Intel Core i9 12900K Alder Lake Governors

Intel Core i9-12900K P-State / intel_cpufreq governor benchmarking by Michael Larabel for a future article.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2201151-NE-ALDERLAKE88
Jump To Table - Results

View

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

Limit displaying results to tests within:

AV1 4 Tests
Web Browsers 1 Tests
Timed Code Compilation 5 Tests
C/C++ Compiler Tests 7 Tests
CPU Massive 6 Tests
Creator Workloads 16 Tests
Desktop Graphics 3 Tests
Encoding 8 Tests
Game Development 3 Tests
HPC - High Performance Computing 2 Tests
Imaging 3 Tests
Machine Learning 2 Tests
Multi-Core 15 Tests
NVIDIA GPU Compute 2 Tests
Programmer / Developer System Benchmarks 5 Tests
Python Tests 9 Tests
Renderers 3 Tests
Server CPU Tests 6 Tests
Video Encoding 7 Tests
Common Workstation Benchmarks 3 Tests

Statistics

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

Graph Settings

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

Multi-Way Comparison

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

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
p-state performance
January 15 2022
  5 Hours, 48 Minutes
p-state powersave
January 13 2022
  6 Hours, 40 Minutes
intel_cpufreq performance
January 14 2022
  7 Hours, 36 Minutes
intel_cpufreq schedutil
January 14 2022
  8 Hours, 32 Minutes
Invert Hiding All Results Option
  7 Hours, 9 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):

p-state performance

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-pWTZs6/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-pWTZs6/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: intel_pstate performance (EPP: performance) - CPU Microcode: 0x15 - Thermald 2.4.6
Python Notes: Python 3.9.9
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

p-state powersave

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-pWTZs6/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-pWTZs6/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: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0x15 - Thermald 2.4.6
Python Notes: Python 3.9.9
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

intel_cpufreq performance

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-pWTZs6/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-pWTZs6/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: intel_cpufreq performance (EPP: balance_performance) - CPU Microcode: 0x15 - Thermald 2.4.6
Python Notes: Python 3.9.9
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

intel_cpufreq schedutil

Processor: Intel Core i9-12900K @ 6.50GHz (16 Cores / 24 Threads), Motherboard: ASUS ROG STRIX Z690-E GAMING WIFI (0811 BIOS), Chipset: Intel Device 7aa7, Memory: 64GB, Disk: 1000GB Western Digital WDS100T1X0E-00AFY0, Graphics: ASUS Intel ADL-S GT1 3GB (1550MHz), Audio: Intel Device 7ad0, Monitor: ASUS VP28U, Network: Intel I225-V + Intel Wi-Fi 6 AX210/AX211/AX411

OS: Ubuntu 22.04, Kernel: 5.16.0-051600-generic (x86_64), Desktop: GNOME Shell 40.5, Display Server: X Server 1.20.13 + Wayland, OpenGL: 4.6 Mesa 22.0.0-devel (git-074bde9 2022-01-11 jammy-oibaf-ppa), Vulkan: 1.2.199, 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-pWTZs6/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-pWTZs6/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: intel_cpufreq schedutil (EPP: balance_performance) - CPU Microcode: 0x15 - Thermald 2.4.6
Python Notes: Python 3.9.9
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Intel Core i9 12900K Alder Lake GovernorsOpenBenchmarking.orgPhoronix Test SuiteIntel Core i9-12900K @ 6.50GHz (16 Cores / 24 Threads)ASUS ROG STRIX Z690-E GAMING WIFI (0811 BIOS)Intel Device 7aa764GB1000GB Western Digital WDS100T1X0E-00AFY0ASUS Intel ADL-S GT1 3GB (1550MHz)Intel Device 7ad0ASUS VP28UIntel I225-V + Intel Wi-Fi 6 AX210/AX211/AX411Ubuntu 22.045.16.0-051600-generic (x86_64)GNOME Shell 40.5X Server 1.20.13 + Wayland4.6 Mesa 22.0.0-devel (git-074bde9 2022-01-11 jammy-oibaf-ppa)1.2.199GCC 11.2.0ext43840x2160ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerOpenGLVulkanCompilerFile-SystemScreen ResolutionIntel Core I9 12900K Alder Lake Governors PerformanceSystem 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-pWTZs6/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-pWTZs6/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 - p-state performance: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x15 - Thermald 2.4.6 - p-state powersave: Scaling Governor: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0x15 - Thermald 2.4.6 - intel_cpufreq performance: Scaling Governor: intel_cpufreq performance (EPP: balance_performance) - CPU Microcode: 0x15 - Thermald 2.4.6 - intel_cpufreq schedutil: Scaling Governor: intel_cpufreq schedutil (EPP: balance_performance) - CPU Microcode: 0x15 - Thermald 2.4.6 - Python 3.9.9- itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

p-state performancep-state powersaveintel_cpufreq performanceintel_cpufreq schedutilLogarithmic Result OverviewPhoronix Test Suitelibgav1AOM AV1UnvanquishedStargate Digital Audio WorkstationVP9 libvpx EncodingOpenCVOpenJPEGKvazaarx265SVT-AV1TesseractSeleniumBlenderAppleseedOCRMyPDFRawTherapeeTimed Linux Kernel CompilationLuxCoreRenderTimed Mesa CompilationParaViewTimed Godot Game Engine CompilationONNX Runtimelibavif avifencASTC EncoderXonoticTimed Node.js CompilationTimed LLVM CompilationWarsow

Intel Core i9 12900K Alder Lake Governorsopencv: Features 2Dbuild-linux-kernel: allmodconfigselenium: Jetstream 2 - Google Chromebuild-llvm: Unix Makefilesbuild-llvm: Ninjabuild-nodejs: Time To Compilexonotic: 3840 x 2160 - Ultimateblender: Classroom - CPU-Onlylibgav1: Chimera 1080p 10-bitopencv: Object Detectionxonotic: 3840 x 2160 - Ultraluxcorerender: Danish Mood - CPUselenium: Jetstream 2 - Firefoxxonotic: 3840 x 2160 - Highappleseed: Emilyonnx: yolov4 - CPUaom-av1: Speed 4 Two-Pass - Bosphorus 4Kastcenc: Exhaustiveonnx: fcn-resnet101-11 - CPUonnx: shufflenet-v2-10 - CPUonnx: super-resolution-10 - CPUluxcorerender: LuxCore Benchmark - CPUparaview: Many Spheres - 1920 x 1080paraview: Many Spheres - 1920 x 1080aom-av1: Speed 4 Two-Pass - Bosphorus 1080paom-av1: Speed 6 Realtime - Bosphorus 4Kappleseed: Material Testerblender: BMW27 - CPU-Onlywarsow: 1920 x 1080appleseed: Disney Materiallibgav1: Chimera 1080psvt-av1: Preset 4 - Bosphorus 4Kaom-av1: Speed 6 Realtime - Bosphorus 1080pstargate: 192000 - 512luxcorerender: Orange Juice - CPUbuild-linux-kernel: defconfiglibgav1: Summer Nature 4Kselenium: StyleBench - Google Chromebuild-godot: Time To Compileunvanquished: 1920 x 1080 - Ultraavifenc: 6, Losslessstargate: 192000 - 1024luxcorerender: DLSC - CPUkvazaar: Bosphorus 4K - Slowxonotic: 3840 x 2160 - Lowselenium: WASM collisionDetection - Firefoxkvazaar: Bosphorus 4K - Mediumocrmypdf: Processing 60 Page PDF Documentvpxenc: Speed 5 - Bosphorus 4Kselenium: StyleBench - Firefoxopencv: DNN - Deep Neural Networkunvanquished: 1920 x 1080 - Highselenium: WASM collisionDetection - Google Chromebuild-mesa: Time To Compileunvanquished: 1920 x 1080 - Mediumkvazaar: Bosphorus 4K - Ultra Fastrawtherapee: Total Benchmark Timevpxenc: Speed 5 - Bosphorus 1080pkvazaar: Bosphorus 4K - Very Fasttesseract: 1920 x 1080selenium: PSPDFKit WASM - Google Chromeluxcorerender: Rainbow Colors and Prism - CPUsvt-av1: Preset 8 - Bosphorus 4Kselenium: PSPDFKit WASM - Firefoxaom-av1: Speed 10 Realtime - Bosphorus 4Klibgav1: Summer Nature 1080px265: Bosphorus 4Kaom-av1: Speed 8 Realtime - Bosphorus 4Kkvazaar: Bosphorus 1080p - Mediumsvt-av1: Preset 4 - Bosphorus 1080pavifenc: 2selenium: Kraken - Firefoxparaview: Wavelet Volume - 1920 x 1080paraview: Wavelet Volume - 1920 x 1080aom-av1: Speed 8 Realtime - Bosphorus 1080pkvazaar: Bosphorus 1080p - Slowparaview: Wavelet Contour - 1920 x 1080paraview: Wavelet Contour - 1920 x 1080selenium: Kraken - Google Chromex265: Bosphorus 1080pkvazaar: Bosphorus 1080p - Very Fastavifenc: 6selenium: WASM imageConvolute - Firefoxaom-av1: Speed 10 Realtime - Bosphorus 1080pastcenc: Thoroughsvt-av1: Preset 8 - Bosphorus 1080pselenium: WASM imageConvolute - Google Chromeopenjpeg: NASA Curiosity Panorama M34kvazaar: Bosphorus 1080p - Ultra Fastavifenc: 10, Losslessastcenc: Mediumavifenc: 10p-state performancep-state powersaveintel_cpufreq performanceintel_cpufreq schedutil204091595.490294.737379.644352.462315.83334.7873521209.8995.944641050.35610352.40180.58270.1964129217.3050666706.3433.5107984456255552.83722.7317.2112.3214.86115.16389175.16161.7109.936739268.912.36312.743.1893285.3947.973111.9866.064.796118.829.2063.5148423.2212.62194.6488511264.312.9110.80722.571678686240.9207.8025.955289.951.1835.85446.2128.93115.8743247213.5325.805223189.27374.8628.8961.2852.737.67021.120609.01015.37363.46161.4650.88503.97648.36427.480.61102.148.22716.5206.546.924299.64717.7650020187.244.2323.33962.464213587653.307266.359380.200360.728322.53035.0389417231.8861.384731050.80112302.20154.80770.4785650234.4173586356.1936.8742914439152862.63724.8287.2310.9214.61126.67763882.71161.7120.292991249.712.31912.473.1784744.9351.05588.1765.867.001115.131.6063.5149672.9711.87193.3215607255.012.0511.45122.741508823227.4213.9827.933273.749.2737.03645.9727.05101.3578267012.9823.612234275.68178.2328.4148.8451.887.66421.409611.1836.34752.2794.9950.20503.01748.27425.476.0797.378.23916.6149.396.936293.99317.9372818181.324.2773.36052.481191605650.632294.799377.576361.763321.89134.7973981230.1995.894692750.46964232.24179.53870.0709330228.3486196246.3536.8638924434552752.60723.0577.2112.3114.64124.65606282.35161.5119.343384268.512.37412.623.1854964.9851.110111.6466.0967.175118.930.8643.4928723.0212.08194.6569931258.612.1411.43922.581689037241.0214.7127.176289.948.5236.06245.7527.37116.1882248513.0725.614222989.22374.1528.7061.3252.847.73221.622611.01015.84663.49161.5951.16506.06748.56423.980.70102.318.17916.7205.666.935999.70917.7650027187.354.2623.34942.474536537654.617167.801384.364363.841322.69434.7523610233.5815.7413757049.86428592.2198.29968.0857978246.7814246282.9937.0273914458052732.53725.1167.233.953.51126.09676783.37159.7120.18543143.261.8013.981.2670714.9051.75222.0061.168.33274.031.3001.7739182.9410.25181.0259198263.010.5111.8506.0762.21382973.1215.2927.75874.647.2339.27439.0725.6876.7218813.2013.418367919.3762.7926.3813.0923.265.26821.674774.8822.16551.3928.5422.05505.45648.51556.324.8124.828.52916.638.696.984951.36717.8812553342.524.3523.38582.606OpenBenchmarking.org

OpenCV

This is a benchmark of the OpenCV (Computer Vision) library's built-in performance tests. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenCV 4.5.4Test: Features 2Dintel_cpufreq schedutilp-state powersavep-state performanceintel_cpufreq performance110K220K330K440K550KSE +/- 5836.00, N = 4SE +/- 3939.84, N = 12SE +/- 7222.22, N = 9SE +/- 6841.67, N = 125365372135872040911916051. (CXX) g++ options: -fPIC -fsigned-char -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -msse -msse2 -msse3 -fvisibility=hidden -O3 -shared
OpenBenchmarking.orgWatts, Fewer Is BetterOpenCV 4.5.4CPU Power Consumption Monitorintel_cpufreq performancep-state powersavep-state performanceintel_cpufreq schedutil4080120160200Min: 2.59 / Avg: 71.41 / Max: 155.09Min: 2.64 / Avg: 71.37 / Max: 149.87Min: 2.6 / Avg: 71.16 / Max: 158.78Min: 2.7 / Avg: 48.7 / Max: 195.61. intel_cpufreq performance: Approximate power consumption of 13962 Joules per run.2. p-state powersave: Approximate power consumption of 15523 Joules per run.3. p-state performance: Approximate power consumption of 14801 Joules per run.4. intel_cpufreq schedutil: Approximate power consumption of 26310 Joules per run.
OpenBenchmarking.orgCelsius, Fewer Is BetterOpenCV 4.5.4CPU Temperature Monitorintel_cpufreq performancep-state performancep-state powersaveintel_cpufreq schedutil1530456075Min: 0 / Avg: 51.86 / Max: 81Min: 31 / Avg: 51.7 / Max: 77Min: 31 / Avg: 51.14 / Max: 80Min: 31 / Avg: 45.12 / Max: 78

Timed Linux Kernel Compilation

This test times how long it takes to build the Linux kernel in a default configuration (defconfig) for the architecture being tested or alternatively an allmodconfig for building all possible kernel modules for the build. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 5.16Build: allmodconfigintel_cpufreq schedutilp-state powersaveintel_cpufreq performancep-state performance140280420560700SE +/- 0.85, N = 3SE +/- 1.30, N = 3SE +/- 0.61, N = 3SE +/- 0.11, N = 3654.62653.31650.63595.49
OpenBenchmarking.orgWatts, Fewer Is BetterTimed Linux Kernel Compilation 5.16CPU Power Consumption Monitorp-state performanceintel_cpufreq performanceintel_cpufreq schedutilp-state powersave4080120160200Min: 3.06 / Avg: 201.36 / Max: 216.4Min: 3.05 / Avg: 180.76 / Max: 214.2Min: 2.88 / Avg: 180.64 / Max: 215.24Min: 2.89 / Avg: 179.55 / Max: 215.561. p-state performance: Approximate power consumption of 121556 Joules per run.2. intel_cpufreq performance: Approximate power consumption of 119064 Joules per run.3. intel_cpufreq schedutil: Approximate power consumption of 119882 Joules per run.4. p-state powersave: Approximate power consumption of 119399 Joules per run.
OpenBenchmarking.orgCelsius, Fewer Is BetterTimed Linux Kernel Compilation 5.16CPU Temperature Monitorp-state performanceintel_cpufreq schedutilp-state powersaveintel_cpufreq performance20406080100Min: 32 / Avg: 89.77 / Max: 98Min: 32 / Avg: 82.91 / Max: 96Min: 32 / Avg: 81.43 / Max: 96Min: 33 / Avg: 81.2 / Max: 96

Selenium

This test profile uses the Selenium WebDriver for running various browser benchmarks in different available web browsers such as Mozilla Firefox and Google Chrome. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterSeleniumBenchmark: Jetstream 2 - Browser: Google Chromeintel_cpufreq schedutilp-state powersavep-state performanceintel_cpufreq performance60120180240300SE +/- 1.17, N = 3SE +/- 1.38, N = 3SE +/- 0.99, N = 3SE +/- 0.89, N = 3167.80266.36294.74294.801. chrome 97.0.4692.71
MinAvgMaxp-state performance2.732.0121.1p-state powersave2.428.776.1intel_cpufreq schedutil2.523.7120.7intel_cpufreq performance1.65.5120.5OpenBenchmarking.orgWatts, Fewer Is BetterSeleniumCPU Power Consumption Monitor40801201602001. p-state performance: Approximate power consumption of 3001 Joules per run.2. p-state powersave: Approximate power consumption of 2702 Joules per run.3. intel_cpufreq schedutil: Approximate power consumption of 2672 Joules per run.4. intel_cpufreq performance: Approximate power consumption of 8219 Joules per run.
MinAvgMaxp-state performance25.037.969.0p-state powersave0.034.769.0intel_cpufreq schedutil23.033.167.0intel_cpufreq performance0.022.469.0OpenBenchmarking.orgCelsius, Fewer Is BetterSeleniumCPU Temperature Monitor20406080100

Timed LLVM Compilation

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 13.0Build System: Unix Makefilesintel_cpufreq schedutilp-state powersavep-state performanceintel_cpufreq performance80160240320400SE +/- 4.31, N = 3SE +/- 0.86, N = 3SE +/- 2.89, N = 3SE +/- 1.54, N = 3384.36380.20379.64377.58
MinAvgMaxintel_cpufreq performance3.0166.7198.5p-state performance3.2166.5197.5p-state powersave3.2163.6199.8intel_cpufreq schedutil3.0163.5198.4OpenBenchmarking.orgWatts, Fewer Is BetterTimed LLVM Compilation 13.0CPU Power Consumption Monitor501001502002501. intel_cpufreq performance: Approximate power consumption of 65123 Joules per run.2. p-state performance: Approximate power consumption of 65307 Joules per run.3. p-state powersave: Approximate power consumption of 64988 Joules per run.4. intel_cpufreq schedutil: Approximate power consumption of 65223 Joules per run.
MinAvgMaxp-state performance0.078.389.0intel_cpufreq schedutil33.078.190.0intel_cpufreq performance31.078.090.0p-state powersave31.076.590.0OpenBenchmarking.orgCelsius, Fewer Is BetterTimed LLVM Compilation 13.0CPU Temperature Monitor20406080100

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 13.0Build System: Ninjaintel_cpufreq schedutilintel_cpufreq performancep-state powersavep-state performance80160240320400SE +/- 2.65, N = 3SE +/- 1.30, N = 3SE +/- 1.09, N = 3SE +/- 0.27, N = 3363.84361.76360.73352.46
MinAvgMaxp-state performance3.2176.1200.7intel_cpufreq performance3.1171.8200.5p-state powersave3.0170.6201.6intel_cpufreq schedutil2.9170.2200.5OpenBenchmarking.orgWatts, Fewer Is BetterTimed LLVM Compilation 13.0CPU Power Consumption Monitor501001502002501. p-state performance: Approximate power consumption of 64176 Joules per run.2. intel_cpufreq performance: Approximate power consumption of 64123 Joules per run.3. p-state powersave: Approximate power consumption of 64041 Joules per run.4. intel_cpufreq schedutil: Approximate power consumption of 64116 Joules per run.
MinAvgMaxintel_cpufreq schedutil32.079.192.0p-state performance33.078.990.0intel_cpufreq performance32.078.692.0p-state powersave32.078.292.0OpenBenchmarking.orgCelsius, Fewer Is BetterTimed LLVM Compilation 13.0CPU Temperature Monitor20406080100

Timed Node.js Compilation

This test profile times how long it takes to build/compile Node.js itself from source. Node.js is a JavaScript run-time built from the Chrome V8 JavaScript engine while itself is written in C/C++. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Node.js Compilation 17.3Time To Compileintel_cpufreq schedutilp-state powersaveintel_cpufreq performancep-state performance70140210280350SE +/- 1.12, N = 3SE +/- 0.84, N = 3SE +/- 0.77, N = 3SE +/- 0.11, N = 3322.69322.53321.89315.83
MinAvgMaxp-state performance3.1167.9202.8intel_cpufreq performance3.1164.3203.3p-state powersave3.1164.2204.2intel_cpufreq schedutil3.0163.8204.8OpenBenchmarking.orgWatts, Fewer Is BetterTimed Node.js Compilation 17.3CPU Power Consumption Monitor501001502002501. p-state performance: Approximate power consumption of 54076 Joules per run.2. intel_cpufreq performance: Approximate power consumption of 53956 Joules per run.3. p-state powersave: Approximate power consumption of 54068 Joules per run.4. intel_cpufreq schedutil: Approximate power consumption of 53952 Joules per run.
MinAvgMaxp-state performance34.076.890.0p-state powersave34.076.492.0intel_cpufreq performance34.076.294.0intel_cpufreq schedutil34.076.192.0OpenBenchmarking.orgCelsius, Fewer Is BetterTimed Node.js Compilation 17.3CPU Temperature Monitor20406080100

Xonotic

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

OpenBenchmarking.orgFrames Per Second, More Is BetterXonotic 0.8.2Resolution: 3840 x 2160 - Effects Quality: Ultimateintel_cpufreq schedutilp-state performanceintel_cpufreq performancep-state powersave816243240SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 334.7534.7934.8035.04MIN: 17 / MAX: 58MIN: 17 / MAX: 59MIN: 17 / MAX: 58MIN: 17 / MAX: 59
MinAvgMaxp-state performance3.020.830.0intel_cpufreq performance3.120.731.6intel_cpufreq schedutil2.617.129.4OpenBenchmarking.orgWatts, Fewer Is BetterXonotic 0.8.2CPU Power Consumption Monitor9182736451. p-state performance: Approximate power consumption of 6460 Joules per run.2. intel_cpufreq performance: Approximate power consumption of 6430 Joules per run.3. intel_cpufreq schedutil: Approximate power consumption of 5334 Joules per run.
MinAvgMaxintel_cpufreq performance23.027.341.0p-state performance0.027.239.0intel_cpufreq schedutil23.026.454.0OpenBenchmarking.orgCelsius, Fewer Is BetterXonotic 0.8.2CPU Temperature Monitor1530456075

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 NVIDIA OptiX and NVIDIA CUDA is currently supported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.0Blend File: Classroom - Compute: CPU-Onlyintel_cpufreq schedutilp-state powersaveintel_cpufreq performancep-state performance50100150200250SE +/- 1.09, N = 3SE +/- 1.04, N = 3SE +/- 0.39, N = 3SE +/- 0.23, N = 3233.58231.88230.19209.89
MinAvgMaxp-state performance2.9206.7225.1intel_cpufreq performance2.9191.2225.1p-state powersave3.0189.2225.4intel_cpufreq schedutil2.9189.1226.5OpenBenchmarking.orgWatts, Fewer Is BetterBlender 3.0CPU Power Consumption Monitor601201802403001. p-state performance: Approximate power consumption of 44305 Joules per run.2. intel_cpufreq performance: Approximate power consumption of 44873 Joules per run.3. p-state powersave: Approximate power consumption of 44717 Joules per run.4. intel_cpufreq schedutil: Approximate power consumption of 45013 Joules per run.
MinAvgMaxp-state performance37.094.398.0intel_cpufreq performance36.092.098.0p-state powersave35.092.097.0intel_cpufreq schedutil36.090.4100.0OpenBenchmarking.orgCelsius, Fewer Is BetterBlender 3.0CPU Temperature Monitor20406080100

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-bitintel_cpufreq schedutilp-state powersaveintel_cpufreq performancep-state performance20406080100SE +/- 0.02, N = 3SE +/- 0.44, N = 3SE +/- 0.00, N = 3SE +/- 0.05, N = 315.7461.3895.8995.941. (CXX) g++ options: -O3 -lrt
MinAvgMaxp-state performance2.893.9106.1intel_cpufreq performance2.893.8105.7p-state powersave2.842.768.0intel_cpufreq schedutil2.46.914.5OpenBenchmarking.orgWatts, Fewer Is Betterlibgav1 0.16.3CPU Power Consumption Monitor204060801001. p-state performance: Approximate power consumption of 9140 Joules per run.2. intel_cpufreq performance: Approximate power consumption of 9134 Joules per run.3. p-state powersave: Approximate power consumption of 6394 Joules per run.4. intel_cpufreq schedutil: Approximate power consumption of 3945 Joules per run.
MinAvgMaxintel_cpufreq performance31.057.173.0p-state performance31.055.676.0p-state powersave0.038.955.0intel_cpufreq schedutil0.023.827.0OpenBenchmarking.orgCelsius, Fewer Is Betterlibgav1 0.16.3CPU Temperature Monitor20406080100

OpenCV

This is a benchmark of the OpenCV (Computer Vision) library's built-in performance tests. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenCV 4.5.4Test: Object Detectionintel_cpufreq schedutilp-state powersaveintel_cpufreq performancep-state performance30K60K90K120K150KSE +/- 1479.36, N = 4SE +/- 917.32, N = 15SE +/- 903.87, N = 15SE +/- 993.21, N = 151375704731046927464101. (CXX) g++ options: -fPIC -fsigned-char -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -msse -msse2 -msse3 -fvisibility=hidden -O3 -shared
MinAvgMaxintel_cpufreq performance2.670.8150.9p-state performance2.769.6149.5p-state powersave2.669.2148.2intel_cpufreq schedutil2.640.6142.2OpenBenchmarking.orgWatts, Fewer Is BetterOpenCV 4.5.4CPU Power Consumption Monitor40801201602001. intel_cpufreq performance: Approximate power consumption of 3609 Joules per run.2. p-state performance: Approximate power consumption of 3515 Joules per run.3. p-state powersave: Approximate power consumption of 3557 Joules per run.4. intel_cpufreq schedutil: Approximate power consumption of 5745 Joules per run.
MinAvgMaxp-state performance28.054.077.0intel_cpufreq performance0.053.876.0p-state powersave28.053.577.0intel_cpufreq schedutil27.040.070.0OpenBenchmarking.orgCelsius, Fewer Is BetterOpenCV 4.5.4CPU Temperature Monitor20406080100

Xonotic

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

OpenBenchmarking.orgFrames Per Second, More Is BetterXonotic 0.8.2Resolution: 3840 x 2160 - Effects Quality: Ultraintel_cpufreq schedutilp-state performanceintel_cpufreq performancep-state powersave1122334455SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.03, N = 349.8650.3650.4750.80MIN: 23 / MAX: 73MIN: 22 / MAX: 75MIN: 22 / MAX: 75MIN: 22 / MAX: 75
MinAvgMaxintel_cpufreq performance2.922.332.1p-state performance2.822.231.5intel_cpufreq schedutil2.617.729.4OpenBenchmarking.orgWatts, Fewer Is BetterXonotic 0.8.2CPU Power Consumption Monitor9182736451. intel_cpufreq performance: Approximate power consumption of 4843 Joules per run.2. p-state performance: Approximate power consumption of 4833 Joules per run.3. intel_cpufreq schedutil: Approximate power consumption of 3890 Joules per run.
MinAvgMaxintel_cpufreq performance24.028.053.0p-state performance0.027.651.0intel_cpufreq schedutil0.027.049.0OpenBenchmarking.orgCelsius, Fewer Is BetterXonotic 0.8.2CPU Temperature Monitor1530456075

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 2.6Scene: Danish Mood - Acceleration: CPUp-state powersaveintel_cpufreq schedutilintel_cpufreq performancep-state performance0.541.081.622.162.7SE +/- 0.02, N = 15SE +/- 0.02, N = 15SE +/- 0.02, N = 3SE +/- 0.02, N = 32.202.212.242.40MIN: 0.51 / MAX: 2.69MIN: 0.5 / MAX: 2.68MIN: 0.84 / MAX: 2.64MIN: 0.83 / MAX: 2.86
MinAvgMaxp-state performance2.9182.1209.0p-state powersave2.8167.2211.2intel_cpufreq performance2.8166.6209.7intel_cpufreq schedutil2.8165.5211.3OpenBenchmarking.orgWatts, Fewer Is BetterLuxCoreRender 2.6CPU Power Consumption Monitor601201802403001. p-state performance: Approximate power consumption of 12203 Joules per run.2. p-state powersave: Approximate power consumption of 11161 Joules per run.3. intel_cpufreq performance: Approximate power consumption of 11107 Joules per run.4. intel_cpufreq schedutil: Approximate power consumption of 11131 Joules per run.
MinAvgMaxp-state performance35.082.690.0intel_cpufreq schedutil35.078.892.0p-state powersave35.076.793.0intel_cpufreq performance36.076.192.0OpenBenchmarking.orgCelsius, Fewer Is BetterLuxCoreRender 2.6CPU Temperature Monitor20406080100

Selenium

This test profile uses the Selenium WebDriver for running various browser benchmarks in different available web browsers such as Mozilla Firefox and Google Chrome. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterSeleniumBenchmark: Jetstream 2 - Browser: Firefoxintel_cpufreq schedutilp-state powersaveintel_cpufreq performancep-state performance4080120160200SE +/- 1.11, N = 4SE +/- 1.01, N = 3SE +/- 1.67, N = 3SE +/- 0.76, N = 398.30154.81179.54180.581. firefox 96.0
MinAvgMaxp-state performance2.731.6103.5intel_cpufreq performance2.531.0103.6p-state powersave2.628.785.1intel_cpufreq schedutil2.623.978.0OpenBenchmarking.orgWatts, Fewer Is BetterSeleniumCPU Power Consumption Monitor204060801001. p-state performance: Approximate power consumption of 4665 Joules per run.2. intel_cpufreq performance: Approximate power consumption of 4695 Joules per run.3. p-state powersave: Approximate power consumption of 4301 Joules per run.4. intel_cpufreq schedutil: Approximate power consumption of 4228 Joules per run.
MinAvgMaxp-state performance21.040.463.0intel_cpufreq performance21.039.867.0p-state powersave20.036.465.0intel_cpufreq schedutil21.035.662.0OpenBenchmarking.orgCelsius, Fewer Is BetterSeleniumCPU Temperature Monitor20406080100

Xonotic

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

OpenBenchmarking.orgFrames Per Second, More Is BetterXonotic 0.8.2Resolution: 3840 x 2160 - Effects Quality: Highintel_cpufreq schedutilintel_cpufreq performancep-state performancep-state powersave1632486480SE +/- 0.04, N = 3SE +/- 0.07, N = 3SE +/- 0.06, N = 3SE +/- 0.07, N = 368.0970.0770.2070.48MIN: 34 / MAX: 88MIN: 34 / MAX: 89MIN: 34 / MAX: 89MIN: 35 / MAX: 89
MinAvgMaxp-state performance2.923.630.0intel_cpufreq performance3.023.031.8intel_cpufreq schedutil2.717.729.2OpenBenchmarking.orgWatts, Fewer Is BetterXonotic 0.8.2CPU Power Consumption Monitor9182736451. p-state performance: Approximate power consumption of 3746 Joules per run.2. intel_cpufreq performance: Approximate power consumption of 3652 Joules per run.3. intel_cpufreq schedutil: Approximate power consumption of 2897 Joules per run.
MinAvgMaxintel_cpufreq performance25.029.355.0p-state performance24.028.558.0intel_cpufreq schedutil0.026.949.0OpenBenchmarking.orgCelsius, Fewer Is BetterXonotic 0.8.2CPU Temperature Monitor1632486480

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: Emilyintel_cpufreq schedutilp-state powersaveintel_cpufreq performancep-state performance50100150200250246.78234.42228.35217.31
MinAvgMaxp-state performance3.1181.1206.3intel_cpufreq performance3.2174.4208.9p-state powersave3.0169.2210.0intel_cpufreq schedutil3.1158.7208.2OpenBenchmarking.orgWatts, Fewer Is BetterAppleseed 2.0 BetaCPU Power Consumption Monitor60120180240300
MinAvgMaxp-state performance34.083.492.0p-state powersave35.081.493.0intel_cpufreq performance35.078.693.0intel_cpufreq schedutil0.074.093.0OpenBenchmarking.orgCelsius, Fewer Is BetterAppleseed 2.0 BetaCPU Temperature Monitor20406080100

ONNX Runtime

ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Zoo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.10Model: yolov4 - Device: CPUintel_cpufreq performanceintel_cpufreq schedutilp-state powersavep-state performance140280420560700SE +/- 4.38, N = 3SE +/- 6.81, N = 5SE +/- 3.88, N = 3SE +/- 0.87, N = 36246286356701. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt
MinAvgMaxp-state performance3.0163.9181.6p-state powersave2.7157.5182.3intel_cpufreq schedutil2.5157.5181.3intel_cpufreq performance2.8156.2181.8OpenBenchmarking.orgWatts, Fewer Is BetterONNX Runtime 1.10CPU Power Consumption Monitor501001502002501. p-state performance: Approximate power consumption of 20434 Joules per run.2. p-state powersave: Approximate power consumption of 19693 Joules per run.3. intel_cpufreq schedutil: Approximate power consumption of 19595 Joules per run.4. intel_cpufreq performance: Approximate power consumption of 19470 Joules per run.
MinAvgMaxp-state performance32.084.997.0intel_cpufreq schedutil23.083.796.0p-state powersave28.082.197.0intel_cpufreq performance32.077.497.0OpenBenchmarking.orgCelsius, Fewer Is BetterONNX Runtime 1.10CPU Temperature Monitor20406080100

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 3.2Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 4Kintel_cpufreq schedutilp-state powersavep-state performanceintel_cpufreq performance246810SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 32.996.196.346.351. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
MinAvgMaxintel_cpufreq performance2.8135.0194.0p-state performance3.0134.5195.1p-state powersave2.7127.3190.7intel_cpufreq schedutil2.652.7177.4OpenBenchmarking.orgWatts, Fewer Is BetterAOM AV1 3.2CPU Power Consumption Monitor501001502002501. intel_cpufreq performance: Approximate power consumption of 15385 Joules per run.2. p-state performance: Approximate power consumption of 15381 Joules per run.3. p-state powersave: Approximate power consumption of 14854 Joules per run.4. intel_cpufreq schedutil: Approximate power consumption of 11845 Joules per run.
MinAvgMaxintel_cpufreq performance32.069.888.0p-state performance31.068.289.0p-state powersave29.065.286.0intel_cpufreq schedutil21.040.377.0OpenBenchmarking.orgCelsius, Fewer Is BetterAOM AV1 3.2CPU Temperature Monitor20406080100

ASTC Encoder

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

OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 3.2Preset: Exhaustiveintel_cpufreq schedutilp-state powersaveintel_cpufreq performancep-state performance918273645SE +/- 0.28, N = 12SE +/- 0.31, N = 9SE +/- 0.23, N = 15SE +/- 0.05, N = 337.0336.8736.8633.511. (CXX) g++ options: -O3 -flto -pthread
MinAvgMaxp-state performance2.8173.1218.4intel_cpufreq performance2.7162.1219.4p-state powersave2.7162.0219.3intel_cpufreq schedutil2.8161.2220.7OpenBenchmarking.orgWatts, Fewer Is BetterASTC Encoder 3.2CPU Power Consumption Monitor601201802403001. p-state performance: Approximate power consumption of 7097 Joules per run.2. intel_cpufreq performance: Approximate power consumption of 7167 Joules per run.3. p-state powersave: Approximate power consumption of 7166 Joules per run.4. intel_cpufreq schedutil: Approximate power consumption of 7175 Joules per run.
MinAvgMaxintel_cpufreq performance28.077.893.0p-state performance28.077.392.0intel_cpufreq schedutil28.076.292.0p-state powersave27.075.892.0OpenBenchmarking.orgCelsius, Fewer Is BetterASTC Encoder 3.2CPU Temperature Monitor20406080100

ONNX Runtime

ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Zoo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.10Model: fcn-resnet101-11 - Device: CPUp-state powersaveintel_cpufreq schedutilintel_cpufreq performancep-state performance20406080100SE +/- 0.17, N = 3SE +/- 0.17, N = 3SE +/- 0.58, N = 3SE +/- 0.00, N = 3919192981. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt
MinAvgMaxp-state performance2.9166.3187.4p-state powersave2.8162.0187.4intel_cpufreq schedutil2.9161.4187.4intel_cpufreq performance3.0160.8187.4OpenBenchmarking.orgWatts, Fewer Is BetterONNX Runtime 1.10CPU Power Consumption Monitor501001502002501. p-state performance: Approximate power consumption of 20789 Joules per run.2. p-state powersave: Approximate power consumption of 20310 Joules per run.3. intel_cpufreq schedutil: Approximate power consumption of 20225 Joules per run.4. intel_cpufreq performance: Approximate power consumption of 20212 Joules per run.
MinAvgMaxp-state powersave32.088.297.0intel_cpufreq schedutil32.087.597.0p-state performance32.086.297.0intel_cpufreq performance33.083.198.0OpenBenchmarking.orgCelsius, Fewer Is BetterONNX Runtime 1.10CPU Temperature Monitor20406080100

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.10Model: shufflenet-v2-10 - Device: CPUintel_cpufreq performancep-state powersavep-state performanceintel_cpufreq schedutil10K20K30K40K50KSE +/- 146.84, N = 3SE +/- 68.81, N = 3SE +/- 16.43, N = 3SE +/- 2.77, N = 3443454439144562445801. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt
MinAvgMaxp-state performance2.9124.6131.4intel_cpufreq schedutil2.7124.2129.7p-state powersave2.9123.6129.4intel_cpufreq performance2.7122.9129.8OpenBenchmarking.orgWatts, Fewer Is BetterONNX Runtime 1.10CPU Power Consumption Monitor40801201602001. p-state performance: Approximate power consumption of 15445 Joules per run.2. intel_cpufreq schedutil: Approximate power consumption of 15441 Joules per run.3. p-state powersave: Approximate power consumption of 15326 Joules per run.4. intel_cpufreq performance: Approximate power consumption of 15195 Joules per run.
MinAvgMaxp-state powersave34.068.873.0intel_cpufreq schedutil33.068.473.0intel_cpufreq performance32.068.373.0p-state performance35.068.273.0OpenBenchmarking.orgCelsius, Fewer Is BetterONNX Runtime 1.10CPU Temperature Monitor20406080100

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.10Model: super-resolution-10 - Device: CPUintel_cpufreq schedutilintel_cpufreq performancep-state powersavep-state performance12002400360048006000SE +/- 18.43, N = 3SE +/- 26.82, N = 3SE +/- 13.51, N = 3SE +/- 40.13, N = 352735275528655551. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt
MinAvgMaxp-state performance2.9160.4179.3intel_cpufreq schedutil2.8156.1181.5p-state powersave2.8156.0180.3intel_cpufreq performance2.9154.7179.6OpenBenchmarking.orgWatts, Fewer Is BetterONNX Runtime 1.10CPU Power Consumption Monitor501001502002501. p-state performance: Approximate power consumption of 19886 Joules per run.2. intel_cpufreq schedutil: Approximate power consumption of 19361 Joules per run.3. p-state powersave: Approximate power consumption of 19344 Joules per run.4. intel_cpufreq performance: Approximate power consumption of 19184 Joules per run.
MinAvgMaxp-state performance32.084.896.0intel_cpufreq performance32.079.094.0intel_cpufreq schedutil33.078.996.0p-state powersave32.078.796.0OpenBenchmarking.orgCelsius, Fewer Is BetterONNX Runtime 1.10CPU Temperature Monitor20406080100

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 2.6Scene: LuxCore Benchmark - Acceleration: CPUintel_cpufreq schedutilintel_cpufreq performancep-state powersavep-state performance0.63681.27361.91042.54723.184SE +/- 0.03, N = 12SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 32.532.602.632.83MIN: 0.56 / MAX: 3.02MIN: 1.01 / MAX: 2.99MIN: 1.09 / MAX: 3.03MIN: 1.02 / MAX: 3.34
MinAvgMaxp-state performance3.0188.4216.2p-state powersave2.9174.3217.1intel_cpufreq performance2.9170.6215.5intel_cpufreq schedutil2.8169.3217.2OpenBenchmarking.orgWatts, Fewer Is BetterLuxCoreRender 2.6CPU Power Consumption Monitor601201802403001. p-state performance: Approximate power consumption of 12436 Joules per run.2. p-state powersave: Approximate power consumption of 11565 Joules per run.3. intel_cpufreq performance: Approximate power consumption of 11430 Joules per run.4. intel_cpufreq schedutil: Approximate power consumption of 11331 Joules per run.
MinAvgMaxp-state performance32.083.093.0intel_cpufreq performance32.081.293.0intel_cpufreq schedutil32.078.194.0p-state powersave32.078.093.0OpenBenchmarking.orgCelsius, Fewer Is BetterLuxCoreRender 2.6CPU Temperature Monitor20406080100

ParaView

This test runs ParaView benchmarks: an open-source data analytics and visualization application. Paraview describes itself as "an open-source, multi-platform data analysis and visualization application. ParaView users can quickly build visualizations to analyze their data using qualitative and quantitative techniques." Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiPolys / Sec, More Is BetterParaView 5.9Test: Many Spheres - Resolution: 1920 x 1080p-state performanceintel_cpufreq performancep-state powersaveintel_cpufreq schedutil160320480640800SE +/- 0.04, N = 3SE +/- 0.12, N = 3SE +/- 0.09, N = 3SE +/- 0.02, N = 3722.73723.06724.83725.12
MinAvgMaxintel_cpufreq performance2.919.059.8p-state performance2.918.460.6p-state powersave2.717.859.7intel_cpufreq schedutil2.617.753.6OpenBenchmarking.orgWatts, Fewer Is BetterParaView 5.9CPU Power Consumption Monitor204060801001. intel_cpufreq performance: Approximate power consumption of 1853 Joules per run.2. p-state performance: Approximate power consumption of 1793 Joules per run.3. p-state powersave: Approximate power consumption of 1743 Joules per run.4. intel_cpufreq schedutil: Approximate power consumption of 1730 Joules per run.
MinAvgMaxintel_cpufreq schedutil24.028.059.0p-state performance24.027.561.0intel_cpufreq performance23.026.651.0p-state powersave23.026.051.0OpenBenchmarking.orgCelsius, Fewer Is BetterParaView 5.9CPU Temperature Monitor20406080100

OpenBenchmarking.orgFrames / Sec, More Is BetterParaView 5.9Test: Many Spheres - Resolution: 1920 x 1080p-state performanceintel_cpufreq performancep-state powersaveintel_cpufreq schedutil246810SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 37.217.217.237.23

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 3.2Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 1080pintel_cpufreq schedutilp-state powersaveintel_cpufreq performancep-state performance3691215SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 33.9510.9212.3112.321. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
MinAvgMaxintel_cpufreq performance2.792.0140.6p-state performance2.691.9124.4p-state powersave2.773.5124.5intel_cpufreq schedutil2.517.175.4OpenBenchmarking.orgWatts, Fewer Is BetterAOM AV1 3.2CPU Power Consumption Monitor40801201602001. intel_cpufreq performance: Approximate power consumption of 5368 Joules per run.2. p-state performance: Approximate power consumption of 5360 Joules per run.3. p-state powersave: Approximate power consumption of 4778 Joules per run.4. intel_cpufreq schedutil: Approximate power consumption of 3066 Joules per run.
MinAvgMaxintel_cpufreq performance31.057.086.0p-state performance31.053.577.0p-state powersave28.050.477.0intel_cpufreq schedutil23.027.862.0OpenBenchmarking.orgCelsius, Fewer Is BetterAOM AV1 3.2CPU Temperature Monitor20406080100

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.2Encoder Mode: Speed 6 Realtime - Input: Bosphorus 4Kintel_cpufreq schedutilp-state powersaveintel_cpufreq performancep-state performance48121620SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.15, N = 6SE +/- 0.01, N = 33.5114.6114.6414.861. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
MinAvgMaxp-state performance2.883.598.0intel_cpufreq performance2.783.4101.1p-state powersave2.780.797.3intel_cpufreq schedutil2.49.920.4OpenBenchmarking.orgWatts, Fewer Is BetterAOM AV1 3.2CPU Power Consumption Monitor204060801001. p-state performance: Approximate power consumption of 3786 Joules per run.2. intel_cpufreq performance: Approximate power consumption of 3820 Joules per run.3. p-state powersave: Approximate power consumption of 3713 Joules per run.4. intel_cpufreq schedutil: Approximate power consumption of 1756 Joules per run.
MinAvgMaxp-state performance27.053.370.0intel_cpufreq performance0.053.273.0p-state powersave28.051.670.0intel_cpufreq schedutil21.024.535.0OpenBenchmarking.orgCelsius, Fewer Is BetterAOM AV1 3.2CPU Temperature Monitor20406080100

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 Testerp-state powersaveintel_cpufreq schedutilintel_cpufreq performancep-state performance306090120150126.68126.10124.66115.16
MinAvgMaxp-state performance3.1194.9213.9p-state powersave3.1179.1212.2intel_cpufreq performance3.2176.3212.0intel_cpufreq schedutil3.1175.0210.1OpenBenchmarking.orgWatts, Fewer Is BetterAppleseed 2.0 BetaCPU Power Consumption Monitor60120180240300
MinAvgMaxp-state performance36.087.694.0p-state powersave35.087.394.0intel_cpufreq schedutil35.078.892.0intel_cpufreq performance36.078.293.0OpenBenchmarking.orgCelsius, Fewer Is BetterAppleseed 2.0 BetaCPU Temperature Monitor20406080100

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 NVIDIA OptiX and NVIDIA CUDA is currently supported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.0Blend File: BMW27 - Compute: CPU-Onlyintel_cpufreq schedutilp-state powersaveintel_cpufreq performancep-state performance20406080100SE +/- 0.18, N = 3SE +/- 0.21, N = 3SE +/- 0.18, N = 3SE +/- 0.13, N = 383.3782.7182.3575.16
MinAvgMaxp-state performance3.0200.6228.0intel_cpufreq performance3.1185.5228.3intel_cpufreq schedutil2.9184.5228.1p-state powersave2.9183.9227.8OpenBenchmarking.orgWatts, Fewer Is BetterBlender 3.0CPU Power Consumption Monitor601201802403001. p-state performance: Approximate power consumption of 15977 Joules per run.2. intel_cpufreq performance: Approximate power consumption of 16080 Joules per run.3. intel_cpufreq schedutil: Approximate power consumption of 16177 Joules per run.4. p-state powersave: Approximate power consumption of 16065 Joules per run.
MinAvgMaxp-state performance33.091.9100.0p-state powersave33.085.998.0intel_cpufreq performance35.084.498.0intel_cpufreq schedutil34.083.298.0OpenBenchmarking.orgCelsius, Fewer Is BetterBlender 3.0CPU Temperature Monitor20406080100

Warsow

This is a benchmark of Warsow, a popular open-source first-person shooter. This game uses the QFusion engine. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterWarsow 2.5 BetaResolution: 1920 x 1080intel_cpufreq schedutilintel_cpufreq performancep-state performancep-state powersave4080120160200SE +/- 0.77, N = 3SE +/- 0.12, N = 3SE +/- 0.03, N = 3SE +/- 0.15, N = 3159.7161.5161.7161.7
MinAvgMaxp-state performance3.330.944.4intel_cpufreq performance2.830.543.0intel_cpufreq schedutil2.619.231.2p-state powersave2.618.336.2OpenBenchmarking.orgWatts, Fewer Is BetterWarsow 2.5 BetaCPU Power Consumption Monitor12243648601. p-state performance: Approximate power consumption of 2587 Joules per run.2. intel_cpufreq performance: Approximate power consumption of 2560 Joules per run.3. intel_cpufreq schedutil: Approximate power consumption of 1615 Joules per run.4. p-state powersave: Approximate power consumption of 1535 Joules per run.
MinAvgMaxintel_cpufreq performance25.031.054.0p-state performance25.030.835.0intel_cpufreq schedutil0.026.330.0p-state powersave0.026.328.0OpenBenchmarking.orgCelsius, Fewer Is BetterWarsow 2.5 BetaCPU Temperature Monitor1530456075

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 Materialp-state powersaveintel_cpufreq schedutilintel_cpufreq performancep-state performance306090120150120.29120.19119.34109.94
MinAvgMaxp-state performance3.2201.5221.5intel_cpufreq performance3.0185.9221.5p-state powersave3.2185.6222.3intel_cpufreq schedutil3.0184.7220.7OpenBenchmarking.orgWatts, Fewer Is BetterAppleseed 2.0 BetaCPU Power Consumption Monitor60120180240300
MinAvgMaxp-state performance34.091.298.0p-state powersave35.090.398.0intel_cpufreq performance36.084.1100.0intel_cpufreq schedutil32.082.698.0OpenBenchmarking.orgCelsius, Fewer Is BetterAppleseed 2.0 BetaCPU Temperature Monitor20406080100

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 1080pintel_cpufreq schedutilp-state powersaveintel_cpufreq performancep-state performance60120180240300SE +/- 0.06, N = 3SE +/- 2.03, N = 3SE +/- 0.24, N = 3SE +/- 0.82, N = 343.26249.71268.51268.911. (CXX) g++ options: -O3 -lrt
MinAvgMaxintel_cpufreq performance2.883.397.0p-state performance2.983.197.0p-state powersave2.774.094.7intel_cpufreq schedutil2.46.610.7OpenBenchmarking.orgWatts, Fewer Is Betterlibgav1 0.16.3CPU Power Consumption Monitor204060801001. intel_cpufreq performance: Approximate power consumption of 3111 Joules per run.2. p-state performance: Approximate power consumption of 3101 Joules per run.3. p-state powersave: Approximate power consumption of 2958 Joules per run.4. intel_cpufreq schedutil: Approximate power consumption of 1395 Joules per run.
MinAvgMaxintel_cpufreq performance32.052.467.0p-state performance32.051.266.0p-state powersave29.048.165.0intel_cpufreq schedutil0.023.425.0OpenBenchmarking.orgCelsius, Fewer Is Betterlibgav1 0.16.3CPU Temperature Monitor20406080100

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 4Kintel_cpufreq schedutilp-state powersavep-state performanceintel_cpufreq performance0.53421.06841.60262.13682.671SE +/- 0.001, N = 3SE +/- 0.011, N = 3SE +/- 0.003, N = 3SE +/- 0.005, N = 31.8012.3192.3632.3741. (CXX) g++ options: -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
MinAvgMaxintel_cpufreq performance2.7126.0216.5p-state performance2.8125.6211.9p-state powersave2.7120.7213.6intel_cpufreq schedutil2.587.4203.3OpenBenchmarking.orgWatts, Fewer Is BetterSVT-AV1 0.8.7CPU Power Consumption Monitor601201802403001. intel_cpufreq performance: Approximate power consumption of 9159 Joules per run.2. p-state performance: Approximate power consumption of 9088 Joules per run.3. p-state powersave: Approximate power consumption of 8928 Joules per run.4. intel_cpufreq schedutil: Approximate power consumption of 8214 Joules per run.
MinAvgMaxp-state performance31.067.290.0intel_cpufreq performance31.066.390.0p-state powersave31.065.290.0intel_cpufreq schedutil29.052.984.0OpenBenchmarking.orgCelsius, Fewer Is BetterSVT-AV1 0.8.7CPU Temperature Monitor20406080100

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 3.2Encoder Mode: Speed 6 Realtime - Input: Bosphorus 1080pintel_cpufreq schedutilp-state powersaveintel_cpufreq performancep-state performance3691215SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.06, N = 33.9812.4712.6212.741. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
MinAvgMaxp-state performance2.759.872.6intel_cpufreq performance2.859.173.9p-state powersave2.656.269.4intel_cpufreq schedutil2.411.327.9OpenBenchmarking.orgWatts, Fewer Is BetterAOM AV1 3.2CPU Power Consumption Monitor204060801001. p-state performance: Approximate power consumption of 3069 Joules per run.2. intel_cpufreq performance: Approximate power consumption of 3075 Joules per run.3. p-state powersave: Approximate power consumption of 2941 Joules per run.4. intel_cpufreq schedutil: Approximate power consumption of 1761 Joules per run.
MinAvgMaxintel_cpufreq performance0.048.571.0p-state performance29.047.073.0p-state powersave27.044.067.0intel_cpufreq schedutil0.026.251.0OpenBenchmarking.orgCelsius, Fewer Is BetterAOM AV1 3.2CPU Temperature Monitor20406080100

Stargate Digital Audio Workstation

Stargate is an open-source, cross-platform digital audio workstation (DAW) software package with "a unique and carefully curated experience" with scalability from old systems up through modern multi-core systems. Stargate is GPLv3 licensed and makes use of Qt5 (PyQt5) for its user-interface. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRender Ratio, More Is BetterStargate Digital Audio Workstation 21.10.9Sample Rate: 192000 - Buffer Size: 512intel_cpufreq schedutilp-state powersaveintel_cpufreq performancep-state performance0.71761.43522.15282.87043.588SE +/- 0.008551, N = 3SE +/- 0.006121, N = 3SE +/- 0.007078, N = 3SE +/- 0.007073, N = 31.2670713.1784743.1854963.1893281. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions
MinAvgMaxp-state powersave2.9142.4179.3p-state performance2.9142.4176.4intel_cpufreq performance2.8142.4179.5intel_cpufreq schedutil2.766.482.9OpenBenchmarking.orgWatts, Fewer Is BetterStargate Digital Audio Workstation 21.10.9CPU Power Consumption Monitor501001502002501. p-state powersave: Approximate power consumption of 8403 Joules per run.2. p-state performance: Approximate power consumption of 8306 Joules per run.3. intel_cpufreq performance: Approximate power consumption of 8400 Joules per run.4. intel_cpufreq schedutil: Approximate power consumption of 8788 Joules per run.
MinAvgMaxintel_cpufreq performance36.070.182.0p-state powersave35.070.084.0p-state performance35.068.884.0intel_cpufreq schedutil31.048.665.0OpenBenchmarking.orgCelsius, Fewer Is BetterStargate Digital Audio Workstation 21.10.9CPU Temperature Monitor20406080100

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 2.6Scene: Orange Juice - Acceleration: CPUintel_cpufreq schedutilp-state powersaveintel_cpufreq performancep-state performance1.21282.42563.63844.85126.064SE +/- 0.05, N = 4SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 34.904.934.985.39MIN: 4.04 / MAX: 5.57MIN: 4.53 / MAX: 5.5MIN: 4.68 / MAX: 5.5MIN: 5.07 / MAX: 5.56
MinAvgMaxp-state performance2.9194.6223.6intel_cpufreq performance2.8174.8223.5p-state powersave2.9174.6223.5intel_cpufreq schedutil2.9172.5224.3OpenBenchmarking.orgWatts, Fewer Is BetterLuxCoreRender 2.6CPU Power Consumption Monitor601201802403001. p-state performance: Approximate power consumption of 13235 Joules per run.2. intel_cpufreq performance: Approximate power consumption of 11947 Joules per run.3. p-state powersave: Approximate power consumption of 11930 Joules per run.4. intel_cpufreq schedutil: Approximate power consumption of 11817 Joules per run.
MinAvgMaxp-state performance36.087.496.0intel_cpufreq performance35.085.297.0intel_cpufreq schedutil36.081.497.0p-state powersave35.076.696.0OpenBenchmarking.orgCelsius, Fewer Is BetterLuxCoreRender 2.6CPU Temperature Monitor20406080100

Timed Linux Kernel Compilation

This test times how long it takes to build the Linux kernel in a default configuration (defconfig) for the architecture being tested or alternatively an allmodconfig for building all possible kernel modules for the build. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 5.16Build: defconfigintel_cpufreq schedutilintel_cpufreq performancep-state powersavep-state performance1224364860SE +/- 0.63, N = 3SE +/- 0.55, N = 5SE +/- 0.50, N = 5SE +/- 0.08, N = 351.7551.1151.0647.97
MinAvgMaxp-state performance2.9158.8209.3intel_cpufreq performance3.1151.7209.1intel_cpufreq schedutil2.8146.3208.7p-state powersave2.8142.7208.6OpenBenchmarking.orgWatts, Fewer Is BetterTimed Linux Kernel Compilation 5.16CPU Power Consumption Monitor601201802403001. p-state performance: Approximate power consumption of 8894 Joules per run.2. intel_cpufreq performance: Approximate power consumption of 8801 Joules per run.3. intel_cpufreq schedutil: Approximate power consumption of 8830 Joules per run.4. p-state powersave: Approximate power consumption of 8793 Joules per run.
MinAvgMaxp-state performance31.075.992.0intel_cpufreq schedutil31.075.892.0intel_cpufreq performance31.073.492.0p-state powersave30.070.490.0OpenBenchmarking.orgCelsius, Fewer Is BetterTimed Linux Kernel Compilation 5.16CPU Temperature Monitor20406080100

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 4Kintel_cpufreq schedutilp-state powersaveintel_cpufreq performancep-state performance306090120150SE +/- 0.08, N = 3SE +/- 1.15, N = 3SE +/- 0.22, N = 3SE +/- 0.34, N = 322.0088.17111.64111.981. (CXX) g++ options: -O3 -lrt
MinAvgMaxp-state performance3.099.6118.7intel_cpufreq performance2.999.2119.5p-state powersave2.758.893.5intel_cpufreq schedutil2.58.713.3OpenBenchmarking.orgWatts, Fewer Is Betterlibgav1 0.16.3CPU Power Consumption Monitor40801201602001. p-state performance: Approximate power consumption of 3619 Joules per run.2. intel_cpufreq performance: Approximate power consumption of 3636 Joules per run.3. p-state powersave: Approximate power consumption of 2645 Joules per run.4. intel_cpufreq schedutil: Approximate power consumption of 1469 Joules per run.
MinAvgMaxp-state performance31.058.077.0intel_cpufreq performance31.056.271.0p-state powersave25.043.767.0intel_cpufreq schedutil0.024.127.0OpenBenchmarking.orgCelsius, Fewer Is Betterlibgav1 0.16.3CPU Temperature Monitor20406080100

Selenium

This test profile uses the Selenium WebDriver for running various browser benchmarks in different available web browsers such as Mozilla Firefox and Google Chrome. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRuns / Minute, More Is BetterSeleniumBenchmark: StyleBench - Browser: Google Chromeintel_cpufreq schedutilp-state powersavep-state performanceintel_cpufreq performance1530456075SE +/- 0.07, N = 3SE +/- 0.12, N = 3SE +/- 0.09, N = 3SE +/- 0.17, N = 361.1065.8066.0066.091. chrome 97.0.4692.71
MinAvgMaxp-state performance2.726.535.2intel_cpufreq performance2.726.537.8p-state powersave2.725.137.5intel_cpufreq schedutil2.520.731.4OpenBenchmarking.orgWatts, Fewer Is BetterSeleniumCPU Power Consumption Monitor11223344551. p-state performance: Approximate power consumption of 1844 Joules per run.2. intel_cpufreq performance: Approximate power consumption of 1826 Joules per run.3. p-state powersave: Approximate power consumption of 1773 Joules per run.4. intel_cpufreq schedutil: Approximate power consumption of 1556 Joules per run.
MinAvgMaxp-state performance25.039.061.0intel_cpufreq performance25.036.961.0p-state powersave23.034.459.0intel_cpufreq schedutil21.032.359.0OpenBenchmarking.orgCelsius, Fewer Is BetterSeleniumCPU Temperature Monitor20406080100

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 Compileintel_cpufreq schedutilintel_cpufreq performancep-state powersavep-state performance1530456075SE +/- 0.30, N = 3SE +/- 0.17, N = 3SE +/- 0.41, N = 3SE +/- 0.22, N = 368.3367.1867.0064.80
MinAvgMaxp-state performance2.9151.6207.4p-state powersave2.9146.5206.5intel_cpufreq schedutil2.8144.4208.0intel_cpufreq performance2.9140.5206.7OpenBenchmarking.orgWatts, Fewer Is BetterTimed Godot Game Engine Compilation 3.2.3CPU Power Consumption Monitor601201802403001. p-state performance: Approximate power consumption of 10512 Joules per run.2. p-state powersave: Approximate power consumption of 10499 Joules per run.3. intel_cpufreq schedutil: Approximate power consumption of 10541 Joules per run.4. intel_cpufreq performance: Approximate power consumption of 10538 Joules per run.
MinAvgMaxp-state performance28.072.690.0intel_cpufreq performance31.072.690.0p-state powersave28.072.190.0intel_cpufreq schedutil31.071.992.0OpenBenchmarking.orgCelsius, Fewer Is BetterTimed Godot Game Engine Compilation 3.2.3CPU Temperature Monitor20406080100

Unvanquished

Unvanquished is a modern fork of the Tremulous first person shooter. Unvanquished is powered by the Daemon engine, a combination of the ioquake3 engine with the graphically-beautiful XreaL engine. Unvanquished supports a modern OpenGL 3 renderer and other advanced graphics features for this open-source game. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterUnvanquished 0.52.1Resolution: 1920 x 1080 - Effects Quality: Ultraintel_cpufreq schedutilp-state powersavep-state performanceintel_cpufreq performance306090120150SE +/- 0.06, N = 3SE +/- 0.49, N = 3SE +/- 0.09, N = 3SE +/- 0.03, N = 374.0115.1118.8118.9
MinAvgMaxintel_cpufreq performance2.928.233.0p-state performance3.128.233.6p-state powersave2.718.233.3intel_cpufreq schedutil2.611.927.5OpenBenchmarking.orgWatts, Fewer Is BetterUnvanquished 0.52.1CPU Power Consumption Monitor10203040501. intel_cpufreq performance: Approximate power consumption of 1638 Joules per run.2. p-state performance: Approximate power consumption of 1653 Joules per run.3. p-state powersave: Approximate power consumption of 1093 Joules per run.4. intel_cpufreq schedutil: Approximate power consumption of 1052 Joules per run.
MinAvgMaxp-state performance25.031.955.0intel_cpufreq performance24.031.457.0p-state powersave24.028.458.0intel_cpufreq schedutil23.025.454.0OpenBenchmarking.orgCelsius, Fewer Is BetterUnvanquished 0.52.1CPU Temperature Monitor1632486480

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, Losslessp-state powersaveintel_cpufreq schedutilintel_cpufreq performancep-state performance714212835SE +/- 0.27, N = 7SE +/- 0.23, N = 11SE +/- 0.16, N = 3SE +/- 0.18, N = 331.6131.3030.8629.211. (CXX) g++ options: -O3 -fPIC -lm
MinAvgMaxp-state performance2.9153.2226.8intel_cpufreq performance2.7146.5222.5intel_cpufreq schedutil2.7146.0227.3p-state powersave2.7145.2227.2OpenBenchmarking.orgWatts, Fewer Is Betterlibavif avifenc 0.9.0CPU Power Consumption Monitor601201802403001. p-state performance: Approximate power consumption of 5056 Joules per run.2. intel_cpufreq performance: Approximate power consumption of 5127 Joules per run.3. intel_cpufreq schedutil: Approximate power consumption of 5164 Joules per run.4. p-state powersave: Approximate power consumption of 5167 Joules per run.
MinAvgMaxintel_cpufreq schedutil28.077.096.0p-state performance29.076.294.0p-state powersave29.072.896.0intel_cpufreq performance28.071.393.0OpenBenchmarking.orgCelsius, Fewer Is Betterlibavif avifenc 0.9.0CPU Temperature Monitor20406080100

Stargate Digital Audio Workstation

Stargate is an open-source, cross-platform digital audio workstation (DAW) software package with "a unique and carefully curated experience" with scalability from old systems up through modern multi-core systems. Stargate is GPLv3 licensed and makes use of Qt5 (PyQt5) for its user-interface. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRender Ratio, More Is BetterStargate Digital Audio Workstation 21.10.9Sample Rate: 192000 - Buffer Size: 1024intel_cpufreq schedutilintel_cpufreq performancep-state performancep-state powersave0.79091.58182.37273.16363.9545SE +/- 0.015445, N = 3SE +/- 0.014564, N = 3SE +/- 0.003789, N = 3SE +/- 0.006068, N = 31.7739183.4928723.5148423.5149671. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions
MinAvgMaxp-state performance2.9148.3180.9intel_cpufreq performance2.9147.7181.3p-state powersave2.9147.6181.1intel_cpufreq schedutil2.780.1102.6OpenBenchmarking.orgWatts, Fewer Is BetterStargate Digital Audio Workstation 21.10.9CPU Power Consumption Monitor501001502002501. p-state performance: Approximate power consumption of 8010 Joules per run.2. intel_cpufreq performance: Approximate power consumption of 8023 Joules per run.3. p-state powersave: Approximate power consumption of 8019 Joules per run.4. intel_cpufreq schedutil: Approximate power consumption of 7824 Joules per run.
MinAvgMaxintel_cpufreq performance33.073.088.0p-state performance33.072.789.0p-state powersave33.072.789.0intel_cpufreq schedutil28.053.966.0OpenBenchmarking.orgCelsius, Fewer Is BetterStargate Digital Audio Workstation 21.10.9CPU Temperature Monitor20406080100

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 2.6Scene: DLSC - Acceleration: CPUintel_cpufreq schedutilp-state powersaveintel_cpufreq performancep-state performance0.72451.4492.17352.8983.6225SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 32.942.973.023.22MIN: 2.77 / MAX: 3.39MIN: 2.85 / MAX: 3.36MIN: 2.87 / MAX: 3.4MIN: 3.14 / MAX: 3.42
MinAvgMaxp-state performance3.0194.2221.1p-state powersave2.9177.5220.2intel_cpufreq performance2.9176.3220.5intel_cpufreq schedutil2.8173.6219.9OpenBenchmarking.orgWatts, Fewer Is BetterLuxCoreRender 2.6CPU Power Consumption Monitor601201802403001. p-state performance: Approximate power consumption of 12626 Joules per run.2. p-state powersave: Approximate power consumption of 11480 Joules per run.3. intel_cpufreq performance: Approximate power consumption of 11399 Joules per run.4. intel_cpufreq schedutil: Approximate power consumption of 11282 Joules per run.
MinAvgMaxp-state performance36.083.496.0intel_cpufreq schedutil35.080.796.0p-state powersave35.080.696.0intel_cpufreq performance36.080.297.0OpenBenchmarking.orgCelsius, Fewer Is BetterLuxCoreRender 2.6CPU Temperature Monitor20406080100

Kvazaar

This is a test of Kvazaar as a CPU-based H.265/HEVC 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 2.1Video Input: Bosphorus 4K - Video Preset: Slowintel_cpufreq schedutilp-state powersaveintel_cpufreq performancep-state performance3691215SE +/- 0.05, N = 3SE +/- 0.12, N = 5SE +/- 0.15, N = 3SE +/- 0.02, N = 310.2511.8712.0812.621. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
MinAvgMaxp-state performance2.9174.4209.9intel_cpufreq performance2.7168.3209.3p-state powersave2.9165.3208.7intel_cpufreq schedutil2.5133.1194.2OpenBenchmarking.orgWatts, Fewer Is BetterKvazaar 2.1CPU Power Consumption Monitor601201802403001. p-state performance: Approximate power consumption of 9009 Joules per run.2. intel_cpufreq performance: Approximate power consumption of 9089 Joules per run.3. p-state powersave: Approximate power consumption of 9056 Joules per run.4. intel_cpufreq schedutil: Approximate power consumption of 8339 Joules per run.
MinAvgMaxp-state performance28.080.194.0p-state powersave27.079.596.0intel_cpufreq performance28.077.496.0intel_cpufreq schedutil23.066.492.0OpenBenchmarking.orgCelsius, Fewer Is BetterKvazaar 2.1CPU Temperature Monitor20406080100

Xonotic

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

OpenBenchmarking.orgFrames Per Second, More Is BetterXonotic 0.8.2Resolution: 3840 x 2160 - Effects Quality: Lowintel_cpufreq schedutilp-state powersavep-state performanceintel_cpufreq performance4080120160200SE +/- 0.26, N = 3SE +/- 0.24, N = 3SE +/- 0.31, N = 3SE +/- 0.05, N = 3181.03193.32194.65194.66MIN: 98 / MAX: 297MIN: 102 / MAX: 297MIN: 107 / MAX: 298MIN: 107 / MAX: 298
MinAvgMaxintel_cpufreq performance2.928.434.7p-state performance3.028.334.1intel_cpufreq schedutil2.817.829.5OpenBenchmarking.orgWatts, Fewer Is BetterXonotic 0.8.2CPU Power Consumption Monitor10203040501. intel_cpufreq performance: Approximate power consumption of 1792 Joules per run.2. p-state performance: Approximate power consumption of 1784 Joules per run.3. intel_cpufreq schedutil: Approximate power consumption of 1199 Joules per run.
MinAvgMaxintel_cpufreq performance25.032.654.0p-state performance26.030.958.0intel_cpufreq schedutil0.028.355.0OpenBenchmarking.orgCelsius, Fewer Is BetterXonotic 0.8.2CPU Temperature Monitor1632486480

Selenium

This test profile uses the Selenium WebDriver for running various browser benchmarks in different available web browsers such as Mozilla Firefox and Google Chrome. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterSeleniumBenchmark: WASM collisionDetection - Browser: Firefoxp-state performanceintel_cpufreq schedutilintel_cpufreq performancep-state powersave60120180240300SE +/- 2.19, N = 15SE +/- 3.64, N = 15SE +/- 2.76, N = 14SE +/- 2.44, N = 6264.3263.0258.6255.01. firefox 96.0
MinAvgMaxp-state performance2.921.642.6intel_cpufreq performance2.621.042.7p-state powersave2.619.539.8intel_cpufreq schedutil2.618.034.6OpenBenchmarking.orgWatts, Fewer Is BetterSeleniumCPU Power Consumption Monitor12243648601. p-state performance: Approximate power consumption of 361 Joules per run.2. intel_cpufreq performance: Approximate power consumption of 359 Joules per run.3. p-state powersave: Approximate power consumption of 325 Joules per run.4. intel_cpufreq schedutil: Approximate power consumption of 321 Joules per run.
MinAvgMaxintel_cpufreq performance24.033.655.0p-state performance0.032.254.0p-state powersave22.031.151.0intel_cpufreq schedutil21.030.154.0OpenBenchmarking.orgCelsius, Fewer Is BetterSeleniumCPU Temperature Monitor1530456075

Kvazaar

This is a test of Kvazaar as a CPU-based H.265/HEVC 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 2.1Video Input: Bosphorus 4K - Video Preset: Mediumintel_cpufreq schedutilp-state powersaveintel_cpufreq performancep-state performance3691215SE +/- 0.05, N = 3SE +/- 0.12, N = 3SE +/- 0.09, N = 3SE +/- 0.03, N = 310.5112.0512.1412.911. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
MinAvgMaxp-state performance3.0177.0212.3intel_cpufreq performance2.9168.1210.6p-state powersave2.9165.8212.9intel_cpufreq schedutil2.8135.1200.1OpenBenchmarking.orgWatts, Fewer Is BetterKvazaar 2.1CPU Power Consumption Monitor601201802403001. p-state performance: Approximate power consumption of 8968 Joules per run.2. intel_cpufreq performance: Approximate power consumption of 8966 Joules per run.3. p-state powersave: Approximate power consumption of 8953 Joules per run.4. intel_cpufreq schedutil: Approximate power consumption of 8287 Joules per run.
MinAvgMaxp-state performance0.080.597.0p-state powersave0.077.596.0intel_cpufreq performance34.077.397.0intel_cpufreq schedutil32.065.792.0OpenBenchmarking.orgCelsius, Fewer Is BetterKvazaar 2.1CPU Temperature Monitor20406080100

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 13.2.0+dfsgProcessing 60 Page PDF Documentintel_cpufreq schedutilp-state powersaveintel_cpufreq performancep-state performance3691215SE +/- 0.08, N = 15SE +/- 0.11, N = 15SE +/- 0.09, N = 15SE +/- 0.04, N = 511.8511.4511.4410.81
MinAvgMaxp-state performance2.892.9219.8intel_cpufreq performance2.788.1221.0intel_cpufreq schedutil2.785.6223.3OpenBenchmarking.orgWatts, Fewer Is BetterOCRMyPDF 13.2.0+dfsgCPU Power Consumption Monitor601201802403001. p-state performance: Approximate power consumption of 1375 Joules per run.2. intel_cpufreq performance: Approximate power consumption of 1363 Joules per run.3. intel_cpufreq schedutil: Approximate power consumption of 1358 Joules per run.
MinAvgMaxp-state performance29.057.090.0intel_cpufreq performance31.057.092.0intel_cpufreq schedutil29.055.490.0OpenBenchmarking.orgCelsius, Fewer Is BetterOCRMyPDF 13.2.0+dfsgCPU Temperature Monitor20406080100

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 4Kintel_cpufreq schedutilp-state performanceintel_cpufreq performancep-state powersave510152025SE +/- 0.03, N = 3SE +/- 0.05, N = 3SE +/- 0.15, N = 3SE +/- 0.22, N = 36.0722.5722.5822.741. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11
MinAvgMaxp-state powersave2.893.4127.2p-state performance2.793.4127.1intel_cpufreq performance2.993.0129.8intel_cpufreq schedutil2.513.324.4OpenBenchmarking.orgWatts, Fewer Is BetterVP9 libvpx Encoding 1.10.0CPU Power Consumption Monitor40801201602001. p-state powersave: Approximate power consumption of 3021 Joules per run.2. p-state performance: Approximate power consumption of 3021 Joules per run.3. intel_cpufreq performance: Approximate power consumption of 3040 Joules per run.4. intel_cpufreq schedutil: Approximate power consumption of 1414 Joules per run.
MinAvgMaxp-state powersave29.059.278.0intel_cpufreq performance30.058.978.0p-state performance31.058.876.0intel_cpufreq schedutil23.027.739.0OpenBenchmarking.orgCelsius, Fewer Is BetterVP9 libvpx Encoding 1.10.0CPU Temperature Monitor20406080100

Selenium

This test profile uses the Selenium WebDriver for running various browser benchmarks in different available web browsers such as Mozilla Firefox and Google Chrome. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRuns / Minute, More Is BetterSeleniumBenchmark: StyleBench - Browser: Firefoxintel_cpufreq schedutilp-state powersavep-state performanceintel_cpufreq performance4080120160200SE +/- 0.51, N = 3SE +/- 1.45, N = 3SE +/- 1.00, N = 3SE +/- 0.67, N = 362.2150.0167.0168.01. firefox 96.0
MinAvgMaxp-state performance2.929.045.3intel_cpufreq performance2.728.844.5p-state powersave2.623.441.4intel_cpufreq schedutil2.78.232.3OpenBenchmarking.orgWatts, Fewer Is BetterSeleniumCPU Power Consumption Monitor12243648601. p-state performance: Approximate power consumption of 1161 Joules per run.2. intel_cpufreq performance: Approximate power consumption of 1153 Joules per run.3. p-state powersave: Approximate power consumption of 1008 Joules per run.4. intel_cpufreq schedutil: Approximate power consumption of 640 Joules per run.
MinAvgMaxp-state performance25.034.553.0intel_cpufreq performance0.033.250.0p-state powersave23.030.857.0intel_cpufreq schedutil0.024.335.0OpenBenchmarking.orgCelsius, Fewer Is BetterSeleniumCPU Temperature Monitor1632486480

OpenCV

This is a benchmark of the OpenCV (Computer Vision) library's built-in performance tests. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenCV 4.5.4Test: DNN - Deep Neural Networkintel_cpufreq schedutilintel_cpufreq performancep-state powersavep-state performance3K6K9K12K15KSE +/- 317.64, N = 12SE +/- 219.00, N = 15SE +/- 231.61, N = 15SE +/- 296.76, N = 13138299037882386861. (CXX) g++ options: -fPIC -fsigned-char -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -msse -msse2 -msse3 -fvisibility=hidden -O3 -shared
MinAvgMaxintel_cpufreq performance2.9121.2196.0p-state powersave2.8120.4194.4p-state performance2.9118.9189.8intel_cpufreq schedutil2.8117.6190.2OpenBenchmarking.orgWatts, Fewer Is BetterOpenCV 4.5.4CPU Power Consumption Monitor501001502002501. intel_cpufreq performance: Approximate power consumption of 1592 Joules per run.2. p-state powersave: Approximate power consumption of 1557 Joules per run.3. p-state performance: Approximate power consumption of 1519 Joules per run.4. intel_cpufreq schedutil: Approximate power consumption of 2107 Joules per run.
MinAvgMaxintel_cpufreq performance32.062.386.0p-state powersave33.061.688.0p-state performance34.061.089.0intel_cpufreq schedutil32.060.984.0OpenBenchmarking.orgCelsius, Fewer Is BetterOpenCV 4.5.4CPU Temperature Monitor20406080100

Unvanquished

Unvanquished is a modern fork of the Tremulous first person shooter. Unvanquished is powered by the Daemon engine, a combination of the ioquake3 engine with the graphically-beautiful XreaL engine. Unvanquished supports a modern OpenGL 3 renderer and other advanced graphics features for this open-source game. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterUnvanquished 0.52.1Resolution: 1920 x 1080 - Effects Quality: Highintel_cpufreq schedutilp-state powersavep-state performanceintel_cpufreq performance50100150200250SE +/- 0.15, N = 3SE +/- 0.62, N = 3SE +/- 0.23, N = 3SE +/- 0.23, N = 373.1227.4240.9241.0
MinAvgMaxp-state performance3.131.940.2intel_cpufreq performance2.931.238.4p-state powersave2.721.733.1intel_cpufreq schedutil2.78.927.8OpenBenchmarking.orgWatts, Fewer Is BetterUnvanquished 0.52.1CPU Power Consumption Monitor11223344551. p-state performance: Approximate power consumption of 1116 Joules per run.2. intel_cpufreq performance: Approximate power consumption of 1101 Joules per run.3. p-state powersave: Approximate power consumption of 788 Joules per run.4. intel_cpufreq schedutil: Approximate power consumption of 799 Joules per run.
MinAvgMaxintel_cpufreq performance24.034.155.0p-state performance25.033.159.0p-state powersave24.030.455.0intel_cpufreq schedutil23.024.131.0OpenBenchmarking.orgCelsius, Fewer Is BetterUnvanquished 0.52.1CPU Temperature Monitor1632486480

Selenium

This test profile uses the Selenium WebDriver for running various browser benchmarks in different available web browsers such as Mozilla Firefox and Google Chrome. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterSeleniumBenchmark: WASM collisionDetection - Browser: Google Chromeintel_cpufreq schedutilintel_cpufreq performancep-state powersavep-state performance50100150200250SE +/- 2.99, N = 12SE +/- 2.78, N = 15SE +/- 3.14, N = 15SE +/- 1.03, N = 5215.29214.71213.98207.801. chrome 97.0.4692.71
MinAvgMaxintel_cpufreq performance2.614.735.0p-state performance2.714.734.8intel_cpufreq schedutil2.513.834.2p-state powersave2.613.634.5OpenBenchmarking.orgWatts, Fewer Is BetterSeleniumCPU Power Consumption Monitor10203040501. intel_cpufreq performance: Approximate power consumption of 215 Joules per run.2. p-state performance: Approximate power consumption of 212 Joules per run.3. intel_cpufreq schedutil: Approximate power consumption of 204 Joules per run.4. p-state powersave: Approximate power consumption of 203 Joules per run.
MinAvgMaxintel_cpufreq performance23.029.353.0p-state performance24.027.852.0p-state powersave21.027.354.0intel_cpufreq schedutil21.026.457.0OpenBenchmarking.orgCelsius, Fewer Is BetterSeleniumCPU Temperature Monitor1632486480

Timed Mesa Compilation

This test profile times how long it takes to compile Mesa with Meson/Ninja. For minimizing build dependencies and avoid versioning conflicts, test this is just the core Mesa build without LLVM or the extra Gallium3D/Mesa drivers enabled. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Mesa Compilation 21.0Time To Compilep-state powersaveintel_cpufreq schedutilintel_cpufreq performancep-state performance714212835SE +/- 0.25, N = 3SE +/- 0.23, N = 9SE +/- 0.11, N = 3SE +/- 0.10, N = 327.9327.7627.1825.96
MinAvgMaxp-state performance3.1145.0210.2intel_cpufreq performance3.1140.3209.1intel_cpufreq schedutil3.0139.6210.5p-state powersave3.1133.9209.8OpenBenchmarking.orgWatts, Fewer Is BetterTimed Mesa Compilation 21.0CPU Power Consumption Monitor601201802403001. p-state performance: Approximate power consumption of 4496 Joules per run.2. intel_cpufreq performance: Approximate power consumption of 4536 Joules per run.3. intel_cpufreq schedutil: Approximate power consumption of 4484 Joules per run.4. p-state powersave: Approximate power consumption of 4506 Joules per run.
MinAvgMaxp-state performance35.074.190.0intel_cpufreq schedutil36.073.493.0intel_cpufreq performance35.072.692.0p-state powersave35.071.090.0OpenBenchmarking.orgCelsius, Fewer Is BetterTimed Mesa Compilation 21.0CPU Temperature Monitor20406080100

Unvanquished

Unvanquished is a modern fork of the Tremulous first person shooter. Unvanquished is powered by the Daemon engine, a combination of the ioquake3 engine with the graphically-beautiful XreaL engine. Unvanquished supports a modern OpenGL 3 renderer and other advanced graphics features for this open-source game. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterUnvanquished 0.52.1Resolution: 1920 x 1080 - Effects Quality: Mediumintel_cpufreq schedutilp-state powersavep-state performanceintel_cpufreq performance60120180240300SE +/- 0.32, N = 3SE +/- 0.48, N = 3SE +/- 0.22, N = 3SE +/- 0.15, N = 374.6273.7289.9289.9
MinAvgMaxp-state performance2.931.840.5intel_cpufreq performance3.231.439.8p-state powersave2.823.433.4intel_cpufreq schedutil2.68.728.3OpenBenchmarking.orgWatts, Fewer Is BetterUnvanquished 0.52.1CPU Power Consumption Monitor11223344551. p-state performance: Approximate power consumption of 976 Joules per run.2. intel_cpufreq performance: Approximate power consumption of 963 Joules per run.3. p-state powersave: Approximate power consumption of 742 Joules per run.4. intel_cpufreq schedutil: Approximate power consumption of 756 Joules per run.
MinAvgMaxintel_cpufreq performance24.034.158.0p-state performance25.033.558.0p-state powersave24.032.657.0intel_cpufreq schedutil22.024.854.0OpenBenchmarking.orgCelsius, Fewer Is BetterUnvanquished 0.52.1CPU Temperature Monitor1632486480

Kvazaar

This is a test of Kvazaar as a CPU-based H.265/HEVC 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 2.1Video Input: Bosphorus 4K - Video Preset: Ultra Fastintel_cpufreq schedutilintel_cpufreq performancep-state powersavep-state performance1224364860SE +/- 0.40, N = 15SE +/- 0.45, N = 15SE +/- 0.48, N = 4SE +/- 0.13, N = 447.2348.5249.2751.181. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
MinAvgMaxp-state performance3.0144.4210.4p-state powersave2.9140.8205.0intel_cpufreq performance2.8139.1209.1intel_cpufreq schedutil2.6134.4203.1OpenBenchmarking.orgWatts, Fewer Is BetterKvazaar 2.1CPU Power Consumption Monitor601201802403001. p-state performance: Approximate power consumption of 2275 Joules per run.2. p-state powersave: Approximate power consumption of 2287 Joules per run.3. intel_cpufreq performance: Approximate power consumption of 2282 Joules per run.4. intel_cpufreq schedutil: Approximate power consumption of 2258 Joules per run.
MinAvgMaxintel_cpufreq performance35.071.493.0p-state performance33.067.892.0p-state powersave34.067.590.0intel_cpufreq schedutil0.067.092.0OpenBenchmarking.orgCelsius, Fewer Is BetterKvazaar 2.1CPU Temperature Monitor20406080100

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 Timeintel_cpufreq schedutilp-state powersaveintel_cpufreq performancep-state performance918273645SE +/- 0.31, N = 3SE +/- 0.16, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 339.2737.0436.0635.851. RawTherapee, version 5.8, command line.
MinAvgMaxp-state performance2.683.9126.3intel_cpufreq performance2.883.4129.9p-state powersave2.679.2129.0intel_cpufreq schedutil2.775.5126.9OpenBenchmarking.orgWatts, Fewer Is BetterRawTherapeeCPU Power Consumption Monitor40801201602001. p-state performance: Approximate power consumption of 3384 Joules per run.2. intel_cpufreq performance: Approximate power consumption of 3418 Joules per run.3. p-state powersave: Approximate power consumption of 3300 Joules per run.4. intel_cpufreq schedutil: Approximate power consumption of 3372 Joules per run.
MinAvgMaxp-state performance23.051.274.0intel_cpufreq performance23.050.476.0p-state powersave22.048.471.0intel_cpufreq schedutil0.046.671.0OpenBenchmarking.orgCelsius, Fewer Is BetterRawTherapeeCPU Temperature Monitor20406080100

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 1080pintel_cpufreq schedutilintel_cpufreq performancep-state powersavep-state performance1020304050SE +/- 0.40, N = 15SE +/- 0.15, N = 4SE +/- 0.15, N = 4SE +/- 0.13, N = 439.0745.7545.9746.211. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11
MinAvgMaxp-state performance3.064.288.5p-state powersave2.862.988.6intel_cpufreq performance2.962.789.2intel_cpufreq schedutil2.650.485.6OpenBenchmarking.orgWatts, Fewer Is BetterVP9 libvpx Encoding 1.10.0CPU Power Consumption Monitor204060801001. p-state performance: Approximate power consumption of 1124 Joules per run.2. p-state powersave: Approximate power consumption of 1116 Joules per run.3. intel_cpufreq performance: Approximate power consumption of 1113 Joules per run.4. intel_cpufreq schedutil: Approximate power consumption of 997 Joules per run.
MinAvgMaxintel_cpufreq performance31.058.976.0p-state performance32.056.674.0p-state powersave31.054.570.0intel_cpufreq schedutil24.047.073.0OpenBenchmarking.orgCelsius, Fewer Is BetterVP9 libvpx Encoding 1.10.0CPU Temperature Monitor20406080100

Kvazaar

This is a test of Kvazaar as a CPU-based H.265/HEVC 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 2.1Video Input: Bosphorus 4K - Video Preset: Very Fastintel_cpufreq schedutilp-state powersaveintel_cpufreq performancep-state performance714212835SE +/- 0.08, N = 3SE +/- 0.09, N = 3SE +/- 0.22, N = 9SE +/- 0.04, N = 325.6827.0527.3728.931. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
MinAvgMaxp-state performance3.1159.2205.5intel_cpufreq performance2.9153.9208.0p-state powersave1.6151.7207.2intel_cpufreq schedutil2.7142.5193.3OpenBenchmarking.orgWatts, Fewer Is BetterKvazaar 2.1CPU Power Consumption Monitor601201802403001. p-state performance: Approximate power consumption of 3980 Joules per run.2. intel_cpufreq performance: Approximate power consumption of 3984 Joules per run.3. p-state powersave: Approximate power consumption of 3994 Joules per run.4. intel_cpufreq schedutil: Approximate power consumption of 3895 Joules per run.
MinAvgMaxp-state performance35.077.093.0p-state powersave34.074.796.0intel_cpufreq performance35.074.396.0intel_cpufreq schedutil32.069.189.0OpenBenchmarking.orgCelsius, Fewer Is BetterKvazaar 2.1CPU Temperature Monitor20406080100

Tesseract

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

OpenBenchmarking.orgFrames Per Second, More Is BetterTesseract 2014-05-12Resolution: 1920 x 1080intel_cpufreq schedutilp-state powersavep-state performanceintel_cpufreq performance306090120150SE +/- 0.16, N = 3SE +/- 0.47, N = 3SE +/- 0.40, N = 3SE +/- 0.41, N = 376.72101.36115.87116.19
MinAvgMaxintel_cpufreq performance3.027.832.8p-state performance2.927.732.4p-state powersave2.815.538.1intel_cpufreq schedutil2.712.229.2OpenBenchmarking.orgWatts, Fewer Is BetterTesseract 2014-05-12CPU Power Consumption Monitor11223344551. intel_cpufreq performance: Approximate power consumption of 981 Joules per run.2. p-state performance: Approximate power consumption of 989 Joules per run.3. p-state powersave: Approximate power consumption of 553 Joules per run.4. intel_cpufreq schedutil: Approximate power consumption of 434 Joules per run.
MinAvgMaxintel_cpufreq performance27.031.336.0p-state performance27.031.139.0p-state powersave26.029.155.0intel_cpufreq schedutil25.027.349.0OpenBenchmarking.orgCelsius, Fewer Is BetterTesseract 2014-05-12CPU Temperature Monitor1530456075

Selenium

This test profile uses the Selenium WebDriver for running various browser benchmarks in different available web browsers such as Mozilla Firefox and Google Chrome. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, Fewer Is BetterSeleniumBenchmark: PSPDFKit WASM - Browser: Google Chromep-state powersaveintel_cpufreq performancep-state performance6001200180024003000SE +/- 16.13, N = 3SE +/- 0.00, N = 3SE +/- 4.58, N = 32670248524721. chrome 97.0.4692.71
MinAvgMaxp-state performance2.924.492.6intel_cpufreq performance2.724.297.1p-state powersave2.718.685.0OpenBenchmarking.orgWatts, Fewer Is BetterSeleniumCPU Power Consumption Monitor204060801001. p-state performance: Approximate power consumption of 765 Joules per run.2. intel_cpufreq performance: Approximate power consumption of 766 Joules per run.3. p-state powersave: Approximate power consumption of 625 Joules per run.
MinAvgMaxintel_cpufreq performance24.032.159.0p-state performance23.031.962.0p-state powersave21.028.557.0OpenBenchmarking.orgCelsius, Fewer Is BetterSeleniumCPU Temperature Monitor20406080100

Benchmark: PSPDFKit WASM - Browser: Google Chrome

intel_cpufreq schedutil: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: NameError: name 'StaleElementReferenceException' is not defined

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 2.6Scene: Rainbow Colors and Prism - Acceleration: CPUp-state powersaveintel_cpufreq performanceintel_cpufreq schedutilp-state performance3691215SE +/- 0.09, N = 4SE +/- 0.10, N = 15SE +/- 0.08, N = 4SE +/- 0.10, N = 412.9813.0713.2013.53MIN: 11.66 / MAX: 14.09MIN: 11.2 / MAX: 14.04MIN: 11.97 / MAX: 13.95MIN: 12.44 / MAX: 14.01
MinAvgMaxp-state performance2.9138.3210.7intel_cpufreq schedutil2.9138.2213.3intel_cpufreq performance2.9136.7214.1p-state powersave3.0131.8213.9OpenBenchmarking.orgWatts, Fewer Is BetterLuxCoreRender 2.6CPU Power Consumption Monitor601201802403001. p-state performance: Approximate power consumption of 2386 Joules per run.2. intel_cpufreq schedutil: Approximate power consumption of 2419 Joules per run.3. intel_cpufreq performance: Approximate power consumption of 2442 Joules per run.4. p-state powersave: Approximate power consumption of 2372 Joules per run.
MinAvgMaxp-state performance35.071.292.0intel_cpufreq performance35.070.093.0p-state powersave35.068.692.0intel_cpufreq schedutil34.067.592.0OpenBenchmarking.orgCelsius, Fewer Is BetterLuxCoreRender 2.6CPU Temperature Monitor20406080100

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 4Kintel_cpufreq schedutilp-state powersaveintel_cpufreq performancep-state performance612182430SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.17, N = 3SE +/- 0.08, N = 313.4223.6125.6125.811. (CXX) g++ options: -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
MinAvgMaxp-state performance2.9121.0177.2intel_cpufreq performance2.7118.8161.6p-state powersave2.7104.0157.5intel_cpufreq schedutil2.654.1150.9OpenBenchmarking.orgWatts, Fewer Is BetterSVT-AV1 0.8.7CPU Power Consumption Monitor501001502002501. p-state performance: Approximate power consumption of 3429 Joules per run.2. intel_cpufreq performance: Approximate power consumption of 3405 Joules per run.3. p-state powersave: Approximate power consumption of 3156 Joules per run.4. intel_cpufreq schedutil: Approximate power consumption of 2688 Joules per run.
MinAvgMaxp-state performance31.062.180.0intel_cpufreq performance31.060.582.0p-state powersave31.057.380.0intel_cpufreq schedutil26.040.576.0OpenBenchmarking.orgCelsius, Fewer Is BetterSVT-AV1 0.8.7CPU Temperature Monitor20406080100

Selenium

This test profile uses the Selenium WebDriver for running various browser benchmarks in different available web browsers such as Mozilla Firefox and Google Chrome. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, Fewer Is BetterSeleniumBenchmark: PSPDFKit WASM - Browser: Firefoxintel_cpufreq schedutilp-state powersavep-state performanceintel_cpufreq performance8001600240032004000SE +/- 8.19, N = 3SE +/- 3.18, N = 3SE +/- 1.00, N = 3SE +/- 3.61, N = 336792342223122291. firefox 96.0
MinAvgMaxp-state performance2.924.967.4intel_cpufreq performance2.824.266.3p-state powersave2.619.260.5intel_cpufreq schedutil2.610.333.5OpenBenchmarking.orgWatts, Fewer Is BetterSeleniumCPU Power Consumption Monitor204060801001. p-state performance: Approximate power consumption of 723 Joules per run.2. intel_cpufreq performance: Approximate power consumption of 708 Joules per run.3. p-state powersave: Approximate power consumption of 587 Joules per run.4. intel_cpufreq schedutil: Approximate power consumption of 437 Joules per run.
MinAvgMaxintel_cpufreq performance24.031.654.0p-state performance24.031.359.0p-state powersave23.029.154.0intel_cpufreq schedutil23.025.551.0OpenBenchmarking.orgCelsius, Fewer Is BetterSeleniumCPU Temperature Monitor1632486480

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 3.2Encoder Mode: Speed 10 Realtime - Input: Bosphorus 4Kintel_cpufreq schedutilp-state powersaveintel_cpufreq performancep-state performance20406080100SE +/- 0.21, N = 3SE +/- 1.02, N = 15SE +/- 0.13, N = 6SE +/- 0.18, N = 619.3775.6889.2289.271. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
MinAvgMaxp-state performance2.861.398.8intel_cpufreq performance2.961.199.4p-state powersave2.645.886.9intel_cpufreq schedutil2.78.513.2OpenBenchmarking.orgWatts, Fewer Is BetterAOM AV1 3.2CPU Power Consumption Monitor204060801001. p-state performance: Approximate power consumption of 735 Joules per run.2. intel_cpufreq performance: Approximate power consumption of 733 Joules per run.3. p-state powersave: Approximate power consumption of 596 Joules per run.4. intel_cpufreq schedutil: Approximate power consumption of 331 Joules per run.
MinAvgMaxintel_cpufreq performance28.044.760.0p-state performance27.041.762.0p-state powersave25.039.157.0intel_cpufreq schedutil0.025.328.0OpenBenchmarking.orgCelsius, Fewer Is BetterAOM AV1 3.2CPU Temperature Monitor20406080100

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 1080pintel_cpufreq schedutilp-state powersaveintel_cpufreq performancep-state performance80160240320400SE +/- 0.04, N = 3SE +/- 1.56, N = 3SE +/- 0.25, N = 5SE +/- 0.39, N = 562.79178.23374.15374.861. (CXX) g++ options: -O3 -lrt
MinAvgMaxintel_cpufreq performance3.072.1106.9p-state performance3.071.7106.7p-state powersave3.023.751.3intel_cpufreq schedutil2.67.69.9OpenBenchmarking.orgWatts, Fewer Is Betterlibgav1 0.16.3CPU Power Consumption Monitor204060801001. intel_cpufreq performance: Approximate power consumption of 995 Joules per run.2. p-state performance: Approximate power consumption of 990 Joules per run.3. p-state powersave: Approximate power consumption of 576 Joules per run.4. intel_cpufreq schedutil: Approximate power consumption of 470 Joules per run.
MinAvgMaxintel_cpufreq performance33.049.765.0p-state performance33.049.770.0p-state powersave29.035.249.0intel_cpufreq schedutil23.027.535.0OpenBenchmarking.orgCelsius, Fewer Is Betterlibgav1 0.16.3CPU Temperature Monitor20406080100

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 4Kintel_cpufreq schedutilp-state powersaveintel_cpufreq performancep-state performance714212835SE +/- 0.28, N = 5SE +/- 0.31, N = 3SE +/- 0.22, N = 3SE +/- 0.12, N = 326.3828.4128.7028.891. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
MinAvgMaxintel_cpufreq performance2.8148.9189.2p-state performance2.9148.3187.8p-state powersave2.7146.0190.5intel_cpufreq schedutil2.6131.7189.3OpenBenchmarking.orgWatts, Fewer Is Betterx265 3.4CPU Power Consumption Monitor501001502002501. intel_cpufreq performance: Approximate power consumption of 3722 Joules per run.2. p-state performance: Approximate power consumption of 3707 Joules per run.3. p-state powersave: Approximate power consumption of 3700 Joules per run.4. intel_cpufreq schedutil: Approximate power consumption of 3555 Joules per run.
MinAvgMaxp-state performance30.069.990.0intel_cpufreq performance31.069.685.0p-state powersave29.065.985.0intel_cpufreq schedutil25.063.586.0OpenBenchmarking.orgCelsius, Fewer Is Betterx265 3.4CPU Temperature Monitor20406080100

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 3.2Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4Kintel_cpufreq schedutilp-state powersavep-state performanceintel_cpufreq performance1428425670SE +/- 0.03, N = 3SE +/- 0.37, N = 4SE +/- 0.10, N = 5SE +/- 0.02, N = 513.0948.8461.2861.321. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
MinAvgMaxp-state performance2.879.6112.1intel_cpufreq performance2.878.1113.4p-state powersave2.748.981.2intel_cpufreq schedutil2.69.413.2OpenBenchmarking.orgWatts, Fewer Is BetterAOM AV1 3.2CPU Power Consumption Monitor40801201602001. p-state performance: Approximate power consumption of 1162 Joules per run.2. intel_cpufreq performance: Approximate power consumption of 1125 Joules per run.3. p-state powersave: Approximate power consumption of 844 Joules per run.4. intel_cpufreq schedutil: Approximate power consumption of 493 Joules per run.
MinAvgMaxintel_cpufreq performance28.048.466.0p-state performance27.048.066.0p-state powersave25.037.250.0intel_cpufreq schedutil23.024.628.0OpenBenchmarking.orgCelsius, Fewer Is BetterAOM AV1 3.2CPU Temperature Monitor20406080100

Kvazaar

This is a test of Kvazaar as a CPU-based H.265/HEVC 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 2.1Video Input: Bosphorus 1080p - Video Preset: Mediumintel_cpufreq schedutilp-state powersavep-state performanceintel_cpufreq performance1224364860SE +/- 0.24, N = 5SE +/- 0.20, N = 4SE +/- 0.11, N = 5SE +/- 0.17, N = 523.2651.8852.7352.841. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
MinAvgMaxp-state performance2.8109.3152.6intel_cpufreq performance2.7108.4156.6p-state powersave2.7103.4152.4intel_cpufreq schedutil2.733.574.8OpenBenchmarking.orgWatts, Fewer Is BetterKvazaar 2.1CPU Power Consumption Monitor40801201602001. p-state performance: Approximate power consumption of 1684 Joules per run.2. intel_cpufreq performance: Approximate power consumption of 1669 Joules per run.3. p-state powersave: Approximate power consumption of 1629 Joules per run.4. intel_cpufreq schedutil: Approximate power consumption of 1004 Joules per run.
MinAvgMaxp-state performance32.059.681.0intel_cpufreq performance32.058.382.0p-state powersave31.055.274.0intel_cpufreq schedutil0.034.147.0OpenBenchmarking.orgCelsius, Fewer Is BetterKvazaar 2.1CPU Temperature Monitor20406080100

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 1080pintel_cpufreq schedutilp-state powersavep-state performanceintel_cpufreq performance246810SE +/- 0.049, N = 3SE +/- 0.056, N = 3SE +/- 0.022, N = 3SE +/- 0.021, N = 35.2687.6647.6707.7321. (CXX) g++ options: -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
MinAvgMaxintel_cpufreq performance2.7110.3178.4p-state performance2.9109.6178.4p-state powersave2.8108.6182.0intel_cpufreq schedutil2.871.7144.6OpenBenchmarking.orgWatts, Fewer Is BetterSVT-AV1 0.8.7CPU Power Consumption Monitor501001502002501. intel_cpufreq performance: Approximate power consumption of 2758 Joules per run.2. p-state performance: Approximate power consumption of 2776 Joules per run.3. p-state powersave: Approximate power consumption of 2751 Joules per run.4. intel_cpufreq schedutil: Approximate power consumption of 2509 Joules per run.
MinAvgMaxintel_cpufreq performance32.063.686.0p-state performance32.062.884.0p-state powersave31.060.981.0intel_cpufreq schedutil28.046.580.0OpenBenchmarking.orgCelsius, Fewer Is BetterSVT-AV1 0.8.7CPU Temperature Monitor20406080100

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: 2intel_cpufreq schedutilintel_cpufreq performancep-state powersavep-state performance510152025SE +/- 0.19, N = 3SE +/- 0.23, N = 3SE +/- 0.25, N = 3SE +/- 0.05, N = 321.6721.6221.4121.121. (CXX) g++ options: -O3 -fPIC -lm
MinAvgMaxp-state performance2.8100.2214.8p-state powersave2.899.2214.5intel_cpufreq performance2.898.9218.9intel_cpufreq schedutil2.697.2215.5OpenBenchmarking.orgWatts, Fewer Is Betterlibavif avifenc 0.9.0CPU Power Consumption Monitor601201802403001. p-state performance: Approximate power consumption of 2538 Joules per run.2. p-state powersave: Approximate power consumption of 2546 Joules per run.3. intel_cpufreq performance: Approximate power consumption of 2538 Joules per run.4. intel_cpufreq schedutil: Approximate power consumption of 2496 Joules per run.
MinAvgMaxintel_cpufreq performance28.062.290.0p-state powersave27.061.189.0p-state performance29.059.088.0intel_cpufreq schedutil25.056.286.0OpenBenchmarking.orgCelsius, Fewer Is Betterlibavif avifenc 0.9.0CPU Temperature Monitor20406080100

Selenium

This test profile uses the Selenium WebDriver for running various browser benchmarks in different available web browsers such as Mozilla Firefox and Google Chrome. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterSeleniumBenchmark: Kraken - Browser: Firefoxintel_cpufreq schedutilp-state powersaveintel_cpufreq performancep-state performance2004006008001000SE +/- 8.68, N = 3SE +/- 0.82, N = 3SE +/- 0.78, N = 3SE +/- 0.35, N = 3774.8611.1611.0609.01. firefox 96.0
MinAvgMaxintel_cpufreq performance2.620.440.7p-state performance2.720.240.5p-state powersave2.618.537.8intel_cpufreq schedutil2.517.842.3OpenBenchmarking.orgWatts, Fewer Is BetterSeleniumCPU Power Consumption Monitor12243648601. intel_cpufreq performance: Approximate power consumption of 495 Joules per run.2. p-state performance: Approximate power consumption of 499 Joules per run.3. p-state powersave: Approximate power consumption of 455 Joules per run.4. intel_cpufreq schedutil: Approximate power consumption of 499 Joules per run.
MinAvgMaxintel_cpufreq performance21.032.357.0p-state performance23.029.854.0p-state powersave20.029.051.0intel_cpufreq schedutil21.028.451.0OpenBenchmarking.orgCelsius, Fewer Is BetterSeleniumCPU Temperature Monitor1632486480

ParaView

This test runs ParaView benchmarks: an open-source data analytics and visualization application. Paraview describes itself as "an open-source, multi-platform data analysis and visualization application. ParaView users can quickly build visualizations to analyze their data using qualitative and quantitative techniques." Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiVoxels / Sec, More Is BetterParaView 5.9Test: Wavelet Volume - Resolution: 1920 x 1080intel_cpufreq schedutilp-state powersavep-state performanceintel_cpufreq performance2004006008001000SE +/- 8.36, N = 4SE +/- 4.52, N = 4SE +/- 0.15, N = 4SE +/- 0.29, N = 4822.17836.351015.371015.85
MinAvgMaxp-state performance2.719.936.4intel_cpufreq performance2.719.735.7p-state powersave2.613.935.2intel_cpufreq schedutil2.613.534.8OpenBenchmarking.orgWatts, Fewer Is BetterParaView 5.9CPU Power Consumption Monitor10203040501. p-state performance: Approximate power consumption of 348 Joules per run.2. intel_cpufreq performance: Approximate power consumption of 344 Joules per run.3. p-state powersave: Approximate power consumption of 271 Joules per run.4. intel_cpufreq schedutil: Approximate power consumption of 269 Joules per run.
MinAvgMaxp-state performance23.028.062.0p-state powersave23.027.457.0intel_cpufreq performance24.027.455.0intel_cpufreq schedutil23.026.251.0OpenBenchmarking.orgCelsius, Fewer Is BetterParaView 5.9CPU Temperature Monitor20406080100

OpenBenchmarking.orgFrames / Sec, More Is BetterParaView 5.9Test: Wavelet Volume - Resolution: 1920 x 1080intel_cpufreq schedutilp-state powersavep-state performanceintel_cpufreq performance1428425670SE +/- 0.52, N = 4SE +/- 0.28, N = 4SE +/- 0.01, N = 4SE +/- 0.02, N = 451.3952.2763.4663.49

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 3.2Encoder Mode: Speed 8 Realtime - Input: Bosphorus 1080pintel_cpufreq schedutilp-state powersavep-state performanceintel_cpufreq performance4080120160200SE +/- 0.06, N = 3SE +/- 1.18, N = 15SE +/- 0.48, N = 8SE +/- 0.32, N = 828.5494.99161.46161.591. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
MinAvgMaxp-state performance2.749.7101.1intel_cpufreq performance2.849.3101.6p-state powersave2.723.752.9intel_cpufreq schedutil2.77.19.7OpenBenchmarking.orgWatts, Fewer Is BetterAOM AV1 3.2CPU Power Consumption Monitor204060801001. p-state performance: Approximate power consumption of 397 Joules per run.2. intel_cpufreq performance: Approximate power consumption of 395 Joules per run.3. p-state powersave: Approximate power consumption of 251 Joules per run.4. intel_cpufreq schedutil: Approximate power consumption of 185 Joules per run.
MinAvgMaxintel_cpufreq performance28.040.658.0p-state performance28.039.155.0p-state powersave25.032.149.0intel_cpufreq schedutil23.023.825.0OpenBenchmarking.orgCelsius, Fewer Is BetterAOM AV1 3.2CPU Temperature Monitor1632486480

Kvazaar

This is a test of Kvazaar as a CPU-based H.265/HEVC 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 2.1Video Input: Bosphorus 1080p - Video Preset: Slowintel_cpufreq schedutilp-state powersavep-state performanceintel_cpufreq performance1224364860SE +/- 0.20, N = 3SE +/- 0.18, N = 4SE +/- 0.05, N = 4SE +/- 0.16, N = 422.0550.2050.8851.161. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
MinAvgMaxintel_cpufreq performance2.8108.1150.6p-state performance2.9107.7150.2p-state powersave2.7102.7153.6intel_cpufreq schedutil2.632.068.1OpenBenchmarking.orgWatts, Fewer Is BetterKvazaar 2.1CPU Power Consumption Monitor40801201602001. intel_cpufreq performance: Approximate power consumption of 1703 Joules per run.2. p-state performance: Approximate power consumption of 1724 Joules per run.3. p-state powersave: Approximate power consumption of 1644 Joules per run.4. intel_cpufreq schedutil: Approximate power consumption of 1003 Joules per run.
MinAvgMaxintel_cpufreq performance33.059.481.0p-state performance32.057.178.0p-state powersave31.056.476.0intel_cpufreq schedutil0.035.250.0OpenBenchmarking.orgCelsius, Fewer Is BetterKvazaar 2.1CPU Temperature Monitor20406080100

ParaView

This test runs ParaView benchmarks: an open-source data analytics and visualization application. Paraview describes itself as "an open-source, multi-platform data analysis and visualization application. ParaView users can quickly build visualizations to analyze their data using qualitative and quantitative techniques." Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiPolys / Sec, More Is BetterParaView 5.9Test: Wavelet Contour - Resolution: 1920 x 1080p-state powersavep-state performanceintel_cpufreq schedutilintel_cpufreq performance110220330440550SE +/- 0.32, N = 3SE +/- 0.44, N = 3SE +/- 0.13, N = 3SE +/- 0.98, N = 3503.02503.98505.46506.07
MinAvgMaxp-state performance2.923.237.8intel_cpufreq performance2.722.939.4p-state powersave2.718.737.3intel_cpufreq schedutil2.718.634.9OpenBenchmarking.orgWatts, Fewer Is BetterParaView 5.9CPU Power Consumption Monitor11223344551. p-state performance: Approximate power consumption of 510 Joules per run.2. intel_cpufreq performance: Approximate power consumption of 503 Joules per run.3. p-state powersave: Approximate power consumption of 417 Joules per run.4. intel_cpufreq schedutil: Approximate power consumption of 415 Joules per run.
MinAvgMaxp-state performance23.032.062.0intel_cpufreq performance24.029.759.0intel_cpufreq schedutil0.029.157.0p-state powersave23.026.359.0OpenBenchmarking.orgCelsius, Fewer Is BetterParaView 5.9CPU Temperature Monitor20406080100

OpenBenchmarking.orgFrames / Sec, More Is BetterParaView 5.9Test: Wavelet Contour - Resolution: 1920 x 1080p-state powersavep-state performanceintel_cpufreq schedutilintel_cpufreq performance1122334455SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.10, N = 348.2748.3648.5148.56

Selenium

This test profile uses the Selenium WebDriver for running various browser benchmarks in different available web browsers such as Mozilla Firefox and Google Chrome. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterSeleniumBenchmark: Kraken - Browser: Google Chromeintel_cpufreq schedutilp-state performancep-state powersaveintel_cpufreq performance120240360480600SE +/- 1.70, N = 3SE +/- 2.87, N = 3SE +/- 0.38, N = 3SE +/- 1.28, N = 3556.3427.4425.4423.91. chrome 97.0.4692.71
MinAvgMaxp-state performance2.619.250.9intel_cpufreq performance2.615.638.6p-state powersave2.514.336.3intel_cpufreq schedutil1.513.031.1OpenBenchmarking.orgWatts, Fewer Is BetterSeleniumCPU Power Consumption Monitor14284256701. p-state performance: Approximate power consumption of 409 Joules per run.2. intel_cpufreq performance: Approximate power consumption of 328 Joules per run.3. p-state powersave: Approximate power consumption of 310 Joules per run.4. intel_cpufreq schedutil: Approximate power consumption of 308 Joules per run.
MinAvgMaxp-state performance22.030.462.0intel_cpufreq schedutil23.029.261.0intel_cpufreq performance23.028.062.0p-state powersave20.027.359.0OpenBenchmarking.orgCelsius, Fewer Is BetterSeleniumCPU Temperature Monitor20406080100

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 1080pintel_cpufreq schedutilp-state powersavep-state performanceintel_cpufreq performance20406080100SE +/- 0.33, N = 3SE +/- 0.16, N = 6SE +/- 0.16, N = 6SE +/- 0.22, N = 624.8176.0780.6180.701. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
MinAvgMaxintel_cpufreq performance2.982.1131.6p-state performance2.881.4130.2p-state powersave2.871.1117.7intel_cpufreq schedutil2.613.633.8OpenBenchmarking.orgWatts, Fewer Is Betterx265 3.4CPU Power Consumption Monitor40801201602001. intel_cpufreq performance: Approximate power consumption of 944 Joules per run.2. p-state performance: Approximate power consumption of 936 Joules per run.3. p-state powersave: Approximate power consumption of 853 Joules per run.4. intel_cpufreq schedutil: Approximate power consumption of 385 Joules per run.
MinAvgMaxintel_cpufreq performance32.050.867.0p-state performance31.050.873.0p-state powersave31.048.069.0intel_cpufreq schedutil27.030.534.0OpenBenchmarking.orgCelsius, Fewer Is Betterx265 3.4CPU Temperature Monitor20406080100

Kvazaar

This is a test of Kvazaar as a CPU-based H.265/HEVC 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 2.1Video Input: Bosphorus 1080p - Video Preset: Very Fastintel_cpufreq schedutilp-state powersavep-state performanceintel_cpufreq performance20406080100SE +/- 0.07, N = 3SE +/- 0.26, N = 7SE +/- 0.23, N = 7SE +/- 0.14, N = 724.8297.37102.14102.311. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
MinAvgMaxp-state performance2.790.8157.3intel_cpufreq performance2.890.4157.2p-state powersave2.880.2146.5intel_cpufreq schedutil2.513.630.9OpenBenchmarking.orgWatts, Fewer Is BetterKvazaar 2.1CPU Power Consumption Monitor40801201602001. p-state performance: Approximate power consumption of 895 Joules per run.2. intel_cpufreq performance: Approximate power consumption of 904 Joules per run.3. p-state powersave: Approximate power consumption of 814 Joules per run.4. intel_cpufreq schedutil: Approximate power consumption of 385 Joules per run.
MinAvgMaxp-state performance31.053.077.0intel_cpufreq performance32.052.877.0p-state powersave28.049.674.0intel_cpufreq schedutil25.028.832.0OpenBenchmarking.orgCelsius, Fewer Is BetterKvazaar 2.1CPU Temperature Monitor20406080100

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: 6intel_cpufreq schedutilp-state powersavep-state performanceintel_cpufreq performance246810SE +/- 0.032, N = 5SE +/- 0.028, N = 6SE +/- 0.027, N = 6SE +/- 0.028, N = 68.5298.2398.2278.1791. (CXX) g++ options: -O3 -fPIC -lm
MinAvgMaxp-state performance2.968.3208.7intel_cpufreq performance2.967.1211.1p-state powersave2.867.1216.3intel_cpufreq schedutil2.864.2209.7OpenBenchmarking.orgWatts, Fewer Is Betterlibavif avifenc 0.9.0CPU Power Consumption Monitor601201802403001. p-state performance: Approximate power consumption of 842 Joules per run.2. intel_cpufreq performance: Approximate power consumption of 828 Joules per run.3. p-state powersave: Approximate power consumption of 828 Joules per run.4. intel_cpufreq schedutil: Approximate power consumption of 809 Joules per run.
MinAvgMaxintel_cpufreq schedutil28.049.684.0p-state performance29.049.385.0p-state powersave29.048.886.0intel_cpufreq performance29.048.785.0OpenBenchmarking.orgCelsius, Fewer Is Betterlibavif avifenc 0.9.0CPU Temperature Monitor20406080100

Selenium

This test profile uses the Selenium WebDriver for running various browser benchmarks in different available web browsers such as Mozilla Firefox and Google Chrome. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterSeleniumBenchmark: WASM imageConvolute - Browser: Firefoxintel_cpufreq performanceintel_cpufreq schedutilp-state powersavep-state performance48121620SE +/- 0.14, N = 7SE +/- 0.03, N = 6SE +/- 0.03, N = 6SE +/- 0.03, N = 716.716.616.616.51. firefox 96.0
MinAvgMaxp-state performance2.815.740.9intel_cpufreq performance2.815.740.6p-state powersave2.613.438.1intel_cpufreq schedutil2.711.231.6OpenBenchmarking.orgWatts, Fewer Is BetterSeleniumCPU Power Consumption Monitor11223344551. p-state performance: Approximate power consumption of 162 Joules per run.2. intel_cpufreq performance: Approximate power consumption of 161 Joules per run.3. p-state powersave: Approximate power consumption of 143 Joules per run.4. intel_cpufreq schedutil: Approximate power consumption of 133 Joules per run.
MinAvgMaxp-state powersave20.027.655.0p-state performance23.027.557.0intel_cpufreq performance23.026.240.0intel_cpufreq schedutil20.023.528.0OpenBenchmarking.orgCelsius, Fewer Is BetterSeleniumCPU Temperature Monitor1632486480

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 3.2Encoder Mode: Speed 10 Realtime - Input: Bosphorus 1080pintel_cpufreq schedutilp-state powersaveintel_cpufreq performancep-state performance50100150200250SE +/- 0.11, N = 3SE +/- 1.93, N = 15SE +/- 0.41, N = 9SE +/- 0.57, N = 938.69149.39205.66206.541. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
MinAvgMaxp-state performance3.041.292.9intel_cpufreq performance2.941.292.3p-state powersave2.726.359.5intel_cpufreq schedutil2.87.011.8OpenBenchmarking.orgWatts, Fewer Is BetterAOM AV1 3.2CPU Power Consumption Monitor204060801001. p-state performance: Approximate power consumption of 298 Joules per run.2. intel_cpufreq performance: Approximate power consumption of 302 Joules per run.3. p-state powersave: Approximate power consumption of 219 Joules per run.4. intel_cpufreq schedutil: Approximate power consumption of 145 Joules per run.
MinAvgMaxintel_cpufreq performance31.041.056.0p-state performance29.038.653.0p-state powersave27.034.750.0intel_cpufreq schedutil28.031.736.0OpenBenchmarking.orgCelsius, Fewer Is BetterAOM AV1 3.2CPU Temperature Monitor1632486480

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 3.2Preset: Thoroughintel_cpufreq schedutilp-state powersaveintel_cpufreq performancep-state performance246810SE +/- 0.0067, N = 6SE +/- 0.0036, N = 6SE +/- 0.0012, N = 6SE +/- 0.0024, N = 66.98496.93626.93596.92421. (CXX) g++ options: -O3 -flto -pthread
MinAvgMaxintel_cpufreq performance2.677.3212.0p-state performance2.877.3213.2intel_cpufreq schedutil2.776.8211.6p-state powersave1.575.1212.3OpenBenchmarking.orgWatts, Fewer Is BetterASTC Encoder 3.2CPU Power Consumption Monitor601201802403001. intel_cpufreq performance: Approximate power consumption of 851 Joules per run.2. p-state performance: Approximate power consumption of 850 Joules per run.3. intel_cpufreq schedutil: Approximate power consumption of 845 Joules per run.4. p-state powersave: Approximate power consumption of 813 Joules per run.
MinAvgMaxp-state powersave23.051.781.0intel_cpufreq performance23.050.282.0p-state performance24.049.781.0intel_cpufreq schedutil24.044.878.0OpenBenchmarking.orgCelsius, Fewer Is BetterASTC Encoder 3.2CPU Temperature Monitor20406080100

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 1080pintel_cpufreq schedutilp-state powersavep-state performanceintel_cpufreq performance20406080100SE +/- 0.42, N = 4SE +/- 0.41, N = 6SE +/- 0.16, N = 6SE +/- 0.34, N = 651.3793.9999.6599.711. (CXX) g++ options: -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
MinAvgMaxp-state performance2.988.1155.3intel_cpufreq performance2.987.4157.0p-state powersave2.780.2145.8intel_cpufreq schedutil2.543.880.5OpenBenchmarking.orgWatts, Fewer Is BetterSVT-AV1 0.8.7CPU Power Consumption Monitor40801201602001. p-state performance: Approximate power consumption of 910 Joules per run.2. intel_cpufreq performance: Approximate power consumption of 903 Joules per run.3. p-state powersave: Approximate power consumption of 869 Joules per run.4. intel_cpufreq schedutil: Approximate power consumption of 712 Joules per run.
MinAvgMaxp-state performance31.053.380.0p-state powersave31.052.076.0intel_cpufreq performance31.052.081.0intel_cpufreq schedutil22.035.655.0OpenBenchmarking.orgCelsius, Fewer Is BetterSVT-AV1 0.8.7CPU Temperature Monitor20406080100

Selenium

This test profile uses the Selenium WebDriver for running various browser benchmarks in different available web browsers such as Mozilla Firefox and Google Chrome. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterSeleniumBenchmark: WASM imageConvolute - Browser: Google Chromep-state powersaveintel_cpufreq schedutilintel_cpufreq performancep-state performance48121620SE +/- 0.08, N = 6SE +/- 0.02, N = 6SE +/- 0.03, N = 7SE +/- 0.06, N = 717.9317.8817.7617.761. chrome 97.0.4692.71
MinAvgMaxp-state performance2.710.025.0intel_cpufreq performance2.67.824.1intel_cpufreq schedutil2.66.723.4p-state powersave2.66.521.6OpenBenchmarking.orgWatts, Fewer Is BetterSeleniumCPU Power Consumption Monitor8162432401. p-state performance: Approximate power consumption of 102 Joules per run.2. intel_cpufreq performance: Approximate power consumption of 80 Joules per run.3. intel_cpufreq schedutil: Approximate power consumption of 71 Joules per run.4. p-state powersave: Approximate power consumption of 69 Joules per run.
MinAvgMaxp-state performance21.024.942.0intel_cpufreq performance0.024.757.0intel_cpufreq schedutil20.022.946.0p-state powersave20.021.924.0OpenBenchmarking.orgCelsius, Fewer Is BetterSeleniumCPU Temperature Monitor1632486480

OpenJPEG

OpenJPEG is an open-source JPEG 2000 codec written in the C programming language. The default input for this test profile is the NASA/JPL-Caltech/MSSS Curiosity panorama 717MB TIFF image file converting to JPEG2000 format. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenJPEG 2.4Encode: NASA Curiosity Panorama M34intel_cpufreq schedutilp-state powersaveintel_cpufreq performancep-state performance30K60K90K120K150KSE +/- 1026.14, N = 5SE +/- 625.34, N = 8SE +/- 16.41, N = 8SE +/- 24.53, N = 81255337281850027500201. (CXX) g++ options: -rdynamic
MinAvgMaxintel_cpufreq performance2.953.9129.8p-state performance3.053.7129.4p-state powersave2.834.079.1intel_cpufreq schedutil2.722.065.5OpenBenchmarking.orgWatts, Fewer Is BetterOpenJPEG 2.4CPU Power Consumption Monitor40801201602001. intel_cpufreq performance: Approximate power consumption of 451 Joules per run.2. p-state performance: Approximate power consumption of 450 Joules per run.3. p-state powersave: Approximate power consumption of 318 Joules per run.4. intel_cpufreq schedutil: Approximate power consumption of 295 Joules per run.
MinAvgMaxintel_cpufreq performance30.044.967.0p-state performance30.044.066.0p-state powersave30.037.857.0intel_cpufreq schedutil26.033.953.0OpenBenchmarking.orgCelsius, Fewer Is BetterOpenJPEG 2.4CPU Temperature Monitor20406080100

Kvazaar

This is a test of Kvazaar as a CPU-based H.265/HEVC 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 2.1Video Input: Bosphorus 1080p - Video Preset: Ultra Fastintel_cpufreq schedutilp-state powersavep-state performanceintel_cpufreq performance4080120160200SE +/- 0.39, N = 4SE +/- 0.68, N = 9SE +/- 0.33, N = 9SE +/- 0.29, N = 942.52181.32187.24187.351. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
MinAvgMaxintel_cpufreq performance2.871.9162.9p-state performance2.871.0166.3p-state powersave2.866.7157.2intel_cpufreq schedutil2.513.134.8OpenBenchmarking.orgWatts, Fewer Is BetterKvazaar 2.1CPU Power Consumption Monitor501001502002501. intel_cpufreq performance: Approximate power consumption of 519 Joules per run.2. p-state performance: Approximate power consumption of 513 Joules per run.3. p-state powersave: Approximate power consumption of 489 Joules per run.4. intel_cpufreq schedutil: Approximate power consumption of 239 Joules per run.
MinAvgMaxp-state powersave28.046.173.0intel_cpufreq performance31.046.074.0p-state performance30.045.271.0intel_cpufreq schedutil23.026.228.0OpenBenchmarking.orgCelsius, Fewer Is BetterKvazaar 2.1CPU Temperature Monitor20406080100

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, Losslessintel_cpufreq schedutilp-state powersaveintel_cpufreq performancep-state performance0.97921.95842.93763.91684.896SE +/- 0.005, N = 8SE +/- 0.010, N = 8SE +/- 0.015, N = 8SE +/- 0.011, N = 84.3524.2774.2624.2321. (CXX) g++ options: -O3 -fPIC -lm
MinAvgMaxp-state performance2.728.9128.8intel_cpufreq performance2.728.6128.9p-state powersave2.728.5130.0intel_cpufreq schedutil2.628.4126.6OpenBenchmarking.orgWatts, Fewer Is Betterlibavif avifenc 0.9.0CPU Power Consumption Monitor40801201602001. p-state performance: Approximate power consumption of 242 Joules per run.2. intel_cpufreq performance: Approximate power consumption of 236 Joules per run.3. p-state powersave: Approximate power consumption of 239 Joules per run.4. intel_cpufreq schedutil: Approximate power consumption of 238 Joules per run.
MinAvgMaxp-state performance24.038.271.0p-state powersave25.037.771.0intel_cpufreq performance24.034.869.0intel_cpufreq schedutil24.033.370.0OpenBenchmarking.orgCelsius, Fewer Is Betterlibavif avifenc 0.9.0CPU Temperature Monitor20406080100

ASTC Encoder

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

OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 3.2Preset: Mediumintel_cpufreq schedutilp-state powersaveintel_cpufreq performancep-state performance0.76181.52362.28543.04723.809SE +/- 0.0035, N = 9SE +/- 0.0035, N = 9SE +/- 0.0018, N = 9SE +/- 0.0016, N = 93.38583.36053.34943.33961. (CXX) g++ options: -O3 -flto -pthread
MinAvgMaxp-state performance2.827.5119.7intel_cpufreq performance2.627.2119.7p-state powersave2.627.1119.8intel_cpufreq schedutil2.626.9119.6OpenBenchmarking.orgWatts, Fewer Is BetterASTC Encoder 3.2CPU Power Consumption Monitor40801201602001. p-state performance: Approximate power consumption of 202 Joules per run.2. intel_cpufreq performance: Approximate power consumption of 203 Joules per run.3. p-state powersave: Approximate power consumption of 202 Joules per run.4. intel_cpufreq schedutil: Approximate power consumption of 200 Joules per run.
MinAvgMaxp-state performance24.036.070.0intel_cpufreq schedutil24.035.362.0intel_cpufreq performance23.034.659.0p-state powersave24.031.669.0OpenBenchmarking.orgCelsius, Fewer Is BetterASTC Encoder 3.2CPU Temperature Monitor20406080100

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: 10intel_cpufreq schedutilp-state powersaveintel_cpufreq performancep-state performance0.58641.17281.75922.34562.932SE +/- 0.008, N = 10SE +/- 0.005, N = 10SE +/- 0.005, N = 10SE +/- 0.005, N = 102.6062.4812.4742.4641. (CXX) g++ options: -O3 -fPIC -lm
MinAvgMaxintel_cpufreq performance2.823.296.0p-state performance2.822.995.0p-state powersave2.622.997.1intel_cpufreq schedutil2.622.491.2OpenBenchmarking.orgWatts, Fewer Is Betterlibavif avifenc 0.9.0CPU Power Consumption Monitor204060801001. intel_cpufreq performance: Approximate power consumption of 151 Joules per run.2. p-state performance: Approximate power consumption of 147 Joules per run.3. p-state powersave: Approximate power consumption of 149 Joules per run.4. intel_cpufreq schedutil: Approximate power consumption of 148 Joules per run.
MinAvgMaxp-state powersave28.038.374.0intel_cpufreq schedutil27.035.873.0p-state performance28.035.177.0intel_cpufreq performance27.035.174.0OpenBenchmarking.orgCelsius, Fewer Is Betterlibavif avifenc 0.9.0CPU Temperature Monitor20406080100

CPU Temperature Monitor

OpenBenchmarking.orgCelsiusCPU Temperature MonitorPhoronix Test Suite System Monitoringp-state performancep-state powersaveintel_cpufreq performanceintel_cpufreq schedutil20406080100Min: 0 / Avg: 60.7 / Max: 100Min: 0 / Avg: 58.87 / Max: 98Min: 0 / Avg: 54.56 / Max: 100Min: 0 / Avg: 51.98 / Max: 100

CPU Power Consumption Monitor

OpenBenchmarking.orgWattsCPU Power Consumption MonitorPhoronix Test Suite System Monitoringp-state performancep-state powersaveintel_cpufreq performanceintel_cpufreq schedutil4080120160200Min: 1.58 / Avg: 109.02 / Max: 228.01Min: 1.33 / Avg: 103.68 / Max: 227.75Min: 1.57 / Avg: 92.22 / Max: 228.32Min: 1.42 / Avg: 84.21 / Max: 228.12

p-state performance

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-pWTZs6/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-pWTZs6/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: intel_pstate performance (EPP: performance) - CPU Microcode: 0x15 - Thermald 2.4.6
Python Notes: Python 3.9.9
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 15 January 2022 06:29 by user phoronix.

p-state powersave

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-pWTZs6/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-pWTZs6/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: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0x15 - Thermald 2.4.6
Python Notes: Python 3.9.9
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 13 January 2022 09:20 by user phoronix.

intel_cpufreq performance

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-pWTZs6/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-pWTZs6/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: intel_cpufreq performance (EPP: balance_performance) - CPU Microcode: 0x15 - Thermald 2.4.6
Python Notes: Python 3.9.9
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 14 January 2022 14:21 by user phoronix.

intel_cpufreq schedutil

Processor: Intel Core i9-12900K @ 6.50GHz (16 Cores / 24 Threads), Motherboard: ASUS ROG STRIX Z690-E GAMING WIFI (0811 BIOS), Chipset: Intel Device 7aa7, Memory: 64GB, Disk: 1000GB Western Digital WDS100T1X0E-00AFY0, Graphics: ASUS Intel ADL-S GT1 3GB (1550MHz), Audio: Intel Device 7ad0, Monitor: ASUS VP28U, Network: Intel I225-V + Intel Wi-Fi 6 AX210/AX211/AX411

OS: Ubuntu 22.04, Kernel: 5.16.0-051600-generic (x86_64), Desktop: GNOME Shell 40.5, Display Server: X Server 1.20.13 + Wayland, OpenGL: 4.6 Mesa 22.0.0-devel (git-074bde9 2022-01-11 jammy-oibaf-ppa), Vulkan: 1.2.199, 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-pWTZs6/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-pWTZs6/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: intel_cpufreq schedutil (EPP: balance_performance) - CPU Microcode: 0x15 - Thermald 2.4.6
Python Notes: Python 3.9.9
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 14 January 2022 04:56 by user phoronix.