System76 Thelio Major 3990X 2023 Benchmarks

AMD Ryzen Threadripper 3990X benchmarking by Michael Larabel for a future article.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2302076-NE-3990XTHRE21
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

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Toggle/Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
2020
October 23 2020
  8 Hours, 23 Minutes
February 2023
February 06 2023
  7 Hours, 57 Minutes
Invert Behavior (Only Show Selected Data)
  8 Hours, 10 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):

2020

Processor: AMD Ryzen Threadripper 3990X 64-Core @ 2.90GHz (64 Cores / 128 Threads), Motherboard: Gigabyte TRX40 AORUS PRO WIFI (F4p BIOS), Chipset: AMD Starship/Matisse, Memory: 128GB, 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

February 2023

Processor: AMD Ryzen Threadripper 3990X 64-Core @ 2.90GHz (64 Cores / 128 Threads), Motherboard: Gigabyte TRX40 AORUS PRO WIFI (F4p BIOS), Chipset: AMD Starship/Matisse, Memory: 128GB, Disk: Samsung SSD 970 EVO Plus 500GB + 257GB Flash Drive, Graphics: AMD Radeon RX 5700 8GB (1750/875MHz), Audio: AMD Navi 10 HDMI Audio, Monitor: DELL P2415Q, Network: Intel I211 + Intel Wi-Fi 6 AX200

OS: Ubuntu 23.04, Kernel: 6.2.0-060200rc7daily20230206-generic (x86_64), Desktop: GNOME Shell 43.2, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 22.2.5 (LLVM 15.0.6 DRM 3.49), Compiler: GCC 12.2.0, File-System: ext4, Screen Resolution: 3840x2160

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,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-defaulted --enable-offload-targets=nvptx-none=/build/gcc-12-AKimc9/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-AKimc9/gcc-12-12.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Disk Notes: NONE / errors=remount-ro,relatime,rw / Block Size: 4096
Processor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0x8301055
Graphics Notes: BAR1 / Visible vRAM Size: 256 MB - vBIOS Version: 113-D1820201-101
Java Notes: OpenJDK Runtime Environment (build 11.0.18+10-post-Ubuntu-0ubuntu1)
Python Notes: Python 3.11.1
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Mitigation of untrained return thunk; SMT enabled with STIBP protection + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

System76 Thelio Major 3990X 2023 BenchmarksProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLVulkanCompilerFile-SystemScreen Resolution2020February 2023AMD Ryzen Threadripper 3990X 64-Core @ 2.90GHz (64 Cores / 128 Threads)Gigabyte TRX40 AORUS PRO WIFI (F4p BIOS)AMD Starship/Matisse128GBSamsung 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 + 257GB Flash DriveAMD Radeon RX 5700 8GB (1750/875MHz)Ubuntu 23.046.2.0-060200rc7daily20230206-generic (x86_64)GNOME Shell 43.2X Server + Wayland4.6 Mesa 22.2.5 (LLVM 15.0.6 DRM 3.49)GCC 12.2.0OpenBenchmarking.orgKernel Details- 2020: snd_usb_audio.ignore_ctl_error=1- February 2023: Transparent Huge Pages: madviseCompiler Details- 2020: --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 - February 2023: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,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-defaulted --enable-offload-targets=nvptx-none=/build/gcc-12-AKimc9/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-AKimc9/gcc-12-12.2.0/debian/tmp-gcn/usr --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- 2020: NONE / errors=remount-ro,noatime,rw- February 2023: NONE / errors=remount-ro,relatime,rw / Block Size: 4096Processor Details- 2020: Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8301025- February 2023: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0x8301055Graphics Details- 2020: GLAMOR- February 2023: BAR1 / Visible vRAM Size: 256 MB - vBIOS Version: 113-D1820201-101Java Details- 2020: OpenJDK Runtime Environment (build 11.0.8+10-post-Ubuntu-0ubuntu120.04)- February 2023: OpenJDK Runtime Environment (build 11.0.18+10-post-Ubuntu-0ubuntu1)Python Details- 2020: Python 3.8.5- February 2023: Python 3.11.1Security Details- 2020: 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 - February 2023: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Mitigation of untrained return thunk; SMT enabled with STIBP protection + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

2020 vs. February 2023 ComparisonPhoronix Test SuiteBaseline+111.2%+111.2%+222.4%+222.4%+333.6%+333.6%444.7%178.2%172.3%120.2%110.2%108.1%100%99.1%91.7%90.7%79.6%71.3%68.9%67.1%66.2%61.2%59.8%58.5%56.3%55.7%54.1%50.8%49.9%47%41.9%40.7%36.4%34.7%33.2%32.9%24%19.6%18.4%17.3%16.6%15.3%15.2%14.5%14.2%13.5%11.9%11.8%11.3%10.5%9.4%9.1%8.6%8.3%8.2%7.6%7.6%6.9%6.6%6.5%6.5%6.4%6.1%6%4.9%4.6%4.5%4.4%4.1%4%3.9%3.9%3.8%3.7%3.6%3.4%3.3%2.6%2.5%2.5%2.4%2.3%2.2%2.1%Vulkan GPU - alexnetVulkan GPU - vgg16Vulkan GPU-v3-v3 - mobilenet-v32.F.P.1.T4x - YesVulkan GPU-v2-v2 - mobilenet-v2Vulkan GPU - shufflenet-v2Vulkan GPU - mnasnetVulkan GPU - googlenetVulkan GPU - resnet50Vulkan GPU - resnet18goDust 2D tau100.0Vulkan GPU - yolov4-tinyfloatchaospickle_pure_pythonraytraceVulkan GPU - efficientnet-b0django_template2x - 3 - YesVulkan GPU - squeezenetcrypto_pyaesVulkan GPU - mobilenetP.I.O.A.3.V.1.TImage Rendering4x - NonbodyTime To Compile34.5%fatigue21920 x 1080Bosphorus 4K24.6%regex_compileBosphorus 1080p23.2%V.Q.O - Bosphorus 1080p20%air3840 x 2160 - High1.8.b.Y.T.H.V.E18.3%3840 x 2160 - UltraP.S.O - Bosphorus 1080p16.7%json_loadsColor EnhanceDhrystone 2Time To Compile15%Time To Compile14.6%Wavelet Blur8A.R.T3840 x 2160 - UltimateT.F.A.T.T3840 x 2160AntialiasClassroom - CPU-Only10.4%2to3Time To CompileBarbershop - CPU-Only9%vklBenchmark9%3840 x 2160 - LowSeek RandF.F.TWavelet Contour - 1920 x 1080Wavelet Contour - 1920 x 1080ReflectTile GlassRenderer2 - 3840 x 2160S.M.MM.M.B.S.T - f32 - CPU6.5%MemorialFishy Cat - CPU-Only6.3%D.L.M.FText RenderingR.N.N.I - f32 - CPU5.9%CoreMark Size 666 - I.P.S5.8%T.B.T5.7%IP Batch 1D - f32 - CPU5.2%O.B5.1%San Miguel - SciVisCropCompositeSqueezeNetXFrog Forest - Path Tracer4.1%CPU - yolov4-tinyV.G.RP.P.A.S.TRand ReadCartoon3.8%20k Atoms3.8%tfft2San Miguel - Path Tracer3.6%WAV To FLACNASA Streamlines - Path Tracer3.4%BMW27 - CPU-Only3.4%N.2.3.C.F.RQ.1.H.C3.4%Rhodopsin ProteinIP Batch All - f32 - CPU3.2%R.N.N.T - f32 - CPU3%Total Time2.9%XFrog Forest - SciVis2.8%Rand FillpathlibRand FillCPU - SqueezeNet v1.1proteinEmilyD.B.d - f32 - CPUNCNNNCNNNCNNG'MICRealSR-NCNNNCNNNCNNNCNNNCNNNCNNNCNNPyPerformanceMonte Carlo Simulations of Ionised NebulaeNCNNPyPerformancePyPerformancePyPerformancePyPerformanceNCNNPyPerformanceWaifu2x-NCNN VulkanNCNNPyPerformanceNCNNG'MICJava 2D MicrobenchmarkRealSR-NCNNPyPerformanceTimed PHP CompilationPolyhedron Fortran BenchmarksTesseractx265PyPerformancex265SVT-VP9Polyhedron Fortran BenchmarksXonoticSVT-HEVCXonoticSVT-VP9PyPerformanceGEGLBYTE Unix BenchmarkTimed Apache CompilationTimed MPlayer CompilationGEGLSQLiteJava 2D MicrobenchmarkXonoticPyBenchTesseractGEGLBlenderPyPerformanceTimed FFmpeg CompilationBlenderOpenVKLXonoticLevelDBLuaJITParaViewParaViewGEGLGEGLET: LegacyLuaJIToneDNNIntel Open Image DenoiseBlenderLuaJITJava 2D MicrobenchmarkoneDNNCoremarkRawTherapeeoneDNNOptcarrotOSPrayGEGLLuaJITTensorFlow LiteOSPrayRNNoiseNCNNJava 2D MicrobenchmarkHuginLevelDBGEGLLAMMPS Molecular Dynamics SimulatorPolyhedron Fortran BenchmarksOSPrayFLAC Audio EncodingOSPrayBlenderFFTEWebP Image EncodeLAMMPS Molecular Dynamics SimulatoroneDNNoneDNNStockfishOSPrayLevelDBPyPerformanceLevelDBTNNPolyhedron Fortran BenchmarksAppleseedoneDNN2020February 2023

System76 Thelio Major 3990X 2023 Benchmarkspolyhedron: tfft2j2dbench: All Rendering Testsj2dbench: Image Renderingopenvkl: vklBenchmarkj2dbench: Vector Graphics Renderinglammps: 20k Atomsbyte: Dhrystone 2leveldb: Rand Deleteleveldb: Seq Fillleveldb: Seq Fillpolyhedron: fatigue2hint: FLOATmocassin: Dust 2D tau100.0kripke: hmmer: Pfam Database Searchleveldb: Seek Randgmic: 2D Function Plotting, 1000 Timesblender: Barbershop - CPU-Onlycouchdb: 100 - 1000 - 24onednn: Recurrent Neural Network Training - f32 - CPUrealsr-ncnn: 4x - Yesncnn: CPU - yolov4-tinyleveldb: Rand Readsqlite: 8gegl: Cartoontesseract: 1920 x 1080ospray: San Miguel - SciVispolyhedron: induct2pyperformance: python_startupblender: Classroom - CPU-Onlyappleseed: Emilygmic: 3D Elevated Function In Rand Colors, 100 Timesonednn: IP Batch All - f32 - CPUospray: San Miguel - Path Tracerpyperformance: raytraceleveldb: Rand Fillleveldb: Rand Fillleveldb: Overwriteleveldb: Overwritej2dbench: Text Renderinggegl: Wavelet Blurtensorflow-lite: SqueezeNetpyperformance: 2to3gegl: Color Enhancerawtherapee: Total Benchmark Timestockfish: Total Timepolyhedron: proteinblender: Fishy Cat - CPU-Onlygit: Time To Complete Common Git Commandsonednn: IP Batch 1D - f32 - CPUhugin: Panorama Photo Assistant + Stitching Timencnn: Vulkan GPU - resnet50ncnn: Vulkan GPU - yolov4-tinyncnn: Vulkan GPU - alexnetncnn: Vulkan GPU - resnet18ncnn: Vulkan GPU - vgg16ncnn: Vulkan GPU - googlenetncnn: Vulkan GPU - efficientnet-b0ncnn: Vulkan GPU - mnasnetncnn: Vulkan GPU - shufflenet-v2ncnn: Vulkan GPU-v3-v3 - mobilenet-v3ncnn: Vulkan GPU-v2-v2 - mobilenet-v2ncnn: Vulkan GPU - mobilenetncnn: Vulkan GPU - squeezenetxonotic: 3840 x 2160 - Ultimatecompress-zstd: 19build-php: Time To Compilepyperformance: gogegl: Antialiasonednn: Deconvolution Batch deconv_1d - f32 - CPUonednn: Matrix Multiply Batch Shapes Transformer - f32 - CPUnamd: ATPase Simulation - 327,506 Atomsonednn: Recurrent Neural Network Inference - f32 - CPUrealsr-ncnn: 4x - Noxonotic: 3840 x 2160 - Ultrablender: BMW27 - CPU-Onlywebp: Quality 100, Lossless, Highest Compressionospray: XFrog Forest - Path Tracerospray: NASA Streamlines - Path Tracergegl: Tile Glasstesseract: 3840 x 2160pyperformance: django_templatexonotic: 3840 x 2160 - Highgegl: Reflectpyperformance: regex_compilepyperformance: pickle_pure_pythonlibraw: Post-Processing Benchmarkcompress-zstd: 3pyperformance: pathlibluajit: Compositecoremark: CoreMark Size 666 - Iterations Per Secondxonotic: 3840 x 2160 - Lowx265: Bosphorus 4Kpolyhedron: airpyperformance: nbodyetlegacy: Renderer2 - 3840 x 2160pyperformance: chaospyperformance: crypto_pyaespyperformance: floatbuild-apache: Time To Compilepyperformance: json_loadspybench: Total For Average Test Timesopenssl: RSA 4096-bit Performancewaifu2x-ncnn: 2x - 3 - Yesospray: XFrog Forest - SciVisbuild-ffmpeg: Time To Compilernnoise: tnn: CPU - SqueezeNet v1.1gmic: Plotting Isosurface Of A 3D Volume, 1000 Timeswebp: Quality 100, Losslessparaview: Wavelet Contour - 1920 x 1080paraview: Wavelet Contour - 1920 x 1080ospray: Magnetic Reconnection - SciVisencode-flac: WAV To FLACospray: NASA Streamlines - SciVisx265: Bosphorus 1080pbuild-mplayer: Time To Compilegegl: Croplammps: Rhodopsin Proteinwebp: Quality 100, Highest Compressionoidn: Memorialleveldb: Fill Syncleveldb: Fill Syncrays1bench: Large Scenesvt-hevc: 1080p 8-bit YUV To HEVC Video Encodesvt-vp9: PSNR/SSIM Optimized - Bosphorus 1080pffte: N=256, 3D Complex FFT Routineonednn: Deconvolution Batch deconv_3d - f32 - CPUsvt-vp9: Visual Quality Optimized - Bosphorus 1080poptcarrot: Optimized Benchmarkluajit: Jacobi Successive Over-Relaxationluajit: Dense LU Matrix Factorizationluajit: Sparse Matrix Multiplyluajit: Fast Fourier Transformluajit: Monte Carlo2020February 202349.087815320.96040108553596.5131508461.157844283.975062126.90843076608.7597.960591.61223.948.61373293210.0225222344881177165.035171.029222.556131.12119.187328.325114.44436.30109.997114.99794.521369.069067.4621.9212.884.95133.24476184.88623.77815.70439623.72622.7621.25122.821836.33907217764.72550791.330258.09750.51014646348612.7246.3448.3651.2644146.7399.6515.0429.853.3484.368.5111.554.663.488.474.609.985.82268.307837581.735.45223341.0761.550970.5085440.42677115.06816.512335.618213032.4333.5007.3220.4132.965311.582247.5383.469256431.59116044141.837285.816.31541.472256436.977296506.688829626.251.71108241.510410310821.26723.994115077.39.10113.7619.73618.809252.18019.37916.2953145.937301.8843.487.97190.9158.1910.6138.84323.8457.13827.015953.9602.4311.30208.29394.07129515.004228932.07153326.72131.332055.733668.791221.29254.69506.8447.358868529.018822112036752.9430464238150041.012765625.93549644913.1595.580592.27623.936.5367154749.5573013245462287167.563157.938101.076142.95120.379338.11054.44434.92105.932100.69298.075490.629970.7521.8512.693.81130.32908586.38324.52785.50277608.57223.3611.01923.223141.43042064856.54848673.627650.39753.40014231224612.4449.2647.8171.3298444.9995.069.005.481.8630.324.447.392.341.743.112.216.793.86300.113793782.347.69513637.1631.559130.5415290.42898121.80012.109393.524461533.5333.2897.0319.7430.932346.838130.5453.881067929.54512927641.907196.015.91610.412132341.733949550.045135521.061.4380.2257.364.568.765.024.45820.584214942.85.90413.3918.09718.069246.19113.65416.1203384.404324.7643.487.69290.9147.2312.1628.45324.6297.37828.745975.0952.4309.57176.07337.63133898.121153682.02930272.24124.952067.423894.041301.16275.53513.88OpenBenchmarking.org

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: tfft2February 20232020112233445547.3549.08

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: All Rendering TestsFebruary 202320202M4M6M8M10MSE +/- 27217.75, N = 4SE +/- 81902.34, N = 48868529.027815320.96

OpenBenchmarking.orgUnits Per Second, More Is BetterJava 2D Microbenchmark 1.0Rendering Test: Image RenderingFebruary 202320203M6M9M12M15MSE +/- 82053.86, N = 20SE +/- 33957.70, N = 412036752.948553596.51

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: vklBenchmark2020February 2023100200300400500SE +/- 1.89, N = 3SE +/- 2.19, N = 3461.15423.00MIN: 1 / MAX: 1298MIN: 1 / MAX: 1246

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 RenderingFebruary 202320202M4M6M8M10MSE +/- 17710.86, N = 4SE +/- 24423.75, N = 48150041.017844283.98

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 Atoms2020February 2023612182430SE +/- 0.03, N = 3SE +/- 0.10, N = 326.9125.94-pthread1. (CXX) g++ options: -O3 -lm

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 2February 2023202011M22M33M44M55MSE +/- 253679.25, N = 3SE +/- 368061.43, N = 1249644913.143076608.7

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 DeleteFebruary 20232020130260390520650SE +/- 0.94, N = 3SE +/- 0.60, N = 3595.58597.96-lpthread1. (CXX) g++ options: -O3 -lsnappy

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Sequential Fill2020February 2023130260390520650SE +/- 6.42, N = 3SE +/- 1.08, N = 3591.61592.28-lpthread1. (CXX) g++ options: -O3 -lsnappy

OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: Sequential FillFebruary 20232020612182430SE +/- 0.06, N = 3SE +/- 0.27, N = 323.923.9-lpthread1. (CXX) g++ options: -O3 -lsnappy

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: fatigue2February 20232020112233445536.5048.61

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: FLOAT2020February 202380M160M240M320M400MSE +/- 36581.81, N = 3SE +/- 264281.08, N = 3373293210.02367154749.561. (CC) gcc options: -O3 -march=native -lm

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 tau100.0February 2023202050100150200250SE +/- 1.45, N = 3SE +/- 0.88, N = 3132223-lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lz-pthread1. (F9X) gfortran options: -cpp -Jsource/ -ffree-line-length-0 -lm -std=legacy -O3 -O2 -lmpi_usempif08 -lmpi_mpifh -lmpi

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 1.2.4February 2023202010M20M30M40M50MSE +/- 33206.63, N = 3SE +/- 167341.17, N = 345462287448811771. (CXX) g++ options: -O3 -fopenmp

Timed HMMer Search

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed HMMer Search 3.3.1Pfam Database Search2020February 20234080120160200SE +/- 0.31, N = 3SE +/- 0.38, N = 3165.04167.561. (CC) gcc options: -O3 -pthread -lhmmer -leasel -lm

LevelDB

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

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Seek RandomFebruary 202320204080120160200SE +/- 0.23, N = 3SE +/- 0.18, N = 3157.94171.03-lpthread1. (CXX) g++ options: -O3 -lsnappy

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 TimesFebruary 2023202050100150200250SE +/- 0.33, N = 3SE +/- 1.54, N = 3101.08222.561. Version 2.4.5, Copyright (c) 2008-2019, David Tschumperle.

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-Only2020February 2023306090120150SE +/- 0.27, N = 3SE +/- 0.41, N = 3131.12142.95

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: 242020February 2023306090120150SE +/- 0.94, N = 3SE +/- 0.20, N = 3119.19120.381. (CXX) g++ options: -std=c++14 -lmozjs-68 -lm -lerl_interface -lei -fPIC -MMD

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: CPU2020February 202370140210280350SE +/- 0.49, N = 3SE +/- 2.43, N = 15328.33338.11-lpthread - MIN: 324.39MIN: 323.961. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -ldl

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: YesFebruary 20232020306090120150SE +/- 0.51, N = 6SE +/- 0.16, N = 354.44114.44

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: CPU - Model: yolov4-tinyFebruary 20232020816243240SE +/- 0.15, N = 3SE +/- 0.24, N = 334.9236.30MIN: 34.15 / MAX: 38.74MIN: 35.04 / MAX: 56.231. (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 ReadFebruary 2023202020406080100SE +/- 1.20, N = 3SE +/- 0.20, N = 3105.93110.00-lpthread1. (CXX) g++ options: -O3 -lsnappy

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: 8February 20232020306090120150SE +/- 0.31, N = 3SE +/- 0.34, N = 3100.69115.00-lreadline -ltermcap-ldl -lpthread1. (CC) gcc options: -O2 -lz -lm

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: Cartoon2020February 202320406080100SE +/- 0.33, N = 3SE +/- 0.23, N = 394.5298.08

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 1080February 20232020110220330440550SE +/- 4.02, N = 3SE +/- 3.18, N = 15490.63369.07

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: SciVisFebruary 202320201632486480SE +/- 0.46, N = 14SE +/- 0.79, N = 670.7567.46MIN: 62.5 / MAX: 76.92MIN: 62.5 / MAX: 76.92

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: induct2February 2023202051015202521.8521.92

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_startupFebruary 202320203691215SE +/- 0.03, N = 3SE +/- 0.00, N = 312.612.8

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-Only2020February 202320406080100SE +/- 0.44, N = 3SE +/- 0.31, N = 384.9593.81

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: EmilyFebruary 20232020306090120150130.33133.24

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 Times2020February 202320406080100SE +/- 0.33, N = 3SE +/- 0.34, N = 384.8986.381. Version 2.4.5, Copyright (c) 2008-2019, David Tschumperle.

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: CPU2020February 2023612182430SE +/- 0.30, N = 3SE +/- 0.27, N = 423.7824.53-lpthread - MIN: 22.66MIN: 23.591. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -ldl

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 Tracer2020February 20231.28252.5653.84755.136.4125SE +/- 0.01, N = 3SE +/- 0.01, N = 35.705.50MIN: 5.65 / MAX: 5.78MIN: 5.46 / MAX: 5.68

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: raytraceFebruary 20232020100200300400500SE +/- 0.33, N = 3277439

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 FillFebruary 20232020130260390520650SE +/- 1.42, N = 3SE +/- 1.02, N = 3608.57623.73-lpthread1. (CXX) g++ options: -O3 -lsnappy

OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: Random FillFebruary 20232020612182430SE +/- 0.07, N = 3SE +/- 0.03, N = 323.322.7-lpthread1. (CXX) g++ options: -O3 -lsnappy

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: OverwriteFebruary 20232020130260390520650SE +/- 0.82, N = 3SE +/- 0.23, N = 3611.02621.25-lpthread1. (CXX) g++ options: -O3 -lsnappy

OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: OverwriteFebruary 20232020612182430SE +/- 0.03, N = 3SE +/- 0.00, N = 323.222.8-lpthread1. (CXX) g++ options: -O3 -lsnappy

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 RenderingFebruary 202320205K10K15K20K25KSE +/- 198.50, N = 20SE +/- 265.68, N = 423141.4321836.34

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 BlurFebruary 202320201428425670SE +/- 0.15, N = 3SE +/- 0.24, N = 356.5564.73

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: SqueezeNetFebruary 2023202011K22K33K44K55KSE +/- 262.36, N = 3SE +/- 188.76, N = 348673.650791.3

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: 2to3February 2023202070140210280350SE +/- 0.33, N = 3276302

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 EnhanceFebruary 202320201326395265SE +/- 0.04, N = 3SE +/- 0.10, N = 350.4058.10

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 Time2020February 20231224364860SE +/- 0.04, N = 3SE +/- 0.26, N = 350.5153.401. 2020: RawTherapee, version 5.8, command line.2. February 2023: RawTherapee, version 5.9, command line.

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 Time2020February 202330M60M90M120M150MSE +/- 263429.87, N = 3SE +/- 803242.53, N = 31464634861423122461. (CXX) g++ options: -m64 -lpthread -fno-exceptions -std=c++11 -pedantic -O3 -msse -msse3 -mpopcnt -flto

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: proteinFebruary 20232020369121512.4412.72

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-Only2020February 20231122334455SE +/- 0.02, N = 3SE +/- 0.12, N = 346.3449.26

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 CommandsFebruary 202320201122334455SE +/- 0.16, N = 3SE +/- 0.10, N = 347.8248.371. February 2023: git version 2.38.12. 2020: git version 2.25.1

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: CPU2020February 20230.29920.59840.89761.19681.496SE +/- 0.01741, N = 4SE +/- 0.04058, N = 151.264411.32984-lpthread - MIN: 1.17MIN: 1.151. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -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 TimeFebruary 202320201122334455SE +/- 0.12, N = 3SE +/- 0.31, N = 345.0046.74

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: Vulkan GPU - Model: resnet50February 202320203691215SE +/- 0.03, N = 3SE +/- 0.09, N = 25.069.65MIN: 4.98 / MAX: 14.49MIN: 9.05 / MAX: 31.861. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: yolov4-tinyFebruary 2023202048121620SE +/- 0.03, N = 3SE +/- 0.02, N = 39.0015.04MIN: 8.84 / MAX: 12.27MIN: 12.6 / MAX: 42.11. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: alexnetFebruary 20232020714212835SE +/- 0.03, N = 3SE +/- 0.24, N = 35.4829.85MIN: 5.13 / MAX: 10.61MIN: 25.42 / MAX: 55.991. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: resnet18February 202320200.75151.5032.25453.0063.7575SE +/- 0.02, N = 3SE +/- 0.01, N = 31.863.34MIN: 1.79 / MAX: 10.57MIN: 3.22 / MAX: 5.291. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: vgg16February 2023202020406080100SE +/- 3.74, N = 3SE +/- 0.04, N = 330.3284.36MIN: 13.86 / MAX: 49.77MIN: 67.87 / MAX: 109.541. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: googlenetFebruary 20232020246810SE +/- 0.00, N = 3SE +/- 0.02, N = 34.448.51MIN: 4.41 / MAX: 4.84MIN: 7.13 / MAX: 29.751. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: efficientnet-b0February 202320203691215SE +/- 0.08, N = 3SE +/- 0.11, N = 37.3911.55MIN: 6.9 / MAX: 28.13MIN: 10.46 / MAX: 34.721. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: mnasnetFebruary 202320201.04852.0973.14554.1945.2425SE +/- 0.00, N = 3SE +/- 0.01, N = 32.344.66MIN: 2.3 / MAX: 2.63MIN: 4.41 / MAX: 5.41. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: shufflenet-v2February 202320200.7831.5662.3493.1323.915SE +/- 0.00, N = 3SE +/- 0.00, N = 31.743.48MIN: 1.72 / MAX: 2.67MIN: 3.38 / MAX: 4.251. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3February 20232020246810SE +/- 0.00, N = 3SE +/- 0.24, N = 33.118.47MIN: 3.06 / MAX: 6.37MIN: 7.45 / MAX: 27.991. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2February 202320201.0352.073.1054.145.175SE +/- 0.01, N = 3SE +/- 0.01, N = 32.214.60MIN: 2.16 / MAX: 4.69MIN: 4.27 / MAX: 9.61. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: mobilenetFebruary 202320203691215SE +/- 0.02, N = 3SE +/- 0.16, N = 36.799.98MIN: 6.71 / MAX: 7.44MIN: 8.51 / MAX: 38.161. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: squeezenetFebruary 202320201.30952.6193.92855.2386.5475SE +/- 0.04, N = 3SE +/- 0.05, N = 33.865.82MIN: 3.7 / MAX: 4.78MIN: 5.53 / MAX: 19.721. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

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: UltimateFebruary 2023202070140210280350SE +/- 1.55, N = 3SE +/- 1.88, N = 3300.11268.31MIN: 55 / MAX: 559MIN: 52 / MAX: 532

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: 19February 2023202020406080100SE +/- 0.13, N = 3SE +/- 0.06, N = 382.381.71. (CC) gcc options: -O3 -pthread -lz -llzma

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 Compile2020February 20231122334455SE +/- 0.05, N = 3SE +/- 0.09, N = 335.4547.70

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: goFebruary 2023202050100150200250SE +/- 0.00, N = 3SE +/- 0.33, N = 3136233

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: AntialiasFebruary 20232020918273645SE +/- 0.07, N = 3SE +/- 0.03, N = 337.1641.08

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: CPU2020February 20230.35080.70161.05241.40321.754SE +/- 0.01640, N = 8SE +/- 0.01350, N = 31.550971.55913-lpthread - MIN: 1.45MIN: 1.491. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU2020February 20230.12180.24360.36540.48720.609SE +/- 0.006670, N = 4SE +/- 0.005684, N = 150.5085440.541529-lpthread - MIN: 0.46MIN: 0.461. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -ldl

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 Atoms2020February 20230.09650.1930.28950.3860.4825SE +/- 0.00043, N = 3SE +/- 0.00183, N = 30.426770.42898

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: CPU2020February 2023306090120150SE +/- 0.34, N = 3SE +/- 0.99, N = 3115.07121.80-lpthread - MIN: 112.93MIN: 118.311. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -ldl

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: NoFebruary 2023202048121620SE +/- 0.23, N = 14SE +/- 0.06, N = 312.1116.51

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: UltraFebruary 2023202090180270360450SE +/- 4.49, N = 3SE +/- 0.35, N = 3393.52335.62MIN: 185 / MAX: 682MIN: 192 / MAX: 628

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-Only2020February 2023816243240SE +/- 0.11, N = 3SE +/- 0.02, N = 332.4333.53

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 CompressionFebruary 20232020816243240SE +/- 0.14, N = 3SE +/- 0.22, N = 333.2933.50-pthread1. (CC) gcc options: -fvisibility=hidden -O2 -lm -ljpeg -lpng16 -ltiff

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 Tracer2020February 2023246810SE +/- 0.02, N = 3SE +/- 0.03, N = 37.327.03MIN: 7.04 / MAX: 7.52MIN: 6.9 / MAX: 7.25

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: NASA Streamlines - Renderer: Path Tracer2020February 2023510152025SE +/- 0.00, N = 12SE +/- 0.13, N = 320.4119.74MIN: 20 / MAX: 21.28MIN: 19.23 / MAX: 20.41

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: Tile GlassFebruary 20232020816243240SE +/- 0.01, N = 3SE +/- 0.04, N = 330.9332.97

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 2160February 2023202080160240320400SE +/- 2.86, N = 3SE +/- 1.73, N = 3346.84311.58

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_templateFebruary 202320201122334455SE +/- 0.03, N = 3SE +/- 0.23, N = 330.547.5

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: HighFebruary 20232020100200300400500SE +/- 4.55, N = 3SE +/- 3.24, N = 3453.88383.47MIN: 209 / MAX: 809MIN: 235 / MAX: 737

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: ReflectFebruary 20232020714212835SE +/- 0.02, N = 3SE +/- 0.08, N = 329.5531.59

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_compileFebruary 202320204080120160200SE +/- 0.33, N = 3SE +/- 0.58, N = 3129160

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: pickle_pure_pythonFebruary 20232020100200300400500SE +/- 0.00, N = 3SE +/- 2.40, N = 3276441

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 BenchmarkFebruary 202320201020304050SE +/- 0.19, N = 3SE +/- 0.46, N = 341.9041.831. (CXX) g++ options: -O2 -fopenmp -ljpeg -lz -lm

Zstd Compression

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

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.5Compression Level: 32020February 202316003200480064008000SE +/- 14.49, N = 3SE +/- 6.53, N = 37285.87196.01. (CC) gcc options: -O3 -pthread -lz -llzma

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: pathlibFebruary 2023202048121620SE +/- 0.00, N = 3SE +/- 0.03, N = 315.916.3

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: CompositeFebruary 2023202030060090012001500SE +/- 1.82, N = 3SE +/- 2.00, N = 31610.411541.471. (CC) gcc options: -lm -ldl -O2 -fomit-frame-pointer -U_FORTIFY_SOURCE -fno-stack-protector

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 Second2020February 2023500K1000K1500K2000K2500KSE +/- 15042.16, N = 3SE +/- 14325.36, N = 32256436.982132341.731. (CC) gcc options: -O2 -lrt" -lrt

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: LowFebruary 20232020120240360480600SE +/- 3.70, N = 3SE +/- 1.68, N = 3550.05506.69MIN: 252 / MAX: 1144MIN: 316 / MAX: 1048

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 4K2020February 2023612182430SE +/- 0.07, N = 3SE +/- 0.03, N = 326.2521.061. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

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: airFebruary 202320200.38480.76961.15441.53921.9241.431.71

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: nbodyFebruary 2023202020406080100SE +/- 0.10, N = 3SE +/- 0.33, N = 380.2108.0

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 2160February 2023202060120180240300SE +/- 2.02, N = 3SE +/- 3.22, N = 3257.3241.5

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: chaosFebruary 2023202020406080100SE +/- 0.03, N = 364.5104.0

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: crypto_pyaesFebruary 2023202020406080100SE +/- 0.03, N = 368.7103.0

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: floatFebruary 2023202020406080100SE +/- 0.07, N = 3SE +/- 0.33, N = 365.0108.0

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 Compile2020February 2023612182430SE +/- 0.02, N = 3SE +/- 0.07, N = 321.2724.46

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_loadsFebruary 20232020612182430SE +/- 0.03, N = 3SE +/- 0.03, N = 320.523.9

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 TimesFebruary 202320202004006008001000SE +/- 4.67, N = 3SE +/- 2.40, N = 3842941

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 Performance2020February 20233K6K9K12K15KSE +/- 116.95, N = 3SE +/- 81.34, N = 315077.314942.81. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

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: YesFebruary 202320203691215SE +/- 0.343, N = 15SE +/- 0.010, N = 35.9049.101

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: SciVis2020February 202348121620SE +/- 0.06, N = 3SE +/- 0.06, N = 313.7613.39MIN: 13.51 / MAX: 14.08MIN: 12.99 / MAX: 13.7

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 CompileFebruary 20232020510152025SE +/- 0.03, N = 3SE +/- 0.06, N = 318.1019.74

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 2020-06-28February 20232020510152025SE +/- 0.02, N = 3SE +/- 0.04, N = 318.0718.811. (CC) gcc options: -O2 -pedantic -fvisibility=hidden

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 v1.1February 2023202060120180240300SE +/- 0.90, N = 3SE +/- 0.59, N = 3246.19252.18MIN: 244.08 / MAX: 249.94MIN: 249.83 / MAX: 254.131. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -O3 -rdynamic -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 TimesFebruary 20232020510152025SE +/- 0.08, N = 3SE +/- 0.02, N = 313.6519.381. Version 2.4.5, Copyright (c) 2008-2019, David Tschumperle.

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, LosslessFebruary 2023202048121620SE +/- 0.05, N = 3SE +/- 0.06, N = 316.1216.30-pthread1. (CC) gcc options: -fvisibility=hidden -O2 -lm -ljpeg -lpng16 -ltiff

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 1080February 202320207001400210028003500SE +/- 25.14, N = 11SE +/- 34.36, N = 73384.403145.94

OpenBenchmarking.orgFrames / Sec, More Is BetterParaView 5.4.1Test: Wavelet Contour - Resolution: 1920 x 1080February 2023202070140210280350SE +/- 2.41, N = 11SE +/- 3.30, N = 7324.76301.88

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: SciVisFebruary 202320201020304050SE +/- 0.00, N = 3SE +/- 0.00, N = 1243.4843.48MIN: 41.67 / MAX: 45.45MIN: 41.67 / MAX: 45.45

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 FLACFebruary 20232020246810SE +/- 0.013, N = 5SE +/- 0.015, N = 57.6927.9711. (CXX) g++ options: -O2 -fvisibility=hidden -logg -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: NASA Streamlines - Renderer: SciVisFebruary 2023202020406080100SE +/- 0.00, N = 3SE +/- 0.00, N = 1390.9190.91MIN: 83.33 / MAX: 100MIN: 83.33 / MAX: 100

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 1080p2020February 20231326395265SE +/- 0.21, N = 3SE +/- 0.14, N = 358.1947.231. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

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 Compile2020February 20233691215SE +/- 0.03, N = 3SE +/- 0.02, N = 310.6112.16

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: CropFebruary 20232020246810SE +/- 0.047, N = 3SE +/- 0.043, N = 38.4538.843

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 ProteinFebruary 20232020612182430SE +/- 0.37, N = 15SE +/- 0.21, N = 1424.6323.85-pthread1. (CXX) g++ options: -O3 -lm

WebP Image Encode

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

OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100, Highest Compression2020February 2023246810SE +/- 0.015, N = 3SE +/- 0.005, N = 37.1387.378-pthread1. (CC) gcc options: -fvisibility=hidden -O2 -lm -ljpeg -lpng16 -ltiff

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: MemorialFebruary 20232020714212835SE +/- 0.01, N = 3SE +/- 0.03, N = 328.7427.01

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 Sync2020February 202313002600390052006500SE +/- 15.69, N = 3SE +/- 19.28, N = 35953.965975.10-lpthread1. (CXX) g++ options: -O3 -lsnappy

OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: Fill SyncFebruary 202320200.541.081.622.162.7SE +/- 0.03, N = 3SE +/- 0.00, N = 32.42.4-lpthread1. (CXX) g++ options: -O3 -lsnappy

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 Scene2020February 202370140210280350SE +/- 0.24, N = 3SE +/- 0.31, N = 3311.30309.57

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 Encode2020February 202350100150200250SE +/- 1.79, N = 3SE +/- 2.46, N = 3208.29176.071. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

SVT-VP9

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-VP9 CPU-based multi-threaded video encoder for the VP9 video format with a sample 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 1080p2020February 202390180270360450SE +/- 2.19, N = 3SE +/- 3.73, N = 5394.07337.631. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

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 RoutineFebruary 2023202030K60K90K120K150KSE +/- 232.46, N = 3SE +/- 641.63, N = 3133898.12129515.001. (F9X) gfortran options: -O3 -fomit-frame-pointer -fopenmp

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: CPUFebruary 202320200.46610.93221.39831.86442.3305SE +/- 0.00541, N = 3SE +/- 0.01201, N = 32.029302.07153MIN: 1.95-lpthread - MIN: 1.931. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -ldl

SVT-VP9

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-VP9 CPU-based multi-threaded video encoder for the VP9 video format with a sample 1080p YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.1Tuning: Visual Quality Optimized - Input: Bosphorus 1080p2020February 202370140210280350SE +/- 2.60, N = 3SE +/- 0.81, N = 3326.72272.241. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

Optcarrot

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

OpenBenchmarking.orgFPS, More Is BetterOptcarrotOptimized Benchmark2020February 2023306090120150SE +/- 0.25, N = 4SE +/- 1.09, N = 4131.33124.951. 2020: ruby 2.7.0p0 (2019-12-25 revision 647ee6f091) [x86_64-linux-gnu]2. February 2023: ruby 3.0.4p208 (2022-04-12 revision 3fa771dded) [x86_64-linux-gnu]

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-RelaxationFebruary 20232020400800120016002000SE +/- 4.22, N = 3SE +/- 3.21, N = 32067.422055.731. (CC) gcc options: -lm -ldl -O2 -fomit-frame-pointer -U_FORTIFY_SOURCE -fno-stack-protector

OpenBenchmarking.orgMflops, More Is BetterLuaJIT 2.1-gitTest: Dense LU Matrix FactorizationFebruary 202320208001600240032004000SE +/- 7.37, N = 3SE +/- 18.22, N = 33894.043668.791. (CC) gcc options: -lm -ldl -O2 -fomit-frame-pointer -U_FORTIFY_SOURCE -fno-stack-protector

OpenBenchmarking.orgMflops, More Is BetterLuaJIT 2.1-gitTest: Sparse Matrix MultiplyFebruary 2023202030060090012001500SE +/- 1.63, N = 3SE +/- 3.63, N = 31301.161221.291. (CC) gcc options: -lm -ldl -O2 -fomit-frame-pointer -U_FORTIFY_SOURCE -fno-stack-protector

OpenBenchmarking.orgMflops, More Is BetterLuaJIT 2.1-gitTest: Fast Fourier TransformFebruary 2023202060120180240300SE +/- 0.61, N = 3SE +/- 23.04, N = 3275.53254.691. (CC) gcc options: -lm -ldl -O2 -fomit-frame-pointer -U_FORTIFY_SOURCE -fno-stack-protector

OpenBenchmarking.orgMflops, More Is BetterLuaJIT 2.1-gitTest: Monte CarloFebruary 20232020110220330440550SE +/- 0.81, N = 3SE +/- 0.10, N = 3513.88506.841. (CC) gcc options: -lm -ldl -O2 -fomit-frame-pointer -U_FORTIFY_SOURCE -fno-stack-protector

Geometric Mean Of All Test Results

OpenBenchmarking.orgGeometric Mean, More Is BetterGeometric Mean Of All Test ResultsResult Composite - System76 Thelio Major 3990X 2023 BenchmarksFebruary 2023202071421283529.2125.51

136 Results Shown

Polyhedron Fortran Benchmarks
Java 2D Microbenchmark:
  All Rendering Tests
  Image Rendering
OpenVKL
Java 2D Microbenchmark
LAMMPS Molecular Dynamics Simulator
BYTE Unix Benchmark
LevelDB:
  Rand Delete
  Seq Fill
  Seq Fill
Polyhedron Fortran Benchmarks
Hierarchical INTegration
Monte Carlo Simulations of Ionised Nebulae
Kripke
Timed HMMer Search
LevelDB
G'MIC
Blender
Apache CouchDB
oneDNN
RealSR-NCNN
NCNN
LevelDB
SQLite
GEGL
Tesseract
OSPray
Polyhedron Fortran Benchmarks
PyPerformance
Blender
Appleseed
G'MIC
oneDNN
OSPray
PyPerformance
LevelDB:
  Rand Fill:
    Microseconds Per Op
    MB/s
  Overwrite:
    Microseconds Per Op
    MB/s
Java 2D Microbenchmark
GEGL
TensorFlow Lite
PyPerformance
GEGL
RawTherapee
Stockfish
Polyhedron Fortran Benchmarks
Blender
Git
oneDNN
Hugin
NCNN:
  Vulkan GPU - resnet50
  Vulkan GPU - yolov4-tiny
  Vulkan GPU - alexnet
  Vulkan GPU - resnet18
  Vulkan GPU - vgg16
  Vulkan GPU - googlenet
  Vulkan GPU - efficientnet-b0
  Vulkan GPU - mnasnet
  Vulkan GPU - shufflenet-v2
  Vulkan GPU-v3-v3 - mobilenet-v3
  Vulkan GPU-v2-v2 - mobilenet-v2
  Vulkan GPU - mobilenet
  Vulkan GPU - squeezenet
Xonotic
Zstd Compression
Timed PHP Compilation
PyPerformance
GEGL
oneDNN:
  Deconvolution Batch deconv_1d - f32 - CPU
  Matrix Multiply Batch Shapes Transformer - f32 - CPU
NAMD
oneDNN
RealSR-NCNN
Xonotic
Blender
WebP Image Encode
OSPray:
  XFrog Forest - Path Tracer
  NASA Streamlines - Path Tracer
GEGL
Tesseract
PyPerformance
Xonotic
GEGL
PyPerformance:
  regex_compile
  pickle_pure_python
LibRaw
Zstd Compression
PyPerformance
LuaJIT
Coremark
Xonotic
x265
Polyhedron Fortran Benchmarks
PyPerformance
ET: Legacy
PyPerformance:
  chaos
  crypto_pyaes
  float
Timed Apache Compilation
PyPerformance
PyBench
OpenSSL
Waifu2x-NCNN Vulkan
OSPray
Timed FFmpeg Compilation
RNNoise
TNN
G'MIC
WebP Image Encode
ParaView:
  Wavelet Contour - 1920 x 1080:
    MiPolys / Sec
    Frames / Sec
OSPray
FLAC Audio Encoding
OSPray
x265
Timed MPlayer Compilation
GEGL
LAMMPS Molecular Dynamics Simulator
WebP Image Encode
Intel Open Image Denoise
LevelDB:
  Fill Sync:
    Microseconds Per Op
    MB/s
rays1bench
SVT-HEVC
SVT-VP9
FFTE
oneDNN
SVT-VP9
Optcarrot
LuaJIT:
  Jacobi Successive Over-Relaxation
  Dense LU Matrix Factorization
  Sparse Matrix Multiply
  Fast Fourier Transform
  Monte Carlo
Geometric Mean Of All Test Results

2020

Processor: AMD Ryzen Threadripper 3990X 64-Core @ 2.90GHz (64 Cores / 128 Threads), Motherboard: Gigabyte TRX40 AORUS PRO WIFI (F4p BIOS), Chipset: AMD Starship/Matisse, Memory: 128GB, 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.

February 2023

Processor: AMD Ryzen Threadripper 3990X 64-Core @ 2.90GHz (64 Cores / 128 Threads), Motherboard: Gigabyte TRX40 AORUS PRO WIFI (F4p BIOS), Chipset: AMD Starship/Matisse, Memory: 128GB, Disk: Samsung SSD 970 EVO Plus 500GB + 257GB Flash Drive, Graphics: AMD Radeon RX 5700 8GB (1750/875MHz), Audio: AMD Navi 10 HDMI Audio, Monitor: DELL P2415Q, Network: Intel I211 + Intel Wi-Fi 6 AX200

OS: Ubuntu 23.04, Kernel: 6.2.0-060200rc7daily20230206-generic (x86_64), Desktop: GNOME Shell 43.2, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 22.2.5 (LLVM 15.0.6 DRM 3.49), Compiler: GCC 12.2.0, File-System: ext4, Screen Resolution: 3840x2160

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,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-defaulted --enable-offload-targets=nvptx-none=/build/gcc-12-AKimc9/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-AKimc9/gcc-12-12.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Disk Notes: NONE / errors=remount-ro,relatime,rw / Block Size: 4096
Processor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0x8301055
Graphics Notes: BAR1 / Visible vRAM Size: 256 MB - vBIOS Version: 113-D1820201-101
Java Notes: OpenJDK Runtime Environment (build 11.0.18+10-post-Ubuntu-0ubuntu1)
Python Notes: Python 3.11.1
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Mitigation of untrained return thunk; SMT enabled with STIBP protection + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 6 February 2023 18:19 by user phoronix.