min: 4.9 / Avg: 5.05 / Max: 5.21Min: 9.07 / Avg: 10.81 / Max: 11.291. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

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: MediumCompuLab Airtop3GM-10000.95851.9172.87553.8344.7925SE +/- 0.03, N = 3SE +/- 0.01, N = 34.261.991. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
MinAvgMaxCompuLab Airtop347.070.890.0GM-100059.067.577.0OpenBenchmarking.orgCelsius, Fewer Is BetterKvazaar 2.0CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.071.575.0OpenBenchmarking.orgCelsius, Fewer Is BetterKvazaar 2.0System Temperature Monitor20406080100
OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 4K - Video Preset: MediumCompuLab Airtop3GM-1000246810Min: 4.23 / Avg: 4.26 / Max: 4.31Min: 1.97 / Avg: 1.99 / Max: 2.011. (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 FastCompuLab Airtop3GM-1000510152025SE +/- 0.12, N = 3SE +/- 0.15, N = 422.2110.381. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
MinAvgMaxCompuLab Airtop355.073.190.0GM-100061.068.278.0OpenBenchmarking.orgCelsius, Fewer Is BetterKvazaar 2.0CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.074.275.0OpenBenchmarking.orgCelsius, Fewer Is BetterKvazaar 2.0System Temperature Monitor20406080100
OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 4K - Video Preset: Ultra FastCompuLab Airtop3GM-1000510152025Min: 21.98 / Avg: 22.21 / Max: 22.39Min: 10.22 / Avg: 10.38 / Max: 10.811. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

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 AtomsCompuLab Airtop3GM-10000.94021.88042.82063.76084.701SE +/- 0.00439, N = 3SE +/- 0.00286, N = 31.960104.17868
MinAvgMaxCompuLab Airtop361.079.4100.0GM-100063.071.382.0OpenBenchmarking.orgCelsius, Fewer Is BetterNAMD 2.14CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.074.975.0OpenBenchmarking.orgCelsius, Fewer Is BetterNAMD 2.14System Temperature Monitor20406080100
OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD 2.14ATPase Simulation - 327,506 AtomsCompuLab Airtop3GM-1000246810Min: 1.95 / Avg: 1.96 / Max: 1.97Min: 4.17 / Avg: 4.18 / Max: 4.18

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 1080p - Video Preset: MediumCompuLab Airtop3GM-1000510152025SE +/- 0.12, N = 3SE +/- 0.15, N = 319.029.011. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
MinAvgMaxCompuLab Airtop354.072.890.0GM-100060.068.078.0OpenBenchmarking.orgCelsius, Fewer Is BetterKvazaar 2.0CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.074.375.0OpenBenchmarking.orgCelsius, Fewer Is BetterKvazaar 2.0System Temperature Monitor20406080100
OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 1080p - Video Preset: MediumCompuLab Airtop3GM-1000510152025Min: 18.85 / Avg: 19.02 / Max: 19.24Min: 8.86 / Avg: 9.01 / Max: 9.31. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

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 SceneCompuLab Airtop3GM-100080160240320400SE +/- 0.40, N = 3SE +/- 2.21, N = 3177.73374.751. (CXX) g++ options: -std=c++11 -O3 -ffast-math -rdynamic -ldl -lImath -lIlmImf -lIex -lHalf -lz -lIlmThread -lxml2 -lfreetype -lpthread
MinAvgMaxCompuLab Airtop358.077.294.0GM-100062.069.179.0OpenBenchmarking.orgCelsius, Fewer Is BetterYafaRay 3.4.1CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.074.975.0OpenBenchmarking.orgCelsius, Fewer Is BetterYafaRay 3.4.1System Temperature Monitor20406080100
OpenBenchmarking.orgSeconds, Fewer Is BetterYafaRay 3.4.1Total Time For Sample SceneCompuLab Airtop3GM-100070140210280350Min: 177.05 / Avg: 177.73 / Max: 178.44Min: 370.45 / Avg: 374.75 / Max: 377.781. (CXX) g++ options: -std=c++11 -O3 -ffast-math -rdynamic -ldl -lImath -lIlmImf -lIex -lHalf -lz -lIlmThread -lxml2 -lfreetype -lpthread

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: DLSCCompuLab Airtop3GM-10000.31730.63460.95191.26921.5865SE +/- 0.02, N = 3SE +/- 0.01, N = 151.410.67MIN: 1.31 / MAX: 1.69MIN: 0.59 / MAX: 0.97
MinAvgMaxCompuLab Airtop358.074.591.0GM-100061.068.377.0OpenBenchmarking.orgCelsius, Fewer Is BetterLuxCoreRender 2.3CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.074.075.0OpenBenchmarking.orgCelsius, Fewer Is BetterLuxCoreRender 2.3System Temperature Monitor20406080100
OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.3Scene: DLSCCompuLab Airtop3GM-1000246810Min: 1.38 / Avg: 1.41 / Max: 1.44Min: 0.65 / Avg: 0.67 / Max: 0.75

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: Vulkan GPU-v2-v2 - Model: mobilenet-v2CompuLab Airtop3GM-10000.6751.352.0252.73.375SE +/- 0.01, N = 3SE +/- 0.03, N = 31.433.00MIN: 1.4 / MAX: 9.39MIN: 2.89 / MAX: 3.841. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2CompuLab Airtop3GM-1000246810Min: 1.41 / Avg: 1.43 / Max: 1.45Min: 2.95 / Avg: 3 / Max: 3.041. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

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: Windowed GaussianCompuLab Airtop3GM-1000612182430SE +/- 0.15, N = 5SE +/- 0.28, N = 1412.4526.12
MinAvgMaxCompuLab Airtop349.070.487.0GM-100059.068.077.0OpenBenchmarking.orgCelsius, Fewer Is BetterNumenta Anomaly Benchmark 1.1CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.072.975.0OpenBenchmarking.orgCelsius, Fewer Is BetterNumenta Anomaly Benchmark 1.1System Temperature Monitor20406080100
OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Windowed GaussianCompuLab Airtop3GM-1000612182430Min: 11.94 / Avg: 12.45 / Max: 12.86Min: 22.58 / Avg: 26.11 / Max: 26.66

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: Vulkan GPU - Model: mnasnetCompuLab Airtop3GM-10000.69751.3952.09252.793.4875SE +/- 0.00, N = 3SE +/- 0.02, N = 31.483.10MIN: 1.46 / MAX: 1.51MIN: 3 / MAX: 4.161. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: mnasnetCompuLab Airtop3GM-1000246810Min: 1.47 / Avg: 1.48 / Max: 1.48Min: 3.06 / Avg: 3.1 / Max: 3.131. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

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 CompileCompuLab Airtop3GM-100030060090012001500SE +/- 4.62, N = 3SE +/- 1.30, N = 3769.661604.06
OpenBenchmarking.orgCelsius, Fewer Is BetterTimed LLVM Compilation 10.0CPU Temperature MonitorCompuLab Airtop3GM-100020406080100Min: 56 / Avg: 77.27 / Max: 91Min: 61 / Avg: 69.21 / Max: 78
OpenBenchmarking.orgCelsius, Fewer Is BetterTimed LLVM Compilation 10.0System Temperature MonitorGM-10001428425670Min: 64 / Avg: 74.93 / Max: 75
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 10.0Time To CompileCompuLab Airtop3GM-100030060090012001500Min: 762.19 / Avg: 769.66 / Max: 778.09Min: 1602.47 / Avg: 1604.06 / Max: 1606.63

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: Recurrent Neural Network Training - Data Type: f32 - Engine: CPUCompuLab Airtop3GM-1000140280420560700SE +/- 2.57, N = 3SE +/- 8.43, N = 3322.59670.34MIN: 310.92MIN: 612.851. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
MinAvgMaxCompuLab Airtop355.073.388.0GM-100061.068.677.0OpenBenchmarking.orgCelsius, Fewer Is BetteroneDNN 1.5CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.073.875.0OpenBenchmarking.orgCelsius, Fewer Is BetteroneDNN 1.5System Temperature Monitor20406080100
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPUCompuLab Airtop3GM-1000120240360480600Min: 318.23 / Avg: 322.59 / Max: 327.12Min: 653.52 / Avg: 670.34 / Max: 679.851. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -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: Vulkan GPU-v3-v3 - Model: mobilenet-v3CompuLab Airtop3GM-10000.76281.52562.28843.05123.814SE +/- 0.00, N = 3SE +/- 0.03, N = 31.663.39MIN: 1.65 / MAX: 1.69MIN: 3.29 / MAX: 4.221. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3CompuLab Airtop3GM-1000246810Min: 1.66 / Avg: 1.66 / Max: 1.67Min: 3.34 / Avg: 3.39 / Max: 3.421. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

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: Rainbow Colors and PrismCompuLab Airtop3GM-10000.34430.68861.03291.37721.7215SE +/- 0.01, N = 3SE +/- 0.01, N = 121.530.75MIN: 1.48 / MAX: 1.81MIN: 0.65 / MAX: 1.15
MinAvgMaxCompuLab Airtop357.075.291.0GM-100061.068.578.0OpenBenchmarking.orgCelsius, Fewer Is BetterLuxCoreRender 2.3CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.074.075.0OpenBenchmarking.orgCelsius, Fewer Is BetterLuxCoreRender 2.3System Temperature Monitor20406080100
OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.3Scene: Rainbow Colors and PrismCompuLab Airtop3GM-1000246810Min: 1.52 / Avg: 1.53 / Max: 1.54Min: 0.73 / Avg: 0.75 / Max: 0.83

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 4 - Input: 1080pCompuLab Airtop3GM-10000.66221.32441.98662.64883.311SE +/- 0.013, N = 3SE +/- 0.025, N = 32.9431.4461. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie
MinAvgMaxCompuLab Airtop357.072.990.0GM-100061.069.380.0OpenBenchmarking.orgCelsius, Fewer Is BetterSVT-AV1 0.8CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.074.075.0OpenBenchmarking.orgCelsius, Fewer Is BetterSVT-AV1 0.8System Temperature Monitor20406080100
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 4 - Input: 1080pCompuLab Airtop3GM-1000246810Min: 2.93 / Avg: 2.94 / Max: 2.97Min: 1.42 / Avg: 1.45 / Max: 1.51. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie

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: MemorialCompuLab Airtop3GM-1000246810SE +/- 0.10, N = 3SE +/- 0.04, N = 67.533.70
MinAvgMaxCompuLab Airtop357.073.889.0GM-100061.068.677.0OpenBenchmarking.orgCelsius, Fewer Is BetterIntel Open Image Denoise 1.2.0CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.074.275.0OpenBenchmarking.orgCelsius, Fewer Is BetterIntel Open Image Denoise 1.2.0System Temperature Monitor20406080100
OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 1.2.0Scene: MemorialCompuLab Airtop3GM-10003691215Min: 7.43 / Avg: 7.53 / Max: 7.72Min: 3.65 / Avg: 3.7 / Max: 3.91

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: Vulkan GPU - Model: mobilenetCompuLab Airtop3GM-10003691215SE +/- 0.02, N = 3SE +/- 0.00, N = 34.599.31MIN: 4.54 / MAX: 12.63MIN: 9 / MAX: 10.281. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: mobilenetCompuLab Airtop3GM-10003691215Min: 4.57 / Avg: 4.59 / Max: 4.63Min: 9.31 / Avg: 9.31 / Max: 9.321. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

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 TestCompuLab Airtop3GM-100010K20K30K40K50KSE +/- 370.06, N = 3SE +/- 339.20, N = 448752241101. (CXX) g++ options: -pipe -lpthread
MinAvgMaxCompuLab Airtop357.075.893.0GM-100061.069.276.0OpenBenchmarking.orgCelsius, Fewer Is Better7-Zip Compression 16.02CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.073.775.0OpenBenchmarking.orgCelsius, Fewer Is Better7-Zip Compression 16.02System Temperature Monitor20406080100
OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 16.02Compress Speed TestCompuLab Airtop3GM-10008K16K24K32K40KMin: 48097 / Avg: 48751.67 / Max: 49378Min: 23670 / Avg: 24110 / Max: 251171. (CXX) g++ options: -pipe -lpthread

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Deconvolution Batch deconv_3d - Data Type: u8s8f32 - Engine: CPUCompuLab Airtop3GM-1000246810SE +/- 0.02023, N = 9SE +/- 0.01402, N = 93.313566.69517MIN: 3.15MIN: 6.491. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
MinAvgMaxCompuLab Airtop354.069.388.0GM-100061.068.177.0OpenBenchmarking.orgCelsius, Fewer Is BetteroneDNN 1.5CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.068.475.0OpenBenchmarking.orgCelsius, Fewer Is BetteroneDNN 1.5System Temperature Monitor20406080100
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Deconvolution Batch deconv_3d - Data Type: u8s8f32 - Engine: CPUCompuLab Airtop3GM-10003691215Min: 3.23 / Avg: 3.31 / Max: 3.45Min: 6.64 / Avg: 6.7 / Max: 6.741. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

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 1080p - Video Preset: Very FastCompuLab Airtop3GM-10001122334455SE +/- 0.46, N = 4SE +/- 0.24, N = 1447.2123.541. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
MinAvgMaxCompuLab Airtop355.072.590.0GM-100061.068.278.0OpenBenchmarking.orgCelsius, Fewer Is BetterKvazaar 2.0CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.073.375.0OpenBenchmarking.orgCelsius, Fewer Is BetterKvazaar 2.0System Temperature Monitor20406080100
OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 1080p - Video Preset: Very FastCompuLab Airtop3GM-10001020304050Min: 45.85 / Avg: 47.21 / Max: 47.92Min: 23.26 / Avg: 23.54 / Max: 26.621. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

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: BlowfishCompuLab Airtop3GM-10003K6K9K12K15KSE +/- 227.62, N = 4SE +/- 60.95, N = 13152727654-lbz21. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -pthread -lm -lz -ldl -lcrypt
MinAvgMaxCompuLab Airtop350.072.988.0GM-100060.068.276.0OpenBenchmarking.orgCelsius, Fewer Is BetterJohn The Ripper 1.9.0-jumbo-1CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.073.375.0OpenBenchmarking.orgCelsius, Fewer Is BetterJohn The Ripper 1.9.0-jumbo-1System Temperature Monitor20406080100
OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 1.9.0-jumbo-1Test: BlowfishCompuLab Airtop3GM-10003K6K9K12K15KMin: 15019 / Avg: 15271.75 / Max: 15954Min: 7579 / Avg: 7653.77 / Max: 83851. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -pthread -lm -lz -ldl -lcrypt

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: Vulkan GPU - Model: efficientnet-b0CompuLab Airtop3GM-10001.17682.35363.53044.70725.884SE +/- 0.00, N = 3SE +/- 0.02, N = 32.645.23MIN: 2.61 / MAX: 2.67MIN: 5.06 / MAX: 5.951. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: efficientnet-b0CompuLab Airtop3GM-1000246810Min: 2.63 / Avg: 2.64 / Max: 2.64Min: 5.18 / Avg: 5.23 / Max: 5.261. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

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: MD5CompuLab Airtop3GM-1000200K400K600K800K1000KSE +/- 10984.38, N = 4SE +/- 3391.63, N = 15836454430834-lbz21. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -pthread -lm -lz -ldl -lcrypt
MinAvgMaxCompuLab Airtop352.072.589.0GM-100060.068.178.0OpenBenchmarking.orgCelsius, Fewer Is BetterJohn The Ripper 1.9.0-jumbo-1CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.074.275.0OpenBenchmarking.orgCelsius, Fewer Is BetterJohn The Ripper 1.9.0-jumbo-1System Temperature Monitor20406080100
OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 1.9.0-jumbo-1Test: MD5CompuLab Airtop3GM-1000140K280K420K560K700KMin: 822476 / Avg: 836453.75 / Max: 869222Min: 424345 / Avg: 430834 / Max: 4776961. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -pthread -lm -lz -ldl -lcrypt

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: 0CompuLab Airtop3GM-10004080120160200SE +/- 0.27, N = 3SE +/- 0.11, N = 399.61190.821. (CXX) g++ options: -O3 -fPIC
MinAvgMaxCompuLab Airtop357.077.994.0GM-100061.069.578.0OpenBenchmarking.orgCelsius, Fewer Is Betterlibavif avifenc 0.7.3CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.074.675.0OpenBenchmarking.orgCelsius, Fewer Is Betterlibavif avifenc 0.7.3System Temperature Monitor20406080100
OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.7.3Encoder Speed: 0CompuLab Airtop3GM-1000306090120150Min: 99.27 / Avg: 99.61 / Max: 100.15Min: 190.69 / Avg: 190.82 / Max: 191.041. (CXX) g++ options: -O3 -fPIC

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: Vulkan GPU - Model: yolov4-tinyCompuLab Airtop3GM-100048121620SE +/- 0.19, N = 3SE +/- 0.01, N = 38.5016.28MIN: 8.02 / MAX: 9.19MIN: 15.64 / MAX: 17.641. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
MinAvgMaxCompuLab Airtop352.069.480.0GM-100059.066.870.0OpenBenchmarking.orgCelsius, Fewer Is BetterNCNN 20200916CPU Temperature Monitor20406080100
OpenBenchmarking.orgCelsius, Fewer Is BetterNCNN 20200916System Temperature MonitorGM-1000142842567027.8
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: yolov4-tinyCompuLab Airtop3GM-100048121620Min: 8.31 / Avg: 8.5 / Max: 8.88Min: 16.26 / Avg: 16.28 / Max: 16.291. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

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 4KCompuLab Airtop3GM-10003691215SE +/- 0.11, N = 3SE +/- 0.05, N = 312.366.531. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
MinAvgMaxCompuLab Airtop356.076.791.0GM-100061.069.680.0OpenBenchmarking.orgCelsius, Fewer Is Betterx265 3.4CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.074.575.0OpenBenchmarking.orgCelsius, Fewer Is Betterx265 3.4System Temperature Monitor20406080100
OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.4Video Input: Bosphorus 4KCompuLab Airtop3GM-100048121620Min: 12.13 / Avg: 12.36 / Max: 12.47Min: 6.47 / Avg: 6.53 / Max: 6.641. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

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: CylinderCompuLab Airtop3GM-1000150300450600750SE +/- 1.24, N = 3SE +/- 1.81, N = 3378.58706.791. (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
MinAvgMaxCompuLab Airtop351.076.288.0GM-100059.069.078.0OpenBenchmarking.orgCelsius, Fewer Is BetterIncompact3D 2020-09-17CPU Temperature Monitor20406080100
OpenBenchmarking.orgCelsius, Fewer Is BetterIncompact3D 2020-09-17System Temperature MonitorGM-10001428425670Min: 64 / Avg: 74.91 / Max: 75
OpenBenchmarking.orgSeconds, Fewer Is BetterIncompact3D 2020-09-17Input: CylinderCompuLab Airtop3GM-1000120240360480600Min: 376.18 / Avg: 378.58 / Max: 380.34Min: 703.74 / Avg: 706.79 / Max: 710.011. (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

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: 2CompuLab Airtop3GM-100020406080100SE +/- 0.11, N = 3SE +/- 1.76, N = 359.41110.741. (CXX) g++ options: -O3 -fPIC
MinAvgMaxCompuLab Airtop356.076.794.0GM-100061.069.478.0OpenBenchmarking.orgCelsius, Fewer Is Betterlibavif avifenc 0.7.3CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.074.375.0OpenBenchmarking.orgCelsius, Fewer Is Betterlibavif avifenc 0.7.3System Temperature Monitor20406080100
OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.7.3Encoder Speed: 2CompuLab Airtop3GM-100020406080100Min: 59.19 / Avg: 59.41 / Max: 59.55Min: 107.37 / Avg: 110.74 / Max: 113.321. (CXX) g++ options: -O3 -fPIC

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: Inception ResNet V2CompuLab Airtop3GM-10001.2M2.4M3.6M4.8M6MSE +/- 1078.35, N = 3SE +/- 40177.63, N = 329461275441300
MinAvgMaxCompuLab Airtop357.077.595.0GM-100061.069.278.0OpenBenchmarking.orgCelsius, Fewer Is BetterTensorFlow Lite 2020-08-23CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.074.775.0OpenBenchmarking.orgCelsius, Fewer Is BetterTensorFlow Lite 2020-08-23System Temperature Monitor20406080100
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception ResNet V2CompuLab Airtop3GM-1000900K1800K2700K3600K4500KMin: 2943980 / Avg: 2946126.67 / Max: 2947380Min: 5360970 / Avg: 5441300 / Max: 5483210

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception V4CompuLab Airtop3GM-10001.3M2.6M3.9M5.2M6.5MSE +/- 1363.50, N = 3SE +/- 34182.46, N = 332606976011180
MinAvgMaxCompuLab Airtop357.077.596.0GM-100061.069.077.0OpenBenchmarking.orgCelsius, Fewer Is BetterTensorFlow Lite 2020-08-23CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.074.775.0OpenBenchmarking.orgCelsius, Fewer Is BetterTensorFlow Lite 2020-08-23System Temperature Monitor20406080100
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception V4CompuLab Airtop3GM-10001000K2000K3000K4000K5000KMin: 3258190 / Avg: 3260696.67 / Max: 3262880Min: 5942980 / Avg: 6011180 / Max: 6049390

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: Vulkan GPU - Model: shufflenet-v2CompuLab Airtop3GM-10000.53551.0711.60652.1422.6775SE +/- 0.00, N = 3SE +/- 0.01, N = 31.302.38MIN: 1.29 / MAX: 1.36MIN: 2.24 / MAX: 4.751. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: shufflenet-v2CompuLab Airtop3GM-1000246810Min: 1.3 / Avg: 1.3 / Max: 1.3Min: 2.35 / Avg: 2.38 / Max: 2.391. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

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 DocumentCompuLab Airtop3GM-1000918273645SE +/- 0.07, N = 3SE +/- 0.48, N = 621.6939.61
MinAvgMaxCompuLab Airtop354.075.691.0GM-100061.070.679.0OpenBenchmarking.orgCelsius, Fewer Is BetterOCRMyPDF 10.3.1+dfsgCPU Temperature Monitor20406080100
MinAvgMaxGM-100064.073.775.0OpenBenchmarking.orgCelsius, Fewer Is BetterOCRMyPDF 10.3.1+dfsgSystem Temperature Monitor20406080100
OpenBenchmarking.orgSeconds, Fewer Is BetterOCRMyPDF 10.3.1+dfsgProcessing 60 Page PDF DocumentCompuLab Airtop3GM-1000816243240Min: 21.58 / Avg: 21.69 / Max: 21.8Min: 37.2 / Avg: 39.61 / Max: 40.36

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 1080pCompuLab Airtop3GM-1000140280420560700SE +/- 2.55, N = 3SE +/- 2.32, N = 3644.69354.51MIN: 479.82 / MAX: 947.65MIN: 226.96 / MAX: 562.81. (CC) gcc options: -pthread
OpenBenchmarking.orgCelsius, Fewer Is Betterdav1d 0.7.0CPU Temperature MonitorCompuLab Airtop3GM-10001632486480Min: 49 / Avg: 69.57 / Max: 87Min: 61 / Avg: 69.66 / Max: 76
OpenBenchmarking.orgCelsius, Fewer Is Betterdav1d 0.7.0System Temperature MonitorGM-10001428425670Min: 64 / Avg: 74.79 / Max: 75
OpenBenchmarking.orgFPS, More Is Betterdav1d 0.7.0Video Input: Chimera 1080pCompuLab Airtop3GM-1000110220330440550Min: 639.82 / Avg: 644.69 / Max: 648.42Min: 350.42 / Avg: 354.51 / Max: 358.461. (CC) gcc options: -pthread

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: Mobilenet FloatCompuLab Airtop3GM-100060K120K180K240K300KSE +/- 175.70, N = 3SE +/- 4495.68, N = 3153645278393
MinAvgMaxCompuLab Airtop357.076.894.0GM-100061.069.278.0OpenBenchmarking.orgCelsius, Fewer Is BetterTensorFlow Lite 2020-08-23CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.074.275.0OpenBenchmarking.orgCelsius, Fewer Is BetterTensorFlow Lite 2020-08-23System Temperature Monitor20406080100
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet FloatCompuLab Airtop3GM-100050K100K150K200K250KMin: 153358 / Avg: 153644.67 / Max: 153964Min: 269404 / Avg: 278393 / Max: 283066

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: 1080pCompuLab Airtop3GM-10000.03020.06040.09060.12080.151SE +/- 0.001, N = 3SE +/- 0.000, N = 30.1340.0741. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie
MinAvgMaxCompuLab Airtop355.081.495.0GM-100061.071.279.0OpenBenchmarking.orgCelsius, Fewer Is BetterSVT-AV1 0.8CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.074.775.0OpenBenchmarking.orgCelsius, Fewer Is BetterSVT-AV1 0.8System Temperature Monitor20406080100
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 0 - Input: 1080pCompuLab Airtop3GM-100012345Min: 0.13 / Avg: 0.13 / Max: 0.14Min: 0.07 / Avg: 0.07 / Max: 0.081. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie

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: TradesoapCompuLab Airtop3GM-100014002800420056007000SE +/- 30.62, N = 13SE +/- 85.52, N = 2036926680
MinAvgMaxCompuLab Airtop349.068.383.0GM-100059.068.676.0OpenBenchmarking.orgCelsius, Fewer Is BetterDaCapo Benchmark 9.12-MR1CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.069.575.0OpenBenchmarking.orgCelsius, Fewer Is BetterDaCapo Benchmark 9.12-MR1System Temperature Monitor20406080100
OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: TradesoapCompuLab Airtop3GM-100012002400360048006000Min: 3532 / Avg: 3692.38 / Max: 3893Min: 5549 / Avg: 6679.85 / Max: 7130

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: SqueezeNetCompuLab Airtop3GM-100090K180K270K360K450KSE +/- 69.61, N = 3SE +/- 5447.42, N = 4226512406369
MinAvgMaxCompuLab Airtop357.076.693.0GM-100060.068.978.0OpenBenchmarking.orgCelsius, Fewer Is BetterTensorFlow Lite 2020-08-23CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.074.275.0OpenBenchmarking.orgCelsius, Fewer Is BetterTensorFlow Lite 2020-08-23System Temperature Monitor20406080100
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: SqueezeNetCompuLab Airtop3GM-100070K140K210K280K350KMin: 226406 / Avg: 226511.67 / Max: 226643Min: 390032 / Avg: 406369.25 / Max: 412184

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet QuantCompuLab Airtop3GM-100060K120K180K240K300KSE +/- 67.72, N = 3SE +/- 4770.18, N = 3156496279524
MinAvgMaxCompuLab Airtop357.076.993.0GM-100061.069.378.0OpenBenchmarking.orgCelsius, Fewer Is BetterTensorFlow Lite 2020-08-23CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.074.275.0OpenBenchmarking.orgCelsius, Fewer Is BetterTensorFlow Lite 2020-08-23System Temperature Monitor20406080100
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet QuantCompuLab Airtop3GM-100050K100K150K200K250KMin: 156370 / Avg: 156496 / Max: 156602Min: 269984 / Avg: 279524.33 / Max: 284312

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 CompileCompuLab Airtop3GM-1000306090120150SE +/- 0.33, N = 3SE +/- 0.58, N = 364.69114.80
MinAvgMaxCompuLab Airtop359.077.493.0GM-100063.070.679.0OpenBenchmarking.orgCelsius, Fewer Is BetterTimed PHP Compilation 7.4.2CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.074.175.0OpenBenchmarking.orgCelsius, Fewer Is BetterTimed PHP Compilation 7.4.2System Temperature Monitor20406080100
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed PHP Compilation 7.4.2Time To CompileCompuLab Airtop3GM-100020406080100Min: 64.11 / Avg: 64.69 / Max: 65.24Min: 113.64 / Avg: 114.8 / Max: 115.38

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 ReadCompuLab Airtop3GM-10009M18M27M36M45MSE +/- 49809.36, N = 3SE +/- 338773.40, N = 443465596246163311. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
MinAvgMaxCompuLab Airtop353.073.091.0GM-100062.069.380.0OpenBenchmarking.orgCelsius, Fewer Is BetterFacebook RocksDB 6.3.6CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.074.375.0OpenBenchmarking.orgCelsius, Fewer Is BetterFacebook RocksDB 6.3.6System Temperature Monitor20406080100
OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.3.6Test: Random ReadCompuLab Airtop3GM-10008M16M24M32M40MMin: 43372847 / Avg: 43465595.67 / Max: 43543453Min: 24244615 / Avg: 24616331 / Max: 256318081. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread

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: vklBenchmarkCompuLab Airtop3GM-1000306090120150SE +/- 0.98, N = 3SE +/- 0.39, N = 3141.9380.39MIN: 1 / MAX: 580MIN: 1 / MAX: 345
OpenBenchmarking.orgCelsius, Fewer Is BetterOpenVKL 0.9CPU Temperature MonitorCompuLab Airtop3GM-100020406080100Min: 56 / Avg: 80.16 / Max: 95Min: 61 / Avg: 72.18 / Max: 78
OpenBenchmarking.orgCelsius, Fewer Is BetterOpenVKL 0.9System Temperature MonitorGM-10001428425670Min: 64 / Avg: 74.23 / Max: 75
OpenBenchmarking.orgItems / Sec, More Is BetterOpenVKL 0.9Benchmark: vklBenchmarkCompuLab Airtop3GM-1000306090120150Min: 140.83 / Avg: 141.93 / Max: 143.89Min: 79.75 / Avg: 80.39 / Max: 81.08

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 ScoreCompuLab Airtop3GM-100020040060080010001128640

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 1080pCompuLab Airtop3GM-10001224364860SE +/- 0.30, N = 5SE +/- 0.37, N = 1354.9131.421. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
MinAvgMaxCompuLab Airtop356.074.590.0GM-100061.069.078.0OpenBenchmarking.orgCelsius, Fewer Is Betterx265 3.4CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.073.076.0OpenBenchmarking.orgCelsius, Fewer Is Betterx265 3.4System Temperature Monitor20406080100
OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.4Video Input: Bosphorus 1080pCompuLab Airtop3GM-10001122334455Min: 54.1 / Avg: 54.91 / Max: 55.77Min: 30.88 / Avg: 31.42 / Max: 35.81. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

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: Vulkan GPU - Model: blazefaceCompuLab Airtop3GM-10000.2340.4680.7020.9361.17SE +/- 0.00, N = 3SE +/- 0.01, N = 30.611.04MIN: 0.6 / MAX: 0.63MIN: 0.94 / MAX: 1.71. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: blazefaceCompuLab Airtop3GM-1000246810Min: 0.61 / Avg: 0.61 / Max: 0.61Min: 1.01 / Avg: 1.04 / Max: 1.051. (CXX) g++ options: -O3 -rdynamic -lgomp -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 tau100.0CompuLab Airtop3GM-100070140210280350SE +/- 0.58, N = 3SE +/- 1.33, N = 32023441. (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
MinAvgMaxCompuLab Airtop357.076.588.0GM-100061.069.076.0OpenBenchmarking.orgCelsius, Fewer Is BetterMonte Carlo Simulations of Ionised Nebulae 2019-03-24CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.074.875.0OpenBenchmarking.orgCelsius, Fewer Is BetterMonte Carlo Simulations of Ionised Nebulae 2019-03-24System Temperature Monitor20406080100
OpenBenchmarking.orgSeconds, Fewer Is BetterMonte Carlo Simulations of Ionised Nebulae 2019-03-24Input: Dust 2D tau100.0CompuLab Airtop3GM-100060120180240300Min: 201 / Avg: 202 / Max: 203Min: 341 / Avg: 343.67 / Max: 3451. (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

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 CompileCompuLab Airtop3GM-1000306090120150SE +/- 0.08, N = 3SE +/- 0.70, N = 391.59155.40
MinAvgMaxCompuLab Airtop352.073.088.0GM-100060.068.676.0OpenBenchmarking.orgCelsius, Fewer Is BetterTimed GDB GNU Debugger Compilation 9.1CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.072.075.0OpenBenchmarking.orgCelsius, Fewer Is BetterTimed GDB GNU Debugger Compilation 9.1System Temperature Monitor20406080100
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed GDB GNU Debugger Compilation 9.1Time To CompileCompuLab Airtop3GM-1000306090120150Min: 91.45 / Avg: 91.59 / Max: 91.71Min: 154.06 / Avg: 155.39 / Max: 156.42

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: Summer Nature 4KCompuLab Airtop3GM-1000306090120150SE +/- 1.02, N = 3SE +/- 1.39, N = 4157.4192.95MIN: 139.25 / MAX: 172.94MIN: 77.22 / MAX: 122.951. (CC) gcc options: -pthread
MinAvgMaxCompuLab Airtop347.070.682.0GM-100059.068.776.0OpenBenchmarking.orgCelsius, Fewer Is Betterdav1d 0.7.0CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.072.075.0OpenBenchmarking.orgCelsius, Fewer Is Betterdav1d 0.7.0System Temperature Monitor20406080100
OpenBenchmarking.orgFPS, More Is Betterdav1d 0.7.0Video Input: Summer Nature 4KCompuLab Airtop3GM-1000306090120150Min: 155.88 / Avg: 157.41 / Max: 159.33Min: 91.52 / Avg: 92.95 / Max: 97.131. (CC) gcc options: -pthread

OpenBenchmarking.orgFPS, More Is Betterdav1d 0.7.0Video Input: Summer Nature 1080pCompuLab Airtop3GM-1000130260390520650SE +/- 1.68, N = 3SE +/- 0.50, N = 3582.07344.07MIN: 481.99 / MAX: 638.3MIN: 298.25 / MAX: 380.671. (CC) gcc options: -pthread
MinAvgMaxCompuLab Airtop349.069.280.0GM-100059.069.475.0OpenBenchmarking.orgCelsius, Fewer Is Betterdav1d 0.7.0CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.073.175.0OpenBenchmarking.orgCelsius, Fewer Is Betterdav1d 0.7.0System Temperature Monitor20406080100
OpenBenchmarking.orgFPS, More Is Betterdav1d 0.7.0Video Input: Summer Nature 1080pCompuLab Airtop3GM-1000100200300400500Min: 578.72 / Avg: 582.07 / Max: 583.88Min: 343.12 / Avg: 344.07 / Max: 344.81. (CC) gcc options: -pthread

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: SqueezeNetV1.0CompuLab Airtop3GM-10003691215SE +/- 0.007, N = 3SE +/- 0.024, N = 36.58111.117MIN: 6.13 / MAX: 44.44MIN: 9.82 / MAX: 23.661. (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: SqueezeNetV1.0CompuLab Airtop3GM-10003691215Min: 6.57 / Avg: 6.58 / Max: 6.6Min: 11.07 / Avg: 11.12 / Max: 11.151. (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

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 All - Data Type: f32 - Engine: CPUCompuLab Airtop3GM-1000306090120150SE +/- 0.12, N = 3SE +/- 0.53, N = 367.69114.29MIN: 65.58MIN: 99.971. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
MinAvgMaxCompuLab Airtop356.073.388.0GM-100061.068.174.0OpenBenchmarking.orgCelsius, Fewer Is BetteroneDNN 1.5CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.073.875.0OpenBenchmarking.orgCelsius, Fewer Is BetteroneDNN 1.5System Temperature Monitor20406080100
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: IP Batch All - Data Type: f32 - Engine: CPUCompuLab Airtop3GM-100020406080100Min: 67.46 / Avg: 67.69 / Max: 67.88Min: 113.26 / Avg: 114.29 / Max: 1151. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

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 TestCompuLab Airtop3GM-100060120180240300SE +/- 0.53, N = 3SE +/- 2.25, N = 3160.39269.93
MinAvgMaxCompuLab Airtop334.063.074.0GM-100059.068.774.0OpenBenchmarking.orgCelsius, Fewer Is BetterWireGuard + Linux Networking Stack Stress TestCPU Temperature Monitor20406080100
MinAvgMaxGM-100064.071.575.0OpenBenchmarking.orgCelsius, Fewer Is BetterWireGuard + Linux Networking Stack Stress TestSystem Temperature Monitor20406080100
OpenBenchmarking.orgSeconds, Fewer Is BetterWireGuard + Linux Networking Stack Stress TestCompuLab Airtop3GM-100050100150200250Min: 159.4 / Avg: 160.39 / Max: 161.23Min: 266.32 / Avg: 269.93 / Max: 274.07

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: resnet50CompuLab Airtop3GM-10001122334455SE +/- 0.05, N = 3SE +/- 0.19, N = 328.5147.33MIN: 27.85 / MAX: 37.31MIN: 44.74 / MAX: 59.621. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: resnet50CompuLab Airtop3GM-10001020304050Min: 28.46 / Avg: 28.51 / Max: 28.6Min: 47.11 / Avg: 47.33 / Max: 47.711. (CXX) g++ options: -O3 -rdynamic -lgomp -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 TimeCompuLab Airtop3GM-100020406080100SE +/- 0.49, N = 3SE +/- 0.89, N = 345.8475.79
MinAvgMaxCompuLab Airtop356.080.192.0GM-100061.072.277.0OpenBenchmarking.orgCelsius, Fewer Is BetterHuginCPU Temperature Monitor20406080100
MinAvgMaxGM-100064.074.175.0OpenBenchmarking.orgCelsius, Fewer Is BetterHuginSystem Temperature Monitor20406080100
OpenBenchmarking.orgSeconds, Fewer Is BetterHuginPanorama Photo Assistant + Stitching TimeCompuLab Airtop3GM-10001530456075Min: 45.17 / Avg: 45.84 / Max: 46.79Min: 74.1 / Avg: 75.79 / Max: 77.14

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 6.0.16CompuLab Airtop3GM-1000160K320K480K640K800KSE +/- 4773.08, N = 3SE +/- 3781.40, N = 3751370.01458524.511. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
MinAvgMaxCompuLab Airtop350.068.682.0GM-100058.065.373.0OpenBenchmarking.orgCelsius, Fewer Is BetterKeyDB 6.0.16CPU Temperature Monitor20406080100
OpenBenchmarking.orgCelsius, Fewer Is BetterKeyDB 6.0.16System Temperature MonitorGM-1000142842567027.8
OpenBenchmarking.orgOps/sec, More Is BetterKeyDB 6.0.16CompuLab Airtop3GM-1000130K260K390K520K650KMin: 743323.33 / Avg: 751370.01 / Max: 759841.39Min: 454149.5 / Avg: 458524.51 / Max: 466054.441. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

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 AI ScoreCompuLab Airtop3GM-1000500100015002000250022361372
OpenBenchmarking.orgCelsius, Fewer Is BetterAI Benchmark Alpha 0.1.2CPU Temperature MonitorCompuLab Airtop3GM-100020406080100Min: 41 / Avg: 70.68 / Max: 90Min: 58 / Avg: 68.63 / Max: 76
OpenBenchmarking.orgCelsius, Fewer Is BetterAI Benchmark Alpha 0.1.2System Temperature MonitorGM-10001428425670Min: 64 / Avg: 73.64 / Max: 75

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.orgMB/s, More Is BetterLevelDB 1.22Benchmark: Sequential FillCompuLab Airtop3GM-10001224364860SE +/- 0.78, N = 3SE +/- 0.41, N = 552.832.51. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: Sequential FillCompuLab Airtop3GM-10001122334455Min: 51.4 / Avg: 52.77 / Max: 54.1Min: 31.4 / Avg: 32.52 / Max: 33.81. (CXX) g++ options: -O3 -lsnappy -lpthread

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Random ReadCompuLab Airtop3GM-1000246810SE +/- 0.090, N = 15SE +/- 0.022, N = 87.6634.7481. (CXX) g++ options: -O3 -lsnappy -lpthread
MinAvgMaxCompuLab Airtop347.065.377.0GM-100057.063.670.0OpenBenchmarking.orgCelsius, Fewer Is BetterLevelDB 1.22CPU Temperature Monitor20406080100
OpenBenchmarking.orgCelsius, Fewer Is BetterLevelDB 1.22System Temperature MonitorGM-1000142842567027.8
OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Random ReadCompuLab Airtop3GM-10003691215Min: 7.14 / Avg: 7.66 / Max: 8.25Min: 4.65 / Avg: 4.75 / Max: 4.821. (CXX) g++ options: -O3 -lsnappy -lpthread

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: NASNet MobileCompuLab Airtop3GM-100070K140K210K280K350KSE +/- 758.89, N = 3SE +/- 4505.57, N = 4199708321246
MinAvgMaxCompuLab Airtop357.076.791.0GM-100061.069.278.0OpenBenchmarking.orgCelsius, Fewer Is BetterTensorFlow Lite 2020-08-23CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.074.275.0OpenBenchmarking.orgCelsius, Fewer Is BetterTensorFlow Lite 2020-08-23System Temperature Monitor20406080100
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: NASNet MobileCompuLab Airtop3GM-100060K120K180K240K300KMin: 198260 / Avg: 199708 / Max: 200826Min: 307741 / Avg: 321246 / Max: 326227

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: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPUCompuLab Airtop3GM-100050100150200250SE +/- 0.47, N = 3SE +/- 0.93, N = 3143.89231.39MIN: 141.15MIN: 223.491. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
MinAvgMaxCompuLab Airtop356.072.284.0GM-100061.068.376.0OpenBenchmarking.orgCelsius, Fewer Is BetteroneDNN 1.5CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.073.475.0OpenBenchmarking.orgCelsius, Fewer Is BetteroneDNN 1.5System Temperature Monitor20406080100
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPUCompuLab Airtop3GM-10004080120160200Min: 143.25 / Avg: 143.89 / Max: 144.8Min: 229.67 / Avg: 231.39 / Max: 232.851. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -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: mobilenetCompuLab Airtop3GM-1000714212835SE +/- 0.03, N = 3SE +/- 0.17, N = 319.0030.33MIN: 18.81 / MAX: 19.51MIN: 28.89 / MAX: 41.861. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: mobilenetCompuLab Airtop3GM-1000714212835Min: 18.96 / Avg: 19 / Max: 19.06Min: 30.09 / Avg: 30.33 / Max: 30.651. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: alexnetCompuLab Airtop3GM-1000510152025SE +/- 0.08, N = 3SE +/- 0.06, N = 314.2322.53MIN: 14 / MAX: 14.66MIN: 21.39 / MAX: 32.991. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: alexnetCompuLab Airtop3GM-1000510152025Min: 14.07 / Avg: 14.23 / Max: 14.34Min: 22.45 / Avg: 22.53 / Max: 22.661. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: squeezenetCompuLab Airtop3GM-1000612182430SE +/- 0.03, N = 3SE +/- 0.12, N = 316.2025.54MIN: 15.74 / MAX: 23.82MIN: 24.15 / MAX: 35.431. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: squeezenetCompuLab Airtop3GM-1000612182430Min: 16.15 / Avg: 16.2 / Max: 16.25Min: 25.33 / Avg: 25.54 / Max: 25.761. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

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.orgMB/s, More Is BetterLevelDB 1.22Benchmark: Random FillCompuLab Airtop3GM-10001122334455SE +/- 0.44, N = 15SE +/- 0.32, N = 1549.031.11. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: Random FillCompuLab Airtop3GM-10001020304050Min: 46.5 / Avg: 48.95 / Max: 50.9Min: 29.5 / Avg: 31.1 / Max: 32.51. (CXX) g++ options: -O3 -lsnappy -lpthread

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 TimeCompuLab Airtop3GM-100020406080100SE +/- 0.51, N = 3SE +/- 1.25, N = 360.8395.481. RawTherapee, version 5.8, command line.
MinAvgMaxCompuLab Airtop351.076.788.0GM-100060.069.977.0OpenBenchmarking.orgCelsius, Fewer Is BetterRawTherapeeCPU Temperature Monitor20406080100
MinAvgMaxGM-100064.074.475.0OpenBenchmarking.orgCelsius, Fewer Is BetterRawTherapeeSystem Temperature Monitor20406080100
OpenBenchmarking.orgSeconds, Fewer Is BetterRawTherapeeTotal Benchmark TimeCompuLab Airtop3GM-100020406080100Min: 59.81 / Avg: 60.83 / Max: 61.38Min: 92.99 / Avg: 95.48 / Max: 96.861. RawTherapee, version 5.8, command line.

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.orgMB/s, More Is BetterLevelDB 1.22Benchmark: OverwriteCompuLab Airtop3GM-10001122334455SE +/- 0.41, N = 15SE +/- 0.26, N = 1548.330.81. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: OverwriteCompuLab Airtop3GM-10001020304050Min: 46.5 / Avg: 48.27 / Max: 50.8Min: 29.4 / Avg: 30.77 / Max: 32.41. (CXX) g++ options: -O3 -lsnappy -lpthread

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: resnet18CompuLab Airtop3GM-1000612182430SE +/- 0.22, N = 3SE +/- 0.04, N = 315.1923.56MIN: 14.53 / MAX: 15.97MIN: 21.32 / MAX: 35.121. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: resnet18CompuLab Airtop3GM-1000612182430Min: 14.75 / Avg: 15.19 / Max: 15.42Min: 23.5 / Avg: 23.56 / Max: 23.631. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

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 BenchmarkCompuLab Airtop3GM-10000.18430.36860.55290.73720.9215SE +/- 0.002, N = 3SE +/- 0.001, N = 30.8190.5331. (CXX) g++ options: -O3 -pthread -lrt -lpthread -lm
MinAvgMaxCompuLab Airtop353.072.289.0GM-100058.067.577.0OpenBenchmarking.orgCelsius, Fewer Is BetterGROMACS 2020.3CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.067.775.0OpenBenchmarking.orgCelsius, Fewer Is BetterGROMACS 2020.3System Temperature Monitor20406080100
OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2020.3Water BenchmarkCompuLab Airtop3GM-1000246810Min: 0.82 / Avg: 0.82 / Max: 0.82Min: 0.53 / Avg: 0.53 / Max: 0.541. (CXX) g++ options: -O3 -pthread -lrt -lpthread -lm

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 CompileCompuLab Airtop3GM-1000714212835SE +/- 0.03, N = 3SE +/- 0.35, N = 720.9132.12
MinAvgMaxCompuLab Airtop352.071.285.0GM-100060.069.276.0OpenBenchmarking.orgCelsius, Fewer Is BetterTimed Apache Compilation 2.4.41CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.072.675.0OpenBenchmarking.orgCelsius, Fewer Is BetterTimed Apache Compilation 2.4.41System Temperature Monitor20406080100
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Apache Compilation 2.4.41Time To CompileCompuLab Airtop3GM-1000714212835Min: 20.86 / Avg: 20.91 / Max: 20.95Min: 30 / Avg: 32.12 / Max: 32.56

Mlpack Benchmark

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

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_icaCompuLab Airtop3GM-10001428425670SE +/- 0.52, N = 3SE +/- 1.11, N = 342.1464.72
MinAvgMaxCompuLab Airtop351.076.486.0GM-100060.068.876.0OpenBenchmarking.orgCelsius, Fewer Is BetterMlpack BenchmarkCPU Temperature Monitor20406080100
MinAvgMaxGM-100064.073.875.0OpenBenchmarking.orgCelsius, Fewer Is BetterMlpack BenchmarkSystem Temperature Monitor20406080100
OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_icaCompuLab Airtop3GM-10001326395265Min: 41.12 / Avg: 42.14 / Max: 42.8Min: 62.5 / Avg: 64.72 / Max: 65.89

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 0CompuLab Airtop3GM-1000246810SE +/- 0.02, N = 3SE +/- 0.03, N = 37.775.091. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=c++11
MinAvgMaxCompuLab Airtop356.082.890.0GM-100061.071.178.0OpenBenchmarking.orgCelsius, Fewer Is BetterVP9 libvpx Encoding 1.8.2CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.074.675.0OpenBenchmarking.orgCelsius, Fewer Is BetterVP9 libvpx Encoding 1.8.2System Temperature Monitor20406080100
OpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.8.2Speed: Speed 0CompuLab Airtop3GM-10003691215Min: 7.73 / Avg: 7.77 / Max: 7.8Min: 5.05 / Avg: 5.09 / Max: 5.151. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=c++11

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 Training ScoreCompuLab Airtop3GM-100020040060080010001108732

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 1080p 10-bitCompuLab Airtop3GM-1000306090120150SE +/- 0.05, N = 3SE +/- 0.61, N = 3114.5876.17MIN: 72.92 / MAX: 273.76MIN: 47.76 / MAX: 187.81. (CC) gcc options: -pthread
OpenBenchmarking.orgCelsius, Fewer Is Betterdav1d 0.7.0CPU Temperature MonitorCompuLab Airtop3GM-10001632486480Min: 49 / Avg: 70.26 / Max: 84Min: 59 / Avg: 69.19 / Max: 74
OpenBenchmarking.orgCelsius, Fewer Is Betterdav1d 0.7.0System Temperature MonitorGM-10001428425670Min: 64 / Avg: 71.18 / Max: 75
OpenBenchmarking.orgFPS, More Is Betterdav1d 0.7.0Video Input: Chimera 1080p 10-bitCompuLab Airtop3GM-100020406080100Min: 114.51 / Avg: 114.58 / Max: 114.69Min: 75.47 / Avg: 76.17 / Max: 77.381. (CC) gcc options: -pthread

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: yolov4-tinyCompuLab Airtop3GM-10001020304050SE +/- 0.19, N = 3SE +/- 0.16, N = 329.0643.08MIN: 28.14 / MAX: 101.73MIN: 41.28 / MAX: 53.541. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
MinAvgMaxCompuLab Airtop356.075.286.0GM-100061.069.178.0OpenBenchmarking.orgCelsius, Fewer Is BetterNCNN 20200916CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.074.475.0OpenBenchmarking.orgCelsius, Fewer Is BetterNCNN 20200916System Temperature Monitor20406080100
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: yolov4-tinyCompuLab Airtop3GM-1000918273645Min: 28.68 / Avg: 29.06 / Max: 29.27Min: 42.84 / Avg: 43.08 / Max: 43.391. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

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 Fill SyncCompuLab Airtop3GM-10007001400210028003500SE +/- 4.06, N = 3SE +/- 40.71, N = 15234434731. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
MinAvgMaxCompuLab Airtop346.049.955.0GM-100055.057.662.0OpenBenchmarking.orgCelsius, Fewer Is BetterFacebook RocksDB 6.3.6CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.064.765.0OpenBenchmarking.orgCelsius, Fewer Is BetterFacebook RocksDB 6.3.6System Temperature Monitor20406080100
OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.3.6Test: Random Fill SyncCompuLab Airtop3GM-10006001200180024003000Min: 2337 / Avg: 2344.33 / Max: 2351Min: 3180 / Avg: 3472.73 / Max: 37601. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread

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 5CompuLab Airtop3GM-1000714212835SE +/- 0.15, N = 3SE +/- 0.20, N = 828.6119.651. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=c++11
MinAvgMaxCompuLab Airtop357.078.488.0GM-100061.070.877.0OpenBenchmarking.orgCelsius, Fewer Is BetterVP9 libvpx Encoding 1.8.2CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.073.675.0OpenBenchmarking.orgCelsius, Fewer Is BetterVP9 libvpx Encoding 1.8.2System Temperature Monitor20406080100
OpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.8.2Speed: Speed 5CompuLab Airtop3GM-1000612182430Min: 28.32 / Avg: 28.61 / Max: 28.81Min: 19.38 / Avg: 19.65 / Max: 21.021. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=c++11

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: FastCompuLab Airtop3GM-1000246810SE +/- 0.00, N = 7SE +/- 0.01, N = 65.537.931. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread
MinAvgMaxCompuLab Airtop341.056.377.0GM-100058.066.275.0OpenBenchmarking.orgCelsius, Fewer Is BetterASTC Encoder 2.0CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.067.475.0OpenBenchmarking.orgCelsius, Fewer Is BetterASTC Encoder 2.0System Temperature Monitor20406080100
OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.0Preset: FastCompuLab Airtop3GM-10003691215Min: 5.51 / Avg: 5.53 / Max: 5.54Min: 7.9 / Avg: 7.93 / Max: 7.981. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread

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: inception-v3CompuLab Airtop3GM-10001428425670SE +/- 0.09, N = 3SE +/- 0.28, N = 344.4463.68MIN: 43.87 / MAX: 110.57MIN: 58.94 / MAX: 77.621. (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
MinAvgMaxCompuLab Airtop357.075.694.0GM-100061.069.180.0OpenBenchmarking.orgCelsius, Fewer Is BetterMobile Neural Network 2020-09-17CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.074.775.0OpenBenchmarking.orgCelsius, Fewer Is BetterMobile Neural Network 2020-09-17System Temperature Monitor20406080100
OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2020-09-17Model: inception-v3CompuLab Airtop3GM-10001224364860Min: 44.29 / Avg: 44.44 / Max: 44.61Min: 63.13 / Avg: 63.68 / Max: 63.971. (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

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 ReadCompuLab Airtop3GM-1000246810SE +/- 0.037, N = 6SE +/- 0.045, N = 156.8364.8541. (CXX) g++ options: -O3 -lsnappy -lpthread
MinAvgMaxCompuLab Airtop353.069.782.0GM-100059.066.372.0OpenBenchmarking.orgCelsius, Fewer Is BetterLevelDB 1.22CPU Temperature Monitor20406080100
OpenBenchmarking.orgCelsius, Fewer Is BetterLevelDB 1.22System Temperature MonitorGM-1000142842567027.8
OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Hot ReadCompuLab Airtop3GM-10003691215Min: 6.73 / Avg: 6.84 / Max: 7Min: 4.59 / Avg: 4.85 / Max: 5.131. (CXX) g++ options: -O3 -lsnappy -lpthread

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 SynthesisCompuLab Airtop3GM-1000816243240SE +/- 0.13, N = 4SE +/- 0.19, N = 423.7133.381. (CC) gcc options: -O2 -std=c99
MinAvgMaxCompuLab Airtop349.070.777.0GM-100059.068.671.0OpenBenchmarking.orgCelsius, Fewer Is BettereSpeak-NG Speech Engine 20200907CPU Temperature Monitor20406080100
OpenBenchmarking.orgCelsius, Fewer Is BettereSpeak-NG Speech Engine 20200907System Temperature MonitorGM-1000142842567027.8
OpenBenchmarking.orgSeconds, Fewer Is BettereSpeak-NG Speech Engine 20200907Text-To-Speech SynthesisCompuLab Airtop3GM-1000714212835Min: 23.33 / Avg: 23.71 / Max: 23.92Min: 32.84 / Avg: 33.38 / Max: 33.671. (CC) gcc options: -O2 -std=c99

Mlpack Benchmark

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

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_qdaCompuLab Airtop3GM-100020406080100SE +/- 0.23, N = 3SE +/- 0.01, N = 362.6887.81
MinAvgMaxCompuLab Airtop353.071.184.0GM-100061.069.276.0OpenBenchmarking.orgCelsius, Fewer Is BetterMlpack BenchmarkCPU Temperature Monitor20406080100
MinAvgMaxGM-100064.073.075.0OpenBenchmarking.orgCelsius, Fewer Is BetterMlpack BenchmarkSystem Temperature Monitor20406080100
OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_qdaCompuLab Airtop3GM-100020406080100Min: 62.34 / Avg: 62.68 / Max: 63.13Min: 87.8 / Avg: 87.81 / Max: 87.82

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 ProteinCompuLab Airtop3GM-1000246810SE +/- 0.062, N = 10SE +/- 0.047, N = 156.7864.8701. (CXX) g++ options: -O3 -pthread -lm
MinAvgMaxCompuLab Airtop359.071.191.0GM-100062.068.578.0OpenBenchmarking.orgCelsius, Fewer Is BetterLAMMPS Molecular Dynamics Simulator 24Aug2020CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.069.375.0OpenBenchmarking.orgCelsius, Fewer Is BetterLAMMPS Molecular Dynamics Simulator 24Aug2020System Temperature Monitor20406080100
OpenBenchmarking.orgns/day, More Is BetterLAMMPS Molecular Dynamics Simulator 24Aug2020Model: Rhodopsin ProteinCompuLab Airtop3GM-10003691215Min: 6.38 / Avg: 6.79 / Max: 6.96Min: 4.71 / Avg: 4.87 / Max: 5.131. (CXX) g++ options: -O3 -pthread -lm

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: ReactorCompuLab Airtop3GM-100060120180240300SE +/- 2.24, N = 12SE +/- 3.29, N = 3196.07271.43
OpenBenchmarking.orgCelsius, Fewer Is BetterJava Gradle BuildCPU Temperature MonitorCompuLab Airtop3GM-100020406080100Min: 48 / Avg: 75.61 / Max: 88Min: 59 / Avg: 70.57 / Max: 76
OpenBenchmarking.orgCelsius, Fewer Is BetterJava Gradle BuildSystem Temperature MonitorGM-10001428425670Min: 64 / Avg: 73.2 / Max: 75
OpenBenchmarking.orgSeconds, Fewer Is BetterJava Gradle BuildGradle Build: ReactorCompuLab Airtop3GM-100050100150200250Min: 187.44 / Avg: 196.07 / Max: 215.73Min: 267.43 / Avg: 271.43 / Max: 277.96

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 FillCompuLab Airtop3GM-1000200K400K600K800K1000KSE +/- 7973.52, N = 3SE +/- 7757.34, N = 58717386347391. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
MinAvgMaxCompuLab Airtop351.071.483.0GM-100061.069.176.0OpenBenchmarking.orgCelsius, Fewer Is BetterFacebook RocksDB 6.3.6CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.071.475.0OpenBenchmarking.orgCelsius, Fewer Is BetterFacebook RocksDB 6.3.6System Temperature Monitor20406080100
OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.3.6Test: Random FillCompuLab Airtop3GM-1000150K300K450K600K750KMin: 860466 / Avg: 871737.67 / Max: 887143Min: 614178 / Avg: 634738.6 / Max: 6585481. (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: pickle_pure_pythonCompuLab Airtop3GM-1000100200300400500SE +/- 2.73, N = 3339462
MinAvgMaxCompuLab Airtop341.061.469.0GM-100057.067.171.0OpenBenchmarking.orgCelsius, Fewer Is BetterPyPerformance 1.0.0CPU Temperature Monitor20406080100
OpenBenchmarking.orgCelsius, Fewer Is BetterPyPerformance 1.0.0System Temperature MonitorGM-1000142842567027.8
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: pickle_pure_pythonCompuLab Airtop3GM-100080160240320400Min: 457 / Avg: 462.33 / Max: 466

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: chaosCompuLab Airtop3GM-1000306090120150SE +/- 0.06, N = 3SE +/- 1.00, N = 385.9117.0
MinAvgMaxCompuLab Airtop349.072.479.0GM-100058.067.672.0OpenBenchmarking.orgCelsius, Fewer Is BetterPyPerformance 1.0.0CPU Temperature Monitor20406080100
OpenBenchmarking.orgCelsius, Fewer Is BetterPyPerformance 1.0.0System Temperature MonitorGM-1000142842567027.8
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: chaosCompuLab Airtop3GM-100020406080100Min: 85.8 / Avg: 85.9 / Max: 86Min: 115 / Avg: 117 / Max: 118

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: floatCompuLab Airtop3GM-1000306090120150SE +/- 0.06, N = 389.9122.0
MinAvgMaxCompuLab Airtop347.069.576.0GM-100057.067.072.0OpenBenchmarking.orgCelsius, Fewer Is BetterPyPerformance 1.0.0CPU Temperature Monitor20406080100
OpenBenchmarking.orgCelsius, Fewer Is BetterPyPerformance 1.0.0System Temperature MonitorGM-1000142842567027.8
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: floatCompuLab Airtop3GM-100020406080100Min: 89.8 / Avg: 89.9 / Max: 90

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 PNGCompuLab Airtop3GM-1000612182430SE +/- 0.06, N = 3SE +/- 0.42, N = 318.2224.631. rsvg-convert version 2.50.1
MinAvgMaxCompuLab Airtop353.068.477.0GM-100061.069.073.0OpenBenchmarking.orgCelsius, Fewer Is BetterlibrsvgCPU Temperature Monitor20406080100
MinAvgMaxGM-100064.069.875.0OpenBenchmarking.orgCelsius, Fewer Is BetterlibrsvgSystem Temperature Monitor20406080100
OpenBenchmarking.orgSeconds, Fewer Is BetterlibrsvgOperation: SVG Files To PNGCompuLab Airtop3GM-1000612182430Min: 18.15 / Avg: 18.22 / Max: 18.34Min: 24.21 / Avg: 24.63 / Max: 25.481. rsvg-convert version 2.50.1

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: crypto_pyaesCompuLab Airtop3GM-1000306090120150SE +/- 0.03, N = 3SE +/- 0.33, N = 385.9116.0
MinAvgMaxCompuLab Airtop343.065.973.0GM-100057.066.070.0OpenBenchmarking.orgCelsius, Fewer Is BetterPyPerformance 1.0.0CPU Temperature Monitor20406080100
OpenBenchmarking.orgCelsius, Fewer Is BetterPyPerformance 1.0.0System Temperature MonitorGM-1000142842567027.8
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: crypto_pyaesCompuLab Airtop3GM-100020406080100Min: 85.8 / Avg: 85.87 / Max: 85.9Min: 115 / Avg: 115.67 / Max: 116

WebP Image Encode

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

OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100, Lossless, Highest CompressionCompuLab Airtop3GM-10001122334455SE +/- 0.10, N = 3SE +/- 0.09, N = 334.8046.981. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff
MinAvgMaxCompuLab Airtop349.068.879.0GM-100059.070.376.0OpenBenchmarking.orgCelsius, Fewer Is BetterWebP Image Encode 1.1CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.067.975.0OpenBenchmarking.orgCelsius, Fewer Is BetterWebP Image Encode 1.1System Temperature Monitor20406080100
OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100, Lossless, Highest CompressionCompuLab Airtop3GM-10001020304050Min: 34.6 / Avg: 34.8 / Max: 34.92Min: 46.81 / Avg: 46.98 / Max: 47.091. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff

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: goCompuLab Airtop3GM-100060120180240300SE +/- 1.67, N = 3200270
MinAvgMaxCompuLab Airtop353.076.684.0GM-100059.065.573.0OpenBenchmarking.orgCelsius, Fewer Is BetterPyPerformance 1.0.0CPU Temperature Monitor20406080100
OpenBenchmarking.orgCelsius, Fewer Is BetterPyPerformance 1.0.0System Temperature MonitorGM-1000142842567027.8
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: goCompuLab Airtop3GM-100050100150200250Min: 267 / Avg: 270.33 / Max: 272

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: pathlibCompuLab Airtop3GM-1000510152025SE +/- 0.00, N = 3SE +/- 0.00, N = 314.319.3
MinAvgMaxCompuLab Airtop345.064.870.0GM-100057.068.471.0OpenBenchmarking.orgCelsius, Fewer Is BetterPyPerformance 1.0.0CPU Temperature Monitor20406080100
OpenBenchmarking.orgCelsius, Fewer Is BetterPyPerformance 1.0.0System Temperature MonitorGM-1000142842567027.8
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: pathlibCompuLab Airtop3GM-1000510152025Min: 14.3 / Avg: 14.3 / Max: 14.3Min: 19.3 / Avg: 19.3 / Max: 19.3

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 OnlyCompuLab Airtop3GM-10007K14K21K28K35KSE +/- 56.86, N = 3SE +/- 159.81, N = 333554248621. (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 OnlyCompuLab Airtop3GM-10006K12K18K24K30KMin: 33469.39 / Avg: 33553.89 / Max: 33662.04Min: 24664.47 / Avg: 24861.59 / Max: 25178.041. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

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 2020-06-28CompuLab Airtop3GM-1000714212835SE +/- 0.01, N = 3SE +/- 0.17, N = 321.5829.101. (CC) gcc options: -O2 -pedantic -fvisibility=hidden
MinAvgMaxCompuLab Airtop347.065.671.0GM-100058.068.070.0OpenBenchmarking.orgCelsius, Fewer Is BetterRNNoise 2020-06-28CPU Temperature Monitor20406080100
OpenBenchmarking.orgCelsius, Fewer Is BetterRNNoise 2020-06-28System Temperature MonitorGM-1000142842567027.8
OpenBenchmarking.orgSeconds, Fewer Is BetterRNNoise 2020-06-28CompuLab Airtop3GM-1000612182430Min: 21.56 / Avg: 21.58 / Max: 21.6Min: 28.92 / Avg: 29.1 / Max: 29.441. (CC) gcc options: -O2 -pedantic -fvisibility=hidden

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: regex_compileCompuLab Airtop3GM-10004080120160200SE +/- 0.58, N = 3138186
MinAvgMaxCompuLab Airtop342.063.470.0GM-100057.067.571.0OpenBenchmarking.orgCelsius, Fewer Is BetterPyPerformance 1.0.0CPU Temperature Monitor20406080100
OpenBenchmarking.orgCelsius, Fewer Is BetterPyPerformance 1.0.0System Temperature MonitorGM-1000142842567027.8
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: regex_compileCompuLab Airtop3GM-1000306090120150Min: 185 / Avg: 186 / Max: 187

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: Sequential FillCompuLab Airtop3GM-1000300K600K900K1200K1500KSE +/- 12373.00, N = 15SE +/- 13114.25, N = 1513215669810911. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
MinAvgMaxCompuLab Airtop354.072.484.0GM-100062.068.877.0OpenBenchmarking.orgCelsius, Fewer Is BetterFacebook RocksDB 6.3.6CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.071.176.0OpenBenchmarking.orgCelsius, Fewer Is BetterFacebook RocksDB 6.3.6System Temperature Monitor20406080100
OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.3.6Test: Sequential FillCompuLab Airtop3GM-1000200K400K600K800K1000KMin: 1225560 / Avg: 1321566.27 / Max: 1423159Min: 882368 / Avg: 981090.53 / Max: 10736091. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -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: SqueezeNet v1.1CompuLab Airtop3GM-100080160240320400SE +/- 0.04, N = 3SE +/- 0.13, N = 3269.28362.13MIN: 268.32 / MAX: 274.07MIN: 361.7 / MAX: 362.71. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -O3 -rdynamic -ldl
MinAvgMaxCompuLab Airtop349.065.576.0GM-100060.069.974.0OpenBenchmarking.orgCelsius, Fewer Is BetterTNN 0.2.3CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.071.575.0OpenBenchmarking.orgCelsius, Fewer Is BetterTNN 0.2.3System Temperature Monitor20406080100
OpenBenchmarking.orgms, Fewer Is BetterTNN 0.2.3Target: CPU - Model: SqueezeNet v1.1CompuLab Airtop3GM-100060120180240300Min: 269.21 / Avg: 269.28 / Max: 269.34Min: 361.9 / Avg: 362.13 / Max: 362.351. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -O3 -rdynamic -ldl

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: django_templateCompuLab Airtop3GM-10001224364860SE +/- 0.06, N = 3SE +/- 0.15, N = 338.952.3
MinAvgMaxCompuLab Airtop340.062.467.0GM-100057.067.070.0OpenBenchmarking.orgCelsius, Fewer Is BetterPyPerformance 1.0.0CPU Temperature Monitor20406080100
OpenBenchmarking.orgCelsius, Fewer Is BetterPyPerformance 1.0.0System Temperature MonitorGM-1000142842567027.8
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: django_templateCompuLab Airtop3GM-10001020304050Min: 38.8 / Avg: 38.9 / Max: 39Min: 52.1 / Avg: 52.3 / Max: 52.6

WebP Image Encode

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

OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100, Highest CompressionCompuLab Airtop3GM-1000246810SE +/- 0.006, N = 6SE +/- 0.007, N = 56.3808.5721. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff
MinAvgMaxCompuLab Airtop350.065.676.0GM-100059.066.671.0OpenBenchmarking.orgCelsius, Fewer Is BetterWebP Image Encode 1.1CPU Temperature Monitor20406080100
OpenBenchmarking.orgCelsius, Fewer Is BetterWebP Image Encode 1.1System Temperature MonitorGM-1000142842567027.8
OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100, Highest CompressionCompuLab Airtop3GM-10003691215Min: 6.37 / Avg: 6.38 / Max: 6.41Min: 8.55 / Avg: 8.57 / Max: 8.581. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff

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: raytraceCompuLab Airtop3GM-1000110220330440550SE +/- 0.67, N = 3376505
MinAvgMaxCompuLab Airtop344.066.474.0GM-100057.070.273.0OpenBenchmarking.orgCelsius, Fewer Is BetterPyPerformance 1.0.0CPU Temperature Monitor20406080100
OpenBenchmarking.orgCelsius, Fewer Is BetterPyPerformance 1.0.0System Temperature MonitorGM-1000142842567027.8
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: raytraceCompuLab Airtop3GM-100090180270360450Min: 504 / Avg: 505.33 / Max: 506

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 2CompuLab Airtop3GM-100010M20M30M40M50MSE +/- 180310.11, N = 3SE +/- 15338.08, N = 348614938.036200967.7
MinAvgMaxCompuLab Airtop344.059.878.0GM-100057.064.674.0OpenBenchmarking.orgCelsius, Fewer Is BetterBYTE Unix Benchmark 3.6CPU Temperature Monitor20406080100
OpenBenchmarking.orgCelsius, Fewer Is BetterBYTE Unix Benchmark 3.6System Temperature MonitorGM-1000142842567027.8
OpenBenchmarking.orgLPS, More Is BetterBYTE Unix Benchmark 3.6Computational Test: Dhrystone 2CompuLab Airtop3GM-10008M16M24M32M40MMin: 48269766.5 / Avg: 48614938 / Max: 48877954.3Min: 36181160.5 / Avg: 36200967.7 / Max: 36231157.4

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 CommandsCompuLab Airtop3GM-10001428425670SE +/- 0.08, N = 3SE +/- 0.41, N = 344.9760.371. git version 2.27.0
MinAvgMaxCompuLab Airtop353.074.579.0GM-100060.070.874.0OpenBenchmarking.orgCelsius, Fewer Is BetterGitCPU Temperature Monitor20406080100
OpenBenchmarking.orgCelsius, Fewer Is BetterGitSystem Temperature MonitorGM-1000142842567027.8
OpenBenchmarking.orgSeconds, Fewer Is BetterGitTime To Complete Common Git CommandsCompuLab Airtop3GM-10001224364860Min: 44.8 / Avg: 44.97 / Max: 45.05Min: 59.56 / Avg: 60.37 / Max: 60.791. git version 2.27.0

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: nbodyCompuLab Airtop3GM-1000306090120150SE +/- 0.33, N = 3103138
MinAvgMaxCompuLab Airtop347.066.875.0GM-100058.067.972.0OpenBenchmarking.orgCelsius, Fewer Is BetterPyPerformance 1.0.0CPU Temperature Monitor20406080100
OpenBenchmarking.orgCelsius, Fewer Is BetterPyPerformance 1.0.0System Temperature MonitorGM-1000142842567027.8
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: nbodyCompuLab Airtop3GM-1000306090120150Min: 138 / Avg: 138.33 / Max: 139

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: DefaultCompuLab Airtop3GM-10000.39580.79161.18741.58321.979SE +/- 0.000, N = 12SE +/- 0.003, N = 111.3131.7591. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff
MinAvgMaxCompuLab Airtop354.060.881.0GM-100060.064.373.0OpenBenchmarking.orgCelsius, Fewer Is BetterWebP Image Encode 1.1CPU Temperature Monitor20406080100
OpenBenchmarking.orgCelsius, Fewer Is BetterWebP Image Encode 1.1System Temperature MonitorGM-1000142842567027.8
OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: DefaultCompuLab Airtop3GM-1000246810Min: 1.31 / Avg: 1.31 / Max: 1.32Min: 1.75 / Avg: 1.76 / Max: 1.781. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff

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 ImagesCompuLab Airtop3GM-1000612182430SE +/- 0.02, N = 3SE +/- 0.02, N = 320.2727.11
MinAvgMaxCompuLab Airtop344.063.573.0GM-100059.069.673.0OpenBenchmarking.orgCelsius, Fewer Is BetterTesseract OCR 4.1.1CPU Temperature Monitor20406080100
OpenBenchmarking.orgCelsius, Fewer Is BetterTesseract OCR 4.1.1System Temperature MonitorGM-1000142842567027.8
OpenBenchmarking.orgSeconds, Fewer Is BetterTesseract OCR 4.1.1Time To OCR 7 ImagesCompuLab Airtop3GM-1000612182430Min: 20.24 / Avg: 20.27 / Max: 20.3Min: 27.06 / Avg: 27.11 / Max: 27.13

WebP Image Encode

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

OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100CompuLab Airtop3GM-10000.62551.2511.87652.5023.1275SE +/- 0.002, N = 10SE +/- 0.001, N = 92.0822.7801. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff
MinAvgMaxCompuLab Airtop352.060.577.0GM-100059.064.172.0OpenBenchmarking.orgCelsius, Fewer Is BetterWebP Image Encode 1.1CPU Temperature Monitor20406080100
OpenBenchmarking.orgCelsius, Fewer Is BetterWebP Image Encode 1.1System Temperature MonitorGM-1000142842567027.8
OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100CompuLab Airtop3GM-1000246810Min: 2.08 / Avg: 2.08 / Max: 2.09Min: 2.78 / Avg: 2.78 / Max: 2.781. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff

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: Deconvolution Batch deconv_3d - Data Type: f32 - Engine: CPUCompuLab Airtop3GM-1000246810SE +/- 0.02344, N = 9SE +/- 0.08092, N = 156.656408.88371MIN: 6.4MIN: 8.111. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
MinAvgMaxCompuLab Airtop356.069.387.0GM-100061.067.977.0OpenBenchmarking.orgCelsius, Fewer Is BetteroneDNN 1.5CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.068.675.0OpenBenchmarking.orgCelsius, Fewer Is BetteroneDNN 1.5System Temperature Monitor20406080100
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Deconvolution Batch deconv_3d - Data Type: f32 - Engine: CPUCompuLab Airtop3GM-10003691215Min: 6.6 / Avg: 6.66 / Max: 6.82Min: 8.34 / Avg: 8.88 / Max: 9.441. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

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: 2to3CompuLab Airtop3GM-100080160240320400SE +/- 0.67, N = 3264352
MinAvgMaxCompuLab Airtop350.061.178.0GM-100058.067.872.0OpenBenchmarking.orgCelsius, Fewer Is BetterPyPerformance 1.0.0CPU Temperature Monitor20406080100
OpenBenchmarking.orgCelsius, Fewer Is BetterPyPerformance 1.0.0System Temperature MonitorGM-1000142842567027.8
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: 2to3CompuLab Airtop3GM-100060120180240300Min: 263 / Avg: 263.67 / Max: 265

PostgreSQL pgbench

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

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 1 - Clients: 1 - Mode: Read Only - Average LatencyCompuLab Airtop3GM-10000.0090.0180.0270.0360.045SE +/- 0.000, N = 3SE +/- 0.000, N = 30.0300.0401. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
MinAvgMaxCompuLab Airtop354.063.274.0GM-100060.064.570.0OpenBenchmarking.orgCelsius, Fewer Is BetterPostgreSQL pgbench 13.0CPU Temperature Monitor20406080100
OpenBenchmarking.orgCelsius, Fewer Is BetterPostgreSQL pgbench 13.0System Temperature MonitorGM-1000142842567027.8
OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 1 - Clients: 1 - Mode: Read Only - Average LatencyCompuLab Airtop3GM-100012345Min: 0.03 / Avg: 0.03 / Max: 0.03Min: 0.04 / Avg: 0.04 / Max: 0.041. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

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.orgMB/s, More Is BetterLevelDB 1.22Benchmark: Fill SyncCompuLab Airtop3GM-10000.090.180.270.360.45SE +/- 0.00, N = 6SE +/- 0.00, N = 100.30.41. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: Fill SyncCompuLab Airtop3GM-100012345Min: 0.3 / Avg: 0.3 / Max: 0.3Min: 0.4 / Avg: 0.4 / Max: 0.41. (CXX) g++ options: -O3 -lsnappy -lpthread

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 DynamicsCompuLab Airtop3GM-1000510152025SE +/- 0.02, N = 3SE +/- 0.08, N = 316.6822.15
MinAvgMaxCompuLab Airtop359.080.289.0GM-100063.073.877.0OpenBenchmarking.orgCelsius, Fewer Is BetterDolfyn 0.527CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.073.275.0OpenBenchmarking.orgCelsius, Fewer Is BetterDolfyn 0.527System Temperature Monitor20406080100
OpenBenchmarking.orgSeconds, Fewer Is BetterDolfyn 0.527Computational Fluid DynamicsCompuLab Airtop3GM-1000510152025Min: 16.64 / Avg: 16.68 / Max: 16.71Min: 22 / Avg: 22.14 / Max: 22.23

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: json_loadsCompuLab Airtop3GM-1000714212835SE +/- 0.19, N = 3SE +/- 0.03, N = 321.428.4
MinAvgMaxCompuLab Airtop343.063.670.0GM-100057.067.671.0OpenBenchmarking.orgCelsius, Fewer Is BetterPyPerformance 1.0.0CPU Temperature Monitor20406080100
OpenBenchmarking.orgCelsius, Fewer Is BetterPyPerformance 1.0.0System Temperature MonitorGM-1000142842567027.8
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: json_loadsCompuLab Airtop3GM-1000612182430Min: 21.2 / Avg: 21.43 / Max: 21.8Min: 28.4 / Avg: 28.43 / Max: 28.5

WebP Image Encode

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

OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100, LosslessCompuLab Airtop3GM-1000510152025SE +/- 0.00, N = 4SE +/- 0.01, N = 316.0221.201. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff
MinAvgMaxCompuLab Airtop351.065.878.0GM-100059.066.872.0OpenBenchmarking.orgCelsius, Fewer Is BetterWebP Image Encode 1.1CPU Temperature Monitor20406080100
OpenBenchmarking.orgCelsius, Fewer Is BetterWebP Image Encode 1.1System Temperature MonitorGM-1000142842567027.8
OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100, LosslessCompuLab Airtop3GM-1000510152025Min: 16.01 / Avg: 16.02 / Max: 16.03Min: 21.18 / Avg: 21.2 / Max: 21.211. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff

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: python_startupCompuLab Airtop3GM-10003691215SE +/- 0.00, N = 3SE +/- 0.06, N = 36.829.01
MinAvgMaxCompuLab Airtop341.052.660.0GM-100057.065.668.0OpenBenchmarking.orgCelsius, Fewer Is BetterPyPerformance 1.0.0CPU Temperature Monitor20406080100
OpenBenchmarking.orgCelsius, Fewer Is BetterPyPerformance 1.0.0System Temperature MonitorGM-1000142842567027.8
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: python_startupCompuLab Airtop3GM-10003691215Min: 6.82 / Avg: 6.82 / Max: 6.82Min: 8.91 / Avg: 9.01 / Max: 9.13

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: 8CompuLab Airtop3GM-1000246810SE +/- 0.006, N = 7SE +/- 0.014, N = 65.0866.6721. (CXX) g++ options: -O3 -fPIC
MinAvgMaxCompuLab Airtop355.070.895.0GM-100060.069.077.0OpenBenchmarking.orgCelsius, Fewer Is Betterlibavif avifenc 0.7.3CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.066.975.0OpenBenchmarking.orgCelsius, Fewer Is Betterlibavif avifenc 0.7.3System Temperature Monitor20406080100
OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.7.3Encoder Speed: 8CompuLab Airtop3GM-10003691215Min: 5.06 / Avg: 5.09 / Max: 5.1Min: 6.65 / Avg: 6.67 / Max: 6.731. (CXX) g++ options: -O3 -fPIC

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: JythonCompuLab Airtop3GM-100010002000300040005000SE +/- 38.10, N = 7SE +/- 23.71, N = 636894833
MinAvgMaxCompuLab Airtop349.062.278.0GM-100060.067.074.0OpenBenchmarking.orgCelsius, Fewer Is BetterDaCapo Benchmark 9.12-MR1CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.066.675.0OpenBenchmarking.orgCelsius, Fewer Is BetterDaCapo Benchmark 9.12-MR1System Temperature Monitor20406080100
OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: JythonCompuLab Airtop3GM-10008001600240032004000Min: 3592 / Avg: 3689.14 / Max: 3883Min: 4762 / Avg: 4832.5 / Max: 4907

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 SearchCompuLab Airtop3GM-1000306090120150SE +/- 0.10, N = 3SE +/- 0.02, N = 3100.19131.251. (CC) gcc options: -O3 -pthread -lhmmer -leasel -lm
MinAvgMaxCompuLab Airtop352.069.680.0GM-100059.067.872.0OpenBenchmarking.orgCelsius, Fewer Is BetterTimed HMMer Search 3.3.1CPU Temperature Monitor20406080100
OpenBenchmarking.orgCelsius, Fewer Is BetterTimed HMMer Search 3.3.1System Temperature MonitorGM-1000142842567027.8
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed HMMer Search 3.3.1Pfam Database SearchCompuLab Airtop3GM-100020406080100Min: 100.02 / Avg: 100.19 / Max: 100.36Min: 131.21 / Avg: 131.25 / Max: 131.291. (CC) gcc options: -O3 -pthread -lhmmer -leasel -lm

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: FLOATCompuLab Airtop3GM-1000100M200M300M400M500MSE +/- 825158.10, N = 3SE +/- 534147.70, N = 3471438878.81360309999.321. (CC) gcc options: -O3 -march=native -lm
MinAvgMaxCompuLab Airtop343.063.476.0GM-100059.066.669.0OpenBenchmarking.orgCelsius, Fewer Is BetterHierarchical INTegration 1.0CPU Temperature Monitor20406080100
OpenBenchmarking.orgCelsius, Fewer Is BetterHierarchical INTegration 1.0System Temperature MonitorGM-1000142842567027.8
OpenBenchmarking.orgQUIPs, More Is BetterHierarchical INTegration 1.0Test: FLOATCompuLab Airtop3GM-100080M160M240M320M400MMin: 470106259.43 / Avg: 471438878.81 / Max: 472948249.49Min: 359505128.58 / Avg: 360309999.32 / Max: 361320775.571. (CC) gcc options: -O3 -march=native -lm

libavif avifenc

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

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.7.3Encoder Speed: 10CompuLab Airtop3GM-1000246810SE +/- 0.001, N = 8SE +/- 0.007, N = 74.8056.2831. (CXX) g++ options: -O3 -fPIC
MinAvgMaxCompuLab Airtop353.067.588.0GM-100060.067.477.0OpenBenchmarking.orgCelsius, Fewer Is Betterlibavif avifenc 0.7.3CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.066.475.0OpenBenchmarking.orgCelsius, Fewer Is Betterlibavif avifenc 0.7.3System Temperature Monitor20406080100
OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.7.3Encoder Speed: 10CompuLab Airtop3GM-10003691215Min: 4.8 / Avg: 4.81 / Max: 4.81Min: 6.25 / Avg: 6.28 / Max: 6.311. (CXX) g++ options: -O3 -fPIC

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 RNACompuLab Airtop3GM-10003691215SE +/- 0.018, N = 5SE +/- 0.101, N = 118.62811.2681. (CC) gcc options: -std=c99 -O3 -lm -lpthread
MinAvgMaxCompuLab Airtop359.075.991.0GM-100061.070.578.0OpenBenchmarking.orgCelsius, Fewer Is BetterTimed MAFFT Alignment 7.471CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.071.975.0OpenBenchmarking.orgCelsius, Fewer Is BetterTimed MAFFT Alignment 7.471System Temperature Monitor20406080100
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MAFFT Alignment 7.471Multiple Sequence Alignment - LSU RNACompuLab Airtop3GM-10003691215Min: 8.58 / Avg: 8.63 / Max: 8.68Min: 10.64 / Avg: 11.27 / Max: 11.851. (CC) gcc options: -std=c99 -O3 -lm -lpthread

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 BenchmarkCompuLab Airtop3GM-100090180270360450SE +/- 0.95, N = 3SE +/- 0.61, N = 3420.29322.07
MinAvgMaxCompuLab Airtop353.078.487.0GM-100060.072.876.0OpenBenchmarking.orgCelsius, Fewer Is BetterNumpy BenchmarkCPU Temperature Monitor20406080100
MinAvgMaxGM-100064.073.975.0OpenBenchmarking.orgCelsius, Fewer Is BetterNumpy BenchmarkSystem Temperature Monitor20406080100
OpenBenchmarking.orgScore, More Is BetterNumpy BenchmarkCompuLab Airtop3GM-100070140210280350Min: 418.48 / Avg: 420.29 / Max: 421.68Min: 321.05 / Avg: 322.07 / Max: 323.15

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 v2CompuLab Airtop3GM-100080160240320400SE +/- 0.57, N = 3SE +/- 0.15, N = 3283.96369.91MIN: 282.43 / MAX: 316.3MIN: 368.82 / MAX: 373.151. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -O3 -rdynamic -ldl
MinAvgMaxCompuLab Airtop349.070.380.0GM-100059.069.874.0OpenBenchmarking.orgCelsius, Fewer Is BetterTNN 0.2.3CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.066.475.0OpenBenchmarking.orgCelsius, Fewer Is BetterTNN 0.2.3System Temperature Monitor20406080100
OpenBenchmarking.orgms, Fewer Is BetterTNN 0.2.3Target: CPU - Model: MobileNet v2CompuLab Airtop3GM-100070140210280350Min: 283.09 / Avg: 283.96 / Max: 285.04Min: 369.74 / Avg: 369.91 / Max: 370.221. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -O3 -rdynamic -ldl

Mlpack Benchmark

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

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_svmCompuLab Airtop3GM-1000714212835SE +/- 0.01, N = 3SE +/- 0.20, N = 322.4328.93
MinAvgMaxCompuLab Airtop351.067.879.0GM-100061.068.474.0OpenBenchmarking.orgCelsius, Fewer Is BetterMlpack BenchmarkCPU Temperature Monitor20406080100
OpenBenchmarking.orgCelsius, Fewer Is BetterMlpack BenchmarkSystem Temperature MonitorGM-1000142842567027.8
OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_svmCompuLab Airtop3GM-1000612182430Min: 22.42 / Avg: 22.43 / Max: 22.44Min: 28.67 / Avg: 28.93 / Max: 29.31

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: Random DeleteCompuLab Airtop3GM-1000816243240SE +/- 0.21, N = 3SE +/- 0.34, N = 433.7426.191. (CXX) g++ options: -O3 -lsnappy -lpthread
MinAvgMaxCompuLab Airtop352.065.779.0GM-100058.065.072.0OpenBenchmarking.orgCelsius, Fewer Is BetterLevelDB 1.22CPU Temperature Monitor20406080100
OpenBenchmarking.orgCelsius, Fewer Is BetterLevelDB 1.22System Temperature MonitorGM-1000142842567027.8
OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Random DeleteCompuLab Airtop3GM-1000714212835Min: 33.46 / Avg: 33.74 / Max: 34.14Min: 25.66 / Avg: 26.19 / Max: 27.111. (CXX) g++ options: -O3 -lsnappy -lpthread

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-v2-v2 - Model: mobilenet-v2CompuLab Airtop3GM-1000246810SE +/- 0.04, N = 3SE +/- 0.22, N = 35.156.61MIN: 5.01 / MAX: 5.7MIN: 5.61 / MAX: 9.691. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU-v2-v2 - Model: mobilenet-v2CompuLab Airtop3GM-10003691215Min: 5.1 / Avg: 5.15 / Max: 5.23Min: 6.17 / Avg: 6.61 / Max: 6.891. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

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: OverwriteCompuLab Airtop3GM-1000816243240SE +/- 0.31, N = 15SE +/- 0.24, N = 1536.6928.731. (CXX) g++ options: -O3 -lsnappy -lpthread
MinAvgMaxCompuLab Airtop348.055.976.0GM-100057.060.967.0OpenBenchmarking.orgCelsius, Fewer Is BetterLevelDB 1.22CPU Temperature Monitor20406080100
OpenBenchmarking.orgCelsius, Fewer Is BetterLevelDB 1.22System Temperature MonitorGM-1000142842567027.8
OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: OverwriteCompuLab Airtop3GM-1000816243240Min: 34.83 / Avg: 36.69 / Max: 38.01Min: 27.31 / Avg: 28.73 / Max: 30.061. (CXX) g++ options: -O3 -lsnappy -lpthread

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Random FillCompuLab Airtop3GM-1000816243240SE +/- 0.33, N = 15SE +/- 0.30, N = 1536.1828.461. (CXX) g++ options: -O3 -lsnappy -lpthread
MinAvgMaxCompuLab Airtop347.057.277.0GM-100057.060.868.0OpenBenchmarking.orgCelsius, Fewer Is BetterLevelDB 1.22CPU Temperature Monitor20406080100
OpenBenchmarking.orgCelsius, Fewer Is BetterLevelDB 1.22System Temperature MonitorGM-1000142842567027.8
OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Random FillCompuLab Airtop3GM-1000816243240Min: 34.73 / Avg: 36.18 / Max: 38.04Min: 27.23 / Avg: 28.46 / Max: 29.991. (CXX) g++ options: -O3 -lsnappy -lpthread

Mlpack Benchmark

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

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_linearridgeregressionCompuLab Airtop3GM-10000.70651.4132.11952.8263.5325SE +/- 0.03, N = 15SE +/- 0.03, N = 152.473.14
MinAvgMaxCompuLab Airtop346.064.280.0GM-100060.068.176.0OpenBenchmarking.orgCelsius, Fewer Is BetterMlpack BenchmarkCPU Temperature Monitor20406080100
MinAvgMaxGM-100064.064.475.0OpenBenchmarking.orgCelsius, Fewer Is BetterMlpack BenchmarkSystem Temperature Monitor20406080100
OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_linearridgeregressionCompuLab Airtop3GM-1000246810Min: 2.25 / Avg: 2.47 / Max: 2.63Min: 2.97 / Avg: 3.14 / Max: 3.34

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 PerformanceCompuLab Airtop3GM-10002K4K6K8K10K833365781. (CC) gcc options: -O3
MinAvgMaxCompuLab Airtop343.060.065.0GM-100049.059.262.0OpenBenchmarking.orgCelsius, Fewer Is BetterPostMark 1.51CPU Temperature Monitor20406080100
OpenBenchmarking.orgCelsius, Fewer Is BetterPostMark 1.51System Temperature MonitorGM-1000122436486027.8

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: vgg16CompuLab Airtop3GM-100020406080100SE +/- 0.08, N = 3SE +/- 0.13, N = 366.2883.07MIN: 65.89 / MAX: 74.14MIN: 81.47 / MAX: 93.061. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: vgg16CompuLab Airtop3GM-10001632486480Min: 66.12 / Avg: 66.28 / Max: 66.39Min: 82.81 / Avg: 83.07 / Max: 83.241. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

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: GoogleNet - Acceleration: CPU - Iterations: 200CompuLab Airtop3GM-100050K100K150K200K250KSE +/- 196.94, N = 3SE +/- 2728.74, N = 32066222553191. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas
MinAvgMaxCompuLab Airtop357.075.993.0GM-100062.069.278.0OpenBenchmarking.orgCelsius, Fewer Is BetterCaffe 2020-02-13CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.074.875.0OpenBenchmarking.orgCelsius, Fewer Is BetterCaffe 2020-02-13System Temperature Monitor20406080100
OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: GoogleNet - Acceleration: CPU - Iterations: 200CompuLab Airtop3GM-100040K80K120K160K200KMin: 206248 / Avg: 206622 / Max: 206916Min: 250680 / Avg: 255318.67 / Max: 2601281. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

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 5.2.0CompuLab Airtop3GM-1000246810SE +/- 0.020, N = 6SE +/- 0.022, N = 66.4858.007
MinAvgMaxCompuLab Airtop353.066.683.0GM-100061.067.374.0OpenBenchmarking.orgCelsius, Fewer Is BetterGNU Octave Benchmark 5.2.0CPU Temperature Monitor20406080100
OpenBenchmarking.orgCelsius, Fewer Is BetterGNU Octave Benchmark 5.2.0System Temperature MonitorGM-1000142842567027.8
OpenBenchmarking.orgSeconds, Fewer Is BetterGNU Octave Benchmark 5.2.0CompuLab Airtop3GM-10003691215Min: 6.46 / Avg: 6.49 / Max: 6.58Min: 7.98 / Avg: 8.01 / Max: 8.12

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: Sequential FillCompuLab Airtop3GM-1000816243240SE +/- 0.49, N = 3SE +/- 0.33, N = 533.5527.201. (CXX) g++ options: -O3 -lsnappy -lpthread
MinAvgMaxCompuLab Airtop351.066.781.0GM-100058.064.970.0OpenBenchmarking.orgCelsius, Fewer Is BetterLevelDB 1.22CPU Temperature Monitor20406080100
OpenBenchmarking.orgCelsius, Fewer Is BetterLevelDB 1.22System Temperature MonitorGM-1000142842567027.8
OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Sequential FillCompuLab Airtop3GM-1000714212835Min: 32.71 / Avg: 33.55 / Max: 34.4Min: 26.18 / Avg: 27.2 / Max: 28.141. (CXX) g++ options: -O3 -lsnappy -lpthread

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: GoogleNet - Acceleration: CPU - Iterations: 100CompuLab Airtop3GM-100030K60K90K120K150KSE +/- 164.54, N = 3SE +/- 87.22, N = 31028691261401. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas
MinAvgMaxCompuLab Airtop355.074.792.0GM-100061.069.178.0OpenBenchmarking.orgCelsius, Fewer Is BetterCaffe 2020-02-13CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.074.675.0OpenBenchmarking.orgCelsius, Fewer Is BetterCaffe 2020-02-13System Temperature Monitor20406080100
OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: GoogleNet - Acceleration: CPU - Iterations: 100CompuLab Airtop3GM-100020K40K60K80K100KMin: 102554 / Avg: 102869 / Max: 103109Min: 126011 / Avg: 126139.67 / Max: 1263061. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

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 BenchmarkCompuLab Airtop3GM-1000816243240SE +/- 0.10, N = 3SE +/- 0.32, N = 333.3527.261. (CXX) g++ options: -O2 -fopenmp -ljpeg -lz -lm
MinAvgMaxCompuLab Airtop350.074.482.0GM-100059.069.974.0OpenBenchmarking.orgCelsius, Fewer Is BetterLibRaw 0.20CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.069.675.0OpenBenchmarking.orgCelsius, Fewer Is BetterLibRaw 0.20System Temperature Monitor20406080100
OpenBenchmarking.orgMpix/sec, More Is BetterLibRaw 0.20Post-Processing BenchmarkCompuLab Airtop3GM-1000714212835Min: 33.14 / Avg: 33.35 / Max: 33.46Min: 26.9 / Avg: 27.26 / Max: 27.91. (CXX) g++ options: -O2 -fopenmp -ljpeg -lz -lm

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: 3CompuLab Airtop3GM-10008001600240032004000SE +/- 2.03, N = 3SE +/- 4.91, N = 32955.53601.71. (CC) gcc options: -O3 -pthread -lz -llzma
MinAvgMaxCompuLab Airtop344.059.872.0GM-100057.066.473.0OpenBenchmarking.orgCelsius, Fewer Is BetterZstd Compression 1.4.5CPU Temperature Monitor20406080100
OpenBenchmarking.orgCelsius, Fewer Is BetterZstd Compression 1.4.5System Temperature MonitorGM-1000142842567027.8
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.5Compression Level: 3CompuLab Airtop3GM-10006001200180024003000Min: 2953.1 / Avg: 2955.47 / Max: 2959.5Min: 3596 / Avg: 3601.73 / Max: 3611.51. (CC) gcc options: -O3 -pthread -lz -llzma

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: resnet-v2-50CompuLab Airtop3GM-10001224364860SE +/- 0.04, N = 3SE +/- 0.24, N = 342.5851.89MIN: 42.1 / MAX: 110.22MIN: 48.29 / MAX: 64.911. (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-v2-50CompuLab Airtop3GM-10001020304050Min: 42.5 / Avg: 42.58 / Max: 42.65Min: 51.41 / Avg: 51.89 / Max: 52.151. (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

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: 50 - Mode: Read WriteCompuLab Airtop3GM-1000160320480640800SE +/- 1.80, N = 3SE +/- 3.31, N = 35977261. (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 WriteCompuLab Airtop3GM-1000130260390520650Min: 594.62 / Avg: 597.23 / Max: 600.7Min: 721.69 / Avg: 725.84 / Max: 732.381. (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 LatencyCompuLab Airtop3GM-100020406080100SE +/- 0.25, N = 3SE +/- 0.31, N = 383.7368.901. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
MinAvgMaxCompuLab Airtop342.043.746.0GM-100058.059.060.0OpenBenchmarking.orgCelsius, Fewer Is BetterPostgreSQL pgbench 13.0CPU Temperature Monitor1632486480
OpenBenchmarking.orgCelsius, Fewer Is BetterPostgreSQL pgbench 13.0System Temperature MonitorGM-1000142842567027.8
OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 1 - Clients: 50 - Mode: Read Write - Average LatencyCompuLab Airtop3GM-10001632486480Min: 83.25 / Avg: 83.73 / Max: 84.09Min: 68.28 / Avg: 68.9 / Max: 69.291. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

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: blosclzCompuLab Airtop3GM-10002K4K6K8K10KSE +/- 6.83, N = 3SE +/- 11.16, N = 410397.88600.41. (CXX) g++ options: -rdynamic
MinAvgMaxCompuLab Airtop349.064.071.0GM-100062.069.474.0OpenBenchmarking.orgCelsius, Fewer Is BetterC-Blosc 2.0 Beta 5CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.068.175.0OpenBenchmarking.orgCelsius, Fewer Is BetterC-Blosc 2.0 Beta 5System Temperature Monitor20406080100
OpenBenchmarking.orgMB/s, More Is BetterC-Blosc 2.0 Beta 5Compressor: blosclzCompuLab Airtop3GM-10002K4K6K8K10KMin: 10384.1 / Avg: 10397.77 / Max: 10404.8Min: 8567.4 / Avg: 8600.43 / Max: 8614.61. (CXX) g++ options: -rdynamic

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: H2CompuLab Airtop3GM-10007001400210028003500SE +/- 28.32, N = 20SE +/- 39.15, N = 2029283339
MinAvgMaxCompuLab Airtop351.064.683.0GM-100060.067.775.0OpenBenchmarking.orgCelsius, Fewer Is BetterDaCapo Benchmark 9.12-MR1CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.068.275.0OpenBenchmarking.orgCelsius, Fewer Is BetterDaCapo Benchmark 9.12-MR1System Temperature Monitor20406080100
OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: H2CompuLab Airtop3GM-10006001200180024003000Min: 2675 / Avg: 2928.3 / Max: 3192Min: 3013 / Avg: 3338.75 / Max: 3706

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: 100CompuLab Airtop3GM-10009K18K27K36K45KSE +/- 402.90, N = 3SE +/- 486.77, N = 739309442451. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas
MinAvgMaxCompuLab Airtop351.072.890.0GM-100060.068.978.0OpenBenchmarking.orgCelsius, Fewer Is BetterCaffe 2020-02-13CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.074.075.0OpenBenchmarking.orgCelsius, Fewer Is BetterCaffe 2020-02-13System Temperature Monitor20406080100
OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: AlexNet - Acceleration: CPU - Iterations: 100CompuLab Airtop3GM-10008K16K24K32K40KMin: 38523 / Avg: 39309.33 / Max: 39855Min: 41475 / Avg: 44245.29 / Max: 455401. (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: 200CompuLab Airtop3GM-100020K40K60K80K100KSE +/- 476.82, N = 3SE +/- 906.54, N = 379582894241. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas
MinAvgMaxCompuLab Airtop354.072.991.0GM-100061.069.079.0OpenBenchmarking.orgCelsius, Fewer Is BetterCaffe 2020-02-13CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.074.575.0OpenBenchmarking.orgCelsius, Fewer Is BetterCaffe 2020-02-13System Temperature Monitor20406080100
OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: AlexNet - Acceleration: CPU - Iterations: 200CompuLab Airtop3GM-100016K32K48K64K80KMin: 78703 / Avg: 79581.67 / Max: 80342Min: 87616 / Avg: 89424.33 / Max: 904421. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

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: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPUCompuLab Airtop3GM-10000.98661.97322.95983.94644.933SE +/- 0.00566, N = 4SE +/- 0.04995, N = 43.964934.38502MIN: 3.9MIN: 4.021. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
MinAvgMaxCompuLab Airtop355.071.391.0GM-100061.069.278.0OpenBenchmarking.orgCelsius, Fewer Is BetteroneDNN 1.5CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.072.375.0OpenBenchmarking.orgCelsius, Fewer Is BetteroneDNN 1.5System Temperature Monitor20406080100
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPUCompuLab Airtop3GM-1000246810Min: 3.96 / Avg: 3.96 / Max: 3.98Min: 4.24 / Avg: 4.39 / Max: 4.451. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

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: 19CompuLab Airtop3GM-1000612182430SE +/- 0.09, N = 3SE +/- 0.25, N = 325.723.31. (CC) gcc options: -O3 -pthread -lz -llzma
MinAvgMaxCompuLab Airtop345.064.874.0GM-100058.067.172.0OpenBenchmarking.orgCelsius, Fewer Is BetterZstd Compression 1.4.5CPU Temperature Monitor20406080100
OpenBenchmarking.orgCelsius, Fewer Is BetterZstd Compression 1.4.5System Temperature MonitorGM-1000142842567027.8
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.5Compression Level: 19CompuLab Airtop3GM-1000612182430Min: 25.5 / Avg: 25.67 / Max: 25.8Min: 23 / Avg: 23.3 / Max: 23.81. (CC) gcc options: -O3 -pthread -lz -llzma

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 3.1CompuLab Airtop3GM-10000.92031.84062.76093.68124.6015SE +/- 0.00092, N = 3SE +/- 0.00058, N = 34.090163.708311. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -pthread -lmpi_cxx -lmpi
MinAvgMaxCompuLab Airtop349.068.583.0GM-100061.069.076.0OpenBenchmarking.orgCelsius, Fewer Is BetterHigh Performance Conjugate Gradient 3.1CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.074.775.0OpenBenchmarking.orgCelsius, Fewer Is BetterHigh Performance Conjugate Gradient 3.1System Temperature Monitor20406080100
OpenBenchmarking.orgGFLOP/s, More Is BetterHigh Performance Conjugate Gradient 3.1CompuLab Airtop3GM-1000246810Min: 4.09 / Avg: 4.09 / Max: 4.09Min: 3.71 / Avg: 3.71 / Max: 3.711. (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: BLASCompuLab Airtop3GM-10002004006008001000SE +/- 8.54, N = 3SE +/- 6.44, N = 38407841. (CXX) g++ options: -flto -pthread
MinAvgMaxCompuLab Airtop356.075.691.0GM-100062.070.578.0OpenBenchmarking.orgCelsius, Fewer Is BetterLeelaChessZero 0.26CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.074.975.0OpenBenchmarking.orgCelsius, Fewer Is BetterLeelaChessZero 0.26System Temperature Monitor20406080100
OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.26Backend: BLASCompuLab Airtop3GM-1000150300450600750Min: 823 / Avg: 840 / Max: 850Min: 771 / Avg: 783.67 / Max: 7921. (CXX) g++ options: -flto -pthread

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: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPUCompuLab Airtop3GM-100048121620SE +/- 0.05, N = 7SE +/- 0.02, N = 616.5216.12MIN: 16.37MIN: 15.91. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
MinAvgMaxCompuLab Airtop355.066.874.0GM-100061.068.174.0OpenBenchmarking.orgCelsius, Fewer Is BetteroneDNN 1.5CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.068.475.0OpenBenchmarking.orgCelsius, Fewer Is BetteroneDNN 1.5System Temperature Monitor20406080100
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPUCompuLab Airtop3GM-100048121620Min: 16.46 / Avg: 16.52 / Max: 16.82Min: 16.07 / Avg: 16.12 / Max: 16.181. (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: CPUCompuLab Airtop3GM-100048121620SE +/- 0.02, N = 7SE +/- 0.05, N = 717.0216.62MIN: 16.91MIN: 16.361. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
MinAvgMaxCompuLab Airtop357.069.278.0GM-100061.068.576.0OpenBenchmarking.orgCelsius, Fewer Is BetteroneDNN 1.5CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.068.975.0OpenBenchmarking.orgCelsius, Fewer Is BetteroneDNN 1.5System Temperature Monitor20406080100
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPUCompuLab Airtop3GM-100048121620Min: 16.98 / Avg: 17.02 / Max: 17.11Min: 16.47 / Avg: 16.62 / Max: 16.781. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

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 1.2.4CompuLab Airtop3GM-10005M10M15M20M25MSE +/- 86477.80, N = 3SE +/- 42312.00, N = 321264093208895831. (CXX) g++ options: -O3 -fopenmp
MinAvgMaxCompuLab Airtop343.067.681.0GM-100058.067.872.0OpenBenchmarking.orgCelsius, Fewer Is BetterKripke 1.2.4CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.064.275.0OpenBenchmarking.orgCelsius, Fewer Is BetterKripke 1.2.4System Temperature Monitor20406080100
OpenBenchmarking.orgThroughput FoM, More Is BetterKripke 1.2.4CompuLab Airtop3GM-10004M8M12M16M20MMin: 21153180 / Avg: 21264093.33 / Max: 21434480Min: 20805700 / Avg: 20889583.33 / Max: 209412001. (CXX) g++ options: -O3 -fopenmp

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: EigenCompuLab Airtop3GM-1000160320480640800SE +/- 7.36, N = 3SE +/- 2.52, N = 37657581. (CXX) g++ options: -flto -pthread
MinAvgMaxCompuLab Airtop360.077.896.0GM-100063.071.379.0OpenBenchmarking.orgCelsius, Fewer Is BetterLeelaChessZero 0.26CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.074.975.0OpenBenchmarking.orgCelsius, Fewer Is BetterLeelaChessZero 0.26System Temperature Monitor20406080100
OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.26Backend: EigenCompuLab Airtop3GM-1000130260390520650Min: 757 / Avg: 765.33 / Max: 780Min: 755 / Avg: 758 / Max: 7631. (CXX) g++ options: -flto -pthread

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 RoutineCompuLab Airtop3GM-10007K14K21K28K35KSE +/- 76.97, N = 11SE +/- 47.47, N = 1130993.6430890.911. (F9X) gfortran options: -O3 -fomit-frame-pointer -fopenmp
MinAvgMaxCompuLab Airtop358.067.785.0GM-100058.064.474.0OpenBenchmarking.orgCelsius, Fewer Is BetterFFTE 7.0CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.064.575.0OpenBenchmarking.orgCelsius, Fewer Is BetterFFTE 7.0System Temperature Monitor20406080100
OpenBenchmarking.orgMFLOPS, More Is BetterFFTE 7.0N=256, 3D Complex FFT RoutineCompuLab Airtop3GM-10005K10K15K20K25KMin: 30305.11 / Avg: 30993.64 / Max: 31285.97Min: 30699.22 / Avg: 30890.91 / Max: 31121.851. (F9X) gfortran options: -O3 -fomit-frame-pointer -fopenmp

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-10000.72321.44642.16962.89283.616SE +/- 0.007, N = 93.214
MinAvgMaxGM-100055.056.063.0OpenBenchmarking.orgCelsius, Fewer Is BetterWaifu2x-NCNN Vulkan 20200818CPU Temperature Monitor20406080100
MinAvgMaxGM-100054.062.565.0OpenBenchmarking.orgCelsius, Fewer Is BetterWaifu2x-NCNN Vulkan 20200818System Temperature Monitor20406080100

System Temperature Monitor

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

CPU Temperature Monitor

OpenBenchmarking.orgCelsiusCPU Temperature MonitorPhoronix Test Suite System MonitoringCompuLab Airtop3GM-100020406080100Min: 34 / Avg: 70.36 / Max: 100Min: 49 / Avg: 67.98 / Max: 82

ASTC Encoder

MinAvgMaxGM-100064.071.075.0OpenBenchmarking.orgCelsius, Fewer Is BetterASTC Encoder 2.0System Temperature Monitor20406080100

MinAvgMaxCompuLab Airtop342.063.080.0GM-100059.068.576.0OpenBenchmarking.orgCelsius, Fewer Is BetterASTC Encoder 2.0CPU Temperature Monitor20406080100

PostgreSQL pgbench

OpenBenchmarking.orgCelsius, Fewer Is BetterPostgreSQL pgbench 13.0System Temperature MonitorGM-1000142842567027.8

MinAvgMaxCompuLab Airtop342.046.955.0GM-100058.058.960.0OpenBenchmarking.orgCelsius, Fewer Is BetterPostgreSQL pgbench 13.0CPU Temperature Monitor1632486480

LevelDB

OpenBenchmarking.orgCelsius, Fewer Is BetterLevelDB 1.22System Temperature MonitorGM-1000142842567027.8

MinAvgMaxCompuLab Airtop350.068.678.0GM-100058.065.071.0OpenBenchmarking.orgCelsius, Fewer Is BetterLevelDB 1.22CPU Temperature Monitor20406080100

OpenSSL

MinAvgMaxGM-100064.072.375.0OpenBenchmarking.orgCelsius, Fewer Is BetterOpenSSL 1.1.1System Temperature Monitor20406080100

MinAvgMaxCompuLab Airtop346.071.193.0GM-100058.067.276.0OpenBenchmarking.orgCelsius, Fewer Is BetterOpenSSL 1.1.1CPU Temperature Monitor20406080100

SVT-VP9

MinAvgMaxGM-100064.071.275.0OpenBenchmarking.orgCelsius, Fewer Is BetterSVT-VP9 0.1System Temperature Monitor20406080100

MinAvgMaxCompuLab Airtop356.071.988.0GM-100061.068.678.0OpenBenchmarking.orgCelsius, Fewer Is BetterSVT-VP9 0.1CPU Temperature Monitor20406080100

MinAvgMaxGM-100064.070.475.0OpenBenchmarking.orgCelsius, Fewer Is BetterSVT-VP9 0.1System Temperature Monitor20406080100

MinAvgMaxCompuLab Airtop356.069.286.0GM-100061.068.677.0OpenBenchmarking.orgCelsius, Fewer Is BetterSVT-VP9 0.1CPU Temperature Monitor20406080100

Kvazaar

MinAvgMaxGM-100064.072.375.0OpenBenchmarking.orgCelsius, Fewer Is BetterKvazaar 2.0System Temperature Monitor20406080100

MinAvgMaxCompuLab Airtop355.073.191.0GM-100061.068.678.0OpenBenchmarking.orgCelsius, Fewer Is BetterKvazaar 2.0CPU Temperature Monitor20406080100

oneDNN

MinAvgMaxGM-100064.072.575.0OpenBenchmarking.orgCelsius, Fewer Is BetteroneDNN 1.5System Temperature Monitor20406080100

MinAvgMaxCompuLab Airtop357.072.091.0GM-100061.068.479.0OpenBenchmarking.orgCelsius, Fewer Is BetteroneDNN 1.5CPU Temperature Monitor20406080100

MinAvgMaxGM-100064.072.475.0OpenBenchmarking.orgCelsius, Fewer Is BetteroneDNN 1.5System Temperature Monitor20406080100

MinAvgMaxCompuLab Airtop355.072.090.0GM-100061.068.278.0OpenBenchmarking.orgCelsius, Fewer Is BetteroneDNN 1.5CPU Temperature Monitor20406080100

DaCapo Benchmark

MinAvgMaxGM-100064.068.075.0OpenBenchmarking.orgCelsius, Fewer Is BetterDaCapo Benchmark 9.12-MR1System Temperature Monitor20406080100

MinAvgMaxCompuLab Airtop352.066.984.0GM-100060.068.975.0OpenBenchmarking.orgCelsius, Fewer Is BetterDaCapo Benchmark 9.12-MR1CPU Temperature Monitor20406080100

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: googlenetCompuLab Airtop3GM-1000612182430SE +/- 0.32, N = 3SE +/- 0.96, N = 315.0023.99MIN: 14.19 / MAX: 15.74MIN: 17.71 / MAX: 26.791. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: googlenetCompuLab Airtop3GM-1000612182430Min: 14.36 / Avg: 15 / Max: 15.32Min: 22.09 / Avg: 23.99 / Max: 25.191. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: blazefaceCompuLab Airtop3GM-10000.46580.93161.39741.86322.329SE +/- 0.03, N = 3SE +/- 0.24, N = 31.472.07MIN: 1.35 / MAX: 1.58MIN: 1.46 / MAX: 3.261. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: blazefaceCompuLab Airtop3GM-1000246810Min: 1.41 / Avg: 1.47 / Max: 1.51Min: 1.58 / Avg: 2.07 / Max: 2.321. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: efficientnet-b0CompuLab Airtop3GM-10003691215SE +/- 0.14, N = 3SE +/- 1.08, N = 36.7010.25MIN: 6.37 / MAX: 7.12MIN: 7.48 / MAX: 13.21. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: efficientnet-b0CompuLab Airtop3GM-10003691215Min: 6.41 / Avg: 6.7 / Max: 6.85Min: 8.09 / Avg: 10.25 / Max: 11.341. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: mnasnetCompuLab Airtop3GM-1000246810SE +/- 0.01, N = 3SE +/- 0.81, N = 33.916.90MIN: 3.86 / MAX: 4.2MIN: 4.78 / MAX: 16.691. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: mnasnetCompuLab Airtop3GM-10003691215Min: 3.89 / Avg: 3.91 / Max: 3.92Min: 5.29 / Avg: 6.9 / Max: 7.711. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: shufflenet-v2CompuLab Airtop3GM-10001.20382.40763.61144.81526.019SE +/- 0.06, N = 3SE +/- 0.61, N = 33.315.35MIN: 3.05 / MAX: 3.63MIN: 3.72 / MAX: 141. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: shufflenet-v2CompuLab Airtop3GM-1000246810Min: 3.24 / Avg: 3.31 / Max: 3.43Min: 4.13 / Avg: 5.35 / Max: 5.981. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU-v3-v3 - Model: mobilenet-v3CompuLab Airtop3GM-1000246810SE +/- 0.01, N = 3SE +/- 0.69, N = 34.056.51MIN: 4 / MAX: 4.34MIN: 4.68 / MAX: 9.071. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU-v3-v3 - Model: mobilenet-v3CompuLab Airtop3GM-10003691215Min: 4.04 / Avg: 4.05 / Max: 4.06Min: 5.14 / Avg: 6.51 / Max: 7.21. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

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: mobilenet-v1-1.0CompuLab Airtop3GM-1000246810SE +/- 0.048, N = 3SE +/- 0.617, N = 37.8497.783MIN: 7.59 / MAX: 45.29MIN: 4.59 / MAX: 20.891. (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: mobilenet-v1-1.0CompuLab Airtop3GM-10003691215Min: 7.8 / Avg: 7.85 / Max: 7.95Min: 6.55 / Avg: 7.78 / Max: 8.41. (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: MobileNetV2_224CompuLab Airtop3GM-10001.05822.11643.17464.23285.291SE +/- 0.006, N = 3SE +/- 0.368, N = 33.7924.703MIN: 3.51 / MAX: 4.33MIN: 3.43 / MAX: 12.111. (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: MobileNetV2_224CompuLab Airtop3GM-1000246810Min: 3.78 / Avg: 3.79 / Max: 3.8Min: 3.97 / Avg: 4.7 / Max: 5.121. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

ASTC Encoder

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

OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.0Preset: MediumCompuLab Airtop3GM-10003691215SE +/- 0.00, N = 5SE +/- 0.16, N = 158.529.911. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread
MinAvgMaxCompuLab Airtop342.063.080.0GM-100059.068.576.0OpenBenchmarking.orgCelsius, Fewer Is BetterASTC Encoder 2.0CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.071.075.0OpenBenchmarking.orgCelsius, Fewer Is BetterASTC Encoder 2.0System Temperature Monitor20406080100
OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.0Preset: MediumCompuLab Airtop3GM-10003691215Min: 8.51 / Avg: 8.52 / Max: 8.53Min: 7.99 / Avg: 9.91 / Max: 10.161. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread

PostgreSQL pgbench

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

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 1 - Clients: 1 - Mode: Read Write - Average LatencyCompuLab Airtop3GM-10000.53371.06741.60112.13482.6685SE +/- 0.125, N = 12SE +/- 0.018, N = 32.3721.9881. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
MinAvgMaxCompuLab Airtop342.046.955.0GM-100058.058.960.0OpenBenchmarking.orgCelsius, Fewer Is BetterPostgreSQL pgbench 13.0CPU Temperature Monitor1632486480
OpenBenchmarking.orgCelsius, Fewer Is BetterPostgreSQL pgbench 13.0System Temperature MonitorGM-1000142842567027.8
OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 1 - Clients: 1 - Mode: Read Write - Average LatencyCompuLab Airtop3GM-1000246810Min: 1.95 / Avg: 2.37 / Max: 3.13Min: 1.95 / Avg: 1.99 / Max: 2.021. (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 WriteCompuLab Airtop3GM-1000110220330440550SE +/- 20.79, N = 12SE +/- 4.74, N = 34345031. (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 WriteCompuLab Airtop3GM-100090180270360450Min: 319.35 / Avg: 433.67 / Max: 512.38Min: 495.71 / Avg: 503.09 / Max: 511.931. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

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: Seek RandomCompuLab Airtop3GM-1000246810SE +/- 0.183, N = 15SE +/- 0.070, N = 158.9375.9281. (CXX) g++ options: -O3 -lsnappy -lpthread
MinAvgMaxCompuLab Airtop350.068.678.0GM-100058.065.071.0OpenBenchmarking.orgCelsius, Fewer Is BetterLevelDB 1.22CPU Temperature Monitor20406080100
OpenBenchmarking.orgCelsius, Fewer Is BetterLevelDB 1.22System Temperature MonitorGM-1000142842567027.8
OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Seek RandomCompuLab Airtop3GM-10003691215Min: 8.52 / Avg: 8.94 / Max: 11.46Min: 5.43 / Avg: 5.93 / Max: 6.161. (CXX) g++ options: -O3 -lsnappy -lpthread

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 PerformanceCompuLab Airtop3GM-10005001000150020002500SE +/- 21.92, N = 14SE +/- 29.90, N = 152539.91492.71. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
MinAvgMaxCompuLab Airtop346.071.193.0GM-100058.067.276.0OpenBenchmarking.orgCelsius, Fewer Is BetterOpenSSL 1.1.1CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.072.375.0OpenBenchmarking.orgCelsius, Fewer Is BetterOpenSSL 1.1.1System Temperature Monitor20406080100
OpenBenchmarking.orgSigns Per Second, More Is BetterOpenSSL 1.1.1RSA 4096-bit PerformanceCompuLab Airtop3GM-1000400800120016002000Min: 2507.8 / Avg: 2539.87 / Max: 2823.6Min: 1440.2 / Avg: 1492.68 / Max: 1909.11. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

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: Visual Quality Optimized - Input: Bosphorus 1080pCompuLab Airtop3GM-1000306090120150SE +/- 0.95, N = 8SE +/- 1.58, N = 15131.8380.061. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
MinAvgMaxCompuLab Airtop356.071.988.0GM-100061.068.678.0OpenBenchmarking.orgCelsius, Fewer Is BetterSVT-VP9 0.1CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.071.275.0OpenBenchmarking.orgCelsius, Fewer Is BetterSVT-VP9 0.1System Temperature Monitor20406080100
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.1Tuning: Visual Quality Optimized - Input: Bosphorus 1080pCompuLab Airtop3GM-100020406080100Min: 125.31 / Avg: 131.83 / Max: 133.57Min: 77.55 / Avg: 80.06 / Max: 98.981. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.1Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080pCompuLab Airtop3GM-10004080120160200SE +/- 0.26, N = 8SE +/- 1.68, N = 15169.12107.791. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
MinAvgMaxCompuLab Airtop356.069.286.0GM-100061.068.677.0OpenBenchmarking.orgCelsius, Fewer Is BetterSVT-VP9 0.1CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.070.475.0OpenBenchmarking.orgCelsius, Fewer Is BetterSVT-VP9 0.1System Temperature Monitor20406080100
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.1Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080pCompuLab Airtop3GM-1000306090120150Min: 167.55 / Avg: 169.12 / Max: 169.88Min: 104.13 / Avg: 107.79 / Max: 124.021. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

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 1080p - Video Preset: Ultra FastCompuLab Airtop3GM-100020406080100SE +/- 1.01, N = 7SE +/- 0.87, N = 1591.4644.451. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
MinAvgMaxCompuLab Airtop355.073.191.0GM-100061.068.678.0OpenBenchmarking.orgCelsius, Fewer Is BetterKvazaar 2.0CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.072.375.0OpenBenchmarking.orgCelsius, Fewer Is BetterKvazaar 2.0System Temperature Monitor20406080100
OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 1080p - Video Preset: Ultra FastCompuLab Airtop3GM-100020406080100Min: 88.35 / Avg: 91.46 / Max: 96.64Min: 43.3 / Avg: 44.45 / Max: 56.571. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

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: u8s8f32 - Engine: CPUCompuLab Airtop3GM-10001.0892.1783.2674.3565.445SE +/- 0.00614, N = 4SE +/- 0.10124, N = 151.889894.84005MIN: 1.55MIN: 3.331. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
MinAvgMaxCompuLab Airtop357.072.091.0GM-100061.068.479.0OpenBenchmarking.orgCelsius, Fewer Is BetteroneDNN 1.5CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.072.575.0OpenBenchmarking.orgCelsius, Fewer Is BetteroneDNN 1.5System Temperature Monitor20406080100
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: IP Batch 1D - Data Type: u8s8f32 - Engine: CPUCompuLab Airtop3GM-1000246810Min: 1.87 / Avg: 1.89 / Max: 1.9Min: 3.42 / Avg: 4.84 / Max: 4.981. (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: f32 - Engine: CPUCompuLab Airtop3GM-10003691215SE +/- 0.04455, N = 15SE +/- 0.22450, N = 154.497389.53324MIN: 3.82MIN: 6.671. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
MinAvgMaxCompuLab Airtop355.072.090.0GM-100061.068.278.0OpenBenchmarking.orgCelsius, Fewer Is BetteroneDNN 1.5CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.072.475.0OpenBenchmarking.orgCelsius, Fewer Is BetteroneDNN 1.5System Temperature Monitor20406080100
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: IP Batch 1D - Data Type: f32 - Engine: CPUCompuLab Airtop3GM-10003691215Min: 3.97 / Avg: 4.5 / Max: 4.7Min: 6.94 / Avg: 9.53 / Max: 10.461. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

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: TradebeansCompuLab Airtop3GM-10008001600240032004000SE +/- 42.33, N = 20SE +/- 30.71, N = 527913621
MinAvgMaxCompuLab Airtop352.066.984.0GM-100060.068.975.0OpenBenchmarking.orgCelsius, Fewer Is BetterDaCapo Benchmark 9.12-MR1CPU Temperature Monitor20406080100
MinAvgMaxGM-100064.068.075.0OpenBenchmarking.orgCelsius, Fewer Is BetterDaCapo Benchmark 9.12-MR1System Temperature Monitor20406080100
OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: TradebeansCompuLab Airtop3GM-10006001200180024003000Min: 2589 / Avg: 2790.55 / Max: 3482Min: 3510 / Avg: 3621.4 / Max: 3686

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 TestCompuLab Airtop3GM-1000100200300400500SE +/- 0.83, N = 13SE +/- 32.44, N = 15253.17461.45MIN: 74.4 / MAX: 323.5MIN: 18.41 / MAX: 691.921. (CC) gcc options: -O2 -lm -pthread -lmpi
OpenBenchmarking.orgMB/s, More Is BetterIOR 3.2.1Write TestCompuLab Airtop3GM-100080160240320400Min: 248.88 / Avg: 253.17 / Max: 258.01Min: 308.94 / Avg: 461.45 / Max: 626.341. (CC) gcc options: -O2 -lm -pthread -lmpi

222 Results Shown

NCNN
GLmark2
NCNN:
  Vulkan GPU - alexnet
  Vulkan GPU - resnet50
  Vulkan GPU - resnet18
RealSR-NCNN
Apache Cassandra
Waifu2x-NCNN Vulkan
RealSR-NCNN
LevelDB
NCNN
oneDNN
NCNN
Facebook RocksDB
rays1bench
BRL-CAD
ASTC Encoder
PostgreSQL pgbench
oneDNN
PostgreSQL pgbench
ASTC Encoder
oneDNN
Numenta Anomaly Benchmark:
  Earthgecko Skyline
  Bayesian Changepoint
  Relative Entropy
IOR
Timed Linux Kernel Compilation
Kvazaar
oneDNN
Kvazaar:
  Bosphorus 4K - Medium
  Bosphorus 4K - Ultra Fast
NAMD
Kvazaar
YafaRay
LuxCoreRender
NCNN
Numenta Anomaly Benchmark
NCNN
Timed LLVM Compilation
oneDNN
NCNN
LuxCoreRender
SVT-AV1
Intel Open Image Denoise
NCNN
7-Zip Compression
oneDNN
Kvazaar
John The Ripper
NCNN
John The Ripper
libavif avifenc
NCNN
x265
Incompact3D
libavif avifenc
TensorFlow Lite:
  Inception ResNet V2
  Inception V4
NCNN
OCRMyPDF
dav1d
TensorFlow Lite
SVT-AV1
DaCapo Benchmark
TensorFlow Lite:
  SqueezeNet
  Mobilenet Quant
Timed PHP Compilation
Facebook RocksDB
OpenVKL
AI Benchmark Alpha
x265
NCNN
Monte Carlo Simulations of Ionised Nebulae
Timed GDB GNU Debugger Compilation
dav1d:
  Summer Nature 4K
  Summer Nature 1080p
Mobile Neural Network
oneDNN
WireGuard + Linux Networking Stack Stress Test
NCNN
Hugin
KeyDB
AI Benchmark Alpha
LevelDB:
  Seq Fill
  Rand Read
TensorFlow Lite
oneDNN
NCNN:
  CPU - mobilenet
  CPU - alexnet
  CPU - squeezenet
LevelDB
RawTherapee
LevelDB
NCNN
GROMACS
Timed Apache Compilation
Mlpack Benchmark
VP9 libvpx Encoding
AI Benchmark Alpha
dav1d
NCNN
Facebook RocksDB
VP9 libvpx Encoding
ASTC Encoder
Mobile Neural Network
LevelDB
eSpeak-NG Speech Engine
Mlpack Benchmark
LAMMPS Molecular Dynamics Simulator
Java Gradle Build
Facebook RocksDB
PyPerformance:
  pickle_pure_python
  chaos
  float
librsvg
PyPerformance
WebP Image Encode
PyPerformance:
  go
  pathlib
PostgreSQL pgbench
RNNoise
PyPerformance
Facebook RocksDB
TNN
PyPerformance
WebP Image Encode
PyPerformance
BYTE Unix Benchmark
Git
PyPerformance
WebP Image Encode
Tesseract OCR
WebP Image Encode
oneDNN
PyPerformance
PostgreSQL pgbench
LevelDB
Dolfyn
PyPerformance
WebP Image Encode
PyPerformance
libavif avifenc
DaCapo Benchmark
Timed HMMer Search
Hierarchical INTegration
libavif avifenc
Timed MAFFT Alignment
Numpy Benchmark
TNN
Mlpack Benchmark
LevelDB
NCNN
LevelDB:
  Overwrite
  Rand Fill
Mlpack Benchmark
PostMark
NCNN
Caffe
GNU Octave Benchmark
LevelDB
Caffe
LibRaw
Zstd Compression
Mobile Neural Network
PostgreSQL pgbench:
  1 - 50 - Read Write
  1 - 50 - Read Write - Average Latency
C-Blosc
DaCapo Benchmark
Caffe:
  AlexNet - CPU - 100
  AlexNet - CPU - 200
oneDNN
Zstd Compression
High Performance Conjugate Gradient
LeelaChessZero
oneDNN:
  Convolution Batch Shapes Auto - u8s8f32 - CPU
  Convolution Batch Shapes Auto - f32 - CPU
Kripke
LeelaChessZero
FFTE
Waifu2x-NCNN Vulkan
System Temperature Monitor:
  Phoronix Test Suite System Monitoring:
    Celsius
    Celsius
  System Temp Monitor:
    Celsius
  CPU Temp Monitor:
    Celsius
  System Temp Monitor:
    Celsius
  CPU Temp Monitor:
    Celsius
  System Temp Monitor:
    Celsius
  CPU Temp Monitor:
    Celsius
  System Temp Monitor:
    Celsius
  CPU Temp Monitor:
    Celsius
  System Temp Monitor:
    Celsius
  CPU Temp Monitor:
    Celsius
  System Temp Monitor:
    Celsius
  CPU Temp Monitor:
    Celsius
  System Temp Monitor:
    Celsius
  CPU Temp Monitor:
    Celsius
  System Temp Monitor:
    Celsius
  CPU Temp Monitor:
    Celsius
  System Temp Monitor:
    Celsius
  CPU Temp Monitor:
    Celsius
  System Temp Monitor:
    Celsius
  CPU Temp Monitor:
    Celsius
NCNN:
  CPU - googlenet
  CPU - blazeface
  CPU - efficientnet-b0
  CPU - mnasnet
  CPU - shufflenet-v2
  CPU-v3-v3 - mobilenet-v3
Mobile Neural Network:
  mobilenet-v1-1.0
  MobileNetV2_224
ASTC Encoder
PostgreSQL pgbench:
  1 - 1 - Read Write - Average Latency
  1 - 1 - Read Write
LevelDB
OpenSSL
SVT-VP9:
  Visual Quality Optimized - Bosphorus 1080p
  PSNR/SSIM Optimized - Bosphorus 1080p
Kvazaar
oneDNN:
  IP Batch 1D - u8s8f32 - CPU
  IP Batch 1D - f32 - CPU
DaCapo Benchmark
IOR

GM-1000

Processor: Intel Core i7-9700TE @ 3.80GHz (8 Cores), Motherboard: C OZE GM-1000 v0.0.01.001 (5.13 BIOS), Chipset: Intel Cannon Lake PCH, Memory: 32GB, Disk: CIE M8 T405 512GB, Graphics: NVIDIA Quadro P2000 4GB (1455/3003MHz), Audio: Realtek ALC888-VD, Monitor: DELL S2409W, Network: Intel I219-LM + 2 x Intel 10G X550T + Intel I210

OS: Ubuntu 20.10, Kernel: 5.8.0-25-generic (x86_64), Desktop: GNOME Shell 3.38.1, Display Server: X Server 1.20.9, Display Driver: NVIDIA 455.28, OpenGL: 4.6.0, OpenCL: OpenCL 1.2 CUDA 11.1.96, Vulkan: 1.2.142, Compiler: GCC 10.2.0, File-System: ext4, Screen Resolution: 1920x1080

Compiler Notes: --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 Notes: NONE / errors=remount-ro,relatime,rw
Processor Notes: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xd6 - Thermald 2.3
OpenCL Notes: GPU Compute Cores: 768
Java Notes: OpenJDK Runtime Environment (build 11.0.9+10-post-Ubuntu-0ubuntu1)
Python Notes: Python 3.8.6
Security Notes: 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

Testing initiated at 28 October 2020 06:55 by user phoronix.

CompuLab Airtop3

Processor: Intel Xeon E-2288G @ 5.00GHz (8 Cores / 16 Threads), Motherboard: Compulab SBC-ATCFL v1.2 (ATOP3.PRD.0.29.2 BIOS), Chipset: Intel Cannon Lake PCH, Memory: 64GB, Disk: Samsung SSD 970 EVO Plus 250GB, Graphics: NVIDIA Quadro RTX 4000 8GB (1005/6500MHz), Audio: Intel Cannon Lake PCH cAVS, Monitor: VE228, Network: Intel I219-LM + Intel I210

OS: Ubuntu 20.10, Kernel: 5.8.0-26-generic (x86_64), Desktop: GNOME Shell 3.38.1, Display Server: X Server 1.20.9, Display Driver: NVIDIA 455.28, OpenGL: 4.6.0, OpenCL: OpenCL 1.2 CUDA 11.1.96, Vulkan: 1.2.142, Compiler: GCC 10.2.0, File-System: ext4, Screen Resolution: 1920x1080

Compiler Notes: --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 Notes: NONE / errors=remount-ro,relatime,rw
Processor Notes: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xd6 - Thermald 2.3
OpenCL Notes: GPU Compute Cores: 2304
Java Notes: OpenJDK Runtime Environment (build 11.0.9+11-Ubuntu-0ubuntu1)
Python Notes: Python 3.8.6
Security Notes: 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

Testing initiated at 29 October 2020 17:43 by user phoronix.