Creator AMD Ryzen 5 5600G

AMD Ryzen 5 5600G testing with a ASUS TUF GAMING B550M-PLUS (WI-FI) (2423 BIOS) and ASUS AMD Cezanne on Ubuntu 21.10 via the Phoronix Test Suite.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2109039-TJ-CREATORAM04
Jump To Table - Results

View

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

Limit displaying results to tests within:

Audio Encoding 6 Tests
AV1 6 Tests
C/C++ Compiler Tests 16 Tests
CPU Massive 21 Tests
Creator Workloads 63 Tests
Encoding 19 Tests
Game Development 9 Tests
HPC - High Performance Computing 3 Tests
Imaging 13 Tests
Machine Learning 3 Tests
Multi-Core 35 Tests
NVIDIA GPU Compute 5 Tests
OCR 2 Tests
Intel oneAPI 5 Tests
Productivity 3 Tests
Python Tests 3 Tests
Raytracing 5 Tests
Renderers 15 Tests
Server CPU Tests 15 Tests
Single-Threaded 10 Tests
Speech 4 Tests
Telephony 4 Tests
Texture Compression 4 Tests
Video Encoding 13 Tests
Common Workstation Benchmarks 2 Tests

Statistics

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

Graph Settings

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

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
A
September 02 2021
  3 Hours, 40 Minutes
B
September 02 2021
  9 Hours, 48 Minutes
C
September 03 2021
  8 Hours, 29 Minutes
Invert Hiding All Results Option
  7 Hours, 19 Minutes

Only show results where is faster than
Only show results matching title/arguments (delimit multiple options with a comma):
Do not show results matching title/arguments (delimit multiple options with a comma):

A

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --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-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-M6DaQn/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-M6DaQn/gcc-11-11.2.0/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-build-config=bootstrap-lto-lean --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
Processor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa50000c
Python Notes: Python 3.9.6
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 IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected

B

C

Processor: AMD Ryzen 5 5600G @ 3.90GHz (6 Cores / 12 Threads), Motherboard: ASUS TUF GAMING B550M-PLUS (WI-FI) (2423 BIOS), Chipset: AMD Renoir Root Complex, Memory: 16GB, Disk: 1000GB Samsung SSD 980 PRO 1TB, Graphics: ASUS AMD Cezanne (1900/1800MHz), Audio: AMD Device 1637, Monitor: LG Ultra HD, Network: Realtek RTL8125 2.5GbE + Intel Wi-Fi 6 AX200

OS: Ubuntu 21.10, Kernel: 5.14.0-051400rc7daily20210826-generic (x86_64) 20210825, Desktop: GNOME Shell 40.2, Display Server: X Server, OpenGL: 4.6 Mesa 21.3.0-devel (git-9ca7412 2021-08-26 impish-oibaf-ppa) (LLVM 12.0.1), Vulkan: 1.2.185, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 3840x2160

Creator AMD Ryzen 5 5600GOpenBenchmarking.orgPhoronix Test SuiteAMD Ryzen 5 5600G @ 3.90GHz (6 Cores / 12 Threads)ASUS TUF GAMING B550M-PLUS (WI-FI) (2423 BIOS)AMD Renoir Root Complex16GB1000GB Samsung SSD 980 PRO 1TBASUS AMD Cezanne (1900/1800MHz)AMD Device 1637LG Ultra HDRealtek RTL8125 2.5GbE + Intel Wi-Fi 6 AX200Ubuntu 21.105.14.0-051400rc7daily20210826-generic (x86_64) 20210825GNOME Shell 40.2X Server4.6 Mesa 21.3.0-devel (git-9ca7412 2021-08-26 impish-oibaf-ppa) (LLVM 12.0.1)1.2.185GCC 11.2.0ext43840x2160ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerOpenGLVulkanCompilerFile-SystemScreen ResolutionCreator AMD Ryzen 5 5600G BenchmarksSystem Logs- Transparent Huge Pages: madvise- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --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-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-M6DaQn/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-M6DaQn/gcc-11-11.2.0/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-build-config=bootstrap-lto-lean --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 - Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa50000c- Python 3.9.6- 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 IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected

ABCResult OverviewPhoronix Test Suite100%102%103%105%107%dcrawdav1dGraphicsMagickx264VP9 libvpx EncodingSVT-VP9Monkey Audio EncodingSVT-HEVCGoogle SynthMarkLibRawDeepSpeechAOM AV1x265libgav1EmbreeRadiance BenchmarkDarktableOpus Codec EncodingKTX-Software toktxTachyonFFmpegAOBenchSVT-AV1Timed Godot Game Engine CompilationeSpeak-NG Speech Enginerays1benchoneDNNLuxCoreRenderlibrsvgrav1eOgg Audio EncodingRNNoiseHuginGIMPBlenderKvazaarWebP Image EncodeRawTherapeelibavif avifencFLAC Audio EncodingOSPrayEtcpakLuaJITGEGLTTSIOD 3D RendererLAME MP3 EncodingOCRMyPDFlibjpeg-turbo tjbenchG'MICPOV-RaySmallptASTC EncoderBasis UniversalIndigoBenchIntel Open Image DenoiseOpenVKLC-Ray

Creator AMD Ryzen 5 5600Gblender: Barbershop - CPU-Onlyblender: Classroom - CPU-Onlyblender: Pabellon Barcelona - CPU-Onlyappleseed: Emilytoktx: UASTC 4 + Zstd Compression 19blender: Fishy Cat - CPU-Onlyappleseed: Disney Materialospray: San Miguel - Path Traceraom-av1: Speed 4 Two-Pass - Bosphorus 4Koidn: RTLightmap.hdr.4096x4096openvkl: vklBenchmark ISPCopenvkl: vklBenchmark Scalarappleseed: Material Testerradiance: Serialblender: BMW27 - CPU-Onlyospray: XFrog Forest - Path Tracerluxcorerender: Danish Mood - CPUlibgav1: Chimera 1080p 10-bitaom-av1: Speed 0 Two-Pass - Bosphorus 4Kbuild-godot: Time To Compileaom-av1: Speed 6 Two-Pass - Bosphorus 4Kvpxenc: Speed 0 - Bosphorus 4Kkvazaar: Bosphorus 4K - Slowsvt-av1: Preset 4 - Bosphorus 4Kkvazaar: Bosphorus 4K - Mediumoidn: RT.hdr_alb_nrm.3840x2160oidn: RT.ldr_alb_nrm.3840x2160tachyon: Total Timeaom-av1: Speed 4 Two-Pass - Bosphorus 1080pospray: XFrog Forest - SciVisgmic: 2D Function Plotting, 1000 Timesx265: Bosphorus 4Kastcenc: Exhaustiveonednn: Recurrent Neural Network Training - u8s8f32 - CPUonednn: Recurrent Neural Network Training - f32 - CPUonednn: Recurrent Neural Network Training - bf16bf16bf16 - CPUsvt-hevc: 1 - Bosphorus 1080ponednn: Recurrent Neural Network Inference - f32 - CPUonednn: Recurrent Neural Network Inference - u8s8f32 - CPUonednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPUembree: Pathtracer ISPC - Asian Dragon Objc-ray: Total Time - 4K, 16 Rays Per Pixelgegl: Cartoonavifenc: 0embree: Pathtracer - Asian Dragon Objembree: Pathtracer ISPC - Crownradiance: SMP Parallelospray: NASA Streamlines - Path Traceravifenc: 6, Losslessluxcorerender: Orange Juice - CPUembree: Pathtracer - Crownluxcorerender: LuxCore Benchmark - CPUv-ray: CPUluxcorerender: DLSC - CPUembree: Pathtracer ISPC - Asian Dragonindigobench: CPU - Bedroombasis: UASTC Level 3indigobench: CPU - Supercarlibgav1: Summer Nature 4Kgraphics-magick: Sharpengraphics-magick: Noise-Gaussiangraphics-magick: Enhancedgraphics-magick: Resizinggraphics-magick: Swirlgraphics-magick: Rotategraphics-magick: HWB Color Spacerawtherapee: Total Benchmark Timeembree: Pathtracer - Asian Dragonsynthmark: VoiceMark_100vpxenc: Speed 0 - Bosphorus 1080ppovray: Trace Timelibgav1: Chimera 1080paom-av1: Speed 0 Two-Pass - Bosphorus 1080pvpxenc: Speed 5 - Bosphorus 4Konednn: Deconvolution Batch shapes_1d - f32 - CPUaom-av1: Speed 6 Realtime - Bosphorus 4Kgegl: Wavelet Blursvt-av1: Preset 8 - Bosphorus 4Kgegl: Color Enhancegmic: 3D Elevated Function In Rand Colors, 100 Timesdeepspeech: CPUsvt-av1: Preset 4 - Bosphorus 1080pkvazaar: Bosphorus 4K - Very Fastdav1d: Chimera 1080p 10-bitaom-av1: Speed 6 Two-Pass - Bosphorus 1080phugin: Panorama Photo Assistant + Stitching Timerav1e: 5rav1e: 1webp: Quality 100, Lossless, Highest Compressiondcraw: RAW To PPM Image Conversionavifenc: 2ospray: San Miguel - SciVisnatron: Spaceshipgegl: Rotate 90 Degreesbasis: UASTC Level 2dav1d: Summer Nature 4Kaobench: 2048 x 2048 - Total Timegegl: Antialiasespeak: Text-To-Speech Synthesisrav1e: 6kvazaar: Bosphorus 1080p - Slowttsiod-renderer: Phong Rendering With Soft-Shadow Mappingkvazaar: Bosphorus 1080p - Mediumluajit: Compositelibraw: Post-Processing Benchmarkdav1d: Chimera 1080pbasis: ETC1Saom-av1: Speed 6 Realtime - Bosphorus 1080ptjbench: Decompression Throughputgegl: Reflectospray: Magnetic Reconnection - SciViskvazaar: Bosphorus 4K - Ultra Fastluxcorerender: Rainbow Colors and Prism - CPUgegl: Tile Glassetcpak: ETC2toktx: Zstd Compression 19onednn: Deconvolution Batch shapes_1d - u8s8f32 - CPUocrmypdf: Processing 60 Page PDF Documentrsvg: SVG Files To PNGrav1e: 10toktx: UASTC 3 + Zstd Compression 19rays1bench: Large Scenevpxenc: Speed 5 - Bosphorus 1080plibgav1: Summer Nature 1080pencode-ape: WAV To APErnnoise: aom-av1: Speed 8 Realtime - Bosphorus 4Kencode-ogg: WAV To Oggtesseract-ocr: Time To OCR 7 Imagesencode-wavpack: WAV To WavPackwebp: Quality 100, Losslesssvt-av1: Preset 8 - Bosphorus 1080petcpak: ETC1 + Ditheringonednn: IP Shapes 1D - f32 - CPUonednn: IP Shapes 1D - u8s8f32 - CPUospray: NASA Streamlines - SciVisetcpak: ETC1onednn: Deconvolution Batch shapes_3d - u8s8f32 - CPUavifenc: 6toktx: UASTC 3astcenc: Thoroughx265: Bosphorus 1080psmallpt: Global Illumination Renderer; 128 Samplesonednn: Matrix Multiply Batch Shapes Transformer - f32 - CPUonednn: Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPUaom-av1: Speed 9 Realtime - Bosphorus 4Kgimp: unsharp-maskgmic: Plotting Isosurface Of A 3D Volume, 1000 Timeskvazaar: Bosphorus 1080p - Very Fastencode-opus: WAV To Opus Encodeencode-flac: WAV To FLACgimp: auto-levelsgimp: rotateonednn: IP Shapes 3D - f32 - CPUonednn: IP Shapes 3D - u8s8f32 - CPUdav1d: Summer Nature 1080psvt-hevc: 7 - Bosphorus 1080pdarktable: Masskrug - CPU-onlydarktable: Boat - CPU-onlyx264: H.264 Video Encodingkvazaar: Bosphorus 1080p - Ultra Fastgegl: Cropsvt-vp9: Visual Quality Optimized - Bosphorus 1080pgimp: resizebasis: UASTC Level 0onednn: Convolution Batch Shapes Auto - f32 - CPUonednn: Convolution Batch Shapes Auto - u8s8f32 - CPUencode-mp3: WAV To MP3darktable: Server Room - CPU-onlywebp: Quality 100, Highest Compressionaom-av1: Speed 8 Realtime - Bosphorus 1080psvt-vp9: VMAF Optimized - Bosphorus 1080pavifenc: 10, Losslesssvt-vp9: PSNR/SSIM Optimized - Bosphorus 1080paom-av1: Speed 9 Realtime - Bosphorus 1080pneatbench: Allneatbench: CPUgegl: Scaleastcenc: Mediumsvt-hevc: 10 - Bosphorus 1080pffmpeg: H.264 HD To NTSC DVetcpak: DXT1avifenc: 10onednn: Deconvolution Batch shapes_3d - f32 - CPUtoktx: Zstd Compression 9ospray: Magnetic Reconnection - Path Tracerwebp: Quality 100webp: Defaultdarktable: Server Rack - CPU-onlyluajit: Jacobi Successive Over-Relaxationluajit: Dense LU Matrix Factorizationluajit: Sparse Matrix Multiplyluajit: Fast Fourier Transformluajit: Monte CarloABC744.04552.62611.88443.30963376.112250.71282.2346090.983.350.144726242.601664477.553188.471.21153.970.13141.6346.395.295.111.3795.180.280.2899.44796.842.2695.28613.1485.45223906.843909.223909.287.162359.222356.442355.969.079673.60371.8671.91510.27228.9599149.4913.3664.6482.369.70081.1786151.5910.16381.67361.2793.3859.029122017285547868369657.09711.1569834.18510.7451.751168.160.412.17.3980212.6546.74413.58344.29243.70360.938873.75414.3261.6619.1339.8181.5140.52837.49235.52337.37512.202.432.45332.006112.3230.65729.73623.1812.01720.38546.269211768.3243.94406.626.10923.29241.64749924.7219.0924.846.9222.871219.51120.5352.3860120.48420.3174.53419.31247.7933.04206.810.78316.53537.716.15618.74812.21215.44539.568319.6124.863661.8323816.95355.6194.2187612.93212.9199.142548.6112.1444.36143.2803652.3611.52311.50352.486.76.4489.7829.38611.7183.14407401.8373.356.4846.37882.2688.636.77791.656.6976.39121.733123.18856.255.0085.868104.75105.45.68110.21128.5213.613.64.5364.461153.534.0261408.4513.2938.290612.703142.861.8811.1930.1892232.564079.961585.12401.6542.35740.70557.08613.05447.188638376.321251.40280.9452550.993.400.144726243.217646478.402188.241.211.0354.710.13141.9226.495.335.101.3885.190.280.28100.05486.922.2795.25613.3385.45983907.363908.783909.197.182341.312342.532346.039.229473.60071.87471.74710.23929.1502152.3673.3663.8092.369.81201.1885421.5610.26211.66061.2913.40959.689222717488649477177657.17211.2922854.07011.0851.750172.150.4012.707.9035212.8146.70713.73444.27643.65359.781063.75014.28278.8519.4139.6691.5230.52337.72637.63637.30112.202.532.42031.990117.9530.49029.72323.1322.02020.48547.27420.981769.6844.80430.1626.18523.44241.29255324.7379.0924.776.9022.897219.47021.4612.3881020.50120.3294.57519.09247.5432.97208.5610.53816.60238.4316.0918.74112.21815.10839.877319.6594.873561.8420316.95355.9584.2700113.11212.9389.150449.3312.1454.358883.2988053.2711.55611.49452.536.6616.4329.7839.55711.64073.14247421.5075.526.5376.40384.7288.086.70693.596.6566.39321.768822.85696.2435.0765.870105.29109.155.649113.42127.6513.513.54.5364.4597159.844.0161409.0313.2598.568432.719142.861.8871.1940.1912228.804087.551581.03401.07549.95740.09554.90376.080249.300.983.410.144726477.989187.581.201.0254.710.13142.4526.495.365.111.3895.180.280.28100.04406.932.2695.10813.4585.48393909.543904.333907.597.162347.892343.842351.399.203073.59571.87171.68310.25019.1341150.0693.3665.0102.369.80601.161.5710.24321.66661.2923.39459.469222717488549477477657.29211.3081842.43911.0951.822169.400.4112.887.6976412.8646.69413.71444.28643.73860.245663.74914.26277.2719.5739.7621.5260.52537.58437.94637.44212.2032.44531.994117.3030.47329.73623.0592.02320.39547.25620.991770.9044.69430.1626.15223.54241.53998024.7189.0924.686.8922.876219.04321.2332.3871620.51920.4024.58519.20147.6433.21207.7910.52116.56238.9416.08815.37539.886318.5264.900821.8388316.95355.1494.2302613.08712.9399.155848.6112.1554.362363.2970354.3811.52111.53852.146.6456.4299.7359.50911.56753.10159418.8273.826.5406.40583.5087.426.67892.536.6906.39621.839922.81456.2545.0535.859105.09108.675.645112.35127.774.5364.4643156.503.9981408.7853.2508.559432.708142.861.8841.2030.1912230.604093.771580.02400.74549.37OpenBenchmarking.org

Blender

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

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Barbershop - Compute: CPU-OnlyABC160320480640800SE +/- 1.67, N = 3SE +/- 0.44, N = 3744.04740.70740.09
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Barbershop - Compute: CPU-OnlyABC130260390520650Min: 738.46 / Avg: 740.7 / Max: 743.96Min: 739.36 / Avg: 740.09 / Max: 740.88

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Classroom - Compute: CPU-OnlyABC120240360480600SE +/- 0.26, N = 3SE +/- 0.29, N = 3552.62557.08554.90
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Classroom - Compute: CPU-OnlyABC100200300400500Min: 556.61 / Avg: 557.08 / Max: 557.5Min: 554.33 / Avg: 554.9 / Max: 555.25

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Pabellon Barcelona - Compute: CPU-OnlyAB130260390520650SE +/- 0.27, N = 3611.88613.05
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Pabellon Barcelona - Compute: CPU-OnlyAB110220330440550Min: 612.58 / Avg: 613.05 / Max: 613.51

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: EmilyAB100200300400500443.31447.19

KTX-Software toktx

This is a benchmark of The Khronos Group's KTX-Software library and tools. KTX-Software provides "toktx" for converting/creating in the KTX container format for image textures. This benchmark times how long it takes to convert to KTX 2.0 format with various settings using a reference PNG sample input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterKTX-Software toktx 4.0Settings: UASTC 4 + Zstd Compression 19ABC80160240320400SE +/- 0.17, N = 3SE +/- 0.11, N = 3376.11376.32376.08
OpenBenchmarking.orgSeconds, Fewer Is BetterKTX-Software toktx 4.0Settings: UASTC 4 + Zstd Compression 19ABC70140210280350Min: 376.13 / Avg: 376.32 / Max: 376.65Min: 375.9 / Avg: 376.08 / Max: 376.28

Blender

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

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Fishy Cat - Compute: CPU-OnlyABC50100150200250SE +/- 0.15, N = 3SE +/- 0.23, N = 3250.71251.40249.30
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Fishy Cat - Compute: CPU-OnlyABC50100150200250Min: 251.19 / Avg: 251.4 / Max: 251.68Min: 248.86 / Avg: 249.3 / Max: 249.61

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 MaterialAB60120180240300282.23280.95

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 TracerABC0.22280.44560.66840.89121.114SE +/- 0.00, N = 3SE +/- 0.00, N = 30.980.990.98MIN: 0.98MIN: 0.97 / MAX: 0.99
OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: San Miguel - Renderer: Path TracerABC246810Min: 0.98 / Avg: 0.99 / Max: 0.99Min: 0.98 / Avg: 0.98 / Max: 0.98

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.1Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 4KABC0.76731.53462.30193.06923.8365SE +/- 0.00, N = 3SE +/- 0.01, N = 33.353.403.411. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.1Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 4KABC246810Min: 3.4 / Avg: 3.4 / Max: 3.41Min: 3.4 / Avg: 3.41 / Max: 3.421. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

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 1.4.0Run: RTLightmap.hdr.4096x4096ABC0.03150.0630.09450.1260.1575SE +/- 0.00, N = 3SE +/- 0.00, N = 30.140.140.14
OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 1.4.0Run: RTLightmap.hdr.4096x4096ABC12345Min: 0.14 / Avg: 0.14 / Max: 0.14Min: 0.14 / Avg: 0.14 / Max: 0.14

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 1.0Benchmark: vklBenchmark ISPCABC1122334455SE +/- 0.00, N = 3SE +/- 0.00, N = 3474747MIN: 4 / MAX: 628MIN: 4 / MAX: 626MIN: 4 / MAX: 625
OpenBenchmarking.orgItems / Sec, More Is BetterOpenVKL 1.0Benchmark: vklBenchmark ISPCABC1020304050Min: 47 / Avg: 47 / Max: 47Min: 47 / Avg: 47 / Max: 47

OpenBenchmarking.orgItems / Sec, More Is BetterOpenVKL 1.0Benchmark: vklBenchmark ScalarABC612182430SE +/- 0.00, N = 3SE +/- 0.00, N = 3262626MIN: 2 / MAX: 500MIN: 2 / MAX: 499MIN: 2 / MAX: 497
OpenBenchmarking.orgItems / Sec, More Is BetterOpenVKL 1.0Benchmark: vklBenchmark ScalarABC612182430Min: 26 / Avg: 26 / Max: 26Min: 26 / Avg: 26 / Max: 26

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 TesterAB50100150200250242.60243.22

Radiance Benchmark

This is a benchmark of NREL Radiance, a synthetic imaging system that is open-source and developed by the Lawrence Berkeley National Laboratory in California. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRadiance Benchmark 5.0Test: SerialABC100200300400500477.55478.40477.99

Blender

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

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: BMW27 - Compute: CPU-OnlyABC4080120160200SE +/- 0.15, N = 3SE +/- 0.14, N = 3188.47188.24187.58
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: BMW27 - Compute: CPU-OnlyABC306090120150Min: 188.07 / Avg: 188.24 / Max: 188.53Min: 187.36 / Avg: 187.58 / Max: 187.85

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 TracerABC0.27230.54460.81691.08921.3615SE +/- 0.00, N = 3SE +/- 0.00, N = 31.211.211.20MIN: 1.2 / MAX: 1.22MIN: 1.2 / MAX: 1.23MIN: 1.19 / MAX: 1.22
OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: XFrog Forest - Renderer: Path TracerABC246810Min: 1.21 / Avg: 1.21 / Max: 1.22Min: 1.2 / Avg: 1.2 / Max: 1.21

LuxCoreRender

LuxCoreRender is an open-source 3D physically based renderer formerly known as LuxRender. LuxCoreRender supports CPU-based rendering as well as GPU acceleration via OpenCL, NVIDIA CUDA, and NVIDIA OptiX interfaces. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: Danish Mood - Acceleration: CPUABC0.23180.46360.69540.92721.159SE +/- 0.01, N = 15SE +/- 0.01, N = 31.001.031.02MIN: 0.23 / MAX: 1.31MIN: 0.23 / MAX: 1.36MIN: 0.24 / MAX: 1.33
OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: Danish Mood - Acceleration: CPUABC246810Min: 1 / Avg: 1.03 / Max: 1.07Min: 1.01 / Avg: 1.02 / Max: 1.03

libgav1

Libgav1 is an AV1 decoder developed by Google for AV1 profile 0/1 compliance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is Betterlibgav1 0.16.3Video Input: Chimera 1080p 10-bitABC1224364860SE +/- 0.20, N = 3SE +/- 0.09, N = 353.9754.7154.711. (CXX) g++ options: -O3 -lpthread -lrt
OpenBenchmarking.orgFPS, More Is Betterlibgav1 0.16.3Video Input: Chimera 1080p 10-bitABC1122334455Min: 54.33 / Avg: 54.71 / Max: 55.03Min: 54.6 / Avg: 54.71 / Max: 54.881. (CXX) g++ options: -O3 -lpthread -lrt

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.1Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 4KABC0.02930.05860.08790.11720.1465SE +/- 0.00, N = 3SE +/- 0.00, N = 30.130.130.131. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.1Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 4KABC12345Min: 0.13 / Avg: 0.13 / Max: 0.13Min: 0.13 / Avg: 0.13 / Max: 0.131. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

Timed Godot Game Engine Compilation

This test times how long it takes to compile the Godot Game Engine. Godot is a popular, open-source, cross-platform 2D/3D game engine and is built using the SCons build system and targeting the X11 platform. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Godot Game Engine Compilation 3.2.3Time To CompileABC306090120150SE +/- 0.09, N = 3SE +/- 0.07, N = 3141.63141.92142.45
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Godot Game Engine Compilation 3.2.3Time To CompileABC306090120150Min: 141.83 / Avg: 141.92 / Max: 142.09Min: 142.33 / Avg: 142.45 / Max: 142.59

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.1Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 4KABC246810SE +/- 0.00, N = 3SE +/- 0.01, N = 36.396.496.491. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.1Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 4KABC3691215Min: 6.49 / Avg: 6.49 / Max: 6.49Min: 6.48 / Avg: 6.49 / Max: 6.511. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

VP9 libvpx Encoding

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

OpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.10.0Speed: Speed 0 - Input: Bosphorus 4KABC1.2062.4123.6184.8246.03SE +/- 0.05, N = 3SE +/- 0.05, N = 35.295.335.361. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11
OpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.10.0Speed: Speed 0 - Input: Bosphorus 4KABC246810Min: 5.26 / Avg: 5.33 / Max: 5.42Min: 5.26 / Avg: 5.36 / Max: 5.411. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11

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: SlowABC1.14982.29963.44944.59925.749SE +/- 0.00, N = 3SE +/- 0.00, N = 35.115.105.111. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 4K - Video Preset: SlowABC246810Min: 5.1 / Avg: 5.1 / Max: 5.11Min: 5.1 / Avg: 5.11 / Max: 5.111. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

SVT-AV1

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

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8.7Encoder Mode: Preset 4 - Input: Bosphorus 4KABC0.31250.6250.93751.251.5625SE +/- 0.002, N = 3SE +/- 0.003, N = 31.3791.3881.3891. (CXX) g++ options: -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8.7Encoder Mode: Preset 4 - Input: Bosphorus 4KABC246810Min: 1.38 / Avg: 1.39 / Max: 1.39Min: 1.38 / Avg: 1.39 / Max: 1.391. (CXX) g++ options: -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie

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: MediumABC1.16782.33563.50344.67125.839SE +/- 0.00, N = 3SE +/- 0.01, N = 35.185.195.181. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 4K - Video Preset: MediumABC246810Min: 5.19 / Avg: 5.19 / Max: 5.19Min: 5.17 / Avg: 5.18 / Max: 5.21. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

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 1.4.0Run: RT.hdr_alb_nrm.3840x2160ABC0.0630.1260.1890.2520.315SE +/- 0.00, N = 3SE +/- 0.00, N = 30.280.280.28
OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 1.4.0Run: RT.hdr_alb_nrm.3840x2160ABC12345Min: 0.28 / Avg: 0.28 / Max: 0.28Min: 0.28 / Avg: 0.28 / Max: 0.28

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 1.4.0Run: RT.ldr_alb_nrm.3840x2160ABC0.0630.1260.1890.2520.315SE +/- 0.00, N = 3SE +/- 0.00, N = 30.280.280.28
OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 1.4.0Run: RT.ldr_alb_nrm.3840x2160ABC12345Min: 0.28 / Avg: 0.28 / Max: 0.28Min: 0.28 / Avg: 0.28 / Max: 0.28

Tachyon

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTachyon 0.99b6Total TimeABC20406080100SE +/- 0.04, N = 3SE +/- 0.09, N = 399.45100.05100.041. (CC) gcc options: -m64 -O3 -fomit-frame-pointer -ffast-math -ltachyon -lm -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterTachyon 0.99b6Total TimeABC20406080100Min: 99.98 / Avg: 100.05 / Max: 100.12Min: 99.88 / Avg: 100.04 / Max: 100.191. (CC) gcc options: -m64 -O3 -fomit-frame-pointer -ffast-math -ltachyon -lm -lpthread

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.1Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 1080pABC246810SE +/- 0.01, N = 3SE +/- 0.02, N = 36.846.926.931. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.1Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 1080pABC3691215Min: 6.9 / Avg: 6.92 / Max: 6.95Min: 6.91 / Avg: 6.93 / Max: 6.981. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -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: SciVisABC0.51081.02161.53242.04322.554SE +/- 0.00, N = 3SE +/- 0.00, N = 32.262.272.26MIN: 2.25 / MAX: 2.28MIN: 2.25 / MAX: 2.3MIN: 2.17 / MAX: 2.28
OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: XFrog Forest - Renderer: SciVisABC246810Min: 2.27 / Avg: 2.27 / Max: 2.28Min: 2.26 / Avg: 2.26 / Max: 2.26

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 TimesABC20406080100SE +/- 0.18, N = 3SE +/- 0.06, N = 395.2995.2695.11
OpenBenchmarking.orgSeconds, Fewer Is BetterG'MICTest: 2D Function Plotting, 1000 TimesABC20406080100Min: 95.07 / Avg: 95.26 / Max: 95.61Min: 95 / Avg: 95.11 / Max: 95.21

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 4KABC3691215SE +/- 0.05, N = 3SE +/- 0.11, N = 1013.1413.3313.451. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl
OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.4Video Input: Bosphorus 4KABC48121620Min: 13.26 / Avg: 13.33 / Max: 13.43Min: 12.7 / Avg: 13.45 / Max: 13.971. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl

ASTC Encoder

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

OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 3.0Preset: ExhaustiveABC20406080100SE +/- 0.02, N = 3SE +/- 0.02, N = 385.4585.4685.48
OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 3.0Preset: ExhaustiveABC1632486480Min: 85.44 / Avg: 85.46 / Max: 85.5Min: 85.45 / Avg: 85.48 / Max: 85.52

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPUABC8001600240032004000SE +/- 0.54, N = 3SE +/- 0.47, N = 33906.843907.363909.54MIN: 3902.59MIN: 3903.21MIN: 3904.141. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPUABC7001400210028003500Min: 3906.77 / Avg: 3907.36 / Max: 3908.44Min: 3908.92 / Avg: 3909.54 / Max: 3910.471. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPUABC8001600240032004000SE +/- 3.15, N = 3SE +/- 0.13, N = 33909.223908.783904.33MIN: 3903.68MIN: 3898.77MIN: 3900.141. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPUABC7001400210028003500Min: 3902.47 / Avg: 3908.78 / Max: 3911.98Min: 3904.07 / Avg: 3904.33 / Max: 3904.511. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPUABC8001600240032004000SE +/- 2.69, N = 3SE +/- 1.45, N = 33909.283909.193907.59MIN: 3905.69MIN: 3902.49MIN: 3902.521. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPUABC7001400210028003500Min: 3905.9 / Avg: 3909.19 / Max: 3914.52Min: 3905.54 / Avg: 3907.59 / Max: 3910.391. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

SVT-HEVC

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

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 1 - Input: Bosphorus 1080pABC246810SE +/- 0.01, N = 3SE +/- 0.01, N = 37.167.187.161. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 1 - Input: Bosphorus 1080pABC3691215Min: 7.16 / Avg: 7.18 / Max: 7.19Min: 7.14 / Avg: 7.16 / Max: 7.171. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPUABC5001000150020002500SE +/- 4.98, N = 3SE +/- 7.07, N = 32359.222341.312347.89MIN: 2354.43MIN: 2328.92MIN: 2327.561. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPUABC400800120016002000Min: 2335.38 / Avg: 2341.31 / Max: 2351.2Min: 2335.3 / Avg: 2347.89 / Max: 2359.771. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPUABC5001000150020002500SE +/- 5.04, N = 3SE +/- 4.19, N = 32356.442342.532343.84MIN: 2352.25MIN: 2332.18MIN: 2329.721. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPUABC400800120016002000Min: 2337.26 / Avg: 2342.53 / Max: 2352.61Min: 2335.46 / Avg: 2343.84 / Max: 2348.081. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPUABC5001000150020002500SE +/- 3.39, N = 3SE +/- 4.90, N = 32355.962346.032351.39MIN: 2350.41MIN: 2335.13MIN: 2341.351. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPUABC400800120016002000Min: 2339.53 / Avg: 2346.03 / Max: 2350.95Min: 2346.03 / Avg: 2351.39 / Max: 2361.171. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs and supporting instruction sets such as SSE, AVX, AVX2, and AVX-512. Embree also supports making use of the Intel SPMD Program Compiler (ISPC). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer ISPC - Model: Asian Dragon ObjABC3691215SE +/- 0.0270, N = 3SE +/- 0.0250, N = 39.07969.22949.2030MIN: 9.05 / MAX: 9.18MIN: 9.15 / MAX: 9.36MIN: 9.12 / MAX: 9.31
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer ISPC - Model: Asian Dragon ObjABC3691215Min: 9.18 / Avg: 9.23 / Max: 9.28Min: 9.15 / Avg: 9.2 / Max: 9.24

C-Ray

This is a test of C-Ray, a simple raytracer designed to test the floating-point CPU performance. This test is multi-threaded (16 threads per core), will shoot 8 rays per pixel for anti-aliasing, and will generate a 1600 x 1200 image. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total Time - 4K, 16 Rays Per PixelABC1632486480SE +/- 0.04, N = 3SE +/- 0.03, N = 373.6073.6073.601. (CC) gcc options: -lm -lpthread -O3
OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total Time - 4K, 16 Rays Per PixelABC1428425670Min: 73.52 / Avg: 73.6 / Max: 73.66Min: 73.55 / Avg: 73.6 / Max: 73.661. (CC) gcc options: -lm -lpthread -O3

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: CartoonABC1632486480SE +/- 0.00, N = 3SE +/- 0.01, N = 371.8671.8771.87
OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: CartoonABC1428425670Min: 71.87 / Avg: 71.87 / Max: 71.88Min: 71.86 / Avg: 71.87 / Max: 71.89

libavif avifenc

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

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.9.0Encoder Speed: 0ABC1632486480SE +/- 0.13, N = 3SE +/- 0.17, N = 371.9271.7571.681. (CXX) g++ options: -O3 -fPIC -lm
OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.9.0Encoder Speed: 0ABC1428425670Min: 71.51 / Avg: 71.75 / Max: 71.95Min: 71.41 / Avg: 71.68 / Max: 71.981. (CXX) g++ options: -O3 -fPIC -lm

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs and supporting instruction sets such as SSE, AVX, AVX2, and AVX-512. Embree also supports making use of the Intel SPMD Program Compiler (ISPC). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer - Model: Asian Dragon ObjABC3691215SE +/- 0.09, N = 3SE +/- 0.04, N = 310.2710.2410.25MIN: 10.23 / MAX: 10.39MIN: 10.04 / MAX: 10.5MIN: 10.15 / MAX: 10.45
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer - Model: Asian Dragon ObjABC3691215Min: 10.08 / Avg: 10.24 / Max: 10.38Min: 10.2 / Avg: 10.25 / Max: 10.32

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer ISPC - Model: CrownABC3691215SE +/- 0.0256, N = 3SE +/- 0.0058, N = 38.95999.15029.1341MIN: 8.9 / MAX: 9.12MIN: 9.05 / MAX: 9.31MIN: 9.07 / MAX: 9.28
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer ISPC - Model: CrownABC3691215Min: 9.11 / Avg: 9.15 / Max: 9.2Min: 9.12 / Avg: 9.13 / Max: 9.14

Radiance Benchmark

This is a benchmark of NREL Radiance, a synthetic imaging system that is open-source and developed by the Lawrence Berkeley National Laboratory in California. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRadiance Benchmark 5.0Test: SMP ParallelABC306090120150149.49152.37150.07

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: NASA Streamlines - Renderer: Path TracerABC0.7561.5122.2683.0243.78SE +/- 0.00, N = 3SE +/- 0.00, N = 33.363.363.36MIN: 3.31 / MAX: 3.42MIN: 3.31 / MAX: 3.42MIN: 3.3 / MAX: 3.42
OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: NASA Streamlines - Renderer: Path TracerABC246810Min: 3.36 / Avg: 3.36 / Max: 3.37Min: 3.36 / Avg: 3.36 / Max: 3.37

libavif avifenc

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

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.9.0Encoder Speed: 6, LosslessABC1530456075SE +/- 0.19, N = 3SE +/- 0.11, N = 364.6563.8165.011. (CXX) g++ options: -O3 -fPIC -lm
OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.9.0Encoder Speed: 6, LosslessABC1326395265Min: 63.45 / Avg: 63.81 / Max: 64.05Min: 64.84 / Avg: 65.01 / Max: 65.21. (CXX) g++ options: -O3 -fPIC -lm

LuxCoreRender

LuxCoreRender is an open-source 3D physically based renderer formerly known as LuxRender. LuxCoreRender supports CPU-based rendering as well as GPU acceleration via OpenCL, NVIDIA CUDA, and NVIDIA OptiX interfaces. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: Orange Juice - Acceleration: CPUABC0.5311.0621.5932.1242.655SE +/- 0.01, N = 3SE +/- 0.01, N = 32.362.362.36MIN: 2.27 / MAX: 2.37MIN: 2.26 / MAX: 2.39MIN: 2.26 / MAX: 2.38
OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: Orange Juice - Acceleration: CPUABC246810Min: 2.35 / Avg: 2.36 / Max: 2.37Min: 2.34 / Avg: 2.36 / Max: 2.37

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs and supporting instruction sets such as SSE, AVX, AVX2, and AVX-512. Embree also supports making use of the Intel SPMD Program Compiler (ISPC). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer - Model: CrownABC3691215SE +/- 0.0960, N = 3SE +/- 0.0845, N = 39.70089.81209.8060MIN: 9.64 / MAX: 9.86MIN: 9.58 / MAX: 10.13MIN: 9.59 / MAX: 10.09
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer - Model: CrownABC3691215Min: 9.63 / Avg: 9.81 / Max: 9.96Min: 9.65 / Avg: 9.81 / Max: 9.94

LuxCoreRender

LuxCoreRender is an open-source 3D physically based renderer formerly known as LuxRender. LuxCoreRender supports CPU-based rendering as well as GPU acceleration via OpenCL, NVIDIA CUDA, and NVIDIA OptiX interfaces. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: LuxCore Benchmark - Acceleration: CPUABC0.26550.5310.79651.0621.3275SE +/- 0.00, N = 3SE +/- 0.01, N = 31.171.181.16MIN: 0.31 / MAX: 1.48MIN: 0.31 / MAX: 1.48MIN: 0.3 / MAX: 1.47
OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: LuxCore Benchmark - Acceleration: CPUABC246810Min: 1.18 / Avg: 1.18 / Max: 1.18Min: 1.14 / Avg: 1.16 / Max: 1.17

Chaos Group V-RAY

This is a test of Chaos Group's V-RAY benchmark. V-RAY is a commercial renderer that can integrate with various creator software products like SketchUp and 3ds Max. The V-RAY benchmark is standalone and supports CPU and NVIDIA CUDA/RTX based rendering. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgvsamples, More Is BetterChaos Group V-RAY 5Mode: CPUAB2K4K6K8K10KSE +/- 74.04, N = 386158542
OpenBenchmarking.orgvsamples, More Is BetterChaos Group V-RAY 5Mode: CPUAB15003000450060007500Min: 8464 / Avg: 8542 / Max: 8690

LuxCoreRender

LuxCoreRender is an open-source 3D physically based renderer formerly known as LuxRender. LuxCoreRender supports CPU-based rendering as well as GPU acceleration via OpenCL, NVIDIA CUDA, and NVIDIA OptiX interfaces. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: DLSC - Acceleration: CPUABC0.35780.71561.07341.43121.789SE +/- 0.01, N = 3SE +/- 0.00, N = 31.591.561.57MIN: 1.55 / MAX: 1.62MIN: 1.49 / MAX: 1.61MIN: 1.5 / MAX: 1.61
OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: DLSC - Acceleration: CPUABC246810Min: 1.55 / Avg: 1.56 / Max: 1.57Min: 1.56 / Avg: 1.57 / Max: 1.57

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs and supporting instruction sets such as SSE, AVX, AVX2, and AVX-512. Embree also supports making use of the Intel SPMD Program Compiler (ISPC). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer ISPC - Model: Asian DragonABC3691215SE +/- 0.05, N = 3SE +/- 0.04, N = 310.1610.2610.24MIN: 10.13 / MAX: 10.27MIN: 10.16 / MAX: 10.43MIN: 10.15 / MAX: 10.41
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer ISPC - Model: Asian DragonABC3691215Min: 10.2 / Avg: 10.26 / Max: 10.35Min: 10.18 / Avg: 10.24 / Max: 10.32

IndigoBench

This is a test of Indigo Renderer's IndigoBench benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.4Acceleration: CPU - Scene: BedroomABC0.37640.75281.12921.50561.882SE +/- 0.007, N = 3SE +/- 0.006, N = 31.6731.6601.666
OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.4Acceleration: CPU - Scene: BedroomABC246810Min: 1.65 / Avg: 1.66 / Max: 1.67Min: 1.66 / Avg: 1.67 / Max: 1.67

Basis Universal

Basis Universal is a GPU texture codec. This test times how long it takes to convert sRGB PNGs into Basis Univeral assets with various settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.13Settings: UASTC Level 3ABC1428425670SE +/- 0.01, N = 3SE +/- 0.01, N = 361.2861.2961.29
OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.13Settings: UASTC Level 3ABC1224364860Min: 61.27 / Avg: 61.29 / Max: 61.31Min: 61.28 / Avg: 61.29 / Max: 61.3

IndigoBench

This is a test of Indigo Renderer's IndigoBench benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.4Acceleration: CPU - Scene: SupercarABC0.7671.5342.3013.0683.835SE +/- 0.002, N = 3SE +/- 0.009, N = 33.3803.4093.394
OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.4Acceleration: CPU - Scene: SupercarABC246810Min: 3.41 / Avg: 3.41 / Max: 3.41Min: 3.38 / Avg: 3.39 / Max: 3.4

libgav1

Libgav1 is an AV1 decoder developed by Google for AV1 profile 0/1 compliance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is Betterlibgav1 0.16.3Video Input: Summer Nature 4KABC1326395265SE +/- 0.03, N = 3SE +/- 0.04, N = 359.0259.6859.461. (CXX) g++ options: -O3 -lpthread -lrt
OpenBenchmarking.orgFPS, More Is Betterlibgav1 0.16.3Video Input: Summer Nature 4KABC1224364860Min: 59.65 / Avg: 59.68 / Max: 59.73Min: 59.39 / Avg: 59.46 / Max: 59.51. (CXX) g++ options: -O3 -lpthread -lrt

GraphicsMagick

This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample 6000x4000 pixel JPEG image. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: SharpenABC20406080100SE +/- 0.00, N = 3SE +/- 0.00, N = 39192921. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: SharpenABC20406080100Min: 92 / Avg: 92 / Max: 92Min: 92 / Avg: 92 / Max: 921. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: Noise-GaussianABC50100150200250SE +/- 0.33, N = 3SE +/- 0.00, N = 32202272271. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: Noise-GaussianABC4080120160200Min: 226 / Avg: 226.67 / Max: 227Min: 227 / Avg: 227 / Max: 2271. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: EnhancedABC4080120160200SE +/- 0.00, N = 3SE +/- 0.00, N = 31721741741. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: EnhancedABC306090120150Min: 174 / Avg: 174 / Max: 174Min: 174 / Avg: 174 / Max: 1741. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: ResizingABC2004006008001000SE +/- 0.33, N = 3SE +/- 0.88, N = 38558868851. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: ResizingABC160320480640800Min: 885 / Avg: 885.67 / Max: 886Min: 883 / Avg: 884.67 / Max: 8861. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: SwirlABC110220330440550SE +/- 0.88, N = 3SE +/- 0.33, N = 34784944941. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: SwirlABC90180270360450Min: 492 / Avg: 493.67 / Max: 495Min: 494 / Avg: 494.33 / Max: 4951. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: RotateABC170340510680850SE +/- 2.33, N = 3SE +/- 3.21, N = 36837717741. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: RotateABC140280420560700Min: 767 / Avg: 771.33 / Max: 775Min: 769 / Avg: 774 / Max: 7801. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: HWB Color SpaceABC2004006008001000SE +/- 0.33, N = 3SE +/- 0.00, N = 36967767761. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: HWB Color SpaceABC140280420560700Min: 776 / Avg: 776.33 / Max: 777Min: 776 / Avg: 776 / Max: 7761. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread

RawTherapee

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

OpenBenchmarking.orgSeconds, Fewer Is BetterRawTherapeeTotal Benchmark TimeABC1326395265SE +/- 0.02, N = 3SE +/- 0.03, N = 357.1057.1757.291. RawTherapee, version 5.8, command line.
OpenBenchmarking.orgSeconds, Fewer Is BetterRawTherapeeTotal Benchmark TimeABC1122334455Min: 57.14 / Avg: 57.17 / Max: 57.22Min: 57.25 / Avg: 57.29 / Max: 57.341. RawTherapee, version 5.8, command line.

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs and supporting instruction sets such as SSE, AVX, AVX2, and AVX-512. Embree also supports making use of the Intel SPMD Program Compiler (ISPC). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer - Model: Asian DragonABC3691215SE +/- 0.06, N = 3SE +/- 0.06, N = 311.1611.2911.31MIN: 11.09 / MAX: 11.3MIN: 11.1 / MAX: 11.46MIN: 11.17 / MAX: 11.55
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer - Model: Asian DragonABC3691215Min: 11.17 / Avg: 11.29 / Max: 11.36Min: 11.21 / Avg: 11.31 / Max: 11.41

Google SynthMark

SynthMark is a cross platform tool for benchmarking CPU performance under a variety of real-time audio workloads. It uses a polyphonic synthesizer model to provide standardized tests for latency, jitter and computational throughput. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgVoices, More Is BetterGoogle SynthMark 20201109Test: VoiceMark_100ABC2004006008001000SE +/- 11.88, N = 3SE +/- 6.71, N = 9834.19854.07842.441. (CXX) g++ options: -lm -lpthread -std=c++11 -Ofast
OpenBenchmarking.orgVoices, More Is BetterGoogle SynthMark 20201109Test: VoiceMark_100ABC150300450600750Min: 830.65 / Avg: 854.07 / Max: 869.26Min: 822.43 / Avg: 842.44 / Max: 875.811. (CXX) g++ options: -lm -lpthread -std=c++11 -Ofast

VP9 libvpx Encoding

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

OpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.10.0Speed: Speed 0 - Input: Bosphorus 1080pABC3691215SE +/- 0.13, N = 3SE +/- 0.12, N = 310.7411.0811.091. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11
OpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.10.0Speed: Speed 0 - Input: Bosphorus 1080pABC3691215Min: 10.83 / Avg: 11.08 / Max: 11.24Min: 10.87 / Avg: 11.09 / Max: 11.271. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11

POV-Ray

This is a test of POV-Ray, the Persistence of Vision Raytracer. POV-Ray is used to create 3D graphics using ray-tracing. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPOV-Ray 3.7.0.7Trace TimeABC1224364860SE +/- 0.09, N = 3SE +/- 0.18, N = 351.7551.7551.821. (CXX) g++ options: -pipe -O3 -ffast-math -march=native -pthread -R/usr/lib -lSDL -lXpm -lSM -lICE -lX11 -lIlmImf -lIlmImf-2_5 -lImath-2_5 -lHalf-2_5 -lIex-2_5 -lIexMath-2_5 -lIlmThread-2_5 -lIlmThread -ltiff -ljpeg -lpng -lz -lrt -lm -lboost_thread -lboost_system
OpenBenchmarking.orgSeconds, Fewer Is BetterPOV-Ray 3.7.0.7Trace TimeABC1020304050Min: 51.59 / Avg: 51.75 / Max: 51.88Min: 51.52 / Avg: 51.82 / Max: 52.151. (CXX) g++ options: -pipe -O3 -ffast-math -march=native -pthread -R/usr/lib -lSDL -lXpm -lSM -lICE -lX11 -lIlmImf -lIlmImf-2_5 -lImath-2_5 -lHalf-2_5 -lIex-2_5 -lIexMath-2_5 -lIlmThread-2_5 -lIlmThread -ltiff -ljpeg -lpng -lz -lrt -lm -lboost_thread -lboost_system

libgav1

Libgav1 is an AV1 decoder developed by Google for AV1 profile 0/1 compliance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is Betterlibgav1 0.16.3Video Input: Chimera 1080pABC4080120160200SE +/- 0.60, N = 3SE +/- 0.46, N = 3168.16172.15169.401. (CXX) g++ options: -O3 -lpthread -lrt
OpenBenchmarking.orgFPS, More Is Betterlibgav1 0.16.3Video Input: Chimera 1080pABC306090120150Min: 171 / Avg: 172.15 / Max: 173.03Min: 168.51 / Avg: 169.4 / Max: 170.021. (CXX) g++ options: -O3 -lpthread -lrt

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.1Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 1080pABC0.09230.18460.27690.36920.4615SE +/- 0.00, N = 3SE +/- 0.00, N = 30.400.400.411. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.1Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 1080pABC12345Min: 0.4 / Avg: 0.4 / Max: 0.41Min: 0.4 / Avg: 0.41 / Max: 0.411. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

VP9 libvpx Encoding

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

OpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.10.0Speed: Speed 5 - Input: Bosphorus 4KABC3691215SE +/- 0.09, N = 3SE +/- 0.14, N = 312.1012.7012.881. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11
OpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.10.0Speed: Speed 5 - Input: Bosphorus 4KABC48121620Min: 12.59 / Avg: 12.7 / Max: 12.88Min: 12.68 / Avg: 12.88 / Max: 13.151. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPUABC246810SE +/- 0.24589, N = 12SE +/- 0.07130, N = 37.398027.903527.69764MIN: 5.79MIN: 5.78MIN: 5.791. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPUABC3691215Min: 7.06 / Avg: 7.9 / Max: 9.8Min: 7.56 / Avg: 7.7 / Max: 7.81. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.1Encoder Mode: Speed 6 Realtime - Input: Bosphorus 4KABC3691215SE +/- 0.03, N = 3SE +/- 0.03, N = 312.6512.8112.861. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.1Encoder Mode: Speed 6 Realtime - Input: Bosphorus 4KABC48121620Min: 12.76 / Avg: 12.81 / Max: 12.86Min: 12.83 / Avg: 12.86 / Max: 12.921. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -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: Wavelet BlurABC1122334455SE +/- 0.01, N = 3SE +/- 0.02, N = 346.7446.7146.69
OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: Wavelet BlurABC1020304050Min: 46.69 / Avg: 46.71 / Max: 46.72Min: 46.68 / Avg: 46.69 / Max: 46.73

SVT-AV1

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

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8.7Encoder Mode: Preset 8 - Input: Bosphorus 4KABC48121620SE +/- 0.05, N = 3SE +/- 0.06, N = 313.5813.7313.711. (CXX) g++ options: -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8.7Encoder Mode: Preset 8 - Input: Bosphorus 4KABC48121620Min: 13.63 / Avg: 13.73 / Max: 13.81Min: 13.6 / Avg: 13.71 / Max: 13.821. (CXX) g++ options: -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie

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 EnhanceABC1020304050SE +/- 0.00, N = 3SE +/- 0.01, N = 344.2944.2844.29
OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: Color EnhanceABC918273645Min: 44.27 / Avg: 44.28 / Max: 44.28Min: 44.27 / Avg: 44.29 / Max: 44.3

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 TimesABC1020304050SE +/- 0.04, N = 3SE +/- 0.04, N = 343.7043.6543.74
OpenBenchmarking.orgSeconds, Fewer Is BetterG'MICTest: 3D Elevated Function In Random Colors, 100 TimesABC918273645Min: 43.59 / Avg: 43.65 / Max: 43.72Min: 43.69 / Avg: 43.74 / Max: 43.81

DeepSpeech

Mozilla DeepSpeech is a speech-to-text engine powered by TensorFlow for machine learning and derived from Baidu's Deep Speech research paper. This test profile times the speech-to-text process for a roughly three minute audio recording. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterDeepSpeech 0.6Acceleration: CPUABC1428425670SE +/- 0.10, N = 3SE +/- 0.24, N = 360.9459.7860.25
OpenBenchmarking.orgSeconds, Fewer Is BetterDeepSpeech 0.6Acceleration: CPUABC1224364860Min: 59.63 / Avg: 59.78 / Max: 59.97Min: 59.85 / Avg: 60.25 / Max: 60.68

SVT-AV1

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

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8.7Encoder Mode: Preset 4 - Input: Bosphorus 1080pABC0.84471.68942.53413.37884.2235SE +/- 0.005, N = 3SE +/- 0.002, N = 33.7543.7503.7491. (CXX) g++ options: -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8.7Encoder Mode: Preset 4 - Input: Bosphorus 1080pABC246810Min: 3.74 / Avg: 3.75 / Max: 3.76Min: 3.75 / Avg: 3.75 / Max: 3.751. (CXX) g++ options: -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie

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 FastABC48121620SE +/- 0.01, N = 3SE +/- 0.00, N = 314.3014.2814.261. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 4K - Video Preset: Very FastABC48121620Min: 14.27 / Avg: 14.28 / Max: 14.29Min: 14.26 / Avg: 14.26 / Max: 14.271. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

dav1d

OpenBenchmarking.orgFPS, More Is Betterdav1d 0.9.1Video Input: Chimera 1080p 10-bitABC60120180240300SE +/- 0.40, N = 3SE +/- 0.41, N = 3261.66278.85277.27MIN: 208.64 / MAX: 424.22MIN: 221 / MAX: 460.72MIN: 219.87 / MAX: 463.041. (CC) gcc options: -pthread
OpenBenchmarking.orgFPS, More Is Betterdav1d 0.9.1Video Input: Chimera 1080p 10-bitABC50100150200250Min: 278.32 / Avg: 278.85 / Max: 279.62Min: 276.47 / Avg: 277.27 / Max: 277.81. (CC) gcc options: -pthread

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.1Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 1080pABC510152025SE +/- 0.02, N = 3SE +/- 0.10, N = 319.1319.4119.571. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.1Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 1080pABC510152025Min: 19.37 / Avg: 19.41 / Max: 19.44Min: 19.46 / Avg: 19.57 / Max: 19.761. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

Hugin

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

OpenBenchmarking.orgSeconds, Fewer Is BetterHuginPanorama Photo Assistant + Stitching TimeABC918273645SE +/- 0.15, N = 3SE +/- 0.15, N = 339.8239.6739.76
OpenBenchmarking.orgSeconds, Fewer Is BetterHuginPanorama Photo Assistant + Stitching TimeABC816243240Min: 39.52 / Avg: 39.67 / Max: 39.97Min: 39.55 / Avg: 39.76 / Max: 40.06

rav1e

Xiph rav1e is a Rust-written AV1 video encoder. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betterrav1e 0.4Speed: 5ABC0.34340.68681.03021.37361.717SE +/- 0.001, N = 3SE +/- 0.002, N = 31.5141.5231.526
OpenBenchmarking.orgFrames Per Second, More Is Betterrav1e 0.4Speed: 5ABC246810Min: 1.52 / Avg: 1.52 / Max: 1.53Min: 1.52 / Avg: 1.53 / Max: 1.53

OpenBenchmarking.orgFrames Per Second, More Is Betterrav1e 0.4Speed: 1ABC0.11880.23760.35640.47520.594SE +/- 0.002, N = 3SE +/- 0.002, N = 30.5280.5230.525
OpenBenchmarking.orgFrames Per Second, More Is Betterrav1e 0.4Speed: 1ABC246810Min: 0.52 / Avg: 0.52 / Max: 0.53Min: 0.52 / Avg: 0.52 / Max: 0.53

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 CompressionABC918273645SE +/- 0.11, N = 3SE +/- 0.02, N = 337.4937.7337.581. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff
OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100, Lossless, Highest CompressionABC816243240Min: 37.53 / Avg: 37.73 / Max: 37.92Min: 37.56 / Avg: 37.58 / Max: 37.621. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff

dcraw

This test times how long it takes to convert several high-resolution RAW NEF image files to PPM image format using dcraw. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterdcrawRAW To PPM Image ConversionABC918273645SE +/- 0.00, N = 3SE +/- 0.05, N = 335.5237.6437.951. (CC) gcc options: -lm
OpenBenchmarking.orgSeconds, Fewer Is BetterdcrawRAW To PPM Image ConversionABC816243240Min: 37.63 / Avg: 37.64 / Max: 37.64Min: 37.87 / Avg: 37.95 / Max: 38.031. (CC) gcc options: -lm

libavif avifenc

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

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.9.0Encoder Speed: 2ABC918273645SE +/- 0.06, N = 3SE +/- 0.01, N = 337.3837.3037.441. (CXX) g++ options: -O3 -fPIC -lm
OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.9.0Encoder Speed: 2ABC816243240Min: 37.21 / Avg: 37.3 / Max: 37.41Min: 37.42 / Avg: 37.44 / Max: 37.471. (CXX) g++ options: -O3 -fPIC -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: SciVisABC3691215SE +/- 0.00, N = 3SE +/- 0.00, N = 312.2012.2012.20MIN: 11.9 / MAX: 12.99MIN: 11.9 / MAX: 12.99MIN: 11.9 / MAX: 12.99
OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: San Miguel - Renderer: SciVisABC48121620Min: 12.2 / Avg: 12.2 / Max: 12.2Min: 12.2 / Avg: 12.2 / Max: 12.2

Natron

Natron is an open-source, cross-platform compositing software for visual effects (VFX) and motion graphics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterNatron 2.4Input: SpaceshipAB0.56251.1251.68752.252.8125SE +/- 0.03, N = 32.42.5
OpenBenchmarking.orgFPS, More Is BetterNatron 2.4Input: SpaceshipAB246810Min: 2.4 / Avg: 2.47 / Max: 2.5

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: Rotate 90 DegreesABC816243240SE +/- 0.01, N = 3SE +/- 0.01, N = 332.4532.4232.45
OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: Rotate 90 DegreesABC714212835Min: 32.4 / Avg: 32.42 / Max: 32.45Min: 32.43 / Avg: 32.45 / Max: 32.47

Basis Universal

Basis Universal is a GPU texture codec. This test times how long it takes to convert sRGB PNGs into Basis Univeral assets with various settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.13Settings: UASTC Level 2ABC714212835SE +/- 0.01, N = 3SE +/- 0.00, N = 332.0131.9931.99
OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.13Settings: UASTC Level 2ABC714212835Min: 31.98 / Avg: 31.99 / Max: 32Min: 31.99 / Avg: 31.99 / Max: 32

dav1d

OpenBenchmarking.orgFPS, More Is Betterdav1d 0.9.1Video Input: Summer Nature 4KABC306090120150SE +/- 0.18, N = 3SE +/- 0.08, N = 3112.32117.95117.30MIN: 101.06 / MAX: 117.16MIN: 106.78 / MAX: 123.51MIN: 105.93 / MAX: 122.881. (CC) gcc options: -pthread
OpenBenchmarking.orgFPS, More Is Betterdav1d 0.9.1Video Input: Summer Nature 4KABC20406080100Min: 117.64 / Avg: 117.95 / Max: 118.26Min: 117.15 / Avg: 117.3 / Max: 117.411. (CC) gcc options: -pthread

AOBench

AOBench is a lightweight ambient occlusion renderer, written in C. The test profile is using a size of 2048 x 2048. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterAOBenchSize: 2048 x 2048 - Total TimeABC714212835SE +/- 0.01, N = 3SE +/- 0.05, N = 330.6630.4930.471. (CC) gcc options: -lm -O3
OpenBenchmarking.orgSeconds, Fewer Is BetterAOBenchSize: 2048 x 2048 - Total TimeABC714212835Min: 30.47 / Avg: 30.49 / Max: 30.51Min: 30.37 / Avg: 30.47 / Max: 30.541. (CC) gcc options: -lm -O3

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: AntialiasABC714212835SE +/- 0.01, N = 3SE +/- 0.02, N = 329.7429.7229.74
OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: AntialiasABC714212835Min: 29.71 / Avg: 29.72 / Max: 29.74Min: 29.7 / Avg: 29.74 / Max: 29.77

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 SynthesisABC612182430SE +/- 0.04, N = 4SE +/- 0.04, N = 423.1823.1323.061. (CC) gcc options: -O2 -std=c99
OpenBenchmarking.orgSeconds, Fewer Is BettereSpeak-NG Speech Engine 20200907Text-To-Speech SynthesisABC510152025Min: 23.04 / Avg: 23.13 / Max: 23.23Min: 22.98 / Avg: 23.06 / Max: 23.151. (CC) gcc options: -O2 -std=c99

rav1e

Xiph rav1e is a Rust-written AV1 video encoder. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betterrav1e 0.4Speed: 6ABC0.45520.91041.36561.82082.276SE +/- 0.001, N = 3SE +/- 0.002, N = 32.0172.0202.023
OpenBenchmarking.orgFrames Per Second, More Is Betterrav1e 0.4Speed: 6ABC246810Min: 2.02 / Avg: 2.02 / Max: 2.02Min: 2.02 / Avg: 2.02 / Max: 2.03

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: SlowABC510152025SE +/- 0.04, N = 3SE +/- 0.06, N = 320.3820.4820.391. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 1080p - Video Preset: SlowABC510152025Min: 20.41 / Avg: 20.48 / Max: 20.54Min: 20.3 / Avg: 20.39 / Max: 20.511. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

TTSIOD 3D Renderer

A portable GPL 3D software renderer that supports OpenMP and Intel Threading Building Blocks with many different rendering modes. This version does not use OpenGL but is entirely CPU/software based. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterTTSIOD 3D Renderer 2.3bPhong Rendering With Soft-Shadow MappingABC120240360480600SE +/- 1.50, N = 3SE +/- 0.45, N = 3546.27547.27547.261. (CXX) g++ options: -O3 -fomit-frame-pointer -ffast-math -mtune=native -flto -msse -mrecip -mfpmath=sse -msse2 -mssse3 -lSDL -fopenmp -fwhole-program -lstdc++
OpenBenchmarking.orgFPS, More Is BetterTTSIOD 3D Renderer 2.3bPhong Rendering With Soft-Shadow MappingABC100200300400500Min: 544.69 / Avg: 547.27 / Max: 549.9Min: 546.72 / Avg: 547.26 / Max: 548.161. (CXX) g++ options: -O3 -fomit-frame-pointer -ffast-math -mtune=native -flto -msse -mrecip -mfpmath=sse -msse2 -mssse3 -lSDL -fopenmp -fwhole-program -lstdc++

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: MediumABC510152025SE +/- 0.05, N = 3SE +/- 0.06, N = 321.0020.9820.991. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 1080p - Video Preset: MediumABC510152025Min: 20.89 / Avg: 20.98 / Max: 21.07Min: 20.92 / Avg: 20.99 / Max: 21.11. (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: CompositeABC400800120016002000SE +/- 5.11, N = 3SE +/- 4.84, N = 31768.321769.681770.901. (CC) gcc options: -lm -ldl -O2 -fomit-frame-pointer -U_FORTIFY_SOURCE -fno-stack-protector
OpenBenchmarking.orgMflops, More Is BetterLuaJIT 2.1-gitTest: CompositeABC30060090012001500Min: 1759.47 / Avg: 1769.68 / Max: 1775.19Min: 1762.22 / Avg: 1770.9 / Max: 1778.961. (CC) gcc options: -lm -ldl -O2 -fomit-frame-pointer -U_FORTIFY_SOURCE -fno-stack-protector

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 BenchmarkABC1020304050SE +/- 0.05, N = 3SE +/- 0.10, N = 343.9444.8044.691. (CXX) g++ options: -O2 -fopenmp -ljpeg -lz -lm
OpenBenchmarking.orgMpix/sec, More Is BetterLibRaw 0.20Post-Processing BenchmarkABC918273645Min: 44.7 / Avg: 44.8 / Max: 44.85Min: 44.51 / Avg: 44.69 / Max: 44.871. (CXX) g++ options: -O2 -fopenmp -ljpeg -lz -lm

dav1d

OpenBenchmarking.orgFPS, More Is Betterdav1d 0.9.1Video Input: Chimera 1080pABC90180270360450SE +/- 0.70, N = 3SE +/- 0.51, N = 3406.60430.16430.16MIN: 313.16 / MAX: 647.99MIN: 328.03 / MAX: 718.21MIN: 327.65 / MAX: 726.21. (CC) gcc options: -pthread
OpenBenchmarking.orgFPS, More Is Betterdav1d 0.9.1Video Input: Chimera 1080pABC80160240320400Min: 429.24 / Avg: 430.16 / Max: 431.53Min: 429.13 / Avg: 430.16 / Max: 430.71. (CC) gcc options: -pthread

Basis Universal

Basis Universal is a GPU texture codec. This test times how long it takes to convert sRGB PNGs into Basis Univeral assets with various settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.13Settings: ETC1SABC612182430SE +/- 0.04, N = 3SE +/- 0.01, N = 326.1126.1926.15
OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.13Settings: ETC1SABC612182430Min: 26.12 / Avg: 26.18 / Max: 26.26Min: 26.14 / Avg: 26.15 / Max: 26.18

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.1Encoder Mode: Speed 6 Realtime - Input: Bosphorus 1080pABC612182430SE +/- 0.08, N = 3SE +/- 0.06, N = 323.2923.4423.541. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.1Encoder Mode: Speed 6 Realtime - Input: Bosphorus 1080pABC510152025Min: 23.29 / Avg: 23.44 / Max: 23.55Min: 23.42 / Avg: 23.54 / Max: 23.61. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

libjpeg-turbo tjbench

tjbench is a JPEG decompression/compression benchmark that is part of libjpeg-turbo, a JPEG image codec library optimized for SIMD instructions on modern CPU architectures. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMegapixels/sec, More Is Betterlibjpeg-turbo tjbench 2.1.0Test: Decompression ThroughputABC50100150200250SE +/- 0.53, N = 3SE +/- 0.29, N = 3241.65241.29241.541. (CC) gcc options: -O3 -rdynamic
OpenBenchmarking.orgMegapixels/sec, More Is Betterlibjpeg-turbo tjbench 2.1.0Test: Decompression ThroughputABC4080120160200Min: 240.24 / Avg: 241.29 / Max: 241.88Min: 241.16 / Avg: 241.54 / Max: 242.11. (CC) gcc options: -O3 -rdynamic

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: ReflectABC612182430SE +/- 0.02, N = 3SE +/- 0.00, N = 324.7224.7424.72
OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: ReflectABC612182430Min: 24.69 / Avg: 24.74 / Max: 24.77Min: 24.71 / Avg: 24.72 / Max: 24.72

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: SciVisABC3691215SE +/- 0.00, N = 3SE +/- 0.00, N = 39.099.099.09MIN: 9.01 / MAX: 9.17MIN: 8.77 / MAX: 9.17MIN: 9.01 / MAX: 9.17
OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: Magnetic Reconnection - Renderer: SciVisABC3691215Min: 9.09 / Avg: 9.09 / Max: 9.09Min: 9.09 / Avg: 9.09 / Max: 9.09

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 FastABC612182430SE +/- 0.04, N = 3SE +/- 0.03, N = 324.8424.7724.681. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 4K - Video Preset: Ultra FastABC612182430Min: 24.69 / Avg: 24.77 / Max: 24.83Min: 24.64 / Avg: 24.68 / Max: 24.741. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

LuxCoreRender

LuxCoreRender is an open-source 3D physically based renderer formerly known as LuxRender. LuxCoreRender supports CPU-based rendering as well as GPU acceleration via OpenCL, NVIDIA CUDA, and NVIDIA OptiX interfaces. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: Rainbow Colors and Prism - Acceleration: CPUABC246810SE +/- 0.00, N = 3SE +/- 0.01, N = 36.926.906.89MIN: 6.68 / MAX: 6.98MIN: 6.63 / MAX: 6.97MIN: 6.62 / MAX: 6.95
OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.5Scene: Rainbow Colors and Prism - Acceleration: CPUABC3691215Min: 6.9 / Avg: 6.9 / Max: 6.91Min: 6.87 / Avg: 6.89 / Max: 6.91

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 GlassABC510152025SE +/- 0.01, N = 3SE +/- 0.01, N = 322.8722.9022.88
OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: Tile GlassABC510152025Min: 22.87 / Avg: 22.9 / Max: 22.91Min: 22.87 / Avg: 22.88 / Max: 22.89

Etcpak

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

OpenBenchmarking.orgMpx/s, More Is BetterEtcpak 0.7Configuration: ETC2ABC50100150200250SE +/- 0.02, N = 3SE +/- 0.02, N = 3219.51219.47219.04
OpenBenchmarking.orgMpx/s, More Is BetterEtcpak 0.7Configuration: ETC2ABC4080120160200Min: 219.44 / Avg: 219.47 / Max: 219.49Min: 219.01 / Avg: 219.04 / Max: 219.08

KTX-Software toktx

This is a benchmark of The Khronos Group's KTX-Software library and tools. KTX-Software provides "toktx" for converting/creating in the KTX container format for image textures. This benchmark times how long it takes to convert to KTX 2.0 format with various settings using a reference PNG sample input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterKTX-Software toktx 4.0Settings: Zstd Compression 19ABC510152025SE +/- 0.06, N = 3SE +/- 0.01, N = 320.5421.4621.23
OpenBenchmarking.orgSeconds, Fewer Is BetterKTX-Software toktx 4.0Settings: Zstd Compression 19ABC510152025Min: 21.33 / Avg: 21.46 / Max: 21.54Min: 21.21 / Avg: 21.23 / Max: 21.26

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPUABC0.53731.07461.61192.14922.6865SE +/- 0.00124, N = 3SE +/- 0.00172, N = 32.386012.388102.38716MIN: 2.35MIN: 2.35MIN: 2.351. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPUABC246810Min: 2.39 / Avg: 2.39 / Max: 2.39Min: 2.38 / Avg: 2.39 / Max: 2.391. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

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 DocumentABC510152025SE +/- 0.03, N = 3SE +/- 0.08, N = 320.4820.5020.52
OpenBenchmarking.orgSeconds, Fewer Is BetterOCRMyPDF 10.3.1+dfsgProcessing 60 Page PDF DocumentABC510152025Min: 20.46 / Avg: 20.5 / Max: 20.56Min: 20.39 / Avg: 20.52 / Max: 20.65

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 PNGABC510152025SE +/- 0.01, N = 3SE +/- 0.02, N = 320.3220.3320.401. rsvg-convert version 2.50.7
OpenBenchmarking.orgSeconds, Fewer Is BetterlibrsvgOperation: SVG Files To PNGABC510152025Min: 20.31 / Avg: 20.33 / Max: 20.35Min: 20.38 / Avg: 20.4 / Max: 20.441. rsvg-convert version 2.50.7

rav1e

Xiph rav1e is a Rust-written AV1 video encoder. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betterrav1e 0.4Speed: 10ABC1.03162.06323.09484.12645.158SE +/- 0.012, N = 3SE +/- 0.012, N = 34.5344.5754.585
OpenBenchmarking.orgFrames Per Second, More Is Betterrav1e 0.4Speed: 10ABC246810Min: 4.55 / Avg: 4.57 / Max: 4.59Min: 4.57 / Avg: 4.59 / Max: 4.61

KTX-Software toktx

This is a benchmark of The Khronos Group's KTX-Software library and tools. KTX-Software provides "toktx" for converting/creating in the KTX container format for image textures. This benchmark times how long it takes to convert to KTX 2.0 format with various settings using a reference PNG sample input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterKTX-Software toktx 4.0Settings: UASTC 3 + Zstd Compression 19ABC510152025SE +/- 0.06, N = 3SE +/- 0.10, N = 319.3119.0919.20
OpenBenchmarking.orgSeconds, Fewer Is BetterKTX-Software toktx 4.0Settings: UASTC 3 + Zstd Compression 19ABC510152025Min: 19 / Avg: 19.09 / Max: 19.21Min: 19 / Avg: 19.2 / Max: 19.31

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 SceneABC1122334455SE +/- 0.04, N = 3SE +/- 0.01, N = 347.7947.5447.64
OpenBenchmarking.orgmrays/s, More Is Betterrays1bench 2020-01-09Large SceneABC1020304050Min: 47.47 / Avg: 47.54 / Max: 47.6Min: 47.63 / Avg: 47.64 / Max: 47.66

VP9 libvpx Encoding

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

OpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.10.0Speed: Speed 5 - Input: Bosphorus 1080pABC816243240SE +/- 0.15, N = 3SE +/- 0.10, N = 333.0432.9733.211. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11
OpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.10.0Speed: Speed 5 - Input: Bosphorus 1080pABC714212835Min: 32.67 / Avg: 32.97 / Max: 33.19Min: 33.01 / Avg: 33.21 / Max: 33.321. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11

libgav1

Libgav1 is an AV1 decoder developed by Google for AV1 profile 0/1 compliance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is Betterlibgav1 0.16.3Video Input: Summer Nature 1080pABC50100150200250SE +/- 0.30, N = 3SE +/- 0.64, N = 3206.80208.56207.791. (CXX) g++ options: -O3 -lpthread -lrt
OpenBenchmarking.orgFPS, More Is Betterlibgav1 0.16.3Video Input: Summer Nature 1080pABC4080120160200Min: 207.96 / Avg: 208.56 / Max: 208.94Min: 207.1 / Avg: 207.79 / Max: 209.071. (CXX) g++ options: -O3 -lpthread -lrt

Monkey Audio Encoding

This test times how long it takes to encode a sample WAV file to Monkey's Audio APE format. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterMonkey Audio Encoding 3.99.6WAV To APEABC3691215SE +/- 0.04, N = 5SE +/- 0.04, N = 510.7810.5410.521. (CXX) g++ options: -O3 -pedantic -rdynamic -lrt
OpenBenchmarking.orgSeconds, Fewer Is BetterMonkey Audio Encoding 3.99.6WAV To APEABC3691215Min: 10.47 / Avg: 10.54 / Max: 10.65Min: 10.48 / Avg: 10.52 / Max: 10.681. (CXX) g++ options: -O3 -pedantic -rdynamic -lrt

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 2020-06-28ABC48121620SE +/- 0.04, N = 3SE +/- 0.01, N = 316.5416.6016.561. (CC) gcc options: -O2 -pedantic -fvisibility=hidden
OpenBenchmarking.orgSeconds, Fewer Is BetterRNNoise 2020-06-28ABC48121620Min: 16.53 / Avg: 16.6 / Max: 16.67Min: 16.53 / Avg: 16.56 / Max: 16.581. (CC) gcc options: -O2 -pedantic -fvisibility=hidden

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.1Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4KABC918273645SE +/- 0.02, N = 3SE +/- 0.01, N = 337.7038.4338.941. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.1Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4KABC816243240Min: 38.41 / Avg: 38.43 / Max: 38.47Min: 38.92 / Avg: 38.94 / Max: 38.961. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

Ogg Audio Encoding

This test times how long it takes to encode a sample WAV file to Ogg format using the reference Xiph.org tools/libraries. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOgg Audio Encoding 1.3.4WAV To OggABC48121620SE +/- 0.03, N = 3SE +/- 0.04, N = 316.1616.0916.091. (CC) gcc options: -O2 -ffast-math -fsigned-char
OpenBenchmarking.orgSeconds, Fewer Is BetterOgg Audio Encoding 1.3.4WAV To OggABC48121620Min: 16.06 / Avg: 16.09 / Max: 16.15Min: 16.01 / Avg: 16.09 / Max: 16.161. (CC) gcc options: -O2 -ffast-math -fsigned-char

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 ImagesAB510152025SE +/- 0.00, N = 318.7518.74
OpenBenchmarking.orgSeconds, Fewer Is BetterTesseract OCR 4.1.1Time To OCR 7 ImagesAB510152025Min: 18.74 / Avg: 18.74 / Max: 18.74

WavPack Audio Encoding

This test times how long it takes to encode a sample WAV file to WavPack format with very high quality settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterWavPack Audio Encoding 5.3WAV To WavPackAB3691215SE +/- 0.01, N = 512.2112.221. (CXX) g++ options: -rdynamic
OpenBenchmarking.orgSeconds, Fewer Is BetterWavPack Audio Encoding 5.3WAV To WavPackAB48121620Min: 12.19 / Avg: 12.22 / Max: 12.271. (CXX) g++ options: -rdynamic

WebP Image Encode

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

OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100, LosslessABC48121620SE +/- 0.11, N = 3SE +/- 0.02, N = 315.4515.1115.381. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff
OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100, LosslessABC48121620Min: 14.94 / Avg: 15.11 / Max: 15.31Min: 15.34 / Avg: 15.38 / Max: 15.421. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff

SVT-AV1

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

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8.7Encoder Mode: Preset 8 - Input: Bosphorus 1080pABC918273645SE +/- 0.14, N = 3SE +/- 0.15, N = 339.5739.8839.891. (CXX) g++ options: -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8.7Encoder Mode: Preset 8 - Input: Bosphorus 1080pABC816243240Min: 39.59 / Avg: 39.88 / Max: 40.07Min: 39.65 / Avg: 39.89 / Max: 40.161. (CXX) g++ options: -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie

Etcpak

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

OpenBenchmarking.orgMpx/s, More Is BetterEtcpak 0.7Configuration: ETC1 + DitheringABC70140210280350SE +/- 0.08, N = 3SE +/- 0.01, N = 3319.61319.66318.53
OpenBenchmarking.orgMpx/s, More Is BetterEtcpak 0.7Configuration: ETC1 + DitheringABC60120180240300Min: 319.57 / Avg: 319.66 / Max: 319.83Min: 318.52 / Avg: 318.53 / Max: 318.54

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 1D - Data Type: f32 - Engine: CPUABC1.10272.20543.30814.41085.5135SE +/- 0.02070, N = 3SE +/- 0.00056, N = 34.863664.873564.90082MIN: 4.58MIN: 4.59MIN: 4.641. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 1D - Data Type: f32 - Engine: CPUABC246810Min: 4.84 / Avg: 4.87 / Max: 4.91Min: 4.9 / Avg: 4.9 / Max: 4.91. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPUABC0.41450.8291.24351.6582.0725SE +/- 0.00569, N = 3SE +/- 0.00377, N = 31.832381.842031.83883MIN: 1.81MIN: 1.81MIN: 1.811. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPUABC246810Min: 1.83 / Avg: 1.84 / Max: 1.85Min: 1.83 / Avg: 1.84 / Max: 1.841. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -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: NASA Streamlines - Renderer: SciVisABC48121620SE +/- 0.00, N = 3SE +/- 0.00, N = 316.9516.9516.95MIN: 16.13 / MAX: 17.24MIN: 16.39 / MAX: 17.24MIN: 16.39 / MAX: 17.24
OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: NASA Streamlines - Renderer: SciVisABC48121620Min: 16.95 / Avg: 16.95 / Max: 16.95Min: 16.95 / Avg: 16.95 / Max: 16.95

Etcpak

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

OpenBenchmarking.orgMpx/s, More Is BetterEtcpak 0.7Configuration: ETC1ABC80160240320400SE +/- 0.01, N = 3SE +/- 0.18, N = 3355.62355.96355.15
OpenBenchmarking.orgMpx/s, More Is BetterEtcpak 0.7Configuration: ETC1ABC60120180240300Min: 355.93 / Avg: 355.96 / Max: 355.97Min: 354.85 / Avg: 355.15 / Max: 355.48

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPUABC0.96081.92162.88243.84324.804SE +/- 0.05810, N = 15SE +/- 0.06388, N = 154.218764.270014.23026MIN: 4.12MIN: 3.92MIN: 3.881. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPUABC246810Min: 4.01 / Avg: 4.27 / Max: 4.51Min: 3.97 / Avg: 4.23 / Max: 4.511. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

libavif avifenc

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

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.9.0Encoder Speed: 6ABC3691215SE +/- 0.02, N = 3SE +/- 0.03, N = 312.9313.1113.091. (CXX) g++ options: -O3 -fPIC -lm
OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.9.0Encoder Speed: 6ABC48121620Min: 13.09 / Avg: 13.11 / Max: 13.16Min: 13.04 / Avg: 13.09 / Max: 13.141. (CXX) g++ options: -O3 -fPIC -lm

KTX-Software toktx

This is a benchmark of The Khronos Group's KTX-Software library and tools. KTX-Software provides "toktx" for converting/creating in the KTX container format for image textures. This benchmark times how long it takes to convert to KTX 2.0 format with various settings using a reference PNG sample input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterKTX-Software toktx 4.0Settings: UASTC 3ABC3691215SE +/- 0.01, N = 3SE +/- 0.01, N = 312.9212.9412.94
OpenBenchmarking.orgSeconds, Fewer Is BetterKTX-Software toktx 4.0Settings: UASTC 3ABC48121620Min: 12.93 / Avg: 12.94 / Max: 12.95Min: 12.93 / Avg: 12.94 / Max: 12.95

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 3.0Preset: ThoroughABC3691215SE +/- 0.0020, N = 3SE +/- 0.0061, N = 39.14259.15049.1558
OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 3.0Preset: ThoroughABC3691215Min: 9.15 / Avg: 9.15 / Max: 9.15Min: 9.15 / Avg: 9.16 / Max: 9.17

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 1080pABC1122334455SE +/- 0.32, N = 3SE +/- 0.07, N = 348.6149.3348.611. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl
OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.4Video Input: Bosphorus 1080pABC1020304050Min: 48.71 / Avg: 49.33 / Max: 49.75Min: 48.48 / Avg: 48.61 / Max: 48.711. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl

Smallpt

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

OpenBenchmarking.orgSeconds, Fewer Is BetterSmallpt 1.0Global Illumination Renderer; 128 SamplesABC3691215SE +/- 0.01, N = 3SE +/- 0.02, N = 312.1412.1512.161. (CXX) g++ options: -fopenmp -O3
OpenBenchmarking.orgSeconds, Fewer Is BetterSmallpt 1.0Global Illumination Renderer; 128 SamplesABC48121620Min: 12.14 / Avg: 12.15 / Max: 12.16Min: 12.13 / Avg: 12.16 / Max: 12.191. (CXX) g++ options: -fopenmp -O3

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPUABC0.98151.9632.94453.9264.9075SE +/- 0.00057, N = 3SE +/- 0.00240, N = 34.361404.358884.36236MIN: 4.25MIN: 4.26MIN: 4.261. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPUABC246810Min: 4.36 / Avg: 4.36 / Max: 4.36Min: 4.36 / Avg: 4.36 / Max: 4.371. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPUABC0.74221.48442.22662.96883.711SE +/- 0.00452, N = 3SE +/- 0.00592, N = 33.280363.298803.29703MIN: 3.24MIN: 3.25MIN: 3.251. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPUABC246810Min: 3.29 / Avg: 3.3 / Max: 3.3Min: 3.29 / Avg: 3.3 / Max: 3.31. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.1Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4KABC1224364860SE +/- 0.06, N = 3SE +/- 0.14, N = 352.3653.2754.381. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.1Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4KABC1122334455Min: 53.15 / Avg: 53.27 / Max: 53.35Min: 54.16 / Avg: 54.38 / Max: 54.631. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -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 2.10.22Test: unsharp-maskABC3691215SE +/- 0.02, N = 3SE +/- 0.02, N = 311.5211.5611.52
OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.22Test: unsharp-maskABC3691215Min: 11.54 / Avg: 11.56 / Max: 11.59Min: 11.48 / Avg: 11.52 / Max: 11.56

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 TimesABC3691215SE +/- 0.00, N = 3SE +/- 0.01, N = 311.5011.4911.54
OpenBenchmarking.orgSeconds, Fewer Is BetterG'MICTest: Plotting Isosurface Of A 3D Volume, 1000 TimesABC3691215Min: 11.49 / Avg: 11.49 / Max: 11.5Min: 11.52 / Avg: 11.54 / Max: 11.55

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 FastABC1224364860SE +/- 0.25, N = 3SE +/- 0.26, N = 352.4852.5352.141. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 1080p - Video Preset: Very FastABC1122334455Min: 52.04 / Avg: 52.53 / Max: 52.78Min: 51.79 / Avg: 52.14 / Max: 52.641. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

Opus Codec Encoding

Opus is an open audio codec. Opus is a lossy audio compression format designed primarily for interactive real-time applications over the Internet. This test uses Opus-Tools and measures the time required to encode a WAV file to Opus. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpus Codec Encoding 1.3.1WAV To Opus EncodeABC246810SE +/- 0.017, N = 5SE +/- 0.020, N = 56.7006.6616.6451. (CXX) g++ options: -fvisibility=hidden -logg -lm
OpenBenchmarking.orgSeconds, Fewer Is BetterOpus Codec Encoding 1.3.1WAV To Opus EncodeABC3691215Min: 6.62 / Avg: 6.66 / Max: 6.72Min: 6.61 / Avg: 6.64 / Max: 6.721. (CXX) g++ options: -fvisibility=hidden -logg -lm

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 FLACABC246810SE +/- 0.006, N = 5SE +/- 0.003, N = 56.4486.4326.4291. (CXX) g++ options: -O2 -fvisibility=hidden -logg -lm
OpenBenchmarking.orgSeconds, Fewer Is BetterFLAC Audio Encoding 1.3.2WAV To FLACABC3691215Min: 6.41 / Avg: 6.43 / Max: 6.45Min: 6.42 / Avg: 6.43 / Max: 6.441. (CXX) g++ options: -O2 -fvisibility=hidden -logg -lm

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 2.10.22Test: auto-levelsABC3691215SE +/- 0.015, N = 3SE +/- 0.030, N = 39.7829.7839.735
OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.22Test: auto-levelsABC3691215Min: 9.76 / Avg: 9.78 / Max: 9.81Min: 9.69 / Avg: 9.73 / Max: 9.79

OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.22Test: rotateABC3691215SE +/- 0.009, N = 3SE +/- 0.002, N = 39.3869.5579.509
OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.22Test: rotateABC3691215Min: 9.55 / Avg: 9.56 / Max: 9.58Min: 9.51 / Avg: 9.51 / Max: 9.51

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 3D - Data Type: f32 - Engine: CPUABC3691215SE +/- 0.01, N = 3SE +/- 0.01, N = 311.7211.6411.57MIN: 11.68MIN: 11.58MIN: 11.511. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 3D - Data Type: f32 - Engine: CPUABC3691215Min: 11.62 / Avg: 11.64 / Max: 11.67Min: 11.56 / Avg: 11.57 / Max: 11.591. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPUABC0.70741.41482.12222.82963.537SE +/- 0.01269, N = 3SE +/- 0.00599, N = 33.144073.142473.10159MIN: 2.98MIN: 3.01MIN: 2.921. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPUABC246810Min: 3.12 / Avg: 3.14 / Max: 3.16Min: 3.09 / Avg: 3.1 / Max: 3.111. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

dav1d

OpenBenchmarking.orgFPS, More Is Betterdav1d 0.9.1Video Input: Summer Nature 1080pABC90180270360450SE +/- 0.83, N = 3SE +/- 0.41, N = 3401.83421.50418.82MIN: 351 / MAX: 431.64MIN: 364.12 / MAX: 453.2MIN: 358.93 / MAX: 450.811. (CC) gcc options: -pthread
OpenBenchmarking.orgFPS, More Is Betterdav1d 0.9.1Video Input: Summer Nature 1080pABC70140210280350Min: 420.58 / Avg: 421.5 / Max: 423.16Min: 418.12 / Avg: 418.82 / Max: 419.551. (CC) gcc options: -pthread

SVT-HEVC

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

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 7 - Input: Bosphorus 1080pABC20406080100SE +/- 0.06, N = 3SE +/- 0.19, N = 373.3575.5273.821. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 7 - Input: Bosphorus 1080pABC1530456075Min: 75.41 / Avg: 75.52 / Max: 75.6Min: 73.58 / Avg: 73.82 / Max: 74.191. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

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 3.4.1Test: Masskrug - Acceleration: CPU-onlyABC246810SE +/- 0.019, N = 3SE +/- 0.026, N = 36.4846.5376.540
OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 3.4.1Test: Masskrug - Acceleration: CPU-onlyABC3691215Min: 6.51 / Avg: 6.54 / Max: 6.57Min: 6.5 / Avg: 6.54 / Max: 6.59

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 3.4.1Test: Boat - Acceleration: CPU-onlyABC246810SE +/- 0.015, N = 3SE +/- 0.012, N = 36.3786.4036.405
OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 3.4.1Test: Boat - Acceleration: CPU-onlyABC3691215Min: 6.38 / Avg: 6.4 / Max: 6.43Min: 6.39 / Avg: 6.41 / Max: 6.43

x264

This is a simple test of the x264 encoder run on the CPU (OpenCL support disabled) with a sample video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betterx264 2019-12-17H.264 Video EncodingABC20406080100SE +/- 1.01, N = 3SE +/- 0.61, N = 382.2684.7283.501. (CC) gcc options: -ldl -m64 -lm -lpthread -O3 -ffast-math -std=gnu99 -fPIC -fomit-frame-pointer -fno-tree-vectorize
OpenBenchmarking.orgFrames Per Second, More Is Betterx264 2019-12-17H.264 Video EncodingABC1632486480Min: 82.8 / Avg: 84.72 / Max: 86.23Min: 82.65 / Avg: 83.5 / Max: 84.681. (CC) gcc options: -ldl -m64 -lm -lpthread -O3 -ffast-math -std=gnu99 -fPIC -fomit-frame-pointer -fno-tree-vectorize

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 FastABC20406080100SE +/- 0.60, N = 3SE +/- 0.55, N = 388.6388.0887.421. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 1080p - Video Preset: Ultra FastABC20406080100Min: 87.19 / Avg: 88.08 / Max: 89.23Min: 86.44 / Avg: 87.42 / Max: 88.341. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

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: CropABC246810SE +/- 0.070, N = 3SE +/- 0.066, N = 36.7776.7066.678
OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: CropABC3691215Min: 6.62 / Avg: 6.71 / Max: 6.84Min: 6.61 / Avg: 6.68 / Max: 6.81

SVT-VP9

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

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: Visual Quality Optimized - Input: Bosphorus 1080pABC20406080100SE +/- 0.15, N = 3SE +/- 0.11, N = 391.6593.5992.531. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: Visual Quality Optimized - Input: Bosphorus 1080pABC20406080100Min: 93.3 / Avg: 93.59 / Max: 93.82Min: 92.4 / Avg: 92.53 / Max: 92.751. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

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 2.10.22Test: resizeABC246810SE +/- 0.023, N = 3SE +/- 0.051, N = 36.6976.6566.690
OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.22Test: resizeABC3691215Min: 6.61 / Avg: 6.66 / Max: 6.69Min: 6.6 / Avg: 6.69 / Max: 6.78

Basis Universal

Basis Universal is a GPU texture codec. This test times how long it takes to convert sRGB PNGs into Basis Univeral assets with various settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.13Settings: UASTC Level 0ABC246810SE +/- 0.007, N = 3SE +/- 0.003, N = 36.3916.3936.396
OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.13Settings: UASTC Level 0ABC3691215Min: 6.38 / Avg: 6.39 / Max: 6.41Min: 6.39 / Avg: 6.4 / Max: 6.4

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPUABC510152025SE +/- 0.08, N = 3SE +/- 0.02, N = 321.7321.7721.84MIN: 21.44MIN: 21.35MIN: 21.491. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPUABC510152025Min: 21.62 / Avg: 21.77 / Max: 21.87Min: 21.81 / Avg: 21.84 / Max: 21.871. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPUABC612182430SE +/- 0.05, N = 3SE +/- 0.07, N = 323.1922.8622.81MIN: 22.9MIN: 22.27MIN: 22.231. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPUABC510152025Min: 22.79 / Avg: 22.86 / Max: 22.96Min: 22.67 / Avg: 22.81 / Max: 22.91. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

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 MP3ABC246810SE +/- 0.005, N = 3SE +/- 0.012, N = 36.2506.2436.2541. (CC) gcc options: -O3 -ffast-math -funroll-loops -fschedule-insns2 -fbranch-count-reg -fforce-addr -pipe -lm
OpenBenchmarking.orgSeconds, Fewer Is BetterLAME MP3 Encoding 3.100WAV To MP3ABC3691215Min: 6.24 / Avg: 6.24 / Max: 6.25Min: 6.23 / Avg: 6.25 / Max: 6.281. (CC) gcc options: -O3 -ffast-math -funroll-loops -fschedule-insns2 -fbranch-count-reg -fforce-addr -pipe -lm

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 3.4.1Test: Server Room - Acceleration: CPU-onlyABC1.14212.28423.42634.56845.7105SE +/- 0.014, N = 3SE +/- 0.025, N = 35.0085.0765.053
OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 3.4.1Test: Server Room - Acceleration: CPU-onlyABC246810Min: 5.05 / Avg: 5.08 / Max: 5.1Min: 5.01 / Avg: 5.05 / Max: 5.1

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 CompressionABC1.32082.64163.96245.28326.604SE +/- 0.008, N = 3SE +/- 0.000, N = 35.8685.8705.8591. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff
OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100, Highest CompressionABC246810Min: 5.86 / Avg: 5.87 / Max: 5.89Min: 5.86 / Avg: 5.86 / Max: 5.861. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.1Encoder Mode: Speed 8 Realtime - Input: Bosphorus 1080pABC20406080100SE +/- 0.35, N = 3SE +/- 0.19, N = 3104.75105.29105.091. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.1Encoder Mode: Speed 8 Realtime - Input: Bosphorus 1080pABC20406080100Min: 104.75 / Avg: 105.29 / Max: 105.95Min: 104.85 / Avg: 105.09 / Max: 105.471. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

SVT-VP9

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

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: VMAF Optimized - Input: Bosphorus 1080pABC20406080100SE +/- 1.32, N = 3SE +/- 1.39, N = 3105.40109.15108.671. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: VMAF Optimized - Input: Bosphorus 1080pABC20406080100Min: 106.53 / Avg: 109.15 / Max: 110.77Min: 105.94 / Avg: 108.67 / Max: 110.451. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

libavif avifenc

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

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.9.0Encoder Speed: 10, LosslessABC1.2782.5563.8345.1126.39SE +/- 0.017, N = 3SE +/- 0.008, N = 35.6805.6495.6451. (CXX) g++ options: -O3 -fPIC -lm
OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.9.0Encoder Speed: 10, LosslessABC246810Min: 5.62 / Avg: 5.65 / Max: 5.67Min: 5.63 / Avg: 5.65 / Max: 5.661. (CXX) g++ options: -O3 -fPIC -lm

SVT-VP9

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

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080pABC306090120150SE +/- 0.17, N = 3SE +/- 0.74, N = 3110.21113.42112.351. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080pABC20406080100Min: 113.08 / Avg: 113.42 / Max: 113.63Min: 110.98 / Avg: 112.35 / Max: 113.531. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.1Encoder Mode: Speed 9 Realtime - Input: Bosphorus 1080pABC306090120150SE +/- 0.55, N = 3SE +/- 0.53, N = 3128.52127.65127.771. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.1Encoder Mode: Speed 9 Realtime - Input: Bosphorus 1080pABC20406080100Min: 127.04 / Avg: 127.65 / Max: 128.74Min: 126.74 / Avg: 127.77 / Max: 128.521. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

NeatBench

NeatBench is a benchmark of the cross-platform Neat Video software on the CPU and optional GPU (OpenCL / CUDA) support. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterNeatBench 5Acceleration: AllAB3691215SE +/- 0.18, N = 313.613.5
OpenBenchmarking.orgFPS, More Is BetterNeatBench 5Acceleration: AllAB48121620Min: 13.2 / Avg: 13.53 / Max: 13.8

OpenBenchmarking.orgFPS, More Is BetterNeatBench 5Acceleration: CPUAB3691215SE +/- 0.13, N = 313.613.5
OpenBenchmarking.orgFPS, More Is BetterNeatBench 5Acceleration: CPUAB48121620Min: 13.2 / Avg: 13.47 / Max: 13.6

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: ScaleABC1.02062.04123.06184.08245.103SE +/- 0.023, N = 3SE +/- 0.026, N = 34.5364.5364.536
OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: ScaleABC246810Min: 4.49 / Avg: 4.54 / Max: 4.56Min: 4.5 / Avg: 4.54 / Max: 4.59

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 3.0Preset: MediumABC1.00452.0093.01354.0185.0225SE +/- 0.0040, N = 3SE +/- 0.0024, N = 34.46104.45974.4643
OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 3.0Preset: MediumABC246810Min: 4.45 / Avg: 4.46 / Max: 4.47Min: 4.46 / Avg: 4.46 / Max: 4.47

SVT-HEVC

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

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 10 - Input: Bosphorus 1080pABC4080120160200SE +/- 0.82, N = 3SE +/- 0.35, N = 3153.53159.84156.501. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 10 - Input: Bosphorus 1080pABC306090120150Min: 158.69 / Avg: 159.84 / Max: 161.42Min: 155.93 / Avg: 156.5 / Max: 157.151. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

FFmpeg

This test uses FFmpeg for testing the system's audio/video encoding performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterFFmpeg 4.0.2H.264 HD To NTSC DVABC0.90591.81182.71773.62364.5295SE +/- 0.012, N = 3SE +/- 0.025, N = 34.0264.0163.9981. (CC) gcc options: -lavdevice -lavfilter -lavformat -lavcodec -lswresample -lswscale -lavutil -lXv -lX11 -lXext -lm -lxcb -lasound -lSDL2 -lsndio -pthread -lva -lbz2 -llzma -lva-drm -lva-x11 -std=c11 -fomit-frame-pointer -fPIC -O3 -fno-math-errno -fno-signed-zeros -fno-tree-vectorize -MMD -MF -MT
OpenBenchmarking.orgSeconds, Fewer Is BetterFFmpeg 4.0.2H.264 HD To NTSC DVABC246810Min: 3.99 / Avg: 4.02 / Max: 4.04Min: 3.97 / Avg: 4 / Max: 4.051. (CC) gcc options: -lavdevice -lavfilter -lavformat -lavcodec -lswresample -lswscale -lavutil -lXv -lX11 -lXext -lm -lxcb -lasound -lSDL2 -lsndio -pthread -lva -lbz2 -llzma -lva-drm -lva-x11 -std=c11 -fomit-frame-pointer -fPIC -O3 -fno-math-errno -fno-signed-zeros -fno-tree-vectorize -MMD -MF -MT

Etcpak

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

OpenBenchmarking.orgMpx/s, More Is BetterEtcpak 0.7Configuration: DXT1ABC30060090012001500SE +/- 1.11, N = 3SE +/- 1.49, N = 31408.451409.031408.79
OpenBenchmarking.orgMpx/s, More Is BetterEtcpak 0.7Configuration: DXT1ABC2004006008001000Min: 1407.29 / Avg: 1409.03 / Max: 1411.1Min: 1405.89 / Avg: 1408.78 / Max: 1410.85

libavif avifenc

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

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.9.0Encoder Speed: 10ABC0.74091.48182.22272.96363.7045SE +/- 0.009, N = 3SE +/- 0.007, N = 33.2933.2593.2501. (CXX) g++ options: -O3 -fPIC -lm
OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.9.0Encoder Speed: 10ABC246810Min: 3.24 / Avg: 3.26 / Max: 3.27Min: 3.24 / Avg: 3.25 / Max: 3.261. (CXX) g++ options: -O3 -fPIC -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 Intel oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPUABC246810SE +/- 0.02427, N = 3SE +/- 0.00826, N = 38.290618.568438.55943MIN: 8.15MIN: 8.14MIN: 8.141. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPUABC3691215Min: 8.52 / Avg: 8.57 / Max: 8.6Min: 8.54 / Avg: 8.56 / Max: 8.571. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

KTX-Software toktx

This is a benchmark of The Khronos Group's KTX-Software library and tools. KTX-Software provides "toktx" for converting/creating in the KTX container format for image textures. This benchmark times how long it takes to convert to KTX 2.0 format with various settings using a reference PNG sample input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterKTX-Software toktx 4.0Settings: Zstd Compression 9ABC0.61181.22361.83542.44723.059SE +/- 0.004, N = 3SE +/- 0.025, N = 32.7032.7192.708
OpenBenchmarking.orgSeconds, Fewer Is BetterKTX-Software toktx 4.0Settings: Zstd Compression 9ABC246810Min: 2.71 / Avg: 2.72 / Max: 2.73Min: 2.67 / Avg: 2.71 / Max: 2.75

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 TracerABC306090120150SE +/- 0.00, N = 3SE +/- 0.00, N = 3142.86142.86142.86MIN: 111.11 / MAX: 166.67MIN: 111.11 / MAX: 166.67MIN: 125 / MAX: 166.67
OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: Magnetic Reconnection - Renderer: Path TracerABC306090120150Min: 142.86 / Avg: 142.86 / Max: 142.86Min: 142.86 / Avg: 142.86 / Max: 142.86

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 100ABC0.42460.84921.27381.69842.123SE +/- 0.002, N = 3SE +/- 0.001, N = 31.8811.8871.8841. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff
OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100ABC246810Min: 1.88 / Avg: 1.89 / Max: 1.89Min: 1.88 / Avg: 1.88 / Max: 1.891. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff

OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: DefaultABC0.27070.54140.81211.08281.3535SE +/- 0.003, N = 3SE +/- 0.012, N = 61.1931.1941.2031. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff
OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: DefaultABC246810Min: 1.19 / Avg: 1.19 / Max: 1.2Min: 1.19 / Avg: 1.2 / Max: 1.261. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff

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 3.4.1Test: Server Rack - Acceleration: CPU-onlyABC0.0430.0860.1290.1720.215SE +/- 0.002, N = 4SE +/- 0.003, N = 30.1890.1910.191
OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 3.4.1Test: Server Rack - Acceleration: CPU-onlyABC12345Min: 0.19 / Avg: 0.19 / Max: 0.2Min: 0.19 / Avg: 0.19 / Max: 0.2

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-RelaxationABC5001000150020002500SE +/- 5.09, N = 3SE +/- 6.01, N = 32232.562228.802230.601. (CC) gcc options: -lm -ldl -O2 -fomit-frame-pointer -U_FORTIFY_SOURCE -fno-stack-protector
OpenBenchmarking.orgMflops, More Is BetterLuaJIT 2.1-gitTest: Jacobi Successive Over-RelaxationABC400800120016002000Min: 2218.63 / Avg: 2228.8 / Max: 2234.21Min: 2218.66 / Avg: 2230.6 / Max: 2237.741. (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 FactorizationABC9001800270036004500SE +/- 13.16, N = 3SE +/- 15.13, N = 34079.964087.554093.771. (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 FactorizationABC7001400210028003500Min: 4061.25 / Avg: 4087.55 / Max: 4101.81Min: 4074.56 / Avg: 4093.77 / Max: 4123.621. (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 MultiplyABC30060090012001500SE +/- 2.34, N = 3SE +/- 1.71, N = 31585.121581.031580.021. (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 MultiplyABC30060090012001500Min: 1576.36 / Avg: 1581.03 / Max: 1583.55Min: 1577 / Avg: 1580.02 / Max: 1582.921. (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 TransformABC90180270360450SE +/- 3.40, N = 3SE +/- 4.09, N = 3401.60401.07400.741. (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 TransformABC70140210280350Min: 394.32 / Avg: 401.07 / Max: 405.22Min: 392.6 / Avg: 400.74 / Max: 405.51. (CC) gcc options: -lm -ldl -O2 -fomit-frame-pointer -U_FORTIFY_SOURCE -fno-stack-protector

OpenBenchmarking.orgMflops, More Is BetterLuaJIT 2.1-gitTest: Monte CarloABC120240360480600SE +/- 1.58, N = 3SE +/- 0.70, N = 3542.35549.95549.371. (CC) gcc options: -lm -ldl -O2 -fomit-frame-pointer -U_FORTIFY_SOURCE -fno-stack-protector
OpenBenchmarking.orgMflops, More Is BetterLuaJIT 2.1-gitTest: Monte CarloABC100200300400500Min: 546.78 / Avg: 549.95 / Max: 551.53Min: 548.28 / Avg: 549.37 / Max: 550.671. (CC) gcc options: -lm -ldl -O2 -fomit-frame-pointer -U_FORTIFY_SOURCE -fno-stack-protector

194 Results Shown

Blender:
  Barbershop - CPU-Only
  Classroom - CPU-Only
  Pabellon Barcelona - CPU-Only
Appleseed
KTX-Software toktx
Blender
Appleseed
OSPray
AOM AV1
Intel Open Image Denoise
OpenVKL:
  vklBenchmark ISPC
  vklBenchmark Scalar
Appleseed
Radiance Benchmark
Blender
OSPray
LuxCoreRender
libgav1
AOM AV1
Timed Godot Game Engine Compilation
AOM AV1
VP9 libvpx Encoding
Kvazaar
SVT-AV1
Kvazaar
Intel Open Image Denoise:
  RT.hdr_alb_nrm.3840x2160
  RT.ldr_alb_nrm.3840x2160
Tachyon
AOM AV1
OSPray
G'MIC
x265
ASTC Encoder
oneDNN:
  Recurrent Neural Network Training - u8s8f32 - CPU
  Recurrent Neural Network Training - f32 - CPU
  Recurrent Neural Network Training - bf16bf16bf16 - CPU
SVT-HEVC
oneDNN:
  Recurrent Neural Network Inference - f32 - CPU
  Recurrent Neural Network Inference - u8s8f32 - CPU
  Recurrent Neural Network Inference - bf16bf16bf16 - CPU
Embree
C-Ray
GEGL
libavif avifenc
Embree:
  Pathtracer - Asian Dragon Obj
  Pathtracer ISPC - Crown
Radiance Benchmark
OSPray
libavif avifenc
LuxCoreRender
Embree
LuxCoreRender
Chaos Group V-RAY
LuxCoreRender
Embree
IndigoBench
Basis Universal
IndigoBench
libgav1
GraphicsMagick:
  Sharpen
  Noise-Gaussian
  Enhanced
  Resizing
  Swirl
  Rotate
  HWB Color Space
RawTherapee
Embree
Google SynthMark
VP9 libvpx Encoding
POV-Ray
libgav1
AOM AV1
VP9 libvpx Encoding
oneDNN
AOM AV1
GEGL
SVT-AV1
GEGL
G'MIC
DeepSpeech
SVT-AV1
Kvazaar
dav1d
AOM AV1
Hugin
rav1e:
  5
  1
WebP Image Encode
dcraw
libavif avifenc
OSPray
Natron
GEGL
Basis Universal
dav1d
AOBench
GEGL
eSpeak-NG Speech Engine
rav1e
Kvazaar
TTSIOD 3D Renderer
Kvazaar
LuaJIT
LibRaw
dav1d
Basis Universal
AOM AV1
libjpeg-turbo tjbench
GEGL
OSPray
Kvazaar
LuxCoreRender
GEGL
Etcpak
KTX-Software toktx
oneDNN
OCRMyPDF
librsvg
rav1e
KTX-Software toktx
rays1bench
VP9 libvpx Encoding
libgav1
Monkey Audio Encoding
RNNoise
AOM AV1
Ogg Audio Encoding
Tesseract OCR
WavPack Audio Encoding
WebP Image Encode
SVT-AV1
Etcpak
oneDNN:
  IP Shapes 1D - f32 - CPU
  IP Shapes 1D - u8s8f32 - CPU
OSPray
Etcpak
oneDNN
libavif avifenc
KTX-Software toktx
ASTC Encoder
x265
Smallpt
oneDNN:
  Matrix Multiply Batch Shapes Transformer - f32 - CPU
  Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPU
AOM AV1
GIMP
G'MIC
Kvazaar
Opus Codec Encoding
FLAC Audio Encoding
GIMP:
  auto-levels
  rotate
oneDNN:
  IP Shapes 3D - f32 - CPU
  IP Shapes 3D - u8s8f32 - CPU
dav1d
SVT-HEVC
Darktable:
  Masskrug - CPU-only
  Boat - CPU-only
x264
Kvazaar
GEGL
SVT-VP9
GIMP
Basis Universal
oneDNN:
  Convolution Batch Shapes Auto - f32 - CPU
  Convolution Batch Shapes Auto - u8s8f32 - CPU
LAME MP3 Encoding
Darktable
WebP Image Encode
AOM AV1
SVT-VP9
libavif avifenc
SVT-VP9
AOM AV1
NeatBench:
  All
  CPU
GEGL
ASTC Encoder
SVT-HEVC
FFmpeg
Etcpak
libavif avifenc
oneDNN
KTX-Software toktx
OSPray
WebP Image Encode:
  Quality 100
  Default
Darktable
LuaJIT:
  Jacobi Successive Over-Relaxation
  Dense LU Matrix Factorization
  Sparse Matrix Multiply
  Fast Fourier Transform
  Monte Carlo

A

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --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-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-M6DaQn/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-M6DaQn/gcc-11-11.2.0/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-build-config=bootstrap-lto-lean --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
Processor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa50000c
Python Notes: Python 3.9.6
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 IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 2 September 2021 16:23 by user phoronix.

B

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --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-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-M6DaQn/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-M6DaQn/gcc-11-11.2.0/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-build-config=bootstrap-lto-lean --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
Processor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa50000c
Python Notes: Python 3.9.6
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 IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 2 September 2021 20:57 by user phoronix.

C

Processor: AMD Ryzen 5 5600G @ 3.90GHz (6 Cores / 12 Threads), Motherboard: ASUS TUF GAMING B550M-PLUS (WI-FI) (2423 BIOS), Chipset: AMD Renoir Root Complex, Memory: 16GB, Disk: 1000GB Samsung SSD 980 PRO 1TB, Graphics: ASUS AMD Cezanne (1900/1800MHz), Audio: AMD Device 1637, Monitor: LG Ultra HD, Network: Realtek RTL8125 2.5GbE + Intel Wi-Fi 6 AX200

OS: Ubuntu 21.10, Kernel: 5.14.0-051400rc7daily20210826-generic (x86_64) 20210825, Desktop: GNOME Shell 40.2, Display Server: X Server, OpenGL: 4.6 Mesa 21.3.0-devel (git-9ca7412 2021-08-26 impish-oibaf-ppa) (LLVM 12.0.1), Vulkan: 1.2.185, Compiler: GCC 11.2.0, 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-bootstrap --enable-cet --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-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-M6DaQn/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-M6DaQn/gcc-11-11.2.0/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-build-config=bootstrap-lto-lean --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
Processor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa50000c
Python Notes: Python 3.9.6
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 IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 3 September 2021 08:34 by user phoronix.