System76 Thelio Major 3990X Pop OS

AMD Ryzen Threadripper 3990X benchmarking of Pop OS 20.10 by Michael Larabel for a future article.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2010258-FI-SYSTEM76T72
Jump To Table - Results

View

Do Not Show Noisy Results
Do Not Show Results With Incomplete Data
Do Not Show Results With Little Change/Spread
List Notable Results
Show Result Confidence Charts
Allow Limiting Results To Certain Suite(s)

Statistics

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

Graph Settings

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

Multi-Way Comparison

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

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Toggle/Hide
Result
Result
Identifier
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
Pop OS 20.04
October 23 2020
  21 Hours, 47 Minutes
Pop OS 20.10
October 24 2020
  19 Hours, 40 Minutes
Invert Behavior (Only Show Selected Data)
  20 Hours, 43 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):

Pop OS 20.04

Processor: AMD Ryzen Threadripper 3990X 64-Core @ 2.90GHz (64 Cores / 128 Threads), Motherboard: System76 Thelio Major (F4c Z5 BIOS), Chipset: AMD Starship/Matisse, Memory: 126GB, Disk: Samsung SSD 970 EVO Plus 500GB, Graphics: AMD Radeon RX 5600 OEM/5600 XT / 5700/5700 8GB (1750/875MHz), Audio: AMD Navi 10 HDMI Audio, Monitor: DELL P2415Q, Network: Intel I211 + Intel Wi-Fi 6 AX200

OS: Pop 20.04, Kernel: 5.4.0-7642-generic (x86_64), Desktop: GNOME Shell 3.36.4, Display Server: X Server 1.20.8, Display Driver: amdgpu 19.1.0, OpenGL: 4.6 Mesa 20.0.8 (LLVM 10.0.0), Vulkan: 1.2.128, Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 3840x2160

Kernel Notes: snd_usb_audio.ignore_ctl_error=1
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++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-HskZEa/gcc-9-9.3.0/debian/tmp-nvptx/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,noatime,rw
Processor Notes: Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8301025
Graphics Notes: GLAMOR
Java Notes: OpenJDK Runtime Environment (build 11.0.8+10-post-Ubuntu-0ubuntu120.04)
Python Notes: Python 3.8.5
Security Notes: itlb_multihit: Not affected + 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 Full AMD retpoline IBPB: conditional STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Pop OS 20.10

Processor: AMD Ryzen Threadripper 3990X 64-Core @ 2.90GHz (64 Cores / 128 Threads), Motherboard: System76 Thelio Major (F4c Z5 BIOS), Chipset: AMD Starship/Matisse, Memory: 126GB, Disk: Samsung SSD 970 EVO Plus 500GB + 32GB Flash Disk, Graphics: AMD Radeon RX 5600 OEM/5600 XT / 5700/5700 8GB (1750/875MHz), Audio: AMD Navi 10 HDMI Audio, Monitor: DELL P2415Q, Network: Intel I211 + Intel Wi-Fi 6 AX200

OS: Pop 20.10, Kernel: 5.8.0-7625-generic (x86_64), Desktop: GNOME Shell 3.38.1, Display Server: X Server 1.20.8, Display Driver: amdgpu 19.1.0, OpenGL: 4.6 Mesa 20.2.1 (LLVM 11.0.0), Vulkan: 1.2.131, Compiler: GCC 10.2.0, File-System: ext4, Screen Resolution: 3840x2160

Kernel Notes: snd_usb_audio.ignore_ctl_error=1
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,noatime,rw
Processor Notes: Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8301025
Graphics Notes: GLAMOR
Java Notes: OpenJDK Runtime Environment (build 11.0.9+10-post-Ubuntu-0ubuntu1)
Python Notes: Python 3.8.6
Security Notes: itlb_multihit: Not affected + 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 Full AMD retpoline IBPB: conditional STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

System76 Thelio Major 3990X Pop OSProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLVulkanCompilerFile-SystemScreen ResolutionPop OS 20.04Pop OS 20.10AMD Ryzen Threadripper 3990X 64-Core @ 2.90GHz (64 Cores / 128 Threads)System76 Thelio Major (F4c Z5 BIOS)AMD Starship/Matisse126GBSamsung SSD 970 EVO Plus 500GBAMD Radeon RX 5600 OEM/5600 XT / 5700/5700 8GB (1750/875MHz)AMD Navi 10 HDMI AudioDELL P2415QIntel I211 + Intel Wi-Fi 6 AX200Pop 20.045.4.0-7642-generic (x86_64)GNOME Shell 3.36.4X Server 1.20.8amdgpu 19.1.04.6 Mesa 20.0.8 (LLVM 10.0.0)1.2.128GCC 9.3.0ext43840x2160Samsung SSD 970 EVO Plus 500GB + 32GB Flash DiskPop 20.105.8.0-7625-generic (x86_64)GNOME Shell 3.38.14.6 Mesa 20.2.1 (LLVM 11.0.0)1.2.131GCC 10.2.0OpenBenchmarking.orgKernel Details- snd_usb_audio.ignore_ctl_error=1Compiler Details- Pop OS 20.04: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-HskZEa/gcc-9-9.3.0/debian/tmp-nvptx/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 - Pop OS 20.10: --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,noatime,rwProcessor Details- Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8301025Graphics Details- GLAMORJava Details- Pop OS 20.04: OpenJDK Runtime Environment (build 11.0.8+10-post-Ubuntu-0ubuntu120.04)- Pop OS 20.10: OpenJDK Runtime Environment (build 11.0.9+10-post-Ubuntu-0ubuntu1)Python Details- Pop OS 20.04: Python 3.8.5- Pop OS 20.10: Python 3.8.6Security Details- itlb_multihit: Not affected + 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 Full AMD retpoline IBPB: conditional STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Pop OS 20.04 vs. Pop OS 20.10 ComparisonPhoronix Test SuiteBaseline+117.4%+117.4%+234.8%+234.8%+352.2%+352.2%469.4%360.6%332.2%161.8%156.7%97.4%91.8%91.4%86.6%85.9%81.3%72.2%69%68.1%56.5%48.6%41.1%37.7%36%24.1%19.6%19.2%18.8%15.1%14.6%14.4%13.9%10.9%10%9.7%9.7%9.6%9.6%9.3%9.2%8.4%7.6%7.3%7.2%6.9%6.6%6.4%6.1%6%5.9%5.9%5.9%5.9%5.4%5.2%5.1%5%4.7%4.6%4.6%4.6%4.5%4.4%4.4%4%3.9%3.8%3.7%3.7%3.7%3.7%3.6%3.4%3.2%3.1%3.1%3%2.7%2.7%2.6%2.4%2.4%2.4%2.2%2.1%2.1%2.1%2%2%2%2%MMAPVulkan GPU - alexnetVulkan GPU - vgg16tfft2Vulkan GPU-v3-v3 - mobilenet-v3Vulkan GPU-v2-v2 - mobilenet-v2Vulkan GPU - mnasnet4x - YesVulkan GPU - googlenetVulkan GPU - resnet50python_startupVulkan GPU - resnet184x - NoVulkan GPU - shufflenet-v22x - 3 - YesVulkan GPU - yolov4-tinyC.B.S.A - f32 - CPUVulkan GPU - mobilenetVulkan GPU - squeezenetM.M.B.S.T - f32 - CPU2.F.P.1.T22.8%airSocket ActivityImage RenderingP.D.S16.8%scikit_icaTime To CompileWavelet BlurSVG Files To PNGSemaphores12.7%Context Switching12.4%AntialiasEigendjango_templateColor EnhanceVulkan GPU - blazefaceScaleTile Glasspickle_pure_pythonI.R.V8.9%CPU - MobileNet v2Reactor8.4%MEMFD8.2%ReflectCPU - mnasnetCropF.F.Tjson_loads6.7%Rotate 90 DegreesBLAS100 - 1000 - 24CPU - shufflenet-v2DefaultCPU Stressfatigue25.9%CoreMark Size 666 - I.P.SGoogleNet - CPU - 100NUMA5.6%Forking5.4%Cartoon85.3%CPU - blazefaceText Rendering5.2%SqueezeNetV1.05.1%A.R.TRead While Writingauto-levelsregex_compileWavelet Contour - 1920 x 1080Wavelet Contour - 1920 x 1080Bosphorus 1080p - Ultra Fast4.5%S.M.MTime To Compile4.4%Wavelet Contour - 3840 x 2160Wavelet Contour - 3840 x 2160Fill Sync4.3%4.3%4.3%pathlib4.3%D.T.P4.1%CPU - SqueezeNet v1.1P.S.O - Bosphorus 1080p3.9%P.P.B3.9%D.L.M.FInception V43.8%AlexNet - CPU - 100Wavelet Volume - 1920 x 1080Wavelet Volume - 1920 x 1080Q.1.H.C3.7%Wavelet Volume - 3840 x 2160Wavelet Volume - 3840 x 2160Material Tester3840 x 2160 - High3.6%SENDFILE3.5%mdbx3.4%channel23.4%Hot Read3.3%D.I.S3.2%64 - 10000 - 2,5000,1 - 10000MallocV.Q.O - Bosphorus 1080p3.1%Rand Read3.1%1024 - 10000 - 2,5000,1 - 10000test_fpu23%Thoroughcrypto_pyaes2.9%nbody2.8%WAV To MP32.7%2to3Read Test2.7%CompositeTotal Time2.7%PBKDF2-whirlpoolTime To Compile2.6%Device AI Score2.6%1.8.b.Y.T.H.V.E2.5%L.E.H2.5%Q.1.L.H.C2.5%Mobilenet QuantcapacitaD.B.d - f32 - CPUWrite Test2.2%Fastinception-v3Timed Time - Size 1,000192.1%MediumQ.1.L2.1%Rhodopsin Protein2.1%Enc Mode 4 - 1080p2.1%ExhaustiveBlowfishQuality 1003Stress-NGNCNNNCNNPolyhedron Fortran BenchmarksNCNNNCNNNCNNRealSR-NCNNNCNNNCNNPyPerformanceNCNNRealSR-NCNNNCNNWaifu2x-NCNN VulkanNCNNoneDNNNCNNNCNNoneDNNG'MICPolyhedron Fortran BenchmarksStress-NGJava 2D MicrobenchmarkTimed HMMer SearchMlpack BenchmarkTimed FFmpeg CompilationGEGLlibrsvgStress-NGStress-NGGEGLLeelaChessZeroPyPerformanceGEGLNCNNGEGLGEGLPyPerformanceTensorFlow LiteTNNJava Gradle BuildStress-NGGEGLNCNNGEGLLuaJITPyPerformanceGEGLLeelaChessZeroApache CouchDBNCNNWebP Image EncodeStress-NGPolyhedron Fortran BenchmarksCoremarkCaffeStress-NGStress-NGGEGLSQLiteNCNNJava 2D MicrobenchmarkMobile Neural NetworkJava 2D MicrobenchmarkFacebook RocksDBGIMPPyPerformanceParaViewParaViewKvazaarLuaJITTimed PHP CompilationParaViewParaViewLevelDBGNU Octave BenchmarkVkFFTPyPerformancePostMarkTNNSVT-VP9LibRawLuaJITTensorFlow LiteCaffeParaViewParaViewWebP Image EncodeParaViewParaViewAppleseedXonoticStress-NGPolyhedron Fortran BenchmarksPolyhedron Fortran BenchmarksKripkeLevelDBAI Benchmark AlphaInfluxDBStress-NGSVT-VP9LevelDBInfluxDBPolyhedron Fortran BenchmarksASTC EncoderPyPerformancePyPerformanceLAME MP3 EncodingPyPerformanceIORLuaJITStockfishCryptsetupTimed MPlayer CompilationAI Benchmark AlphaSVT-HEVCCloverLeafWebP Image EncodeTensorFlow LitePolyhedron Fortran BenchmarksoneDNNIORASTC EncoderMobile Neural NetworkSQLite SpeedtestZstd CompressionASTC EncoderWebP Image EncodeLAMMPS Molecular Dynamics SimulatorSVT-AV1ASTC EncoderJohn The RipperWebP Image EncodeZstd CompressionPop OS 20.04Pop OS 20.10

System76 Thelio Major 3990X Pop OSncnn: Vulkan GPU - vgg16polyhedron: tfft2ncnn: Vulkan GPU-v3-v3 - mobilenet-v3ncnn: Vulkan GPU-v2-v2 - mobilenet-v2ncnn: Vulkan GPU - mnasnetrealsr-ncnn: 4x - Yesncnn: Vulkan GPU - googlenetncnn: Vulkan GPU - resnet50pyperformance: python_startupncnn: Vulkan GPU - resnet18realsr-ncnn: 4x - Noncnn: Vulkan GPU - shufflenet-v2waifu2x-ncnn: 2x - 3 - Yesncnn: Vulkan GPU - yolov4-tinyonednn: Convolution Batch Shapes Auto - f32 - CPUncnn: Vulkan GPU - mobilenetncnn: Vulkan GPU - squeezenetonednn: Matrix Multiply Batch Shapes Transformer - f32 - CPUgmic: 2D Function Plotting, 1000 Timespolyhedron: airstress-ng: Socket Activityj2dbench: Image Renderinghmmer: Pfam Database Searchmlpack: scikit_icabuild-ffmpeg: Time To Compilegegl: Wavelet Blurrsvg: SVG Files To PNGstress-ng: Semaphoresgegl: Antialiaslczero: Eigenpyperformance: django_templategegl: Color Enhancencnn: Vulkan GPU - blazefacegegl: Scalegegl: Tile Glasspyperformance: pickle_pure_pythontensorflow-lite: Inception ResNet V2tnn: CPU - MobileNet v2stress-ng: MEMFDgegl: Reflectgegl: Croppyperformance: json_loadsgegl: Rotate 90 Degreeslczero: BLAScouchdb: 100 - 1000 - 24ncnn: CPU - shufflenet-v2webp: Defaultstress-ng: CPU Stresspolyhedron: fatigue2coremark: CoreMark Size 666 - Iterations Per Secondcaffe: GoogleNet - CPU - 100stress-ng: NUMAstress-ng: Forkinggegl: Cartoonsqlite: 8j2dbench: Text Renderingj2dbench: All Rendering Testsrocksdb: Read While Writinggimp: auto-levelspyperformance: regex_compileparaview: Wavelet Contour - 1920 x 1080paraview: Wavelet Contour - 1920 x 1080kvazaar: Bosphorus 1080p - Ultra Fastluajit: Sparse Matrix Multiplybuild-php: Time To Compileparaview: Wavelet Contour - 3840 x 2160paraview: Wavelet Contour - 3840 x 2160leveldb: Fill Syncoctave-benchmark: vkfft: pyperformance: pathlibpostmark: Disk Transaction Performancetnn: CPU - SqueezeNet v1.1svt-vp9: PSNR/SSIM Optimized - Bosphorus 1080plibraw: Post-Processing Benchmarkluajit: Dense LU Matrix Factorizationtensorflow-lite: Inception V4caffe: AlexNet - CPU - 100paraview: Wavelet Volume - 1920 x 1080paraview: Wavelet Volume - 1920 x 1080webp: Quality 100, Highest Compressionappleseed: Material Testerxonotic: 3840 x 2160 - Highstress-ng: SENDFILEpolyhedron: mdbxpolyhedron: channel2kripke: leveldb: Hot Readai-benchmark: Device Inference Scoreinfluxdb: 64 - 10000 - 2,5000,1 - 10000stress-ng: Mallocsvt-vp9: Visual Quality Optimized - Bosphorus 1080pleveldb: Rand Readinfluxdb: 1024 - 10000 - 2,5000,1 - 10000polyhedron: test_fpu2astcenc: Thoroughpyperformance: crypto_pyaespyperformance: nbodyencode-mp3: WAV To MP3pyperformance: 2to3ior: Read Testluajit: Compositestockfish: Total Timecryptsetup: PBKDF2-whirlpoolbuild-mplayer: Time To Compileai-benchmark: Device AI Scoresvt-hevc: 1080p 8-bit YUV To HEVC Video Encodecloverleaf: Lagrangian-Eulerian Hydrodynamicswebp: Quality 100, Lossless, Highest Compressiontensorflow-lite: Mobilenet Quantpolyhedron: capacitaonednn: Deconvolution Batch deconv_3d - f32 - CPUior: Write Testastcenc: Fastmnn: inception-v3sqlite-speedtest: Timed Time - Size 1,000compress-zstd: 19astcenc: Mediumwebp: Quality 100, Losslesslammps: Rhodopsin Proteinsvt-av1: Enc Mode 4 - 1080pastcenc: Exhaustivejohn-the-ripper: Blowfishwebp: Quality 100compress-zstd: 3onednn: IP Batch 1D - f32 - CPUrnnoise: tesseract-ocr: Time To OCR 7 Imagesonednn: Recurrent Neural Network Inference - f32 - CPUhugin: Panorama Photo Assistant + Stitching Timencnn: CPU - resnet50selenium: ARES-6 - Firefoxpolyhedron: acgimp: resizencnn: CPU - efficientnet-b0ai-benchmark: Device Training Scorepyperformance: raytracencnn: CPU - mobilenetleveldb: Rand Fillsvt-av1: Enc Mode 0 - 1080pstress-ng: Memory Copyingncnn: CPU-v2-v2 - mobilenet-v2tesseract: 3840 x 2160appleseed: Emilyrocksdb: Rand Fill Syncncnn: Vulkan GPU - efficientnet-b0mnn: MobileNetV2_224hint: FLOATtesseract: 1920 x 1080mocassin: Dust 2D tau100.0leveldb: Rand Fillncnn: CPU - yolov4-tinypybench: Total For Average Test Timesmlpack: scikit_linearridgeregressionetlegacy: Renderer2 - 3840 x 2160espeak: Text-To-Speech Synthesispolyhedron: aermodpolyhedron: mp_prop_designblender: Classroom - CPU-Onlyselenium: Speedometer - Firefoxospray: San Miguel - SciVisbuild-linux-kernel: Time To Compileoptcarrot: Optimized Benchmarkselenium: Basemark - Firefoxpolyhedron: gas_dyn2selenium: Jetstream - Firefoxxonotic: 3840 x 2160 - Ultimategimp: rotatekvazaar: Bosphorus 1080p - Very Fastncnn: CPU - alexnetselenium: CanvasMark - Firefoxbuild-gdb: Time To Compilepolyhedron: linpkselenium: Jetstream 2 - Firefoxpyperformance: chaosgromacs: Water Benchmarkxonotic: 3840 x 2160 - Lowpyperformance: floatmlpack: scikit_qdatensorflow-lite: NASNet Mobilegit: Time To Complete Common Git Commandsblender: Barbershop - CPU-Onlyappleseed: Disney Materialleveldb: Overwriteleveldb: Overwriteglmark2: 3840 x 2160sqlite: 1tensorflow-lite: Mobilenet Floatstress-ng: Cryptoselenium: WebXPRT - Firefoxleveldb: Seq Fillbuild-apache: Time To Compileleveldb: Seq Fillgimp: unsharp-maskdolfyn: Computational Fluid Dynamicsbyte: Dhrystone 2onednn: IP Batch All - f32 - CPUtensorflow-lite: SqueezeNetleveldb: Fill Synclammps: 20k Atomsonednn: Deconvolution Batch deconv_1d - f32 - CPUcryptsetup: PBKDF2-sha512kvazaar: Bosphorus 4K - Mediumj2dbench: Vector Graphics Renderingoidn: Memorialxonotic: 3840 x 2160 - Ultraffte: N=256, 3D Complex FFT Routinegpaw: Carbon Nanotubeselenium: WASM imageConvolute - Firefoxmlpack: scikit_svmpolyhedron: proteinrawtherapee: Total Benchmark Timekvazaar: Bosphorus 1080p - Mediumencode-flac: WAV To FLACblender: Fishy Cat - CPU-Onlyncnn: CPU - googlenetgmic: 3D Elevated Function In Rand Colors, 100 Timeskvazaar: Bosphorus 4K - Very Fastncnn: CPU - resnet18stress-ng: Vector Mathsvt-vp9: VMAF Optimized - Bosphorus 1080pstress-ng: Glibc C String Functionspolyhedron: rnflowleveldb: Rand Deleteospray: XFrog Forest - SciVisopenssl: RSA 4096-bit Performancegmic: Plotting Isosurface Of A 3D Volume, 1000 Timesx265: Bosphorus 4Kluajit: Jacobi Successive Over-Relaxationinfluxdb: 4 - 10000 - 2,5000,1 - 10000leveldb: Seek Randsvt-av1: Enc Mode 8 - 1080pncnn: CPU - vgg16rocksdb: Rand Fillblender: Pabellon Barcelona - CPU-Onlystress-ng: Glibc Qsort Data Sortingx265: Bosphorus 1080pkvazaar: Bosphorus 4K - Slowblender: BMW27 - CPU-Onlyrocksdb: Seq Fillmnn: resnet-v2-50mnn: mobilenet-v1-1.0john-the-ripper: MD5selenium: StyleBench - Firefoxstress-ng: Atomicrocksdb: Rand Readospray: XFrog Forest - Path Traceropenvkl: vklBenchmarknamd: ATPase Simulation - 327,506 Atomsbuild-llvm: Time To Compilepolyhedron: induct2onednn: Recurrent Neural Network Training - f32 - CPUkvazaar: Bosphorus 1080p - Slowbrl-cad: VGR Performance Metricospray: San Miguel - Path Tracerncnn: CPU - squeezenetselenium: Kraken - Firefoxpolyhedron: doduckvazaar: Bosphorus 4K - Ultra Fastglmark2: 1920 x 1080rays1bench: Large Scenemafft: Multiple Sequence Alignment - LSU RNAluajit: Monte Carlostress-ng: Matrix Mathselenium: WASM collisionDetection - Firefoxselenium: Octane - Firefoxocrmypdf: Processing 60 Page PDF Documentcryptsetup: PBKDF2-whirlpoolselenium: Maze Solver - Firefoxpyperformance: goocrmypdf: Processing 60 Page PDF Documentdarktable: Server Room - CPU-onlydarktable: Server Rack - CPU-onlydarktable: Masskrug - CPU-onlydarktable: Boat - CPU-onlycryptsetup: PBKDF2-sha512ospray: Magnetic Reconnection - Path Tracerospray: NASA Streamlines - Path Tracerospray: Magnetic Reconnection - SciVisospray: NASA Streamlines - SciVisparaview: Many Spheres - 3840 x 2160paraview: Many Spheres - 3840 x 2160paraview: Many Spheres - 1920 x 1080paraview: Many Spheres - 1920 x 1080selenium: MotionMark - Firefoxncnn: Vulkan GPU - alexnetncnn: CPU - blazefacencnn: CPU - mnasnetncnn: CPU-v3-v3 - mobilenet-v3mnn: SqueezeNetV1.0stress-ng: Context Switchingstress-ng: CPU Cachestress-ng: MMAPluajit: Fast Fourier Transformjava-gradle-perf: Reactorparaview: Wavelet Volume - 3840 x 2160paraview: Wavelet Volume - 3840 x 2160Pop OS 20.04Pop OS 20.1084.3649.088.474.604.66114.4448.519.6512.83.3416.5123.489.10115.042.127899.985.820.508544222.5561.7121460.218553596.5131508165.03551.9219.73664.72529.14910710303.2341.076140347.558.0971.256.60432.965441608725285.9211328.9831.5918.84323.939.9181462119.18714.401.48123480.9248.612256436.9772961481131436.4660628.8494.521114.99721836.3390721777815320.9604010759955115.8251603145.937301.88243.711221.2935.452164.191711.0682.47.0092050616.37654252.180394.0741.833668.7971202655465219.583513.2517.138150.800832383.4692564939891.744.441.844881177109.51919331512392.31434398195.48326.72109.9971557894.428.559.721031087.3123021610.781541.4714646348670596310.6133131208.290.4033.50033371.216.272.07153316.524.6231.85464.26881.75.3316.29523.8459.69637.6879102.2897285.81.2644118.80924.973115.06846.73938.4244.146.078.52517.66119843928.32623.7260.1288297.2313.39311.5822133.2447612316811.555.375373293210.02252369.069022322.736.309411.59241.528.1195.7455.384.9585.167.4624.295131.33788.1641.97205.39268.307837512.757139.6612.171763889.7873.0391.7411043.767506.688829610842.5477536.748.365131.1257.54923622.8621.251268133.09231423.514517.0323923.921.267591.61219.14016.86343076608.723.778150791.35953.96026.9081.5509716.067844283.975062127.01335.6182130129515.00422893109.74628.020.8712.7250.51062.427.97146.3426.3984.88634.8817.87467815.75374.647401405.6015.32597.96013.7615077.319.37926.252055.731145700.1171.02996.30053.4544442598.66847.4058.1915.8332.4344751433.5495.457522966770.0493383.162731468177.32461.150.42677205.33921.92328.32560.857841665.7025.27829.86.7560.738575311.308.806506.84225010.9376.9346215.423315.2282.1360.0922.9745.4961622356333.3320.4143.4890.915540.16855.265732.05457.17139.0429.855.8813.4513.908.25828076290.9570.95199.60254.69264.2312575.513160.9719.5218.753.302.332.4359.7964.565.197.061.949.7682.075.81510.121.508377.254.280.409650273.2681.4325587.3710164303.1574056192.73245.1117.22456.58125.6009502361.9937.044154343.352.9781.146.02530.158404662848263.7761228.2629.3518.24925.537.4541555112.34813.591.39824863.2551.472389189.5703021399131360.3357529.8089.717121.11920762.6751298808213273.0093887797951515.1121533289.278315.63233.201275.8037.023171.431786.5042.37.3111966117.07352242.386379.1440.253810.8773938753425227.813644.9287.404145.512909370.2077220908290.794.5543.2246400823113.16818731560822.31479267553.14316.81113.4311605455.629.49.441061117.5122941568.551582.4114267741472450810.8903052203.140.4134.32732579.615.892.02358309.614.5231.18562.92980.05.2216.63823.3609.50136.85896922.2457428.51.2405318.45824.507112.92645.87037.7243.345.968.37717.37117944627.88614.0910.1308172.4413.19316.2526135.1363812284711.395.450368160160.20334364.083922023.035.839531.61238.528.4705.8154.6485.9784.166.6724.582129.80779.1941.5207.68265.360087412.896138.1612.041781788.8983.0692.6471033.803511.476546110942.9376836.347.930132.3157.03271223.0615.959270432.81431688.414639.1924124.121.442586.82019.29616.72742730397.923.587751197.96001.09626.6971.53906173605615.947902853.722280527.21333.1577205128567.08880589110.54227.821.0212.6350.86461.997.91946.6426.5685.41934.6717.77470369.86372.647440489.4215.24594.85213.8315149.319.28826.372046.501150845.0170.32295.91953.6544276999.00850.3158.0015.7832.5344885733.4495.473524466769.8494741.952738954627.34459.940.42787204.83221.87327.63360.737855585.6925.31828.56.7460.818568311.558.800506.60225079.79377.03462212.6447288765.4233333.3320.4143.4890.91137.116.485.5912.5313.668.68124978427.8671.501136.58272.28286.3962669.658166.85OpenBenchmarking.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: vgg16Pop OS 20.10Pop OS 20.0420406080100SE +/- 0.21, N = 4SE +/- 0.04, N = 319.5284.36MIN: 13.93 / MAX: 45.71MIN: 67.87 / MAX: 109.541. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Polyhedron Fortran Benchmarks

The Fortran.uk Polyhedron Fortran Benchmarks for comparing Fortran compiler performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPolyhedron Fortran BenchmarksBenchmark: tfft2Pop OS 20.10Pop OS 20.04112233445518.7549.08

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-v3Pop OS 20.10Pop OS 20.04246810SE +/- 0.00, N = 4SE +/- 0.24, N = 33.308.47MIN: 3.24 / MAX: 3.95MIN: 7.45 / MAX: 27.991. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2Pop OS 20.10Pop OS 20.041.0352.073.1054.145.175SE +/- 0.01, N = 4SE +/- 0.01, N = 32.334.60MIN: 2.27 / MAX: 2.83MIN: 4.27 / MAX: 9.61. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: mnasnetPop OS 20.10Pop OS 20.041.04852.0973.14554.1945.2425SE +/- 0.01, N = 4SE +/- 0.01, N = 32.434.66MIN: 2.38 / MAX: 6.46MIN: 4.41 / MAX: 5.41. (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: YesPop OS 20.10Pop OS 20.04306090120150SE +/- 0.10, N = 3SE +/- 0.16, N = 359.80114.44

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: googlenetPop OS 20.10Pop OS 20.04246810SE +/- 0.02, N = 4SE +/- 0.02, N = 34.568.51MIN: 4.5 / MAX: 11.22MIN: 7.13 / MAX: 29.751. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: resnet50Pop OS 20.10Pop OS 20.043691215SE +/- 0.01, N = 4SE +/- 0.09, N = 25.199.65MIN: 5.13 / MAX: 7.96MIN: 9.05 / MAX: 31.861. (CXX) g++ options: -O3 -rdynamic -lgomp -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: python_startupPop OS 20.10Pop OS 20.043691215SE +/- 0.01, N = 3SE +/- 0.00, N = 37.0612.80

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: resnet18Pop OS 20.10Pop OS 20.040.75151.5032.25453.0063.7575SE +/- 0.02, N = 4SE +/- 0.01, N = 31.943.34MIN: 1.87 / MAX: 8.1MIN: 3.22 / MAX: 5.291. (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: NoPop OS 20.10Pop OS 20.0448121620SE +/- 0.023, N = 3SE +/- 0.059, N = 39.76816.512

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-v2Pop OS 20.10Pop OS 20.040.7831.5662.3493.1323.915SE +/- 0.00, N = 4SE +/- 0.00, N = 32.073.48MIN: 2.03 / MAX: 2.39MIN: 3.38 / MAX: 4.251. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

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: YesPop OS 20.10Pop OS 20.043691215SE +/- 0.014, N = 3SE +/- 0.010, N = 35.8159.101

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-tinyPop OS 20.10Pop OS 20.0448121620SE +/- 0.04, N = 4SE +/- 0.02, N = 310.1215.04MIN: 9.51 / MAX: 33.51MIN: 12.6 / MAX: 42.11. (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: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPUPop OS 20.10Pop OS 20.040.47880.95761.43641.91522.394SE +/- 0.02199, N = 3SE +/- 0.02500, N = 61.508372.12789MIN: 1.39MIN: 1.951. (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: mobilenetPop OS 20.10Pop OS 20.043691215SE +/- 0.00, N = 4SE +/- 0.16, N = 37.259.98MIN: 7.17 / MAX: 9.66MIN: 8.51 / MAX: 38.161. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: squeezenetPop OS 20.10Pop OS 20.041.30952.6193.92855.2386.5475SE +/- 0.06, N = 4SE +/- 0.05, N = 34.285.82MIN: 3.98 / MAX: 12.42MIN: 5.53 / MAX: 19.721. (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: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPUPop OS 20.10Pop OS 20.040.11440.22880.34320.45760.572SE +/- 0.001131, N = 3SE +/- 0.006670, N = 40.4096500.508544MIN: 0.39MIN: 0.461. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

G'MIC

G'MIC is an open-source framework for image processing. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterG'MICTest: 2D Function Plotting, 1000 TimesPop OS 20.10Pop OS 20.0460120180240300SE +/- 1.23, N = 3SE +/- 1.54, N = 3273.27222.561. Version 2.4.5, Copyright (c) 2008-2019, David Tschumperle.

Polyhedron Fortran Benchmarks

The Fortran.uk Polyhedron Fortran Benchmarks for comparing Fortran compiler performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPolyhedron Fortran BenchmarksBenchmark: airPop OS 20.10Pop OS 20.040.38480.76961.15441.53921.9241.431.71

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Socket ActivityPop OS 20.10Pop OS 20.045K10K15K20K25KSE +/- 41.65, N = 3SE +/- 178.33, N = 325587.3721460.211. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

Java 2D Microbenchmark

This test runs a series of microbenchmarks to check the performance of the OpenGL-based Java 2D pipeline and the underlying OpenGL drivers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgUnits Per Second, More Is BetterJava 2D Microbenchmark 1.0Rendering Test: Image RenderingPop OS 20.10Pop OS 20.042M4M6M8M10MSE +/- 76198.19, N = 4SE +/- 33957.70, N = 410164303.168553596.51

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 SearchPop OS 20.10Pop OS 20.044080120160200SE +/- 0.19, N = 3SE +/- 0.31, N = 3192.73165.041. (CC) gcc options: -O3 -pthread -lhmmer -leasel -lm

Mlpack Benchmark

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

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_icaPop OS 20.10Pop OS 20.041224364860SE +/- 0.49, N = 3SE +/- 0.46, N = 345.1151.92

Timed FFmpeg Compilation

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed FFmpeg Compilation 4.2.2Time To CompilePop OS 20.10Pop OS 20.04510152025SE +/- 0.03, N = 3SE +/- 0.06, N = 317.2219.74

GEGL

GEGL is the Generic Graphics Library and is the library/framework used by GIMP and other applications like GNOME Photos. This test profile times how long it takes to complete various GEGL operations on a static set of sample JPEG images. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: Wavelet BlurPop OS 20.10Pop OS 20.041428425670SE +/- 0.10, N = 3SE +/- 0.24, N = 356.5864.73

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 PNGPop OS 20.10Pop OS 20.04714212835SE +/- 0.11, N = 3SE +/- 0.04, N = 325.6029.151. Pop OS 20.10: rsvg-convert version 2.50.12. Pop OS 20.04: rsvg-convert version 2.48.7

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: SemaphoresPop OS 20.10Pop OS 20.042M4M6M8M10MSE +/- 73990.03, N = 3SE +/- 10552.55, N = 39502361.9910710303.231. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

GEGL

GEGL is the Generic Graphics Library and is the library/framework used by GIMP and other applications like GNOME Photos. This test profile times how long it takes to complete various GEGL operations on a static set of sample JPEG images. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: AntialiasPop OS 20.10Pop OS 20.04918273645SE +/- 0.02, N = 3SE +/- 0.03, N = 337.0441.08

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: EigenPop OS 20.10Pop OS 20.0430060090012001500SE +/- 9.54, N = 3SE +/- 7.88, N = 3154314031. (CXX) g++ options: -flto -pthread

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_templatePop OS 20.10Pop OS 20.041122334455SE +/- 0.03, N = 3SE +/- 0.23, N = 343.347.5

GEGL

GEGL is the Generic Graphics Library and is the library/framework used by GIMP and other applications like GNOME Photos. This test profile times how long it takes to complete various GEGL operations on a static set of sample JPEG images. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: Color EnhancePop OS 20.10Pop OS 20.041326395265SE +/- 0.12, N = 3SE +/- 0.10, N = 352.9858.10

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: blazefacePop OS 20.10Pop OS 20.040.28130.56260.84391.12521.4065SE +/- 0.01, N = 4SE +/- 0.04, N = 31.141.25MIN: 1.01 / MAX: 5.19MIN: 1.1 / MAX: 15.981. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

GEGL

GEGL is the Generic Graphics Library and is the library/framework used by GIMP and other applications like GNOME Photos. This test profile times how long it takes to complete various GEGL operations on a static set of sample JPEG images. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: ScalePop OS 20.10Pop OS 20.04246810SE +/- 0.052, N = 3SE +/- 0.019, N = 36.0256.604

OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: Tile GlassPop OS 20.10Pop OS 20.04816243240SE +/- 0.01, N = 3SE +/- 0.04, N = 330.1632.97

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_pythonPop OS 20.10Pop OS 20.04100200300400500SE +/- 0.33, N = 3SE +/- 2.40, N = 3404441

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 V2Pop OS 20.10Pop OS 20.04140K280K420K560K700KSE +/- 9494.68, N = 3SE +/- 9183.49, N = 3662848608725

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 v2Pop OS 20.10Pop OS 20.0460120180240300SE +/- 0.33, N = 3SE +/- 3.39, N = 3263.78285.92MIN: 253.36 / MAX: 295.53MIN: 272.2 / MAX: 310.861. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -O3 -rdynamic -ldl

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: MEMFDPop OS 20.10Pop OS 20.0430060090012001500SE +/- 2.24, N = 3SE +/- 1.43, N = 31228.261328.981. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

GEGL

GEGL is the Generic Graphics Library and is the library/framework used by GIMP and other applications like GNOME Photos. This test profile times how long it takes to complete various GEGL operations on a static set of sample JPEG images. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: ReflectPop OS 20.10Pop OS 20.04714212835SE +/- 0.00, N = 3SE +/- 0.08, N = 329.3531.59

OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: CropPop OS 20.10Pop OS 20.04246810SE +/- 0.037, N = 3SE +/- 0.043, N = 38.2498.843

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_loadsPop OS 20.10Pop OS 20.04612182430SE +/- 0.03, N = 3SE +/- 0.03, N = 325.523.9

GEGL

GEGL is the Generic Graphics Library and is the library/framework used by GIMP and other applications like GNOME Photos. This test profile times how long it takes to complete various GEGL operations on a static set of sample JPEG images. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: Rotate 90 DegreesPop OS 20.10Pop OS 20.04918273645SE +/- 0.02, N = 3SE +/- 0.01, N = 337.4539.92

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: BLASPop OS 20.10Pop OS 20.0430060090012001500SE +/- 5.84, N = 3SE +/- 23.33, N = 3155514621. (CXX) g++ options: -flto -pthread

Apache CouchDB

This is a bulk insertion benchmark of Apache CouchDB. CouchDB is a document-oriented NoSQL database implemented in Erlang. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterApache CouchDB 3.1.1Bulk Size: 100 - Inserts: 1000 - Rounds: 24Pop OS 20.10Pop OS 20.04306090120150SE +/- 0.06, N = 3SE +/- 0.94, N = 3112.35119.191. (CXX) g++ options: -std=c++14 -lmozjs-68 -lm -lerl_interface -lei -fPIC -MMD

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: shufflenet-v2Pop OS 20.10Pop OS 20.0448121620SE +/- 0.32, N = 3SE +/- 0.45, N = 313.5914.40MIN: 12.75 / MAX: 19.23MIN: 13.1 / MAX: 33.211. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

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: DefaultPop OS 20.10Pop OS 20.040.33320.66640.99961.33281.666SE +/- 0.005, N = 3SE +/- 0.002, N = 31.3981.4811. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: CPU StressPop OS 20.10Pop OS 20.045K10K15K20K25KSE +/- 34.23, N = 3SE +/- 126.54, N = 324863.2523480.921. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

Polyhedron Fortran Benchmarks

The Fortran.uk Polyhedron Fortran Benchmarks for comparing Fortran compiler performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPolyhedron Fortran BenchmarksBenchmark: fatigue2Pop OS 20.10Pop OS 20.04122436486051.4748.61

Coremark

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

OpenBenchmarking.orgIterations/Sec, More Is BetterCoremark 1.0CoreMark Size 666 - Iterations Per SecondPop OS 20.10Pop OS 20.04500K1000K1500K2000K2500KSE +/- 7921.87, N = 3SE +/- 15042.16, N = 32389189.572256436.981. (CC) gcc options: -O2 -lrt" -lrt

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: 100Pop OS 20.10Pop OS 20.0430K60K90K120K150KSE +/- 403.30, N = 3SE +/- 128.26, N = 31399131481131. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: NUMAPop OS 20.10Pop OS 20.0430060090012001500SE +/- 11.10, N = 3SE +/- 10.43, N = 31360.331436.461. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: ForkingPop OS 20.10Pop OS 20.0413K26K39K52K65KSE +/- 554.14, N = 9SE +/- 318.60, N = 357529.8060628.841. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

GEGL

GEGL is the Generic Graphics Library and is the library/framework used by GIMP and other applications like GNOME Photos. This test profile times how long it takes to complete various GEGL operations on a static set of sample JPEG images. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: CartoonPop OS 20.10Pop OS 20.0420406080100SE +/- 0.07, N = 3SE +/- 0.33, N = 389.7294.52

SQLite

This is a simple benchmark of SQLite. At present this test profile just measures the time to perform a pre-defined number of insertions on an indexed database. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSQLite 3.30.1Threads / Copies: 8Pop OS 20.10Pop OS 20.04306090120150SE +/- 0.19, N = 3SE +/- 0.34, N = 3121.12115.001. (CC) gcc options: -O2 -lz -lm -ldl -lpthread

Java 2D Microbenchmark

This test runs a series of microbenchmarks to check the performance of the OpenGL-based Java 2D pipeline and the underlying OpenGL drivers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgUnits Per Second, More Is BetterJava 2D Microbenchmark 1.0Rendering Test: Text RenderingPop OS 20.10Pop OS 20.045K10K15K20K25KSE +/- 169.43, N = 4SE +/- 265.68, N = 420762.6821836.34

OpenBenchmarking.orgUnits Per Second, More Is BetterJava 2D Microbenchmark 1.0Rendering Test: All Rendering TestsPop OS 20.10Pop OS 20.042M4M6M8M10MSE +/- 32569.86, N = 4SE +/- 81902.34, N = 48213273.017815320.96

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: Read While WritingPop OS 20.10Pop OS 20.042M4M6M8M10MSE +/- 73738.48, N = 3SE +/- 31345.48, N = 3797951575995511. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread

GIMP

GIMP is an open-source image manipulaton program. This test profile will use the system-provided GIMP program otherwise on Windows relys upon a pre-packaged Windows binary from upstream GIMP.org. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.18Test: auto-levelsPop OS 20.10Pop OS 20.0448121620SE +/- 0.09, N = 3SE +/- 0.22, N = 415.1115.83

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_compilePop OS 20.10Pop OS 20.044080120160200SE +/- 0.33, N = 3SE +/- 0.58, N = 3153160

ParaView

This test runs ParaView benchmarks: an open-source data analytics and visualization application. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiPolys / Sec, More Is BetterParaView 5.4.1Test: Wavelet Contour - Resolution: 1920 x 1080Pop OS 20.10Pop OS 20.047001400210028003500SE +/- 15.16, N = 3SE +/- 34.36, N = 73289.283145.94

OpenBenchmarking.orgFrames / Sec, More Is BetterParaView 5.4.1Test: Wavelet Contour - Resolution: 1920 x 1080Pop OS 20.10Pop OS 20.0470140210280350SE +/- 1.46, N = 3SE +/- 3.30, N = 7315.63301.88

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 FastPop OS 20.10Pop OS 20.0450100150200250SE +/- 1.02, N = 3SE +/- 3.51, N = 3233.20243.711. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

LuaJIT

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

OpenBenchmarking.orgMflops, More Is BetterLuaJIT 2.1-gitTest: Sparse Matrix MultiplyPop OS 20.10Pop OS 20.0430060090012001500SE +/- 4.60, N = 3SE +/- 3.63, N = 31275.801221.291. (CC) gcc options: -lm -ldl -O2 -fomit-frame-pointer -U_FORTIFY_SOURCE -fno-stack-protector

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 CompilePop OS 20.10Pop OS 20.04918273645SE +/- 0.04, N = 3SE +/- 0.05, N = 337.0235.45

ParaView

This test runs ParaView benchmarks: an open-source data analytics and visualization application. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames / Sec, More Is BetterParaView 5.4.1Test: Wavelet Contour - Resolution: 3840 x 2160Pop OS 20.10Pop OS 20.044080120160200SE +/- 0.84, N = 3SE +/- 0.20, N = 3171.43164.19

OpenBenchmarking.orgMiPolys / Sec, More Is BetterParaView 5.4.1Test: Wavelet Contour - Resolution: 3840 x 2160Pop OS 20.10Pop OS 20.04400800120016002000SE +/- 8.76, N = 3SE +/- 2.06, N = 31786.501711.07

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 SyncPop OS 20.10Pop OS 20.040.541.081.622.162.7SE +/- 0.03, N = 3SE +/- 0.00, N = 32.32.41. (CXX) g++ options: -O3 -lsnappy -lpthread

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 5.2.0Pop OS 20.10Pop OS 20.04246810SE +/- 0.041, N = 5SE +/- 0.047, N = 57.3117.009

VkFFT

VkFFT is a Fast Fourier Transform (FFT) Library that is GPU accelerated by means of the Vulkan API. The VkFFT benchmark runs FFT performance differences of many different sizes before returning an overall benchmark score. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 2020-09-29Pop OS 20.10Pop OS 20.044K8K12K16K20KSE +/- 52.84, N = 3SE +/- 45.28, N = 31966120506

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: pathlibPop OS 20.10Pop OS 20.0448121620SE +/- 0.06, N = 3SE +/- 0.03, N = 317.016.3

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 PerformancePop OS 20.10Pop OS 20.0416003200480064008000SE +/- 79.00, N = 3735276541. (CC) gcc options: -O3

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 v1.1Pop OS 20.10Pop OS 20.0460120180240300SE +/- 0.04, N = 3SE +/- 0.59, N = 3242.39252.18MIN: 241.15 / MAX: 244.95MIN: 249.83 / MAX: 254.131. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -O3 -rdynamic -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: PSNR/SSIM Optimized - Input: Bosphorus 1080pPop OS 20.10Pop OS 20.0490180270360450SE +/- 2.66, N = 3SE +/- 2.19, N = 3379.14394.071. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

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 BenchmarkPop OS 20.10Pop OS 20.041020304050SE +/- 0.06, N = 3SE +/- 0.46, N = 340.2541.831. (CXX) g++ options: -O2 -fopenmp -ljpeg -lz -lm

LuaJIT

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

OpenBenchmarking.orgMflops, More Is BetterLuaJIT 2.1-gitTest: Dense LU Matrix FactorizationPop OS 20.10Pop OS 20.048001600240032004000SE +/- 9.34, N = 3SE +/- 18.22, N = 33810.873668.791. (CC) gcc options: -lm -ldl -O2 -fomit-frame-pointer -U_FORTIFY_SOURCE -fno-stack-protector

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 V4Pop OS 20.10Pop OS 20.04160K320K480K640K800KSE +/- 8089.81, N = 3SE +/- 12287.55, N = 3739387712026

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: 100Pop OS 20.10Pop OS 20.0412K24K36K48K60KSE +/- 96.78, N = 3SE +/- 240.27, N = 353425554651. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

ParaView

This test runs ParaView benchmarks: an open-source data analytics and visualization application. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames / Sec, More Is BetterParaView 5.4.1Test: Wavelet Volume - Resolution: 1920 x 1080Pop OS 20.10Pop OS 20.0450100150200250SE +/- 1.90, N = 15SE +/- 0.22, N = 3227.81219.58

OpenBenchmarking.orgMiVoxels / Sec, More Is BetterParaView 5.4.1Test: Wavelet Volume - Resolution: 1920 x 1080Pop OS 20.10Pop OS 20.048001600240032004000SE +/- 30.37, N = 15SE +/- 3.52, N = 33644.933513.25

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 CompressionPop OS 20.10Pop OS 20.04246810SE +/- 0.011, N = 3SE +/- 0.015, N = 37.4047.1381. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff

Appleseed

Appleseed is an open-source production renderer focused on physically-based global illumination rendering engine primarily designed for animation and visual effects. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterAppleseed 2.0 BetaScene: Material TesterPop OS 20.10Pop OS 20.04306090120150145.51150.80

Xonotic

This is a benchmark of Xonotic, which is a fork of the DarkPlaces-based Nexuiz game. Development began in March of 2010 on the Xonotic game. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterXonotic 0.8.2Resolution: 3840 x 2160 - Effects Quality: HighPop OS 20.10Pop OS 20.0480160240320400SE +/- 1.03, N = 3SE +/- 3.24, N = 3370.21383.47MIN: 221 / MAX: 712MIN: 235 / MAX: 737

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: SENDFILEPop OS 20.10Pop OS 20.04200K400K600K800K1000KSE +/- 4367.48, N = 3SE +/- 4104.72, N = 3908290.79939891.741. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

Polyhedron Fortran Benchmarks

The Fortran.uk Polyhedron Fortran Benchmarks for comparing Fortran compiler performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPolyhedron Fortran BenchmarksBenchmark: mdbxPop OS 20.10Pop OS 20.041.02382.04763.07144.09525.1194.554.40

OpenBenchmarking.orgSeconds, Fewer Is BetterPolyhedron Fortran BenchmarksBenchmark: channel2Pop OS 20.10Pop OS 20.04102030405043.2241.80

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 1.2.4Pop OS 20.10Pop OS 20.0410M20M30M40M50MSE +/- 261985.44, N = 3SE +/- 167341.17, N = 346400823448811771. (CXX) g++ options: -O3 -fopenmp

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 ReadPop OS 20.10Pop OS 20.04306090120150SE +/- 0.18, N = 3SE +/- 0.39, N = 3113.17109.521. (CXX) g++ options: -O3 -lsnappy -lpthread

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 ScorePop OS 20.10Pop OS 20.0440080012001600200018731933

InfluxDB

This is a benchmark of the InfluxDB open-source time-series database optimized for fast, high-availability storage for IoT and other use-cases. The InfluxDB test profile makes use of InfluxDB Inch for facilitating the benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgval/sec, More Is BetterInfluxDB 1.8.2Concurrent Streams: 64 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000Pop OS 20.10Pop OS 20.04300K600K900K1200K1500KSE +/- 3262.53, N = 3SE +/- 2557.98, N = 31560822.31512392.3

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: MallocPop OS 20.10Pop OS 20.04300M600M900M1200M1500MSE +/- 4454743.33, N = 3SE +/- 3294705.19, N = 31479267553.141434398195.481. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

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 1080pPop OS 20.10Pop OS 20.0470140210280350SE +/- 1.98, N = 3SE +/- 2.60, N = 3316.81326.721. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -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: Random ReadPop OS 20.10Pop OS 20.04306090120150SE +/- 1.63, N = 4SE +/- 0.20, N = 3113.43110.001. (CXX) g++ options: -O3 -lsnappy -lpthread

InfluxDB

This is a benchmark of the InfluxDB open-source time-series database optimized for fast, high-availability storage for IoT and other use-cases. The InfluxDB test profile makes use of InfluxDB Inch for facilitating the benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgval/sec, More Is BetterInfluxDB 1.8.2Concurrent Streams: 1024 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000Pop OS 20.10Pop OS 20.04300K600K900K1200K1500KSE +/- 3082.28, N = 3SE +/- 1531.99, N = 31605455.61557894.4

Polyhedron Fortran Benchmarks

The Fortran.uk Polyhedron Fortran Benchmarks for comparing Fortran compiler performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPolyhedron Fortran BenchmarksBenchmark: test_fpu2Pop OS 20.10Pop OS 20.0471421283529.4028.55

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: ThoroughPop OS 20.10Pop OS 20.043691215SE +/- 0.03, N = 3SE +/- 0.04, N = 39.449.721. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -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: crypto_pyaesPop OS 20.10Pop OS 20.0420406080100106103

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: nbodyPop OS 20.10Pop OS 20.0420406080100SE +/- 0.33, N = 3SE +/- 0.33, N = 3111108

LAME MP3 Encoding

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

OpenBenchmarking.orgSeconds, Fewer Is BetterLAME MP3 Encoding 3.100WAV To MP3Pop OS 20.10Pop OS 20.04246810SE +/- 0.011, N = 3SE +/- 0.024, N = 37.5127.3121. (CC) gcc options: -O3 -ffast-math -funroll-loops -fschedule-insns2 -fbranch-count-reg -fforce-addr -pipe -lm

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: 2to3Pop OS 20.10Pop OS 20.0470140210280350294302

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 TestPop OS 20.10Pop OS 20.0430060090012001500SE +/- 20.07, N = 3SE +/- 24.01, N = 31568.551610.78MIN: 1381.67 / MAX: 1657.33MIN: 1389.69 / MAX: 1676.231. (CC) gcc options: -O2 -lm -pthread -lmpi

LuaJIT

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

OpenBenchmarking.orgMflops, More Is BetterLuaJIT 2.1-gitTest: CompositePop OS 20.10Pop OS 20.0430060090012001500SE +/- 2.02, N = 3SE +/- 2.00, N = 31582.411541.471. (CC) gcc options: -lm -ldl -O2 -fomit-frame-pointer -U_FORTIFY_SOURCE -fno-stack-protector

Stockfish

This is a test of Stockfish, an advanced C++11 chess benchmark that can scale up to 128 CPU cores. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 9Total TimePop OS 20.10Pop OS 20.0430M60M90M120M150MSE +/- 1603296.03, N = 7SE +/- 263429.87, N = 31426774141464634861. (CXX) g++ options: -m64 -lpthread -fno-exceptions -std=c++11 -pedantic -O3 -msse -msse3 -mpopcnt -flto

Cryptsetup

This is a test profile for running the cryptsetup benchmark to report on the system's cryptography performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations Per Second, More Is BetterCryptsetupPBKDF2-whirlpoolPop OS 20.10Pop OS 20.04160K320K480K640K800KSE +/- 2723.47, N = 3SE +/- 1928.95, N = 3724508705963

Timed MPlayer Compilation

This test times how long it takes to build the MPlayer open-source media player program. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MPlayer Compilation 1.4Time To CompilePop OS 20.10Pop OS 20.043691215SE +/- 0.07, N = 3SE +/- 0.03, N = 310.8910.61

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 ScorePop OS 20.10Pop OS 20.04700140021002800350030523131

SVT-HEVC

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-HEVC CPU-based multi-threaded video encoder for the HEVC / H.265 video format with a sample 1080p YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.4.11080p 8-bit YUV To HEVC Video EncodePop OS 20.10Pop OS 20.0450100150200250SE +/- 0.16, N = 3SE +/- 1.79, N = 3203.14208.291. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

CloverLeaf

CloverLeaf is a Lagrangian-Eulerian hydrodynamics benchmark. This test profile currently makes use of CloverLeaf's OpenMP version and benchmarked with the clover_bm8192.in input file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterCloverLeafLagrangian-Eulerian HydrodynamicsPop OS 20.10Pop OS 20.040.09230.18460.27690.36920.4615SE +/- 0.00, N = 3SE +/- 0.00, N = 30.410.401. (F9X) gfortran options: -O3 -march=native -funroll-loops -fopenmp

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 CompressionPop OS 20.10Pop OS 20.04816243240SE +/- 0.17, N = 3SE +/- 0.22, N = 334.3333.501. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff

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 QuantPop OS 20.10Pop OS 20.047K14K21K28K35KSE +/- 314.48, N = 3SE +/- 353.76, N = 332579.633371.2

Polyhedron Fortran Benchmarks

The Fortran.uk Polyhedron Fortran Benchmarks for comparing Fortran compiler performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPolyhedron Fortran BenchmarksBenchmark: capacitaPop OS 20.10Pop OS 20.044812162015.8916.27

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: CPUPop OS 20.10Pop OS 20.040.46610.93221.39831.86442.3305SE +/- 0.00102, N = 3SE +/- 0.01201, N = 32.023582.07153MIN: 1.92MIN: 1.931. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

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 TestPop OS 20.10Pop OS 20.0470140210280350SE +/- 1.71, N = 3SE +/- 4.29, N = 3309.61316.52MIN: 70.58 / MAX: 347.58MIN: 87.5 / MAX: 347.791. (CC) gcc options: -O2 -lm -pthread -lmpi

ASTC Encoder

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

OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.0Preset: FastPop OS 20.10Pop OS 20.041.03952.0793.11854.1585.1975SE +/- 0.02, N = 3SE +/- 0.01, N = 34.524.621. (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-v3Pop OS 20.10Pop OS 20.04714212835SE +/- 0.20, N = 15SE +/- 0.17, N = 1531.1931.85MIN: 29.36 / MAX: 36.62MIN: 30.35 / MAX: 35.691. (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

SQLite Speedtest

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

OpenBenchmarking.orgSeconds, Fewer Is BetterSQLite Speedtest 3.30Timed Time - Size 1,000Pop OS 20.10Pop OS 20.041428425670SE +/- 0.31, N = 3SE +/- 0.08, N = 362.9364.271. (CC) gcc options: -O2 -ldl -lz -lpthread

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: 19Pop OS 20.10Pop OS 20.0420406080100SE +/- 1.07, N = 3SE +/- 0.06, N = 380.081.71. (CC) gcc options: -O3 -pthread -lz -llzma

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: MediumPop OS 20.10Pop OS 20.041.19932.39863.59794.79725.9965SE +/- 0.00, N = 3SE +/- 0.01, N = 35.225.331. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread

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, LosslessPop OS 20.10Pop OS 20.0448121620SE +/- 0.04, N = 3SE +/- 0.06, N = 316.6416.301. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff

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 ProteinPop OS 20.10Pop OS 20.04612182430SE +/- 0.20, N = 15SE +/- 0.21, N = 1423.3623.851. (CXX) g++ options: -O3 -pthread -lm

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: 1080pPop OS 20.10Pop OS 20.043691215SE +/- 0.015, N = 3SE +/- 0.022, N = 39.5019.6961. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie

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: ExhaustivePop OS 20.10Pop OS 20.04918273645SE +/- 0.20, N = 3SE +/- 0.19, N = 336.8537.601. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -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: BlowfishPop OS 20.10Pop OS 20.0420K40K60K80K100KSE +/- 698.02, N = 3SE +/- 733.19, N = 389692879101. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -pthread -lm -lz -ldl -lcrypt -lbz2

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 100Pop OS 20.10Pop OS 20.040.5151.031.5452.062.575SE +/- 0.012, N = 3SE +/- 0.007, N = 32.2452.2891. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff

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: 3Pop OS 20.10Pop OS 20.0416003200480064008000SE +/- 57.84, N = 3SE +/- 14.49, N = 37428.57285.81. (CC) gcc options: -O3 -pthread -lz -llzma

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: IP Batch 1D - Data Type: f32 - Engine: CPUPop OS 20.10Pop OS 20.040.28450.5690.85351.1381.4225SE +/- 0.00845, N = 3SE +/- 0.01741, N = 41.240531.26441MIN: 1.15MIN: 1.171. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

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 2020-06-28Pop OS 20.10Pop OS 20.04510152025SE +/- 0.05, N = 3SE +/- 0.04, N = 318.4618.811. (CC) gcc options: -O2 -pedantic -fvisibility=hidden

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 ImagesPop OS 20.10Pop OS 20.04612182430SE +/- 0.13, N = 3SE +/- 0.09, N = 324.5124.97

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: CPUPop OS 20.10Pop OS 20.04306090120150SE +/- 0.36, N = 3SE +/- 0.34, N = 3112.93115.07MIN: 111.3MIN: 112.931. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

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 TimePop OS 20.10Pop OS 20.041122334455SE +/- 0.43, N = 3SE +/- 0.31, N = 345.8746.74

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: resnet50Pop OS 20.10Pop OS 20.04918273645SE +/- 0.98, N = 3SE +/- 1.06, N = 337.7238.42MIN: 34.84 / MAX: 50.32MIN: 35.21 / MAX: 58.991. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Selenium

This test profile uses the Selenium WebDriver for running various browser benchmarks in different available web browsers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterSeleniumBenchmark: ARES-6 - Browser: FirefoxPop OS 20.10Pop OS 20.041020304050SE +/- 0.09, N = 3SE +/- 0.26, N = 343.3444.141. firefox 82.0

Polyhedron Fortran Benchmarks

The Fortran.uk Polyhedron Fortran Benchmarks for comparing Fortran compiler performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPolyhedron Fortran BenchmarksBenchmark: acPop OS 20.10Pop OS 20.042468105.966.07

GIMP

GIMP is an open-source image manipulaton program. This test profile will use the system-provided GIMP program otherwise on Windows relys upon a pre-packaged Windows binary from upstream GIMP.org. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.18Test: resizePop OS 20.10Pop OS 20.04246810SE +/- 0.019, N = 3SE +/- 0.048, N = 38.3778.525

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: efficientnet-b0Pop OS 20.10Pop OS 20.0448121620SE +/- 0.56, N = 3SE +/- 0.55, N = 317.3717.66MIN: 16.21 / MAX: 21.36MIN: 16.49 / MAX: 33.241. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

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 ScorePop OS 20.10Pop OS 20.043006009001200150011791198

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: raytracePop OS 20.10Pop OS 20.04100200300400500446439

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: mobilenetPop OS 20.10Pop OS 20.04714212835SE +/- 0.17, N = 3SE +/- 0.96, N = 327.8828.32MIN: 26.24 / MAX: 32.46MIN: 25.72 / MAX: 47.51. (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: Random FillPop OS 20.10Pop OS 20.04130260390520650SE +/- 0.57, N = 3SE +/- 1.02, N = 3614.09623.731. (CXX) g++ options: -O3 -lsnappy -lpthread

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: 1080pPop OS 20.10Pop OS 20.040.02930.05860.08790.11720.1465SE +/- 0.000, N = 3SE +/- 0.000, N = 30.1300.1281. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Memory CopyingPop OS 20.10Pop OS 20.042K4K6K8K10KSE +/- 33.35, N = 3SE +/- 43.47, N = 38172.448297.231. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

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-v2Pop OS 20.10Pop OS 20.043691215SE +/- 0.14, N = 3SE +/- 0.25, N = 313.1913.39MIN: 12.15 / MAX: 28.44MIN: 12.05 / MAX: 28.621. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Tesseract

Tesseract is a fork of Cube 2 Sauerbraten with numerous graphics and game-play improvements. Tesseract has been in development since 2012 while its first release happened in May of 2014. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterTesseract 2014-05-12Resolution: 3840 x 2160Pop OS 20.10Pop OS 20.0470140210280350SE +/- 1.73, N = 3SE +/- 1.73, N = 3316.25311.58

Appleseed

Appleseed is an open-source production renderer focused on physically-based global illumination rendering engine primarily designed for animation and visual effects. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterAppleseed 2.0 BetaScene: EmilyPop OS 20.10Pop OS 20.04306090120150135.14133.24

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 SyncPop OS 20.10Pop OS 20.045K10K15K20K25KSE +/- 26.77, N = 3SE +/- 2.65, N = 322847231681. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -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: efficientnet-b0Pop OS 20.10Pop OS 20.043691215SE +/- 0.28, N = 4SE +/- 0.11, N = 311.3911.55MIN: 6.96 / MAX: 37.9MIN: 10.46 / MAX: 34.721. (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: MobileNetV2_224Pop OS 20.10Pop OS 20.041.22632.45263.67894.90526.1315SE +/- 0.029, N = 15SE +/- 0.011, N = 155.4505.375MIN: 4.99 / MAX: 6.16MIN: 5.14 / MAX: 6.331. (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

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: FLOATPop OS 20.10Pop OS 20.0480M160M240M320M400MSE +/- 483895.89, N = 3SE +/- 36581.81, N = 3368160160.20373293210.021. (CC) gcc options: -O3 -march=native -lm

Tesseract

Tesseract is a fork of Cube 2 Sauerbraten with numerous graphics and game-play improvements. Tesseract has been in development since 2012 while its first release happened in May of 2014. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterTesseract 2014-05-12Resolution: 1920 x 1080Pop OS 20.10Pop OS 20.0480160240320400SE +/- 4.54, N = 3SE +/- 3.18, N = 15364.08369.07

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 tau100.0Pop OS 20.10Pop OS 20.0450100150200250SE +/- 0.67, N = 3SE +/- 0.88, N = 3220223-lopen-rte -lopen-pal -lhwloc -ldl -levent -levent_pthreads -lutil -lrt -lz1. (F9X) gfortran options: -cpp -Jsource/ -ffree-line-length-0 -lm -std=legacy -O3 -O2 -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi

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 FillPop OS 20.10Pop OS 20.04612182430SE +/- 0.03, N = 3SE +/- 0.03, N = 323.022.71. (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: yolov4-tinyPop OS 20.10Pop OS 20.04816243240SE +/- 0.32, N = 3SE +/- 0.24, N = 335.8336.30MIN: 34.82 / MAX: 52.07MIN: 35.04 / MAX: 56.231. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

PyBench

This test profile reports the total time of the different average timed test results from PyBench. PyBench reports average test times for different functions such as BuiltinFunctionCalls and NestedForLoops, with this total result providing a rough estimate as to Python's average performance on a given system. This test profile runs PyBench each time for 20 rounds. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyBench 2018-02-16Total For Average Test TimesPop OS 20.10Pop OS 20.042004006008001000SE +/- 1.45, N = 3SE +/- 2.40, N = 3953941

Mlpack Benchmark

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

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_linearridgeregressionPop OS 20.10Pop OS 20.040.36230.72461.08691.44921.8115SE +/- 0.01, N = 3SE +/- 0.01, N = 101.611.59

ET: Legacy

ETLegacy is an open-source engine evolution of Wolfenstein: Enemy Territory, a World War II era first person shooter that was released for free by Splash Damage using the id Tech 3 engine. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterET: Legacy 2.75Renderer: Renderer2 - Resolution: 3840 x 2160Pop OS 20.10Pop OS 20.0450100150200250SE +/- 1.53, N = 3SE +/- 3.22, N = 3238.5241.5

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 SynthesisPop OS 20.10Pop OS 20.04714212835SE +/- 0.03, N = 4SE +/- 0.03, N = 428.4728.121. (CC) gcc options: -O2 -std=c99

Polyhedron Fortran Benchmarks

The Fortran.uk Polyhedron Fortran Benchmarks for comparing Fortran compiler performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPolyhedron Fortran BenchmarksBenchmark: aermodPop OS 20.10Pop OS 20.041.30732.61463.92195.22926.53655.815.74

OpenBenchmarking.orgSeconds, Fewer Is BetterPolyhedron Fortran BenchmarksBenchmark: mp_prop_designPop OS 20.10Pop OS 20.04122436486054.6455.30

Blender

Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL or CUDA is supported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.90Blend File: Classroom - Compute: CPU-OnlyPop OS 20.10Pop OS 20.0420406080100SE +/- 0.60, N = 3SE +/- 0.44, N = 385.9784.95

Selenium

This test profile uses the Selenium WebDriver for running various browser benchmarks in different available web browsers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRuns Per Minute, More Is BetterSeleniumBenchmark: Speedometer - Browser: FirefoxPop OS 20.10Pop OS 20.0420406080100SE +/- 0.88, N = 3SE +/- 0.15, N = 384.185.11. firefox 82.0

OSPray

Intel OSPray is a portable ray-tracing engine for high-performance, high-fidenlity scientific visualizations. OSPray builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: San Miguel - Renderer: SciVisPop OS 20.10Pop OS 20.041530456075SE +/- 0.00, N = 12SE +/- 0.79, N = 666.6767.46MIN: 62.5 / MAX: 76.92MIN: 62.5 / MAX: 76.92

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 CompilePop OS 20.10Pop OS 20.04612182430SE +/- 0.27, N = 7SE +/- 0.26, N = 724.5824.30

Optcarrot

Optcarrot is an NES emulator benchmark for the Ruby language. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOptcarrotOptimized BenchmarkPop OS 20.10Pop OS 20.04306090120150SE +/- 0.45, N = 4SE +/- 0.25, N = 4129.80131.331. Pop OS 20.10: ruby 2.7.1p83 (2020-03-31 revision a0c7c23c9c) [x86_64-linux-gnu]2. Pop OS 20.04: ruby 2.7.0p0 (2019-12-25 revision 647ee6f091) [x86_64-linux-gnu]

Selenium

This test profile uses the Selenium WebDriver for running various browser benchmarks in different available web browsers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOverall Score, More Is BetterSeleniumBenchmark: Basemark - Browser: FirefoxPop OS 20.10Pop OS 20.042004006008001000SE +/- 10.13, N = 3SE +/- 13.44, N = 3779.19788.161. firefox 82.0

Polyhedron Fortran Benchmarks

The Fortran.uk Polyhedron Fortran Benchmarks for comparing Fortran compiler performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPolyhedron Fortran BenchmarksBenchmark: gas_dyn2Pop OS 20.10Pop OS 20.04102030405041.5041.97

Selenium

This test profile uses the Selenium WebDriver for running various browser benchmarks in different available web browsers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterSeleniumBenchmark: Jetstream - Browser: FirefoxPop OS 20.10Pop OS 20.0450100150200250SE +/- 0.78, N = 3SE +/- 0.19, N = 3207.68205.391. firefox 82.0

Xonotic

This is a benchmark of Xonotic, which is a fork of the DarkPlaces-based Nexuiz game. Development began in March of 2010 on the Xonotic game. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterXonotic 0.8.2Resolution: 3840 x 2160 - Effects Quality: UltimatePop OS 20.10Pop OS 20.0460120180240300SE +/- 1.14, N = 3SE +/- 1.88, N = 3265.36268.31MIN: 48 / MAX: 508MIN: 52 / MAX: 532

GIMP

GIMP is an open-source image manipulaton program. This test profile will use the system-provided GIMP program otherwise on Windows relys upon a pre-packaged Windows binary from upstream GIMP.org. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.18Test: rotatePop OS 20.10Pop OS 20.043691215SE +/- 0.01, N = 3SE +/- 0.02, N = 312.9012.76

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 FastPop OS 20.10Pop OS 20.04306090120150SE +/- 0.25, N = 3SE +/- 0.21, N = 3138.16139.661. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

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: alexnetPop OS 20.10Pop OS 20.043691215SE +/- 0.22, N = 3SE +/- 0.39, N = 312.0412.17MIN: 11.35 / MAX: 13.3MIN: 11.18 / MAX: 28.741. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Selenium

This test profile uses the Selenium WebDriver for running various browser benchmarks in different available web browsers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterSeleniumBenchmark: CanvasMark - Browser: FirefoxPop OS 20.10Pop OS 20.044K8K12K16K20KSE +/- 50.26, N = 3SE +/- 66.37, N = 317817176381. firefox 82.0

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 CompilePop OS 20.10Pop OS 20.0420406080100SE +/- 0.08, N = 3SE +/- 0.12, N = 388.9089.79

Polyhedron Fortran Benchmarks

The Fortran.uk Polyhedron Fortran Benchmarks for comparing Fortran compiler performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPolyhedron Fortran BenchmarksBenchmark: linpkPop OS 20.10Pop OS 20.040.68851.3772.06552.7543.44253.063.03

Selenium

This test profile uses the Selenium WebDriver for running various browser benchmarks in different available web browsers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterSeleniumBenchmark: Jetstream 2 - Browser: FirefoxPop OS 20.10Pop OS 20.0420406080100SE +/- 0.50, N = 3SE +/- 1.36, N = 492.6591.741. firefox 82.0

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: chaosPop OS 20.10Pop OS 20.0420406080100103104

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 BenchmarkPop OS 20.10Pop OS 20.040.85571.71142.56713.42284.2785SE +/- 0.056, N = 4SE +/- 0.004, N = 33.8033.7671. (CXX) g++ options: -O3 -pthread -lrt -lpthread -lm

Xonotic

This is a benchmark of Xonotic, which is a fork of the DarkPlaces-based Nexuiz game. Development began in March of 2010 on the Xonotic game. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterXonotic 0.8.2Resolution: 3840 x 2160 - Effects Quality: LowPop OS 20.10Pop OS 20.04110220330440550SE +/- 3.22, N = 3SE +/- 1.68, N = 3511.48506.69MIN: 282 / MAX: 1100MIN: 316 / MAX: 1048

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: floatPop OS 20.10Pop OS 20.0420406080100SE +/- 0.33, N = 3109108

Mlpack Benchmark

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

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_qdaPop OS 20.10Pop OS 20.041020304050SE +/- 0.12, N = 3SE +/- 0.13, N = 342.9342.54

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 MobilePop OS 20.10Pop OS 20.0417K34K51K68K85KSE +/- 364.75, N = 3SE +/- 174.12, N = 376836.377536.7

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 CommandsPop OS 20.10Pop OS 20.041122334455SE +/- 0.16, N = 3SE +/- 0.10, N = 347.9348.371. Pop OS 20.10: git version 2.27.02. Pop OS 20.04: git version 2.25.1

Blender

Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL or CUDA is supported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.90Blend File: Barbershop - Compute: CPU-OnlyPop OS 20.10Pop OS 20.04306090120150SE +/- 0.20, N = 3SE +/- 0.27, N = 3132.31131.12

Appleseed

Appleseed is an open-source production renderer focused on physically-based global illumination rendering engine primarily designed for animation and visual effects. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterAppleseed 2.0 BetaScene: Disney MaterialPop OS 20.10Pop OS 20.04132639526557.0357.55

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: OverwritePop OS 20.10Pop OS 20.04612182430SE +/- 0.03, N = 3SE +/- 0.00, N = 323.022.81. (CXX) g++ options: -O3 -lsnappy -lpthread

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: OverwritePop OS 20.10Pop OS 20.04130260390520650SE +/- 1.04, N = 3SE +/- 0.23, N = 3615.96621.251. (CXX) g++ options: -O3 -lsnappy -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: 3840 x 2160Pop OS 20.10Pop OS 20.04600120018002400300027042681

SQLite

This is a simple benchmark of SQLite. At present this test profile just measures the time to perform a pre-defined number of insertions on an indexed database. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSQLite 3.30.1Threads / Copies: 1Pop OS 20.10Pop OS 20.04816243240SE +/- 0.10, N = 3SE +/- 0.14, N = 332.8133.091. (CC) gcc options: -O2 -lz -lm -ldl -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: Mobilenet FloatPop OS 20.10Pop OS 20.047K14K21K28K35KSE +/- 505.02, N = 3SE +/- 280.19, N = 1131688.431423.5

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: CryptoPop OS 20.10Pop OS 20.043K6K9K12K15KSE +/- 64.72, N = 3SE +/- 52.82, N = 314639.1914517.031. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

Selenium

This test profile uses the Selenium WebDriver for running various browser benchmarks in different available web browsers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterSeleniumBenchmark: WebXPRT - Browser: FirefoxPop OS 20.10Pop OS 20.0450100150200250SE +/- 0.58, N = 32412391. firefox 82.0

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 FillPop OS 20.10Pop OS 20.04612182430SE +/- 0.37, N = 3SE +/- 0.27, N = 324.123.91. (CXX) g++ options: -O3 -lsnappy -lpthread

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 CompilePop OS 20.10Pop OS 20.04510152025SE +/- 0.01, N = 3SE +/- 0.02, N = 321.4421.27

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 FillPop OS 20.10Pop OS 20.04130260390520650SE +/- 8.60, N = 3SE +/- 6.42, N = 3586.82591.611. (CXX) g++ options: -O3 -lsnappy -lpthread

GIMP

GIMP is an open-source image manipulaton program. This test profile will use the system-provided GIMP program otherwise on Windows relys upon a pre-packaged Windows binary from upstream GIMP.org. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.18Test: unsharp-maskPop OS 20.10Pop OS 20.04510152025SE +/- 0.08, N = 3SE +/- 0.26, N = 419.3019.14

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 DynamicsPop OS 20.10Pop OS 20.0448121620SE +/- 0.07, N = 3SE +/- 0.15, N = 316.7316.86

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 2Pop OS 20.10Pop OS 20.049M18M27M36M45MSE +/- 203210.31, N = 3SE +/- 368061.43, N = 1242730397.943076608.7

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: CPUPop OS 20.10Pop OS 20.04612182430SE +/- 0.24, N = 3SE +/- 0.30, N = 323.5923.78MIN: 22.59MIN: 22.661. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

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: SqueezeNetPop OS 20.10Pop OS 20.0411K22K33K44K55KSE +/- 88.63, N = 3SE +/- 188.76, N = 351197.950791.3

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 SyncPop OS 20.10Pop OS 20.0413002600390052006500SE +/- 35.20, N = 3SE +/- 15.69, N = 36001.105953.961. (CXX) g++ options: -O3 -lsnappy -lpthread

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: 20k AtomsPop OS 20.10Pop OS 20.04612182430SE +/- 0.02, N = 3SE +/- 0.03, N = 326.7026.911. (CXX) g++ options: -O3 -pthread -lm

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the 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: CPUPop OS 20.10Pop OS 20.040.3490.6981.0471.3961.745SE +/- 0.01138, N = 3SE +/- 0.01640, N = 81.539061.55097MIN: 1.46MIN: 1.451. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

Cryptsetup

This is a test profile for running the cryptsetup benchmark to report on the system's cryptography performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations Per Second, More Is BetterCryptsetup 2.3.3PBKDF2-sha512Pop OS 20.10400K800K1200K1600K2000KSE +/- 1659.59, N = 31736056

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: MediumPop OS 20.10Pop OS 20.0448121620SE +/- 0.02, N = 3SE +/- 0.03, N = 315.9416.061. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

Java 2D Microbenchmark

This test runs a series of microbenchmarks to check the performance of the OpenGL-based Java 2D pipeline and the underlying OpenGL drivers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgUnits Per Second, More Is BetterJava 2D Microbenchmark 1.0Rendering Test: Vector Graphics RenderingPop OS 20.10Pop OS 20.042M4M6M8M10MSE +/- 10867.93, N = 4SE +/- 24423.75, N = 47902853.727844283.98

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: MemorialPop OS 20.10Pop OS 20.04612182430SE +/- 0.05, N = 3SE +/- 0.03, N = 327.2127.01

Xonotic

This is a benchmark of Xonotic, which is a fork of the DarkPlaces-based Nexuiz game. Development began in March of 2010 on the Xonotic game. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterXonotic 0.8.2Resolution: 3840 x 2160 - Effects Quality: UltraPop OS 20.10Pop OS 20.0470140210280350SE +/- 2.52, N = 3SE +/- 0.35, N = 3333.16335.62MIN: 171 / MAX: 652MIN: 192 / MAX: 628

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 RoutinePop OS 20.10Pop OS 20.0430K60K90K120K150KSE +/- 1566.55, N = 5SE +/- 641.63, N = 3128567.09129515.001. (F9X) gfortran options: -O3 -fomit-frame-pointer -fopenmp

GPAW

GPAW is a density-functional theory (DFT) Python code based on the projector-augmented wave (PAW) method and the atomic simulation environment (ASE). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGPAW 20.1Input: Carbon NanotubePop OS 20.10Pop OS 20.0420406080100SE +/- 0.19, N = 3SE +/- 0.20, N = 3110.54109.751. (CC) gcc options: -pthread -shared -fwrapv -O2 -lxc -lblas -lmpi

Selenium

This test profile uses the Selenium WebDriver for running various browser benchmarks in different available web browsers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterSeleniumBenchmark: WASM imageConvolute - Browser: FirefoxPop OS 20.10Pop OS 20.04714212835SE +/- 0.07, N = 3SE +/- 0.09, N = 327.828.01. firefox 82.0

Mlpack Benchmark

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

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_svmPop OS 20.10Pop OS 20.04510152025SE +/- 0.08, N = 3SE +/- 0.01, N = 321.0220.87

Polyhedron Fortran Benchmarks

The Fortran.uk Polyhedron Fortran Benchmarks for comparing Fortran compiler performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPolyhedron Fortran BenchmarksBenchmark: proteinPop OS 20.10Pop OS 20.04369121512.6312.72

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 TimePop OS 20.10Pop OS 20.041122334455SE +/- 0.12, N = 3SE +/- 0.04, N = 350.8650.511. RawTherapee, version 5.8, command line.

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: MediumPop OS 20.10Pop OS 20.041428425670SE +/- 0.16, N = 3SE +/- 0.12, N = 361.9962.421. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

FLAC Audio Encoding

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

OpenBenchmarking.orgSeconds, Fewer Is BetterFLAC Audio Encoding 1.3.2WAV To FLACPop OS 20.10Pop OS 20.04246810SE +/- 0.007, N = 5SE +/- 0.015, N = 57.9197.9711. (CXX) g++ options: -O2 -fvisibility=hidden -logg -lm

Blender

Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL or CUDA is supported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.90Blend File: Fishy Cat - Compute: CPU-OnlyPop OS 20.10Pop OS 20.041122334455SE +/- 0.13, N = 3SE +/- 0.02, N = 346.6446.34

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: googlenetPop OS 20.10Pop OS 20.04612182430SE +/- 0.29, N = 3SE +/- 0.25, N = 326.5626.39MIN: 25.33 / MAX: 33.49MIN: 25.5 / MAX: 42.771. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

G'MIC

G'MIC is an open-source framework for image processing. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterG'MICTest: 3D Elevated Function In Random Colors, 100 TimesPop OS 20.10Pop OS 20.0420406080100SE +/- 0.22, N = 3SE +/- 0.33, N = 385.4284.891. Version 2.4.5, Copyright (c) 2008-2019, David Tschumperle.

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 FastPop OS 20.10Pop OS 20.04816243240SE +/- 0.10, N = 3SE +/- 0.06, N = 334.6734.881. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

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: resnet18Pop OS 20.10Pop OS 20.0448121620SE +/- 0.13, N = 3SE +/- 0.14, N = 317.7717.87MIN: 16.88 / MAX: 37.92MIN: 17.15 / MAX: 33.141. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Vector MathPop OS 20.10Pop OS 20.04100K200K300K400K500KSE +/- 1816.21, N = 3SE +/- 1685.65, N = 3470369.86467815.751. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

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: VMAF Optimized - Input: Bosphorus 1080pPop OS 20.10Pop OS 20.0480160240320400SE +/- 3.04, N = 3SE +/- 4.81, N = 5372.64374.641. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Glibc C String FunctionsPop OS 20.10Pop OS 20.041.6M3.2M4.8M6.4M8MSE +/- 72240.19, N = 3SE +/- 84078.05, N = 37440489.427401405.601. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

Polyhedron Fortran Benchmarks

The Fortran.uk Polyhedron Fortran Benchmarks for comparing Fortran compiler performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPolyhedron Fortran BenchmarksBenchmark: rnflowPop OS 20.10Pop OS 20.044812162015.2415.32

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 DeletePop OS 20.10Pop OS 20.04130260390520650SE +/- 1.48, N = 3SE +/- 0.60, N = 3594.85597.961. (CXX) g++ options: -O3 -lsnappy -lpthread

OSPray

Intel OSPray is a portable ray-tracing engine for high-performance, high-fidenlity scientific visualizations. OSPray builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: XFrog Forest - Renderer: SciVisPop OS 20.10Pop OS 20.0448121620SE +/- 0.06, N = 3SE +/- 0.06, N = 313.8313.76MIN: 13.51 / MAX: 14.29MIN: 13.51 / MAX: 14.08

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 PerformancePop OS 20.10Pop OS 20.043K6K9K12K15KSE +/- 89.73, N = 3SE +/- 116.95, N = 315149.315077.31. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

G'MIC

G'MIC is an open-source framework for image processing. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterG'MICTest: Plotting Isosurface Of A 3D Volume, 1000 TimesPop OS 20.10Pop OS 20.04510152025SE +/- 0.07, N = 3SE +/- 0.02, N = 319.2919.381. Version 2.4.5, Copyright (c) 2008-2019, David Tschumperle.

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 4KPop OS 20.10Pop OS 20.04612182430SE +/- 0.17, N = 3SE +/- 0.07, N = 326.3726.251. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

LuaJIT

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

OpenBenchmarking.orgMflops, More Is BetterLuaJIT 2.1-gitTest: Jacobi Successive Over-RelaxationPop OS 20.10Pop OS 20.04400800120016002000SE +/- 3.02, N = 3SE +/- 3.21, N = 32046.502055.731. (CC) gcc options: -lm -ldl -O2 -fomit-frame-pointer -U_FORTIFY_SOURCE -fno-stack-protector

InfluxDB

This is a benchmark of the InfluxDB open-source time-series database optimized for fast, high-availability storage for IoT and other use-cases. The InfluxDB test profile makes use of InfluxDB Inch for facilitating the benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgval/sec, More Is BetterInfluxDB 1.8.2Concurrent Streams: 4 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000Pop OS 20.10Pop OS 20.04200K400K600K800K1000KSE +/- 2849.47, N = 3SE +/- 1280.70, N = 31150845.01145700.1

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 RandomPop OS 20.10Pop OS 20.044080120160200SE +/- 1.08, N = 3SE +/- 0.18, N = 3170.32171.031. (CXX) g++ options: -O3 -lsnappy -lpthread

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 8 - Input: 1080pPop OS 20.10Pop OS 20.0420406080100SE +/- 0.49, N = 3SE +/- 0.30, N = 395.9296.301. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie

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: vgg16Pop OS 20.10Pop OS 20.041224364860SE +/- 0.34, N = 3SE +/- 0.94, N = 353.6553.45MIN: 50.43 / MAX: 99.29MIN: 49.47 / MAX: 69.411. (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 FillPop OS 20.10Pop OS 20.04100K200K300K400K500KSE +/- 636.43, N = 3SE +/- 342.03, N = 34427694444251. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread

Blender

Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL or CUDA is supported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.90Blend File: Pabellon Barcelona - Compute: CPU-OnlyPop OS 20.10Pop OS 20.0420406080100SE +/- 0.44, N = 3SE +/- 0.23, N = 399.0098.66

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Glibc Qsort Data SortingPop OS 20.10Pop OS 20.042004006008001000SE +/- 4.40, N = 3SE +/- 7.33, N = 3850.31847.401. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

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 1080pPop OS 20.10Pop OS 20.041326395265SE +/- 0.10, N = 3SE +/- 0.21, N = 358.0058.191. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

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: SlowPop OS 20.10Pop OS 20.0448121620SE +/- 0.04, N = 3SE +/- 0.04, N = 315.7815.831. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

Blender

Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL or CUDA is supported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.90Blend File: BMW27 - Compute: CPU-OnlyPop OS 20.10Pop OS 20.04816243240SE +/- 0.12, N = 3SE +/- 0.11, N = 332.5332.43

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 FillPop OS 20.10Pop OS 20.04100K200K300K400K500KSE +/- 705.24, N = 3SE +/- 211.81, N = 34488574475141. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -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: resnet-v2-50Pop OS 20.10Pop OS 20.04816243240SE +/- 0.18, N = 15SE +/- 0.19, N = 1533.4533.55MIN: 30.99 / MAX: 37.54MIN: 31.67 / MAX: 38.71. (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-v1-1.0Pop OS 20.10Pop OS 20.041.23142.46283.69424.92566.157SE +/- 0.020, N = 15SE +/- 0.022, N = 155.4735.457MIN: 4.9 / MAX: 8.51MIN: 5.02 / MAX: 6.011. (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

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: MD5Pop OS 20.10Pop OS 20.041.1M2.2M3.3M4.4M5.5MSE +/- 29475.04, N = 3SE +/- 25828.49, N = 3524466752296671. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -pthread -lm -lz -ldl -lcrypt -lbz2

Selenium

This test profile uses the Selenium WebDriver for running various browser benchmarks in different available web browsers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRuns / Minute, More Is BetterSeleniumBenchmark: StyleBench - Browser: FirefoxPop OS 20.10Pop OS 20.041632486480SE +/- 0.57, N = 3SE +/- 0.32, N = 369.870.01. firefox 82.0

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: AtomicPop OS 20.10Pop OS 20.04110K220K330K440K550KSE +/- 396.66, N = 3SE +/- 498.11, N = 3494741.95493383.161. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

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 ReadPop OS 20.10Pop OS 20.0460M120M180M240M300MSE +/- 3099756.42, N = 7SE +/- 2702673.93, N = 92738954622731468171. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread

OSPray

Intel OSPray is a portable ray-tracing engine for high-performance, high-fidenlity scientific visualizations. OSPray builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: XFrog Forest - Renderer: Path TracerPop OS 20.10Pop OS 20.04246810SE +/- 0.02, N = 3SE +/- 0.02, N = 37.347.32MIN: 7.04 / MAX: 7.52MIN: 7.04 / MAX: 7.52

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: vklBenchmarkPop OS 20.10Pop OS 20.04100200300400500SE +/- 0.99, N = 3SE +/- 1.89, N = 3459.94461.15MIN: 1 / MAX: 1272MIN: 1 / MAX: 1298

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 AtomsPop OS 20.10Pop OS 20.040.09630.19260.28890.38520.4815SE +/- 0.00111, N = 3SE +/- 0.00043, N = 30.427870.42677

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 CompilePop OS 20.10Pop OS 20.0450100150200250SE +/- 0.24, N = 3SE +/- 0.51, N = 3204.83205.34

Polyhedron Fortran Benchmarks

The Fortran.uk Polyhedron Fortran Benchmarks for comparing Fortran compiler performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPolyhedron Fortran BenchmarksBenchmark: induct2Pop OS 20.10Pop OS 20.0451015202521.8721.92

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: CPUPop OS 20.10Pop OS 20.0470140210280350SE +/- 1.05, N = 3SE +/- 0.49, N = 3327.63328.33MIN: 323.21MIN: 324.391. (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: SlowPop OS 20.10Pop OS 20.041428425670SE +/- 0.14, N = 3SE +/- 0.08, N = 360.7360.851. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

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 MetricPop OS 20.10Pop OS 20.04200K400K600K800K1000K7855587841661. (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 -lXi -lGLU -lGL -lGLdispatch -lX11 -lXext -lXrender -lpthread -ldl -luuid -lm

OSPray

Intel OSPray is a portable ray-tracing engine for high-performance, high-fidenlity scientific visualizations. OSPray builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: San Miguel - Renderer: Path TracerPop OS 20.10Pop OS 20.041.28252.5653.84755.136.4125SE +/- 0.01, N = 4SE +/- 0.01, N = 35.695.70MIN: 5.65 / MAX: 5.78MIN: 5.65 / MAX: 5.78

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: squeezenetPop OS 20.10Pop OS 20.04612182430SE +/- 0.13, N = 3SE +/- 0.20, N = 325.3125.27MIN: 24.5 / MAX: 29.75MIN: 24.36 / MAX: 42.71. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Selenium

This test profile uses the Selenium WebDriver for running various browser benchmarks in different available web browsers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterSeleniumBenchmark: Kraken - Browser: FirefoxPop OS 20.10Pop OS 20.042004006008001000SE +/- 5.31, N = 3SE +/- 2.12, N = 3828.5829.81. firefox 82.0

Polyhedron Fortran Benchmarks

The Fortran.uk Polyhedron Fortran Benchmarks for comparing Fortran compiler performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPolyhedron Fortran BenchmarksBenchmark: doducPop OS 20.10Pop OS 20.042468106.746.75

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: Ultra FastPop OS 20.10Pop OS 20.041428425670SE +/- 0.04, N = 3SE +/- 0.09, N = 360.8160.731. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

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 1080Pop OS 20.10Pop OS 20.042K4K6K8K10K85688575

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 ScenePop OS 20.10Pop OS 20.0470140210280350SE +/- 0.57, N = 3SE +/- 0.24, N = 3311.55311.30

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 RNAPop OS 20.10Pop OS 20.04246810SE +/- 0.049, N = 3SE +/- 0.026, N = 38.8008.8061. (CC) gcc options: -std=c99 -O3 -lm -lpthread

LuaJIT

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

OpenBenchmarking.orgMflops, More Is BetterLuaJIT 2.1-gitTest: Monte CarloPop OS 20.10Pop OS 20.04110220330440550SE +/- 0.43, N = 3SE +/- 0.10, N = 3506.60506.841. (CC) gcc options: -lm -ldl -O2 -fomit-frame-pointer -U_FORTIFY_SOURCE -fno-stack-protector

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Matrix MathPop OS 20.10Pop OS 20.0450K100K150K200K250KSE +/- 1622.53, N = 3SE +/- 1325.79, N = 3225079.79225010.901. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

Selenium

This test profile uses the Selenium WebDriver for running various browser benchmarks in different available web browsers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterSeleniumBenchmark: WASM collisionDetection - Browser: FirefoxPop OS 20.10Pop OS 20.0480160240320400SE +/- 1.16, N = 3SE +/- 1.10, N = 3377.0376.91. firefox 82.0

OpenBenchmarking.orgGeometric Mean, More Is BetterSeleniumBenchmark: Octane - Browser: FirefoxPop OS 20.10Pop OS 20.047K14K21K28K35KSE +/- 152.55, N = 3SE +/- 46.23, N = 334622346211. firefox 82.0

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 DocumentPop OS 20.103691215SE +/- 0.13, N = 312.64

Cryptsetup

This is a test profile for running the cryptsetup benchmark to report on the system's cryptography performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations Per Second, More Is BetterCryptsetup 2.2.2PBKDF2-whirlpoolPop OS 20.10160K320K480K640K800KSE +/- 2948.51, N = 3728876

Selenium

This test profile uses the Selenium WebDriver for running various browser benchmarks in different available web browsers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSeleniumBenchmark: Maze Solver - Browser: FirefoxPop OS 20.10Pop OS 20.041.2152.433.6454.866.075SE +/- 0.03, N = 3SE +/- 0.03, N = 35.45.41. firefox 82.0

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: goPop OS 20.10Pop OS 20.0450100150200250SE +/- 0.33, N = 3233233

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 9.6.0+dfsgProcessing 60 Page PDF DocumentPop OS 20.0448121620SE +/- 0.05, N = 315.23

Darktable

Darktable is an open-source photography / workflow application this will use any system-installed Darktable program or on Windows will automatically download the pre-built binary from the project. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 3.0.1Test: Server Room - Acceleration: CPU-onlyPop OS 20.040.48060.96121.44181.92242.403SE +/- 0.002, N = 32.136

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 3.0.1Test: Server Rack - Acceleration: CPU-onlyPop OS 20.040.02070.04140.06210.08280.1035SE +/- 0.001, N = 30.092

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 3.0.1Test: Masskrug - Acceleration: CPU-onlyPop OS 20.040.66921.33842.00762.67683.346SE +/- 0.004, N = 32.974

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 3.0.1Test: Boat - Acceleration: CPU-onlyPop OS 20.041.23662.47323.70984.94646.183SE +/- 0.007, N = 35.496

Cryptsetup

This is a test profile for running the cryptsetup benchmark to report on the system's cryptography performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations Per Second, More Is BetterCryptsetup 2.2.2PBKDF2-sha512Pop OS 20.04300K600K900K1200K1500KSE +/- 3021.04, N = 31622356

OSPray

Intel OSPray is a portable ray-tracing engine for high-performance, high-fidenlity scientific visualizations. OSPray builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: Magnetic Reconnection - Renderer: Path TracerPop OS 20.10Pop OS 20.0470140210280350SE +/- 0.00, N = 12SE +/- 0.00, N = 12333.33333.33MIN: 200 / MAX: 500MIN: 250 / MAX: 500

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: NASA Streamlines - Renderer: Path TracerPop OS 20.10Pop OS 20.04510152025SE +/- 0.00, N = 12SE +/- 0.00, N = 1220.4120.41MIN: 20 / MAX: 21.28MIN: 20 / MAX: 21.28

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: Magnetic Reconnection - Renderer: SciVisPop OS 20.10Pop OS 20.041020304050SE +/- 0.00, N = 12SE +/- 0.00, N = 1243.4843.48MIN: 41.67 / MAX: 45.45MIN: 41.67 / MAX: 45.45

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: NASA Streamlines - Renderer: SciVisPop OS 20.10Pop OS 20.0420406080100SE +/- 0.00, N = 13SE +/- 0.00, N = 1390.9190.91MIN: 83.33 / MAX: 100MIN: 83.33 / MAX: 100

ParaView

This test runs ParaView benchmarks: an open-source data analytics and visualization application. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiPolys / Sec, More Is BetterParaView 5.4.1Test: Many Spheres - Resolution: 3840 x 2160Pop OS 20.0412002400360048006000SE +/- 12.69, N = 35540.17

OpenBenchmarking.orgFrames / Sec, More Is BetterParaView 5.4.1Test: Many Spheres - Resolution: 3840 x 2160Pop OS 20.041224364860SE +/- 0.13, N = 355.26

OpenBenchmarking.orgMiPolys / Sec, More Is BetterParaView 5.4.1Test: Many Spheres - Resolution: 1920 x 1080Pop OS 20.0412002400360048006000SE +/- 7.08, N = 35732.05

OpenBenchmarking.orgFrames / Sec, More Is BetterParaView 5.4.1Test: Many Spheres - Resolution: 1920 x 1080Pop OS 20.041326395265SE +/- 0.07, N = 357.17

Selenium

This test profile uses the Selenium WebDriver for running various browser benchmarks in different available web browsers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterSeleniumBenchmark: MotionMark - Browser: FirefoxPop OS 20.10Pop OS 20.04306090120150SE +/- 3.45, N = 9SE +/- 3.98, N = 9137.11139.041. firefox 82.0

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: alexnetPop OS 20.10Pop OS 20.04714212835SE +/- 0.23, N = 4SE +/- 0.24, N = 36.4829.85MIN: 5.18 / MAX: 33.26MIN: 25.42 / MAX: 55.991. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: blazefacePop OS 20.10Pop OS 20.041.3232.6463.9695.2926.615SE +/- 0.12, N = 3SE +/- 0.26, N = 35.595.88MIN: 5.27 / MAX: 6.4MIN: 5.3 / MAX: 20.981. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: mnasnetPop OS 20.10Pop OS 20.043691215SE +/- 0.20, N = 3SE +/- 0.76, N = 312.5313.45MIN: 11.97 / MAX: 14.52MIN: 11.94 / MAX: 28.731. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU-v3-v3 - Model: mobilenet-v3Pop OS 20.10Pop OS 20.0448121620SE +/- 0.61, N = 3SE +/- 0.78, N = 313.6613.90MIN: 12.83 / MAX: 17.84MIN: 12.8 / MAX: 29.431. (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: SqueezeNetV1.0Pop OS 20.10Pop OS 20.04246810SE +/- 0.140, N = 15SE +/- 0.095, N = 158.6818.258MIN: 7.65 / MAX: 11.24MIN: 7.68 / MAX: 10.171. (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

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Context SwitchingPop OS 20.10Pop OS 20.046M12M18M24M30MSE +/- 320062.66, N = 3SE +/- 701783.94, N = 1524978427.8628076290.951. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: CPU CachePop OS 20.10Pop OS 20.041632486480SE +/- 1.19, N = 15SE +/- 1.68, N = 1571.5070.951. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: MMAPPop OS 20.10Pop OS 20.042004006008001000SE +/- 12.65, N = 3SE +/- 23.23, N = 151136.58199.601. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

LuaJIT

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

OpenBenchmarking.orgMflops, More Is BetterLuaJIT 2.1-gitTest: Fast Fourier TransformPop OS 20.10Pop OS 20.0460120180240300SE +/- 0.10, N = 3SE +/- 23.04, N = 3272.28254.691. (CC) gcc options: -lm -ldl -O2 -fomit-frame-pointer -U_FORTIFY_SOURCE -fno-stack-protector

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: ReactorPop OS 20.10Pop OS 20.0460120180240300SE +/- 6.43, N = 9SE +/- 4.60, N = 9286.40264.23

ParaView

This test runs ParaView benchmarks: an open-source data analytics and visualization application. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiVoxels / Sec, More Is BetterParaView 5.4.1Test: Wavelet Volume - Resolution: 3840 x 2160Pop OS 20.10Pop OS 20.046001200180024003000SE +/- 38.26, N = 3SE +/- 42.59, N = 152669.662575.51

OpenBenchmarking.orgFrames / Sec, More Is BetterParaView 5.4.1Test: Wavelet Volume - Resolution: 3840 x 2160Pop OS 20.10Pop OS 20.044080120160200SE +/- 2.39, N = 3SE +/- 2.66, N = 15166.85160.97

297 Results Shown

NCNN
Polyhedron Fortran Benchmarks
NCNN:
  Vulkan GPU-v3-v3 - mobilenet-v3
  Vulkan GPU-v2-v2 - mobilenet-v2
  Vulkan GPU - mnasnet
RealSR-NCNN
NCNN:
  Vulkan GPU - googlenet
  Vulkan GPU - resnet50
PyPerformance
NCNN
RealSR-NCNN
NCNN
Waifu2x-NCNN Vulkan
NCNN
oneDNN
NCNN:
  Vulkan GPU - mobilenet
  Vulkan GPU - squeezenet
oneDNN
G'MIC
Polyhedron Fortran Benchmarks
Stress-NG
Java 2D Microbenchmark
Timed HMMer Search
Mlpack Benchmark
Timed FFmpeg Compilation
GEGL
librsvg
Stress-NG
GEGL
LeelaChessZero
PyPerformance
GEGL
NCNN
GEGL:
  Scale
  Tile Glass
PyPerformance
TensorFlow Lite
TNN
Stress-NG
GEGL:
  Reflect
  Crop
PyPerformance
GEGL
LeelaChessZero
Apache CouchDB
NCNN
WebP Image Encode
Stress-NG
Polyhedron Fortran Benchmarks
Coremark
Caffe
Stress-NG:
  NUMA
  Forking
GEGL
SQLite
Java 2D Microbenchmark:
  Text Rendering
  All Rendering Tests
Facebook RocksDB
GIMP
PyPerformance
ParaView:
  Wavelet Contour - 1920 x 1080:
    MiPolys / Sec
    Frames / Sec
Kvazaar
LuaJIT
Timed PHP Compilation
ParaView:
  Wavelet Contour - 3840 x 2160:
    Frames / Sec
    MiPolys / Sec
LevelDB
GNU Octave Benchmark
VkFFT
PyPerformance
PostMark
TNN
SVT-VP9
LibRaw
LuaJIT
TensorFlow Lite
Caffe
ParaView:
  Wavelet Volume - 1920 x 1080:
    Frames / Sec
    MiVoxels / Sec
WebP Image Encode
Appleseed
Xonotic
Stress-NG
Polyhedron Fortran Benchmarks:
  mdbx
  channel2
Kripke
LevelDB
AI Benchmark Alpha
InfluxDB
Stress-NG
SVT-VP9
LevelDB
InfluxDB
Polyhedron Fortran Benchmarks
ASTC Encoder
PyPerformance:
  crypto_pyaes
  nbody
LAME MP3 Encoding
PyPerformance
IOR
LuaJIT
Stockfish
Cryptsetup
Timed MPlayer Compilation
AI Benchmark Alpha
SVT-HEVC
CloverLeaf
WebP Image Encode
TensorFlow Lite
Polyhedron Fortran Benchmarks
oneDNN
IOR
ASTC Encoder
Mobile Neural Network
SQLite Speedtest
Zstd Compression
ASTC Encoder
WebP Image Encode
LAMMPS Molecular Dynamics Simulator
SVT-AV1
ASTC Encoder
John The Ripper
WebP Image Encode
Zstd Compression
oneDNN
RNNoise
Tesseract OCR
oneDNN
Hugin
NCNN
Selenium
Polyhedron Fortran Benchmarks
GIMP
NCNN
AI Benchmark Alpha
PyPerformance
NCNN
LevelDB
SVT-AV1
Stress-NG
NCNN
Tesseract
Appleseed
Facebook RocksDB
NCNN
Mobile Neural Network
Hierarchical INTegration
Tesseract
Monte Carlo Simulations of Ionised Nebulae
LevelDB
NCNN
PyBench
Mlpack Benchmark
ET: Legacy
eSpeak-NG Speech Engine
Polyhedron Fortran Benchmarks:
  aermod
  mp_prop_design
Blender
Selenium
OSPray
Timed Linux Kernel Compilation
Optcarrot
Selenium
Polyhedron Fortran Benchmarks
Selenium
Xonotic
GIMP
Kvazaar
NCNN
Selenium
Timed GDB GNU Debugger Compilation
Polyhedron Fortran Benchmarks
Selenium
PyPerformance
GROMACS
Xonotic
PyPerformance
Mlpack Benchmark
TensorFlow Lite
Git
Blender
Appleseed
LevelDB:
  Overwrite:
    MB/s
    Microseconds Per Op
GLmark2
SQLite
TensorFlow Lite
Stress-NG
Selenium
LevelDB
Timed Apache Compilation
LevelDB
GIMP
Dolfyn
BYTE Unix Benchmark
oneDNN
TensorFlow Lite
LevelDB
LAMMPS Molecular Dynamics Simulator
oneDNN
Cryptsetup
Kvazaar
Java 2D Microbenchmark
Intel Open Image Denoise
Xonotic
FFTE
GPAW
Selenium
Mlpack Benchmark
Polyhedron Fortran Benchmarks
RawTherapee
Kvazaar
FLAC Audio Encoding
Blender
NCNN
G'MIC
Kvazaar
NCNN
Stress-NG
SVT-VP9
Stress-NG
Polyhedron Fortran Benchmarks
LevelDB
OSPray
OpenSSL
G'MIC
x265
LuaJIT
InfluxDB
LevelDB
SVT-AV1
NCNN
Facebook RocksDB
Blender
Stress-NG
x265
Kvazaar
Blender
Facebook RocksDB
Mobile Neural Network:
  resnet-v2-50
  mobilenet-v1-1.0
John The Ripper
Selenium
Stress-NG
Facebook RocksDB
OSPray
OpenVKL
NAMD
Timed LLVM Compilation
Polyhedron Fortran Benchmarks
oneDNN
Kvazaar
BRL-CAD
OSPray
NCNN
Selenium
Polyhedron Fortran Benchmarks
Kvazaar
GLmark2
rays1bench
Timed MAFFT Alignment
LuaJIT
Stress-NG
Selenium:
  WASM collisionDetection - Firefox
  Octane - Firefox
OCRMyPDF
Cryptsetup
Selenium
PyPerformance
OCRMyPDF
Darktable:
  Server Room - CPU-only
  Server Rack - CPU-only
  Masskrug - CPU-only
  Boat - CPU-only
Cryptsetup
OSPray:
  Magnetic Reconnection - Path Tracer
  NASA Streamlines - Path Tracer
  Magnetic Reconnection - SciVis
  NASA Streamlines - SciVis
ParaView:
  Many Spheres - 3840 x 2160:
    MiPolys / Sec
    Frames / Sec
  Many Spheres - 1920 x 1080:
    MiPolys / Sec
    Frames / Sec
Selenium
NCNN:
  Vulkan GPU - alexnet
  CPU - blazeface
  CPU - mnasnet
  CPU-v3-v3 - mobilenet-v3
Mobile Neural Network
Stress-NG:
  Context Switching
  CPU Cache
  MMAP
LuaJIT
Java Gradle Build
ParaView:
  Wavelet Volume - 3840 x 2160:
    MiVoxels / Sec
    Frames / Sec

Pop OS 20.04

Processor: AMD Ryzen Threadripper 3990X 64-Core @ 2.90GHz (64 Cores / 128 Threads), Motherboard: System76 Thelio Major (F4c Z5 BIOS), Chipset: AMD Starship/Matisse, Memory: 126GB, Disk: Samsung SSD 970 EVO Plus 500GB, Graphics: AMD Radeon RX 5600 OEM/5600 XT / 5700/5700 8GB (1750/875MHz), Audio: AMD Navi 10 HDMI Audio, Monitor: DELL P2415Q, Network: Intel I211 + Intel Wi-Fi 6 AX200

OS: Pop 20.04, Kernel: 5.4.0-7642-generic (x86_64), Desktop: GNOME Shell 3.36.4, Display Server: X Server 1.20.8, Display Driver: amdgpu 19.1.0, OpenGL: 4.6 Mesa 20.0.8 (LLVM 10.0.0), Vulkan: 1.2.128, Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 3840x2160

Kernel Notes: snd_usb_audio.ignore_ctl_error=1
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++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-HskZEa/gcc-9-9.3.0/debian/tmp-nvptx/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,noatime,rw
Processor Notes: Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8301025
Graphics Notes: GLAMOR
Java Notes: OpenJDK Runtime Environment (build 11.0.8+10-post-Ubuntu-0ubuntu120.04)
Python Notes: Python 3.8.5
Security Notes: itlb_multihit: Not affected + 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 Full AMD retpoline IBPB: conditional STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 23 October 2020 12:50 by user phoronix.

Pop OS 20.10

Processor: AMD Ryzen Threadripper 3990X 64-Core @ 2.90GHz (64 Cores / 128 Threads), Motherboard: System76 Thelio Major (F4c Z5 BIOS), Chipset: AMD Starship/Matisse, Memory: 126GB, Disk: Samsung SSD 970 EVO Plus 500GB + 32GB Flash Disk, Graphics: AMD Radeon RX 5600 OEM/5600 XT / 5700/5700 8GB (1750/875MHz), Audio: AMD Navi 10 HDMI Audio, Monitor: DELL P2415Q, Network: Intel I211 + Intel Wi-Fi 6 AX200

OS: Pop 20.10, Kernel: 5.8.0-7625-generic (x86_64), Desktop: GNOME Shell 3.38.1, Display Server: X Server 1.20.8, Display Driver: amdgpu 19.1.0, OpenGL: 4.6 Mesa 20.2.1 (LLVM 11.0.0), Vulkan: 1.2.131, Compiler: GCC 10.2.0, File-System: ext4, Screen Resolution: 3840x2160

Kernel Notes: snd_usb_audio.ignore_ctl_error=1
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,noatime,rw
Processor Notes: Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8301025
Graphics Notes: GLAMOR
Java Notes: OpenJDK Runtime Environment (build 11.0.9+10-post-Ubuntu-0ubuntu1)
Python Notes: Python 3.8.6
Security Notes: itlb_multihit: Not affected + 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 Full AMD retpoline IBPB: conditional STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 24 October 2020 10:35 by user phoronix.