Xeon Scalable Ice Lake P-State Governor

Intel Xeon Platinum 8380 Ice Lake P-State CPU frequency scaling Linux benchmarks 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 2105267-IB-XEONSCALA38
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 3 Tests
BLAS (Basic Linear Algebra Sub-Routine) Tests 4 Tests
C++ Boost Tests 2 Tests
Timed Code Compilation 5 Tests
C/C++ Compiler Tests 10 Tests
CPU Massive 14 Tests
Creator Workloads 12 Tests
Encoding 6 Tests
Fortran Tests 7 Tests
Game Development 4 Tests
HPC - High Performance Computing 16 Tests
LAPACK (Linear Algebra Pack) Tests 4 Tests
Machine Learning 2 Tests
Molecular Dynamics 6 Tests
MPI Benchmarks 5 Tests
Multi-Core 26 Tests
NVIDIA GPU Compute 4 Tests
Intel oneAPI 4 Tests
OpenMPI Tests 11 Tests
Programmer / Developer System Benchmarks 7 Tests
Python Tests 5 Tests
Renderers 2 Tests
Scientific Computing 8 Tests
Server CPU Tests 11 Tests
Video Encoding 6 Tests
Common Workstation Benchmarks 2 Tests

Statistics

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

Graph Settings

Force Line Graphs Where Applicable
Convert To Scalar Where Applicable
Prefer Vertical Bar Graphs
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 powersave
May 23 2021
  15 Hours, 42 Minutes
P-State performance
May 24 2021
  11 Hours, 14 Minutes
intel_cpufreq schedutil
May 24 2021
  15 Hours, 54 Minutes
intel_cpufreq performance
May 25 2021
  13 Hours, 43 Minutes
Invert Hiding All Results Option
  14 Hours, 8 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):


Xeon Scalable Ice Lake P-State GovernorOpenBenchmarking.orgPhoronix Test Suite2 x Intel Xeon Platinum 8380 @ 3.40GHz (80 Cores / 160 Threads)Intel M50CYP2SB2U (SE5C6200.86B.0022.D08.2103221623 BIOS)Intel Device 099816 x 32 GB DDR4-3200MT/s Hynix HMA84GR7CJR4N-XN800GB INTEL SSDPF21Q800GBASPEED2 x Intel X710 for 10GBASE-T + 2 x Intel E810-C for QSFPUbuntu 21.045.11.0-17-generic (x86_64)GNOME Shell 3.38.4X Server1.0.2GCC 10.3.0ext41024x768ProcessorMotherboardChipsetMemoryDiskGraphicsNetworkOSKernelDesktopDisplay ServerVulkanCompilerFile-SystemScreen ResolutionXeon Scalable Ice Lake P-State Governor BenchmarksSystem Logs- Transparent Huge Pages: madvise- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-gcn/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-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 powersave: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xd000270 - P-State performance: Scaling Governor: intel_pstate performance - CPU Microcode: 0xd000270 - intel_cpufreq schedutil: Scaling Governor: intel_cpufreq schedutil - CPU Microcode: 0xd000270 - intel_cpufreq performance: Scaling Governor: intel_cpufreq performance - CPU Microcode: 0xd000270 - Python 3.9.4- itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

P-State powersaveP-State performanceintel_cpufreq schedutilintel_cpufreq performanceResult OverviewPhoronix Test Suite100%148%195%243%290%AOM AV1KvazaarPostgreSQL pgbenchSVT-VP9SVT-HEVCSVT-AV1PJSIPTimed Godot Game Engine CompilationDarmstadt Automotive Parallel Heterogeneous SuiteZstd CompressionArrayFireOpenVKLlibavif avifencTimed Linux Kernel CompilationTimed Node.js CompilationRodiniaTensorFlow LiteNAS Parallel BenchmarksQuantum ESPRESSOEmbreeOSPrayBlenderTimed LLVM CompilationIntel Open Image DenoiseTimed Mesa CompilationOpenFOAMONNX RuntimeHigh Performance Conjugate GradientStockfishGROMACSLAMMPS Molecular Dynamics SimulatorLiquid-DSPXcompact3d Incompact3dRELIONNAMDNWChemWRF

P-State powersaveP-State performanceintel_cpufreq schedutilintel_cpufreq performancePer Watt Result OverviewPhoronix Test Suite100%107%113%120%126%AOM AV1NAS Parallel BenchmarksSVT-HEVCIntel Open Image DenoiseOSPrayZstd CompressionKvazaarOpenVKLSVT-AV1StockfishEmbreeArrayFireDarmstadt Automotive Parallel Heterogeneous SuitePJSIPSVT-VP9ONNX RuntimeLiquid-DSPHigh Performance Conjugate GradientGROMACSLAMMPS Molecular Dynamics SimulatorP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.M

Xeon Scalable Ice Lake P-State Governorcompress-zstd: 8, Long Mode - Compression Speedkvazaar: Bosphorus 4K - Very Fastaom-av1: Speed 6 Realtime - Bosphorus 4Kaom-av1: Speed 8 Realtime - Bosphorus 4Kpgbench: 1000 - 250 - Read Write - Average Latencypgbench: 1000 - 250 - Read Writeaom-av1: Speed 9 Realtime - Bosphorus 4Kpjsip: OPTIONS, Statefulpgbench: 1000 - 100 - Read Write - Average Latencypgbench: 1000 - 100 - Read Writekvazaar: Bosphorus 4K - Ultra Fastsvt-hevc: 10 - Bosphorus 1080psvt-vp9: PSNR/SSIM Optimized - Bosphorus 1080psvt-vp9: VMAF Optimized - Bosphorus 1080pdaphne: OpenMP - Points2Imagesvt-av1: Preset 8 - Bosphorus 4Ksvt-hevc: 7 - Bosphorus 1080pbuild-godot: Time To Compileopenvkl: vklBenchmarkStructuredVolumeopenvkl: vklBenchmarkVdbVolumeavifenc: 6, Losslessdaphne: OpenMP - Euclidean Clusteropenvkl: vklBenchmarktensorflow-lite: Mobilenet Quantbuild-linux-kernel: Time To Compileospray: NASA Streamlines - SciVisbuild-nodejs: Time To Compileembree: Pathtracer ISPC - Crownnpb: FT.Cospray: San Miguel - SciVisnpb: SP.Bnpb: LU.Ccompress-zstd: 19, Long Mode - Compression Speedqe: AUSURF112compress-zstd: 19 - Compression Speedoidn: RT.hdr_alb_nrm.3840x2160blender: BMW27 - CPU-Onlyembree: Pathtracer ISPC - Asian Dragonbuild-llvm: Unix Makefilesopenfoam: Motorbike 30Mnpb: EP.Dopenvkl: vklBenchmarkUnstructuredVolumenpb: BT.Cospray: Magnetic Reconnection - SciVisblender: Barbershop - CPU-Onlynpb: IS.Dnpb: MG.Ctensorflow-lite: Inception V4build-mesa: Time To Compileembree: Pathtracer ISPC - Asian Dragon Objrodinia: OpenMP CFD Solverpjsip: OPTIONS, Statelessonnx: shufflenet-v2-10 - OpenMP CPUnpb: CG.Coidn: RT.ldr_alb_nrm.3840x2160hpcg: compress-zstd: 19 - Decompression Speedstockfish: Total Timerodinia: OpenMP LavaMDonnx: fcn-resnet101-11 - OpenMP CPUbuild-llvm: Ninjaonnx: yolov4 - OpenMP CPUoidn: RTLightmap.hdr.4096x4096blender: Classroom - CPU-Onlyarrayfire: BLAS CPUrodinia: OpenMP Streamclusterincompact3d: input.i3d 193 Cells Per Directioncompress-zstd: 19, Long Mode - Decompression Speedgromacs: MPI CPU - water_GMX50_barelammps: 20k Atomsopenfoam: Motorbike 60Mliquid-dsp: 160 - 256 - 57liquid-dsp: 128 - 256 - 57ospray: XFrog Forest - Path Tracerospray: San Miguel - Path Tracernamd: ATPase Simulation - 327,506 Atomsnpb: SP.Cnwchem: C240 Buckyballrelion: Basic - CPUrodinia: OpenMP HotSpot3Dtensorflow-lite: Inception ResNet V2wrf: conus 2.5kmincompact3d: X3D-benchmarking input.i3dospray: NASA Streamlines - Path Tracerospray: XFrog Forest - SciVispgbench: 1000 - 250 - Read Only - Average Latencypgbench: 1000 - 250 - Read Onlypgbench: 1000 - 100 - Read Only - Average Latencypgbench: 1000 - 100 - Read Onlyliquid-dsp: 64 - 256 - 57pjsip: INVITEavifenc: 10, Losslessavifenc: 10aom-av1: Speed 6 Two-Pass - Bosphorus 4Krodinia: OpenMP Leukocytedaphne: OpenMP - NDT Mappingonnx: bertsquad-10 - OpenMP CPUonnx: super-resolution-10 - OpenMP CPUarrayfire: Conjugate Gradient CPUnpb: EP.CP-State powersaveP-State performanceintel_cpufreq schedutilintel_cpufreq performance296.013.267.3817.0710.7232341123.5937694.2832338323.03258.65206.54210.926634.5830.546168.3875.612719744382172232637.469831.3367041126.824.881125102.19766.525190989.7390.91114946.46174911.0246.71106.6982.72.8529.72106.6219199.39814.928620.971757269191166.41111.11107.732999.72116754.1668215318.98387.20924.82741421821239485.722.8740.13592563.217703112239.815196129.2724801.3872.174538.697.71011.19165662711.68.99935.495105.033073933333327013333310.3810.420.2709391313.601882.3350.266104.3395720659892.42290.41110227.7818.870.2779064340.256393329302990000025488.8335.2053.9469.049742.3050968984.2926051.901011.938.2119.0948.623.7746649361.06103621.5886304946.31576.99453.67460.4413527.23899643056.887305.7748.1571060564582999653930.3451020.7781133656.321.486142.8690.85074.0551100543.72100123544.09187300.4749.11178.5286.72.9328.40107.6307190.68514.798920.101803840197815.31114.81105.103014.77120084.2766370718.49789.08954.74642389839240261.262.9340.64712561.817713142839.423194127.3214831.4071.274539.997.81611.05545092677.99.05235.825104.763085100000329300000010.3110.450.2716891817.761888.2349.993104.1855721499885.556290.14333127.7818.870.2719241900.0811236713306613333353937.2484.3419.6946.358924.8447766266.1317610.18311.711.305.8615.903.8146572621.7237972.7403657720.53345.48260.25262.787077.7635.480193.8053.001779976282359924931.987884.7571835239.022.19012591.85767.754091970.9990.91115501.41177878.6846.11156.4981.52.7829.25102.7043191.17315.078634.301748017191705.02111.11107.392926.26117869.4967225418.75487.99274.71041743833439430.662.8840.06592594.717544618239.199194127.6884831.3872.244510.297.71211.20541792693.49.04235.792105.103082533333329146666710.3110.380.2722791642.331880349.436104.1845716329889.907290.41669727.7818.870.2858853790.0811228570300312500025408.4865.1344.0063.286743.0150467566.4546157.581015.838.2619.2048.913.7916618661.27104091.5946282646.34574.88457.02464.7113249.67869587556.750309.1348.6511067046413001631830.0141021.6282133581.321.410142.8691.08174.2420100763.11100123176.72186973.0648.31175.6983.12.9328.28106.1736191.80114.498938.091809667197821.88112.96104.512978.52120124.0567742118.51789.49054.72942338838040226.022.9340.83112609.717862947439.746197127.3324761.4071.224574.837.72711.05617482713.19.10235.849104.273096700000329340000010.3110.420.2705191830.561882.2349.028104.0885726799875.264289.97558627.7818.870.2888764620.0811231983307260000054167.2764.34010.0147.105914.7050369554.0057705.44OpenBenchmarking.org

Zstd Compression

This test measures the time needed to compress/decompress a sample file (a FreeBSD disk image - FreeBSD-12.2-RELEASE-amd64-memstick.img) using Zstd compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 8, Long Mode - Compression Speedintel_cpufreq performanceP-State performanceintel_cpufreq schedutilP-State powersave2004006008001000SE +/- 5.29, N = 3SE +/- 4.09, N = 3SE +/- 2.96, N = 3SE +/- 0.62, N = 31018.61011.9311.7296.01. (CC) gcc options: -O3 -pthread -lz -llzma

Kvazaar

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

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 4K - Video Preset: Very Fastintel_cpufreq performanceP-State performanceP-State powersaveintel_cpufreq schedutil918273645SE +/- 0.07, N = 4SE +/- 0.07, N = 4SE +/- 0.04, N = 3SE +/- 0.02, N = 338.2638.2113.2611.301. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

AOM AV1

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

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.1Encoder Mode: Speed 6 Realtime - Input: Bosphorus 4Kintel_cpufreq performanceP-State performanceP-State powersaveintel_cpufreq schedutil510152025SE +/- 0.23, N = 3SE +/- 0.11, N = 3SE +/- 0.07, N = 3SE +/- 0.02, N = 319.2019.097.385.861. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.1Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4Kintel_cpufreq performanceP-State performanceP-State powersaveintel_cpufreq schedutil1122334455SE +/- 0.52, N = 4SE +/- 0.30, N = 4SE +/- 0.02, N = 3SE +/- 0.03, N = 348.9148.6217.0715.901. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

PostgreSQL pgbench

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

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 1000 - Clients: 250 - Mode: Read Write - Average LatencyP-State performanceintel_cpufreq performanceintel_cpufreq schedutilP-State powersave3691215SE +/- 0.023, N = 3SE +/- 0.023, N = 3SE +/- 0.017, N = 3SE +/- 0.071, N = 33.7743.7913.81410.7231. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 13.0Scaling Factor: 1000 - Clients: 250 - Mode: Read WriteP-State performanceintel_cpufreq performanceintel_cpufreq schedutilP-State powersave14K28K42K56K70KSE +/- 391.43, N = 3SE +/- 405.25, N = 3SE +/- 301.39, N = 3SE +/- 156.62, N = 3664936618665726234111. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

AOM AV1

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

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.1Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4Kintel_cpufreq performanceP-State performanceP-State powersaveintel_cpufreq schedutil1428425670SE +/- 0.43, N = 5SE +/- 0.27, N = 5SE +/- 0.22, N = 3SE +/- 0.16, N = 1561.2761.0623.5921.721. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

PJSIP

PJSIP is a free and open source multimedia communication library written in C language implementing standard based protocols such as SIP, SDP, RTP, STUN, TURN, and ICE. It combines signaling protocol (SIP) with rich multimedia framework and NAT traversal functionality into high level API that is portable and suitable for almost any type of systems ranging from desktops, embedded systems, to mobile handsets. This test profile is making use of pjsip-perf with both the client/server on teh system. More details on the PJSIP benchmark at https://www.pjsip.org/high-performance-sip.htm Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgResponses Per Second, More Is BetterPJSIP 2.11Method: OPTIONS, Statefulintel_cpufreq performanceP-State performanceintel_cpufreq schedutilP-State powersave2K4K6K8K10KSE +/- 6.00, N = 3SE +/- 0.58, N = 3SE +/- 13.93, N = 3SE +/- 31.56, N = 31040910362379737691. (CC) gcc options: -lstdc++ -lssl -lcrypto -luuid -lm -lrt -lpthread -lasound -O2

PostgreSQL pgbench

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

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 1000 - Clients: 100 - Mode: Read Write - Average LatencyP-State performanceintel_cpufreq performanceintel_cpufreq schedutilP-State powersave0.96371.92742.89113.85484.8185SE +/- 0.007, N = 3SE +/- 0.004, N = 3SE +/- 0.035, N = 3SE +/- 0.009, N = 31.5881.5942.7404.2831. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 13.0Scaling Factor: 1000 - Clients: 100 - Mode: Read WriteP-State performanceintel_cpufreq performanceintel_cpufreq schedutilP-State powersave14K28K42K56K70KSE +/- 272.63, N = 3SE +/- 148.39, N = 3SE +/- 464.84, N = 3SE +/- 51.95, N = 3630496282636577233831. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

Kvazaar

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

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 4K - Video Preset: Ultra Fastintel_cpufreq performanceP-State performanceP-State powersaveintel_cpufreq schedutil1122334455SE +/- 0.56, N = 4SE +/- 0.31, N = 15SE +/- 0.14, N = 3SE +/- 0.06, N = 346.3446.3123.0320.531. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

SVT-HEVC

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

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 10 - Input: Bosphorus 1080pP-State performanceintel_cpufreq performanceintel_cpufreq schedutilP-State powersave120240360480600SE +/- 0.97, N = 11SE +/- 1.99, N = 11SE +/- 3.58, N = 15SE +/- 1.12, N = 9576.99574.88345.48258.651. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

SVT-VP9

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

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080pintel_cpufreq performanceP-State performanceintel_cpufreq schedutilP-State powersave100200300400500SE +/- 3.11, N = 13SE +/- 4.77, N = 15SE +/- 2.47, N = 15SE +/- 1.53, N = 7457.02453.67260.25206.541. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: VMAF Optimized - Input: Bosphorus 1080pintel_cpufreq performanceP-State performanceintel_cpufreq schedutilP-State powersave100200300400500SE +/- 2.50, N = 10SE +/- 2.03, N = 10SE +/- 2.52, N = 15SE +/- 1.16, N = 7464.71460.44262.78210.921. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

Darmstadt Automotive Parallel Heterogeneous Suite

DAPHNE is the Darmstadt Automotive Parallel HeterogeNEous Benchmark Suite with OpenCL / CUDA / OpenMP test cases for these automotive benchmarks for evaluating programming models in context to vehicle autonomous driving capabilities. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTest Cases Per Minute, More Is BetterDarmstadt Automotive Parallel Heterogeneous SuiteBackend: OpenMP - Kernel: Points2ImageP-State performanceintel_cpufreq performanceintel_cpufreq schedutilP-State powersave3K6K9K12K15KSE +/- 114.27, N = 15SE +/- 100.42, N = 15SE +/- 115.67, N = 12SE +/- 86.30, N = 313527.2413249.687077.766634.581. (CXX) g++ options: -O3 -std=c++11 -fopenmp

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 4KP-State performanceintel_cpufreq performanceintel_cpufreq schedutilP-State powersave1326395265SE +/- 0.24, N = 4SE +/- 0.31, N = 4SE +/- 0.47, N = 3SE +/- 0.20, N = 356.8956.7535.4830.551. (CXX) g++ options: -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie

SVT-HEVC

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

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 7 - Input: Bosphorus 1080pintel_cpufreq performanceP-State performanceintel_cpufreq schedutilP-State powersave70140210280350SE +/- 1.23, N = 10SE +/- 0.58, N = 10SE +/- 1.34, N = 15SE +/- 1.49, N = 8309.13305.77193.80168.381. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

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 CompileP-State performanceintel_cpufreq performanceintel_cpufreq schedutilP-State powersave20406080100SE +/- 0.18, N = 3SE +/- 0.28, N = 3SE +/- 0.49, N = 3SE +/- 0.95, N = 348.1648.6553.0075.61

OpenVKL

OpenVKL is the Intel Open Volume Kernel Library that offers high-performance volume computation kernels and part of the Intel oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgItems / Sec, More Is BetterOpenVKL 0.9Benchmark: vklBenchmarkStructuredVolumeintel_cpufreq performanceP-State performanceintel_cpufreq schedutilP-State powersave20M40M60M80M100MSE +/- 497134.18, N = 3SE +/- 57856.16, N = 3SE +/- 444572.22, N = 3SE +/- 799905.44, N = 41067046411060564587799762871974438MIN: 1343151 / MAX: 909146052MIN: 1396156 / MAX: 908416224MIN: 1380198 / MAX: 693620172MIN: 1304623 / MAX: 672770484

OpenBenchmarking.orgItems / Sec, More Is BetterOpenVKL 0.9Benchmark: vklBenchmarkVdbVolumeintel_cpufreq performanceP-State performanceintel_cpufreq schedutilP-State powersave6M12M18M24M30MSE +/- 349026.46, N = 15SE +/- 268896.33, N = 15SE +/- 38895.86, N = 3SE +/- 47580.68, N = 330016318299965392359924921722326MIN: 979586 / MAX: 253907928MIN: 979600 / MAX: 247803840MIN: 1060641 / MAX: 156949416MIN: 1031810 / MAX: 151043112

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, Losslessintel_cpufreq performanceP-State performanceintel_cpufreq schedutilP-State powersave918273645SE +/- 0.20, N = 3SE +/- 0.22, N = 3SE +/- 0.41, N = 3SE +/- 0.28, N = 1530.0130.3531.9937.471. (CXX) g++ options: -O3 -fPIC -lm

Darmstadt Automotive Parallel Heterogeneous Suite

DAPHNE is the Darmstadt Automotive Parallel HeterogeNEous Benchmark Suite with OpenCL / CUDA / OpenMP test cases for these automotive benchmarks for evaluating programming models in context to vehicle autonomous driving capabilities. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTest Cases Per Minute, More Is BetterDarmstadt Automotive Parallel Heterogeneous SuiteBackend: OpenMP - Kernel: Euclidean Clusterintel_cpufreq performanceP-State performanceintel_cpufreq schedutilP-State powersave2004006008001000SE +/- 1.25, N = 3SE +/- 2.39, N = 3SE +/- 9.84, N = 15SE +/- 7.84, N = 151021.621020.77884.75831.331. (CXX) g++ options: -O3 -std=c++11 -fopenmp

OpenVKL

OpenVKL is the Intel Open Volume Kernel Library that offers high-performance volume computation kernels and part of the Intel oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgItems / Sec, More Is BetterOpenVKL 0.9Benchmark: vklBenchmarkintel_cpufreq performanceP-State performanceintel_cpufreq schedutilP-State powersave2004006008001000SE +/- 2.40, N = 3SE +/- 2.67, N = 3SE +/- 8.72, N = 3SE +/- 2.19, N = 3821811718670MIN: 1 / MAX: 3226MIN: 1 / MAX: 3166MIN: 1 / MAX: 3134MIN: 1 / MAX: 2830

TensorFlow Lite

This is a benchmark of the TensorFlow Lite implementation. The current Linux support is limited to running on CPUs. This test profile is measuring the average inference time. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet Quantintel_cpufreq performanceP-State performanceintel_cpufreq schedutilP-State powersave9K18K27K36K45KSE +/- 61.65, N = 3SE +/- 117.93, N = 3SE +/- 352.77, N = 3SE +/- 711.79, N = 1233581.333656.335239.041126.8

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. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 5.10.20Time To Compileintel_cpufreq performanceP-State performanceintel_cpufreq schedutilP-State powersave612182430SE +/- 0.19, N = 7SE +/- 0.24, N = 5SE +/- 0.19, N = 14SE +/- 0.38, N = 1521.4121.4922.1924.88

OSPray

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

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: NASA Streamlines - Renderer: SciVisintel_cpufreq performanceP-State performanceintel_cpufreq schedutilP-State powersave306090120150SE +/- 0.00, N = 9SE +/- 0.00, N = 9142.86142.86125.00125.00MIN: 31.25MIN: 31.25MIN: 29.41 / MAX: 142.86MIN: 30.3 / MAX: 142.86

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 15.11Time To CompileP-State performanceintel_cpufreq performanceintel_cpufreq schedutilP-State powersave20406080100SE +/- 0.15, N = 3SE +/- 0.49, N = 3SE +/- 0.27, N = 3SE +/- 0.59, N = 390.8591.0891.86102.20

Embree

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

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer ISPC - Model: Crownintel_cpufreq performanceP-State performanceintel_cpufreq schedutilP-State powersave1632486480SE +/- 0.34, N = 5SE +/- 0.18, N = 5SE +/- 0.18, N = 5SE +/- 0.21, N = 574.2474.0667.7566.53MIN: 64.44 / MAX: 93.9MIN: 64.5 / MAX: 94.28MIN: 60.74 / MAX: 88.34MIN: 59.75 / MAX: 87.7

NAS Parallel Benchmarks

NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: FT.Cintel_cpufreq performanceP-State performanceintel_cpufreq schedutilP-State powersave20K40K60K80K100KSE +/- 63.65, N = 7SE +/- 83.85, N = 7SE +/- 807.72, N = 7SE +/- 842.11, N = 7100763.11100543.7291970.9990989.731. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.1.0

OSPray

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

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: San Miguel - Renderer: SciVisintel_cpufreq performanceP-State performanceintel_cpufreq schedutilP-State powersave20406080100SE +/- 0.00, N = 3SE +/- 0.00, N = 3100.00100.0090.9190.91MIN: 55.56 / MAX: 111.11MIN: 62.5 / MAX: 111.11MIN: 47.62 / MAX: 100MIN: 58.82 / MAX: 100

NAS Parallel Benchmarks

NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: SP.BP-State performanceintel_cpufreq performanceintel_cpufreq schedutilP-State powersave30K60K90K120K150KSE +/- 134.33, N = 9SE +/- 133.35, N = 9SE +/- 203.66, N = 8SE +/- 480.22, N = 8123544.09123176.72115501.41114946.461. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.1.0

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: LU.CP-State performanceintel_cpufreq performanceintel_cpufreq schedutilP-State powersave40K80K120K160K200KSE +/- 364.13, N = 4SE +/- 495.98, N = 4SE +/- 196.76, N = 4SE +/- 1423.68, N = 4187300.47186973.06177878.68174911.021. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.1.0

Zstd Compression

This test measures the time needed to compress/decompress a sample file (a FreeBSD disk image - FreeBSD-12.2-RELEASE-amd64-memstick.img) using Zstd compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19, Long Mode - Compression SpeedP-State performanceintel_cpufreq performanceP-State powersaveintel_cpufreq schedutil1122334455SE +/- 0.21, N = 3SE +/- 0.20, N = 3SE +/- 0.32, N = 15SE +/- 0.46, N = 649.148.346.746.11. (CC) gcc options: -O3 -pthread -lz -llzma

Quantum ESPRESSO

Quantum ESPRESSO is an integrated suite of Open-Source computer codes for electronic-structure calculations and materials modeling at the nanoscale. It is based on density-functional theory, plane waves, and pseudopotentials. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterQuantum ESPRESSO 6.7Input: AUSURF112P-State powersaveintel_cpufreq schedutilintel_cpufreq performanceP-State performance30060090012001500SE +/- 19.34, N = 9SE +/- 22.92, N = 9SE +/- 17.96, N = 9SE +/- 1.74, N = 31106.691156.491175.691178.521. (F9X) gfortran options: -lopenblas -lFoX_dom -lFoX_sax -lFoX_wxml -lFoX_common -lFoX_utils -lFoX_fsys -lfftw3 -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz

Zstd Compression

This test measures the time needed to compress/decompress a sample file (a FreeBSD disk image - FreeBSD-12.2-RELEASE-amd64-memstick.img) using Zstd compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19 - Compression SpeedP-State performanceintel_cpufreq performanceP-State powersaveintel_cpufreq schedutil20406080100SE +/- 0.75, N = 15SE +/- 0.32, N = 3SE +/- 0.55, N = 3SE +/- 0.75, N = 1586.783.182.781.51. (CC) gcc options: -O3 -pthread -lz -llzma

Intel Open Image Denoise

Open Image Denoise is a denoising library for ray-tracing and part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 1.4.0Run: RT.hdr_alb_nrm.3840x2160intel_cpufreq performanceP-State performanceP-State powersaveintel_cpufreq schedutil0.65931.31861.97792.63723.2965SE +/- 0.00, N = 5SE +/- 0.01, N = 5SE +/- 0.00, N = 4SE +/- 0.03, N = 152.932.932.852.78

Blender

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

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: BMW27 - Compute: CPU-Onlyintel_cpufreq performanceP-State performanceintel_cpufreq schedutilP-State powersave714212835SE +/- 0.15, N = 3SE +/- 0.11, N = 3SE +/- 0.27, N = 3SE +/- 0.03, N = 328.2828.4029.2529.72

Embree

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

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer ISPC - Model: Asian DragonP-State performanceP-State powersaveintel_cpufreq performanceintel_cpufreq schedutil20406080100SE +/- 0.42, N = 6SE +/- 0.79, N = 6SE +/- 0.56, N = 6SE +/- 0.80, N = 6107.63106.62106.17102.70MIN: 88.63 / MAX: 112.78MIN: 84.26 / MAX: 112.87MIN: 84.09 / MAX: 112.29MIN: 81.43 / MAX: 111.73

Timed LLVM Compilation

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 12.0Build System: Unix MakefilesP-State performanceintel_cpufreq schedutilintel_cpufreq performanceP-State powersave4080120160200SE +/- 1.07, N = 3SE +/- 1.14, N = 3SE +/- 0.59, N = 3SE +/- 1.18, N = 3190.69191.17191.80199.40

OpenFOAM

OpenFOAM is the leading free, open source software for computational fluid dynamics (CFD). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 8Input: Motorbike 30Mintel_cpufreq performanceP-State performanceP-State powersaveintel_cpufreq schedutil48121620SE +/- 0.01, N = 3SE +/- 0.15, N = 15SE +/- 0.06, N = 3SE +/- 0.14, N = 714.4914.7914.9215.071. (CXX) g++ options: -std=c++11 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -ldynamicMesh -ldecompose -lgenericPatchFields -lmetisDecomp -lscotchDecomp -llagrangian -lregionModels -lOpenFOAM -ldl -lm

NAS Parallel Benchmarks

NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.Dintel_cpufreq performanceP-State performanceintel_cpufreq schedutilP-State powersave2K4K6K8K10KSE +/- 38.79, N = 4SE +/- 60.08, N = 13SE +/- 22.19, N = 3SE +/- 65.72, N = 38938.098920.108634.308620.971. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.1.0

OpenVKL

OpenVKL is the Intel Open Volume Kernel Library that offers high-performance volume computation kernels and part of the Intel oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgItems / Sec, More Is BetterOpenVKL 0.9Benchmark: vklBenchmarkUnstructuredVolumeintel_cpufreq performanceP-State performanceP-State powersaveintel_cpufreq schedutil400K800K1200K1600K2000KSE +/- 4355.52, N = 3SE +/- 8888.13, N = 3SE +/- 19689.28, N = 3SE +/- 4960.83, N = 31809667180384017572691748017MIN: 24362 / MAX: 5849692MIN: 24013 / MAX: 5810552MIN: 18102 / MAX: 5872318MIN: 13879 / MAX: 5825120

NAS Parallel Benchmarks

NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: BT.Cintel_cpufreq performanceP-State performanceintel_cpufreq schedutilP-State powersave40K80K120K160K200KSE +/- 230.36, N = 4SE +/- 313.16, N = 4SE +/- 322.38, N = 4SE +/- 416.58, N = 4197821.88197815.31191705.02191166.411. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.1.0

OSPray

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

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: Magnetic Reconnection - Renderer: SciVisP-State performanceintel_cpufreq performanceintel_cpufreq schedutilP-State powersave306090120150SE +/- 1.64, N = 15SE +/- 1.26, N = 15SE +/- 0.00, N = 8SE +/- 0.00, N = 8114.81112.96111.11111.11MIN: 24.39 / MAX: 125MIN: 26.32 / MAX: 125MIN: 22.73MIN: 22.22

Blender

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

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Barbershop - Compute: CPU-Onlyintel_cpufreq performanceP-State performanceintel_cpufreq schedutilP-State powersave20406080100SE +/- 0.20, N = 3SE +/- 0.34, N = 3SE +/- 0.55, N = 3SE +/- 0.44, N = 3104.51105.10107.39107.73

NAS Parallel Benchmarks

NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: IS.DP-State performanceP-State powersaveintel_cpufreq performanceintel_cpufreq schedutil6001200180024003000SE +/- 15.07, N = 4SE +/- 29.00, N = 4SE +/- 5.86, N = 4SE +/- 32.51, N = 43014.772999.722978.522926.261. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.1.0

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: MG.Cintel_cpufreq performanceP-State performanceintel_cpufreq schedutilP-State powersave30K60K90K120K150KSE +/- 209.39, N = 10SE +/- 89.79, N = 10SE +/- 233.06, N = 10SE +/- 333.81, N = 10120124.05120084.27117869.49116754.161. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.1.0

TensorFlow Lite

This is a benchmark of the TensorFlow Lite implementation. The current Linux support is limited to running on CPUs. This test profile is measuring the average inference time. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception V4P-State performanceintel_cpufreq schedutilintel_cpufreq performanceP-State powersave150K300K450K600K750KSE +/- 2267.77, N = 3SE +/- 2013.17, N = 3SE +/- 6399.11, N = 3SE +/- 5220.61, N = 3663707672254677421682153

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 performanceintel_cpufreq performanceintel_cpufreq schedutilP-State powersave510152025SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.08, N = 3SE +/- 0.06, N = 318.5018.5218.7518.98

Embree

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

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer ISPC - Model: Asian Dragon Objintel_cpufreq performanceP-State performanceintel_cpufreq schedutilP-State powersave20406080100SE +/- 0.14, N = 3SE +/- 0.48, N = 3SE +/- 0.38, N = 3SE +/- 0.41, N = 389.4989.0987.9987.21MIN: 71.05 / MAX: 98.17MIN: 70.73 / MAX: 97.89MIN: 70.3 / MAX: 98.24MIN: 69.09 / MAX: 97.86

Rodinia

Rodinia is a suite focused upon accelerating compute-intensive applications with accelerators. CUDA, OpenMP, and OpenCL parallel models are supported by the included applications. This profile utilizes select OpenCL, NVIDIA CUDA and OpenMP test binaries at the moment. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP CFD Solverintel_cpufreq schedutilintel_cpufreq performanceP-State performanceP-State powersave1.08612.17223.25834.34445.4305SE +/- 0.014, N = 8SE +/- 0.019, N = 8SE +/- 0.036, N = 8SE +/- 0.041, N = 154.7104.7294.7464.8271. (CXX) g++ options: -O2 -lOpenCL

PJSIP

PJSIP is a free and open source multimedia communication library written in C language implementing standard based protocols such as SIP, SDP, RTP, STUN, TURN, and ICE. It combines signaling protocol (SIP) with rich multimedia framework and NAT traversal functionality into high level API that is portable and suitable for almost any type of systems ranging from desktops, embedded systems, to mobile handsets. This test profile is making use of pjsip-perf with both the client/server on teh system. More details on the PJSIP benchmark at https://www.pjsip.org/high-performance-sip.htm Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgResponses Per Second, More Is BetterPJSIP 2.11Method: OPTIONS, StatelessP-State performanceintel_cpufreq performanceintel_cpufreq schedutilP-State powersave9K18K27K36K45KSE +/- 274.68, N = 3SE +/- 83.53, N = 3SE +/- 380.67, N = 7SE +/- 341.07, N = 9423894233841743414211. (CC) gcc options: -lstdc++ -lssl -lcrypto -luuid -lm -lrt -lpthread -lasound -O2

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 1.6Model: shufflenet-v2-10 - Device: OpenMP CPUP-State performanceintel_cpufreq performanceintel_cpufreq schedutilP-State powersave2K4K6K8K10KSE +/- 25.12, N = 3SE +/- 24.06, N = 3SE +/- 65.66, N = 3SE +/- 58.56, N = 1283928380833482121. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt

NAS Parallel Benchmarks

NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: CG.CP-State performanceintel_cpufreq performanceP-State powersaveintel_cpufreq schedutil9K18K27K36K45KSE +/- 113.89, N = 8SE +/- 69.22, N = 8SE +/- 83.38, N = 7SE +/- 42.28, N = 840261.2640226.0239485.7239430.661. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.1.0

Intel Open Image Denoise

Open Image Denoise is a denoising library for ray-tracing and part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 1.4.0Run: RT.ldr_alb_nrm.3840x2160intel_cpufreq performanceP-State performanceintel_cpufreq schedutilP-State powersave0.65931.31861.97792.63723.2965SE +/- 0.01, N = 5SE +/- 0.01, N = 5SE +/- 0.02, N = 4SE +/- 0.01, N = 42.932.932.882.87

High Performance Conjugate Gradient

HPCG is the High Performance Conjugate Gradient and is a new scientific benchmark from Sandia National Lans focused for super-computer testing with modern real-world workloads compared to HPCC. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOP/s, More Is BetterHigh Performance Conjugate Gradient 3.1intel_cpufreq performanceP-State performanceP-State powersaveintel_cpufreq schedutil918273645SE +/- 0.21, N = 3SE +/- 0.20, N = 3SE +/- 0.17, N = 3SE +/- 0.12, N = 340.8340.6540.1440.071. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -pthread -lmpi_cxx -lmpi

Zstd Compression

This test measures the time needed to compress/decompress a sample file (a FreeBSD disk image - FreeBSD-12.2-RELEASE-amd64-memstick.img) using Zstd compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19 - Decompression Speedintel_cpufreq performanceintel_cpufreq schedutilP-State powersaveP-State performance6001200180024003000SE +/- 4.37, N = 3SE +/- 4.60, N = 15SE +/- 16.96, N = 3SE +/- 5.29, N = 152609.72594.72563.22561.81. (CC) gcc options: -O3 -pthread -lz -llzma

Stockfish

This is a test of Stockfish, an advanced open-source C++11 chess benchmark that can scale up to 512 CPU threads. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 13Total Timeintel_cpufreq performanceP-State performanceP-State powersaveintel_cpufreq schedutil40M80M120M160M200MSE +/- 2150017.23, N = 3SE +/- 1592768.45, N = 3SE +/- 1103002.46, N = 3SE +/- 1451422.61, N = 151786294741771314281770311221754461821. (CXX) g++ options: -lgcov -m64 -lpthread -fno-exceptions -std=c++17 -fprofile-use -fno-peel-loops -fno-tracer -pedantic -O3 -msse -msse3 -mpopcnt -mavx2 -mavx512f -mavx512bw -mavx512vnni -mavx512dq -mavx512vl -msse4.1 -mssse3 -msse2 -mbmi2 -flto -flto=jobserver

Rodinia

Rodinia is a suite focused upon accelerating compute-intensive applications with accelerators. CUDA, OpenMP, and OpenCL parallel models are supported by the included applications. This profile utilizes select OpenCL, NVIDIA CUDA and OpenMP test binaries at the moment. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP LavaMDintel_cpufreq schedutilP-State performanceintel_cpufreq performanceP-State powersave918273645SE +/- 0.18, N = 3SE +/- 0.13, N = 3SE +/- 0.47, N = 3SE +/- 0.23, N = 339.2039.4239.7539.821. (CXX) g++ options: -O2 -lOpenCL

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 1.6Model: fcn-resnet101-11 - Device: OpenMP CPUintel_cpufreq performanceP-State powersaveintel_cpufreq schedutilP-State performance4080120160200SE +/- 0.29, N = 3SE +/- 2.36, N = 3SE +/- 1.89, N = 3SE +/- 0.44, N = 31971961941941. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt

Timed LLVM Compilation

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 12.0Build System: NinjaP-State performanceintel_cpufreq performanceintel_cpufreq schedutilP-State powersave306090120150SE +/- 0.50, N = 3SE +/- 0.45, N = 3SE +/- 0.14, N = 3SE +/- 0.40, N = 3127.32127.33127.69129.27

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 1.6Model: yolov4 - Device: OpenMP CPUintel_cpufreq schedutilP-State performanceP-State powersaveintel_cpufreq performance100200300400500SE +/- 5.29, N = 3SE +/- 5.43, N = 3SE +/- 2.02, N = 3SE +/- 0.73, N = 34834834804761. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt

Intel Open Image Denoise

Open Image Denoise is a denoising library for ray-tracing and part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 1.4.0Run: RTLightmap.hdr.4096x4096intel_cpufreq performanceP-State performanceintel_cpufreq schedutilP-State powersave0.3150.630.9451.261.575SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 31.401.401.381.38

Blender

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

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Classroom - Compute: CPU-Onlyintel_cpufreq performanceP-State performanceP-State powersaveintel_cpufreq schedutil1632486480SE +/- 0.15, N = 3SE +/- 0.04, N = 3SE +/- 0.08, N = 3SE +/- 0.13, N = 371.2271.2772.1772.24

ArrayFire

ArrayFire is an GPU and CPU numeric processing library, this test uses the built-in CPU and OpenCL ArrayFire benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOPS, More Is BetterArrayFire 3.7Test: BLAS CPUintel_cpufreq performanceP-State performanceP-State powersaveintel_cpufreq schedutil10002000300040005000SE +/- 11.74, N = 4SE +/- 24.52, N = 4SE +/- 10.80, N = 4SE +/- 36.10, N = 44574.834539.994538.694510.291. (CXX) g++ options: -rdynamic

Rodinia

Rodinia is a suite focused upon accelerating compute-intensive applications with accelerators. CUDA, OpenMP, and OpenCL parallel models are supported by the included applications. This profile utilizes select OpenCL, NVIDIA CUDA and OpenMP test binaries at the moment. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP StreamclusterP-State powersaveintel_cpufreq schedutilintel_cpufreq performanceP-State performance246810SE +/- 0.058, N = 15SE +/- 0.044, N = 6SE +/- 0.076, N = 6SE +/- 0.078, N = 157.7107.7127.7277.8161. (CXX) g++ options: -O2 -lOpenCL

Xcompact3d Incompact3d

Xcompact3d Incompact3d is a Fortran-MPI based, finite difference high-performance code for solving the incompressible Navier-Stokes equation and as many as you need scalar transport equations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: input.i3d 193 Cells Per DirectionP-State performanceintel_cpufreq performanceP-State powersaveintel_cpufreq schedutil3691215SE +/- 0.05, N = 4SE +/- 0.02, N = 4SE +/- 0.03, N = 4SE +/- 0.01, N = 411.0611.0611.1911.211. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz

Zstd Compression

This test measures the time needed to compress/decompress a sample file (a FreeBSD disk image - FreeBSD-12.2-RELEASE-amd64-memstick.img) using Zstd compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19, Long Mode - Decompression Speedintel_cpufreq performanceP-State powersaveintel_cpufreq schedutilP-State performance6001200180024003000SE +/- 2.06, N = 3SE +/- 4.94, N = 15SE +/- 8.19, N = 6SE +/- 9.19, N = 32713.12711.62693.42677.91. (CC) gcc options: -O3 -pthread -lz -llzma

GROMACS

The GROMACS (GROningen MAchine for Chemical Simulations) molecular dynamics package testing with the water_GMX50 data. This test profile allows selecting between CPU and GPU-based GROMACS builds. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2021.2Implementation: MPI CPU - Input: water_GMX50_bareintel_cpufreq performanceP-State performanceintel_cpufreq schedutilP-State powersave3691215SE +/- 0.011, N = 3SE +/- 0.048, N = 3SE +/- 0.035, N = 3SE +/- 0.038, N = 39.1029.0529.0428.9991. (CXX) g++ options: -O3 -pthread

LAMMPS Molecular Dynamics Simulator

LAMMPS is a classical molecular dynamics code, and an acronym for Large-scale Atomic/Molecular Massively Parallel Simulator. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgns/day, More Is BetterLAMMPS Molecular Dynamics Simulator 29Oct2020Model: 20k Atomsintel_cpufreq performanceP-State performanceintel_cpufreq schedutilP-State powersave816243240SE +/- 0.05, N = 3SE +/- 0.05, N = 3SE +/- 0.04, N = 3SE +/- 0.06, N = 335.8535.8335.7935.501. (CXX) g++ options: -O3 -pthread -lm

OpenFOAM

OpenFOAM is the leading free, open source software for computational fluid dynamics (CFD). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 8Input: Motorbike 60Mintel_cpufreq performanceP-State performanceP-State powersaveintel_cpufreq schedutil20406080100SE +/- 0.16, N = 3SE +/- 0.09, N = 3SE +/- 0.19, N = 3SE +/- 0.38, N = 3104.27104.76105.03105.101. (CXX) g++ options: -std=c++11 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -ldynamicMesh -ldecompose -lgenericPatchFields -lmetisDecomp -lscotchDecomp -llagrangian -lregionModels -lOpenFOAM -ldl -lm

Liquid-DSP

LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 160 - Buffer Length: 256 - Filter Length: 57intel_cpufreq performanceP-State performanceintel_cpufreq schedutilP-State powersave700M1400M2100M2800M3500MSE +/- 5955109.85, N = 3SE +/- 2605762.84, N = 3SE +/- 1071343.91, N = 3SE +/- 12922117.13, N = 330967000003085100000308253333330739333331. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 128 - Buffer Length: 256 - Filter Length: 57intel_cpufreq performanceP-State performanceintel_cpufreq schedutilP-State powersave700M1400M2100M2800M3500MSE +/- 5329477.77, N = 3SE +/- 6806124.69, N = 3SE +/- 4817445.15, N = 3SE +/- 10910901.79, N = 332934000003293000000329146666732701333331. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OSPray

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

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: XFrog Forest - Renderer: Path TracerP-State powersaveintel_cpufreq performanceintel_cpufreq schedutilP-State performance3691215SE +/- 0.04, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 310.3810.3110.3110.31MIN: 8.06 / MAX: 10.53MIN: 8.26 / MAX: 10.75MIN: 7.75 / MAX: 10.53MIN: 8.33 / MAX: 10.75

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: San Miguel - Renderer: Path TracerP-State performanceintel_cpufreq performanceP-State powersaveintel_cpufreq schedutil3691215SE +/- 0.04, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.04, N = 310.4510.4210.4210.38MIN: 7.94 / MAX: 10.75MIN: 7.14 / MAX: 10.64MIN: 7.69 / MAX: 10.64MIN: 7.69 / MAX: 10.53

NAMD

NAMD is a parallel molecular dynamics code designed for high-performance simulation of large biomolecular systems. NAMD was developed by the Theoretical and Computational Biophysics Group in the Beckman Institute for Advanced Science and Technology at the University of Illinois at Urbana-Champaign. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD 2.14ATPase Simulation - 327,506 Atomsintel_cpufreq performanceP-State powersaveP-State performanceintel_cpufreq schedutil0.06130.12260.18390.24520.3065SE +/- 0.00021, N = 3SE +/- 0.00040, N = 3SE +/- 0.00055, N = 3SE +/- 0.00043, N = 30.270510.270930.271680.27227

NAS Parallel Benchmarks

NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: SP.Cintel_cpufreq performanceP-State performanceintel_cpufreq schedutilP-State powersave20K40K60K80K100KSE +/- 55.17, N = 4SE +/- 159.72, N = 4SE +/- 142.93, N = 3SE +/- 139.83, N = 391830.5691817.7691642.3391313.601. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.1.0

NWChem

NWChem is an open-source high performance computational chemistry package. Per NWChem's documentation, "NWChem aims to provide its users with computational chemistry tools that are scalable both in their ability to treat large scientific computational chemistry problems efficiently, and in their use of available parallel computing resources from high-performance parallel supercomputers to conventional workstation clusters." Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterNWChem 7.0.2Input: C240 Buckyballintel_cpufreq schedutilintel_cpufreq performanceP-State powersaveP-State performance4008001200160020001880.01882.21882.31888.21. (F9X) gfortran options: -lnwctask -lccsd -lmcscf -lselci -lmp2 -lmoints -lstepper -ldriver -loptim -lnwdft -lgradients -lcphf -lesp -lddscf -ldangchang -lguess -lhessian -lvib -lnwcutil -lrimp2 -lproperty -lsolvation -lnwints -lprepar -lnwmd -lnwpw -lofpw -lpaw -lpspw -lband -lnwpwlib -lcafe -lspace -lanalyze -lqhop -lpfft -ldplot -ldrdy -lvscf -lqmmm -lqmd -letrans -ltce -lbq -lmm -lcons -lperfm -ldntmc -lccca -ldimqm -lga -larmci -lpeigs -l64to32 -lopenblas -lpthread -lrt -llapack -lnwcblas -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lz -lcomex -m64 -ffast-math -std=legacy -fdefault-integer-8 -finline-functions -O2

RELION

RELION - REgularised LIkelihood OptimisatioN - is a stand-alone computer program for Maximum A Posteriori refinement of (multiple) 3D reconstructions or 2D class averages in cryo-electron microscopy (cryo-EM). It is developed in the research group of Sjors Scheres at the MRC Laboratory of Molecular Biology. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRELION 3.1.1Test: Basic - Device: CPUintel_cpufreq performanceintel_cpufreq schedutilP-State performanceP-State powersave80160240320400SE +/- 1.39, N = 3SE +/- 1.38, N = 3SE +/- 1.34, N = 3SE +/- 1.16, N = 3349.03349.44349.99350.271. (CXX) g++ options: -fopenmp -std=c++0x -O3 -rdynamic -ldl -ltiff -lfftw3f -lfftw3 -lpng -pthread -lmpi_cxx -lmpi

Rodinia

Rodinia is a suite focused upon accelerating compute-intensive applications with accelerators. CUDA, OpenMP, and OpenCL parallel models are supported by the included applications. This profile utilizes select OpenCL, NVIDIA CUDA and OpenMP test binaries at the moment. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP HotSpot3Dintel_cpufreq performanceintel_cpufreq schedutilP-State performanceP-State powersave20406080100SE +/- 0.52, N = 3SE +/- 0.27, N = 3SE +/- 0.01, N = 3SE +/- 0.44, N = 3104.09104.18104.19104.341. (CXX) g++ options: -O2 -lOpenCL

TensorFlow Lite

This is a benchmark of the TensorFlow Lite implementation. The current Linux support is limited to running on CPUs. This test profile is measuring the average inference time. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception ResNet V2intel_cpufreq schedutilP-State powersaveP-State performanceintel_cpufreq performance120K240K360K480K600KSE +/- 1875.50, N = 3SE +/- 1289.77, N = 3SE +/- 2262.00, N = 3SE +/- 491.89, N = 3571632572065572149572679

WRF

WRF, the Weather Research and Forecasting Model, is a "next-generation mesoscale numerical weather prediction system designed for both atmospheric research and operational forecasting applications. It features two dynamical cores, a data assimilation system, and a software architecture supporting parallel computation and system extensibility." Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterWRF 4.2.2Input: conus 2.5kmintel_cpufreq performanceP-State performanceintel_cpufreq schedutilP-State powersave2K4K6K8K10K9875.269885.569889.919892.421. (F9X) gfortran options: -O2 -ftree-vectorize -funroll-loops -ffree-form -fconvert=big-endian -frecord-marker=4 -fallow-invalid-boz -lesmf_time -lwrfio_nf -lnetcdff -lnetcdf -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz

Xcompact3d Incompact3d

Xcompact3d Incompact3d is a Fortran-MPI based, finite difference high-performance code for solving the incompressible Navier-Stokes equation and as many as you need scalar transport equations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: X3D-benchmarking input.i3dintel_cpufreq performanceP-State performanceP-State powersaveintel_cpufreq schedutil60120180240300SE +/- 0.09, N = 3SE +/- 0.01, N = 3SE +/- 0.12, N = 3SE +/- 0.11, N = 3289.98290.14290.41290.421. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz

OSPray

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

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: NASA Streamlines - Renderer: Path Tracerintel_cpufreq performanceintel_cpufreq schedutilP-State performanceP-State powersave714212835SE +/- 0.00, N = 5SE +/- 0.00, N = 5SE +/- 0.00, N = 5SE +/- 0.00, N = 527.7827.7827.7827.78MIN: 17.54 / MAX: 29.41MIN: 16.95 / MAX: 28.57MIN: 17.54 / MAX: 29.41MIN: 15.87 / MAX: 29.41

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: XFrog Forest - Renderer: SciVisintel_cpufreq performanceintel_cpufreq schedutilP-State performanceP-State powersave510152025SE +/- 0.00, N = 4SE +/- 0.00, N = 4SE +/- 0.00, N = 4SE +/- 0.00, N = 418.8718.8718.8718.87MIN: 12.99 / MAX: 19.61MIN: 12.2 / MAX: 19.23MIN: 13.89 / MAX: 19.61MIN: 13.7 / MAX: 19.23

CPU Temperature Monitor

OpenBenchmarking.orgCelsiusCPU Temperature MonitorPhoronix Test Suite System MonitoringP-State powersaveintel_cpufreq schedutilP-State performanceintel_cpufreq performance1530456075Min: 28 / Avg: 58.72 / Max: 79Min: 28 / Avg: 59.65 / Max: 78Min: 36 / Avg: 62.03 / Max: 80Min: 36 / Avg: 63.47 / Max: 78

CPU Power Consumption Monitor

OpenBenchmarking.orgWattsCPU Power Consumption MonitorPhoronix Test Suite System Monitoringintel_cpufreq schedutilP-State powersaveP-State performanceintel_cpufreq performance130260390520650Min: 53.9 / Avg: 368.68 / Max: 634.98Min: 53.58 / Avg: 371.79 / Max: 722.02Min: 70.83 / Avg: 413.76 / Max: 639.8Min: 137.84 / Avg: 417.23 / Max: 641.13

CPU Peak Freq (Highest CPU Core Frequency) Monitor

OpenBenchmarking.orgMegahertzCPU Peak Freq (Highest CPU Core Frequency) MonitorPhoronix Test Suite System MonitoringP-State powersaveintel_cpufreq schedutilP-State performanceintel_cpufreq performance6001200180024003000Min: 801 / Avg: 2883.69 / Max: 3537Min: 801 / Avg: 3003.21 / Max: 3442Min: 2195 / Avg: 3186.64 / Max: 3518Min: 2162 / Avg: 3195.19 / Max: 3483

PostgreSQL pgbench

OpenBenchmarking.orgCelsius, Fewer Is BetterPostgreSQL pgbench 13.0CPU Temperature MonitorP-State performanceP-State powersaveintel_cpufreq schedutilintel_cpufreq performance1326395265Min: 45 / Avg: 48.52 / Max: 62Min: 39 / Avg: 50.83 / Max: 66Min: 41 / Avg: 51.26 / Max: 65Min: 49 / Avg: 55.19 / Max: 67

OpenBenchmarking.orgWatts, Fewer Is BetterPostgreSQL pgbench 13.0CPU Power Consumption MonitorP-State powersaveintel_cpufreq schedutilP-State performanceintel_cpufreq performance110220330440550Min: 55 / Avg: 231.4 / Max: 606.41Min: 65.29 / Avg: 245.6 / Max: 612.07Min: 161.84 / Avg: 257.1 / Max: 600.03Min: 148.8 / Avg: 257.7 / Max: 600.3

OpenBenchmarking.orgMegahertz, More Is BetterPostgreSQL pgbench 13.0CPU Peak Freq (Highest CPU Core Frequency) MonitorP-State performanceintel_cpufreq performanceintel_cpufreq schedutilP-State powersave6001200180024003000Min: 3000 / Avg: 3365.53 / Max: 3407Min: 2190 / Avg: 3355.5 / Max: 3436Min: 958 / Avg: 3317.09 / Max: 3442Min: 801 / Avg: 3022.44 / Max: 3437

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 1000 - Clients: 250 - Mode: Read Only - Average LatencyP-State performanceP-State powersaveintel_cpufreq schedutilintel_cpufreq performance0.06480.12960.19440.25920.324SE +/- 0.003, N = 3SE +/- 0.002, N = 15SE +/- 0.005, N = 15SE +/- 0.006, N = 150.2710.2770.2850.2881. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 13.0Scaling Factor: 1000 - Clients: 250 - Mode: Read OnlyP-State performanceP-State powersaveintel_cpufreq schedutilintel_cpufreq performance200K400K600K800K1000KSE +/- 9754.80, N = 3SE +/- 7359.52, N = 15SE +/- 15445.86, N = 15SE +/- 16646.22, N = 159241909064348853798764621. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

OpenBenchmarking.orgCelsius, Fewer Is BetterPostgreSQL pgbench 13.0CPU Temperature MonitorP-State powersaveintel_cpufreq schedutilP-State performanceintel_cpufreq performance1326395265Min: 39 / Avg: 45.32 / Max: 55Min: 37 / Avg: 47.11 / Max: 62Min: 45 / Avg: 48.57 / Max: 63Min: 50 / Avg: 54 / Max: 67

OpenBenchmarking.orgWatts, Fewer Is BetterPostgreSQL pgbench 13.0CPU Power Consumption MonitorP-State powersaveintel_cpufreq schedutilP-State performanceintel_cpufreq performance110220330440550Min: 55.17 / Avg: 180.92 / Max: 370.22Min: 68.62 / Avg: 244.41 / Max: 617.1Min: 150.38 / Avg: 256.11 / Max: 607.4Min: 148.4 / Avg: 260.23 / Max: 604.15

OpenBenchmarking.orgMegahertz, More Is BetterPostgreSQL pgbench 13.0CPU Peak Freq (Highest CPU Core Frequency) Monitorintel_cpufreq performanceP-State performanceintel_cpufreq schedutilP-State powersave6001200180024003000Min: 3000 / Avg: 3361.95 / Max: 3441Min: 3000 / Avg: 3354.76 / Max: 3413Min: 1652 / Avg: 3301.91 / Max: 3405Min: 801 / Avg: 2821.03 / Max: 3436

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 1000 - Clients: 100 - Mode: Read Only - Average LatencyP-State performanceintel_cpufreq schedutilintel_cpufreq performanceP-State powersave0.05760.11520.17280.23040.288SE +/- 0.000, N = 3SE +/- 0.001, N = 3SE +/- 0.000, N = 3SE +/- 0.005, N = 150.0810.0810.0810.2561. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 13.0Scaling Factor: 1000 - Clients: 100 - Mode: Read OnlyP-State performanceintel_cpufreq performanceintel_cpufreq schedutilP-State powersave300K600K900K1200K1500KSE +/- 5304.66, N = 3SE +/- 3615.78, N = 3SE +/- 11834.71, N = 3SE +/- 8388.30, N = 151236713123198312285703933291. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

Liquid-DSP

OpenBenchmarking.orgCelsius, Fewer Is BetterLiquid-DSP 2021.01.31CPU Temperature Monitorintel_cpufreq performanceintel_cpufreq schedutilP-State powersaveP-State performance1530456075Min: 53 / Avg: 64.47 / Max: 75Min: 45 / Avg: 65.91 / Max: 76Min: 44 / Avg: 65.94 / Max: 74Min: 53 / Avg: 68.24 / Max: 74

OpenBenchmarking.orgWatts, Fewer Is BetterLiquid-DSP 2021.01.31CPU Power Consumption MonitorP-State powersaveintel_cpufreq schedutilintel_cpufreq performanceP-State performance100200300400500Min: 57.22 / Avg: 448.6 / Max: 567.92Min: 75.6 / Avg: 466.58 / Max: 591.16Min: 212.42 / Avg: 477.28 / Max: 581.05Min: 178.13 / Avg: 479.63 / Max: 584.33

OpenBenchmarking.orgMegahertz, More Is BetterLiquid-DSP 2021.01.31CPU Peak Freq (Highest CPU Core Frequency) Monitorintel_cpufreq performanceintel_cpufreq schedutilP-State performanceP-State powersave6001200180024003000Min: 3100 / Avg: 3242.06 / Max: 3403Min: 1823 / Avg: 3216.32 / Max: 3407Min: 3102 / Avg: 3213.59 / Max: 3404Min: 801 / Avg: 2843.06 / Max: 3300

OpenBenchmarking.orgsamples/s Per Watt, More Is BetterLiquid-DSP 2021.01.31Threads: 64 - Buffer Length: 256 - Filter Length: 57P-State powersaveintel_cpufreq performanceintel_cpufreq schedutilP-State performance1.4M2.8M4.2M5.6M7M6754065.396437714.606436493.636392760.37

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 64 - Buffer Length: 256 - Filter Length: 57intel_cpufreq performanceP-State performanceP-State powersaveintel_cpufreq schedutil700M1400M2100M2800M3500MSE +/- 8774394.57, N = 3SE +/- 5500404.03, N = 3SE +/- 19182283.49, N = 3SE +/- 69564540.69, N = 1230726000003066133333302990000030031250001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

PJSIP

OpenBenchmarking.orgCelsius, Fewer Is BetterPJSIP 2.11CPU Temperature MonitorP-State powersaveintel_cpufreq schedutilP-State performanceintel_cpufreq performance1122334455Min: 32 / Avg: 33.74 / Max: 39Min: 32 / Avg: 36.64 / Max: 55Min: 44 / Avg: 46.36 / Max: 49Min: 51 / Avg: 53.48 / Max: 57

OpenBenchmarking.orgWatts, Fewer Is BetterPJSIP 2.11CPU Power Consumption MonitorP-State powersaveintel_cpufreq schedutilP-State performanceintel_cpufreq performance50100150200250Min: 59.12 / Avg: 103.68 / Max: 116.59Min: 60.85 / Avg: 107.56 / Max: 231.74Min: 166.83 / Avg: 231.78 / Max: 281.1Min: 184.16 / Avg: 235.01 / Max: 256.39

OpenBenchmarking.orgMegahertz, More Is BetterPJSIP 2.11CPU Peak Freq (Highest CPU Core Frequency) Monitorintel_cpufreq performanceP-State performanceintel_cpufreq schedutilP-State powersave6001200180024003000Min: 3403 / Avg: 3404.52 / Max: 3414Min: 3400 / Avg: 3404.16 / Max: 3409Min: 801 / Avg: 1738.34 / Max: 3403Min: 801 / Avg: 963.23 / Max: 3400

OpenBenchmarking.orgResponses Per Second Per Watt, More Is BetterPJSIP 2.11Method: INVITEP-State powersaveintel_cpufreq schedutilP-State performanceintel_cpufreq performance61218243024.5823.6223.2723.05

OpenBenchmarking.orgResponses Per Second, More Is BetterPJSIP 2.11Method: INVITEintel_cpufreq performanceP-State performanceP-State powersaveintel_cpufreq schedutil12002400360048006000SE +/- 15.21, N = 3SE +/- 7.17, N = 3SE +/- 29.86, N = 15SE +/- 50.72, N = 1554165393254825401. (CC) gcc options: -lstdc++ -lssl -lcrypto -luuid -lm -lrt -lpthread -lasound -O2

libavif avifenc

OpenBenchmarking.orgCelsius, Fewer Is Betterlibavif avifenc 0.9.0CPU Temperature MonitorP-State powersaveintel_cpufreq schedutilP-State performanceintel_cpufreq performance1020304050Min: 36 / Avg: 39.11 / Max: 50Min: 38 / Avg: 40.71 / Max: 43Min: 44 / Avg: 45.31 / Max: 46Min: 47 / Avg: 49.47 / Max: 52

OpenBenchmarking.orgWatts, Fewer Is Betterlibavif avifenc 0.9.0CPU Power Consumption MonitorP-State powersaveintel_cpufreq schedutilP-State performanceintel_cpufreq performance4080120160200Min: 61.75 / Avg: 132.41 / Max: 209.55Min: 70.97 / Avg: 148.01 / Max: 226.15Min: 174.65 / Avg: 208.79 / Max: 243.15Min: 176.23 / Avg: 208.82 / Max: 247.3

OpenBenchmarking.orgMegahertz, More Is Betterlibavif avifenc 0.9.0CPU Peak Freq (Highest CPU Core Frequency) Monitorintel_cpufreq performanceP-State performanceintel_cpufreq schedutilP-State powersave6001200180024003000Min: 3403 / Avg: 3404.06 / Max: 3408Min: 3403 / Avg: 3403.25 / Max: 3404Min: 802 / Avg: 3112.98 / Max: 3405Min: 801 / Avg: 2544.65 / Max: 3404

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.9.0Encoder Speed: 10, LosslessP-State performanceintel_cpufreq performanceintel_cpufreq schedutilP-State powersave246810SE +/- 0.031, N = 6SE +/- 0.040, N = 6SE +/- 0.124, N = 15SE +/- 0.141, N = 157.2487.2768.4868.8331. (CXX) g++ options: -O3 -fPIC -lm

OpenBenchmarking.orgCelsius, Fewer Is Betterlibavif avifenc 0.9.0CPU Temperature MonitorP-State powersaveintel_cpufreq schedutilP-State performanceintel_cpufreq performance1122334455Min: 38 / Avg: 41.72 / Max: 46Min: 40 / Avg: 45.42 / Max: 51Min: 46 / Avg: 47.67 / Max: 49Min: 52 / Avg: 54.13 / Max: 56

OpenBenchmarking.orgWatts, Fewer Is Betterlibavif avifenc 0.9.0CPU Power Consumption MonitorP-State powersaveintel_cpufreq schedutilP-State performanceintel_cpufreq performance4080120160200Min: 62.5 / Avg: 127.88 / Max: 203.15Min: 58.18 / Avg: 142.55 / Max: 217.79Min: 154.93 / Avg: 207.16 / Max: 244.01Min: 149.58 / Avg: 209.44 / Max: 244.26

OpenBenchmarking.orgMegahertz, More Is Betterlibavif avifenc 0.9.0CPU Peak Freq (Highest CPU Core Frequency) Monitorintel_cpufreq performanceP-State performanceintel_cpufreq schedutilP-State powersave6001200180024003000Min: 3403 / Avg: 3404.6 / Max: 3410Min: 3403 / Avg: 3404.2 / Max: 3410Min: 802 / Avg: 2852.45 / Max: 3404Min: 801 / Avg: 2497.91 / Max: 3404

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.9.0Encoder Speed: 10intel_cpufreq performanceP-State performanceintel_cpufreq schedutilP-State powersave1.17112.34223.51334.68445.8555SE +/- 0.013, N = 8SE +/- 0.014, N = 8SE +/- 0.066, N = 15SE +/- 0.099, N = 154.3404.3415.1345.2051. (CXX) g++ options: -O3 -fPIC -lm

AOM AV1

OpenBenchmarking.orgCelsius, Fewer Is BetterAOM AV1 3.1CPU Temperature MonitorP-State powersaveintel_cpufreq schedutilintel_cpufreq performanceP-State performance1224364860Min: 31 / Avg: 35.47 / Max: 41Min: 34 / Avg: 42.78 / Max: 58Min: 45 / Avg: 47.23 / Max: 53Min: 45 / Avg: 51.62 / Max: 62

OpenBenchmarking.orgWatts, Fewer Is BetterAOM AV1 3.1CPU Power Consumption MonitorP-State powersaveintel_cpufreq schedutilP-State performanceintel_cpufreq performance60120180240300Min: 54.55 / Avg: 125.47 / Max: 223.38Min: 64.3 / Avg: 160.5 / Max: 249.64Min: 203.67 / Avg: 301.44 / Max: 346.48Min: 188.59 / Avg: 303.12 / Max: 339.22

OpenBenchmarking.orgMegahertz, More Is BetterAOM AV1 3.1CPU Peak Freq (Highest CPU Core Frequency) MonitorP-State performanceintel_cpufreq performanceintel_cpufreq schedutilP-State powersave6001200180024003000Min: 3400 / Avg: 3404.38 / Max: 3434Min: 3403 / Avg: 3403.73 / Max: 3409Min: 908 / Avg: 2962.81 / Max: 3409Min: 801 / Avg: 2263.2 / Max: 3318

OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterAOM AV1 3.1Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 4Kintel_cpufreq performanceP-State performanceP-State powersaveintel_cpufreq schedutil0.00740.01480.02220.02960.0370.0330.0320.0310.025

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.1Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 4Kintel_cpufreq performanceP-State performanceintel_cpufreq schedutilP-State powersave3691215SE +/- 0.09, N = 3SE +/- 0.03, N = 3SE +/- 0.08, N = 12SE +/- 0.05, N = 310.019.694.003.941. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

Rodinia

OpenBenchmarking.orgCelsius, Fewer Is BetterRodinia 3.1CPU Temperature MonitorP-State powersaveintel_cpufreq schedutilintel_cpufreq performanceP-State performance1530456075Min: 43 / Avg: 50.54 / Max: 59Min: 46 / Avg: 55.88 / Max: 66Min: 58 / Avg: 70.74 / Max: 77Min: 57 / Avg: 71.56 / Max: 78

OpenBenchmarking.orgWatts, Fewer Is BetterRodinia 3.1CPU Power Consumption MonitorP-State powersaveintel_cpufreq schedutilintel_cpufreq performanceP-State performance80160240320400Min: 71.33 / Avg: 180.52 / Max: 301.33Min: 59.89 / Avg: 223.22 / Max: 369.45Min: 157.21 / Avg: 348.25 / Max: 425.7Min: 190.97 / Avg: 348.5 / Max: 420.44

OpenBenchmarking.orgMegahertz, More Is BetterRodinia 3.1CPU Peak Freq (Highest CPU Core Frequency) Monitorintel_cpufreq performanceP-State performanceintel_cpufreq schedutilP-State powersave6001200180024003000Min: 3400 / Avg: 3404.31 / Max: 3417Min: 3233 / Avg: 3403.14 / Max: 3414Min: 1444 / Avg: 2684.73 / Max: 3413Min: 801 / Avg: 2358.38 / Max: 3401

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP LeukocyteP-State performanceintel_cpufreq performanceintel_cpufreq schedutilP-State powersave1530456075SE +/- 0.64, N = 12SE +/- 0.69, N = 15SE +/- 1.35, N = 15SE +/- 0.69, N = 646.3647.1163.2969.051. (CXX) g++ options: -O2 -lOpenCL

Darmstadt Automotive Parallel Heterogeneous Suite

OpenBenchmarking.orgCelsius, Fewer Is BetterDarmstadt Automotive Parallel Heterogeneous SuiteCPU Temperature MonitorP-State powersaveintel_cpufreq schedutilP-State performanceintel_cpufreq performance1020304050Min: 35 / Avg: 38.64 / Max: 41Min: 40 / Avg: 44.28 / Max: 48Min: 46 / Avg: 48.15 / Max: 49Min: 47 / Avg: 49.55 / Max: 50

OpenBenchmarking.orgWatts, Fewer Is BetterDarmstadt Automotive Parallel Heterogeneous SuiteCPU Power Consumption MonitorP-State powersaveintel_cpufreq schedutilintel_cpufreq performanceP-State performance50100150200250Min: 54.57 / Avg: 167.05 / Max: 233.35Min: 72.95 / Avg: 171.91 / Max: 241.75Min: 148.33 / Avg: 233.74 / Max: 287.41Min: 148.96 / Avg: 234.25 / Max: 277.2

OpenBenchmarking.orgMegahertz, More Is BetterDarmstadt Automotive Parallel Heterogeneous SuiteCPU Peak Freq (Highest CPU Core Frequency) MonitorP-State performanceintel_cpufreq performanceintel_cpufreq schedutilP-State powersave6001200180024003000Min: 3403 / Avg: 3403.75 / Max: 3407Min: 3403 / Avg: 3403.25 / Max: 3405Min: 801 / Avg: 2837.77 / Max: 3406Min: 801 / Avg: 2819.74 / Max: 3406

OpenBenchmarking.orgTest Cases Per Minute Per Watt, More Is BetterDarmstadt Automotive Parallel Heterogeneous SuiteBackend: OpenMP - Kernel: NDT MappingP-State powersaveintel_cpufreq schedutilP-State performanceintel_cpufreq performance0.99991.99982.99973.99964.99954.4444.3223.9483.913

OpenBenchmarking.orgTest Cases Per Minute, More Is BetterDarmstadt Automotive Parallel Heterogeneous SuiteBackend: OpenMP - Kernel: NDT MappingP-State performanceintel_cpufreq performanceintel_cpufreq schedutilP-State powersave2004006008001000SE +/- 4.79, N = 3SE +/- 4.97, N = 3SE +/- 19.99, N = 14SE +/- 18.61, N = 15924.84914.70743.01742.301. (CXX) g++ options: -O3 -std=c++11 -fopenmp

ONNX Runtime

OpenBenchmarking.orgCelsius, Fewer Is BetterONNX Runtime 1.6CPU Temperature MonitorP-State powersaveP-State performanceintel_cpufreq schedutilintel_cpufreq performance1428425670Min: 50 / Avg: 64.79 / Max: 70Min: 54 / Avg: 65.08 / Max: 67Min: 53 / Avg: 66.62 / Max: 70Min: 53 / Avg: 68.18 / Max: 71

OpenBenchmarking.orgWatts, Fewer Is BetterONNX Runtime 1.6CPU Power Consumption MonitorP-State powersaveP-State performanceintel_cpufreq schedutilintel_cpufreq performance100200300400500Min: 134.9 / Avg: 446.21 / Max: 551.94Min: 154.61 / Avg: 448.18 / Max: 538.49Min: 171.12 / Avg: 451.38 / Max: 550.48Min: 182.92 / Avg: 451.81 / Max: 550.15

OpenBenchmarking.orgMegahertz, More Is BetterONNX Runtime 1.6CPU Peak Freq (Highest CPU Core Frequency) Monitorintel_cpufreq performanceP-State performanceintel_cpufreq schedutilP-State powersave6001200180024003000Min: 3000 / Avg: 3028.08 / Max: 3404Min: 3000 / Avg: 3024.65 / Max: 3407Min: 2202 / Avg: 3018.2 / Max: 3403Min: 801 / Avg: 2966.78 / Max: 3401

OpenBenchmarking.orgInferences Per Minute Per Watt, More Is BetterONNX Runtime 1.6Model: bertsquad-10 - Device: OpenMP CPUP-State powersaveintel_cpufreq schedutilintel_cpufreq performanceP-State performance0.25670.51340.77011.02681.28351.1411.1171.1131.064

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.6Model: bertsquad-10 - Device: OpenMP CPUP-State powersaveintel_cpufreq schedutilintel_cpufreq performanceP-State performance110220330440550SE +/- 10.98, N = 9SE +/- 8.53, N = 12SE +/- 6.15, N = 12SE +/- 2.17, N = 35095045034771. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt

OpenBenchmarking.orgCelsius, Fewer Is BetterONNX Runtime 1.6CPU Temperature Monitorintel_cpufreq performanceP-State powersaveP-State performanceintel_cpufreq schedutil1428425670Min: 50 / Avg: 66.11 / Max: 74Min: 53 / Avg: 67.25 / Max: 72Min: 52 / Avg: 70.54 / Max: 75Min: 52 / Avg: 70.57 / Max: 75

OpenBenchmarking.orgWatts, Fewer Is BetterONNX Runtime 1.6CPU Power Consumption MonitorP-State performanceP-State powersaveintel_cpufreq schedutilintel_cpufreq performance100200300400500Min: 187.38 / Avg: 459.1 / Max: 563.8Min: 116.19 / Avg: 460.29 / Max: 567.14Min: 196.63 / Avg: 462.28 / Max: 560.86Min: 175.74 / Avg: 462.81 / Max: 568.1

OpenBenchmarking.orgMegahertz, More Is BetterONNX Runtime 1.6CPU Peak Freq (Highest CPU Core Frequency) Monitorintel_cpufreq performanceP-State performanceintel_cpufreq schedutilP-State powersave6001200180024003000Min: 3000 / Avg: 3023.24 / Max: 3403Min: 3000 / Avg: 3021.87 / Max: 3406Min: 3000 / Avg: 3012.86 / Max: 3405Min: 801 / Avg: 2986.56 / Max: 3006

OpenBenchmarking.orgInferences Per Minute Per Watt, More Is BetterONNX Runtime 1.6Model: super-resolution-10 - Device: OpenMP CPUintel_cpufreq performanceP-State powersaveintel_cpufreq schedutilP-State performance4812162015.0314.9914.6214.43

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.6Model: super-resolution-10 - Device: OpenMP CPUintel_cpufreq performanceP-State powersaveintel_cpufreq schedutilP-State performance15003000450060007500SE +/- 156.45, N = 12SE +/- 205.17, N = 12SE +/- 210.11, N = 12SE +/- 200.91, N = 1269556898675666261. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt

ArrayFire

OpenBenchmarking.orgCelsius, Fewer Is BetterArrayFire 3.7CPU Temperature MonitorP-State powersaveintel_cpufreq schedutilintel_cpufreq performanceP-State performance1122334455Min: 38 / Avg: 41.55 / Max: 44Min: 42 / Avg: 44.79 / Max: 48Min: 46 / Avg: 46.93 / Max: 49Min: 46 / Avg: 47.21 / Max: 54

OpenBenchmarking.orgWatts, Fewer Is BetterArrayFire 3.7CPU Power Consumption MonitorP-State powersaveintel_cpufreq schedutilintel_cpufreq performanceP-State performance60120180240300Min: 89.33 / Avg: 183.15 / Max: 264.32Min: 136.62 / Avg: 220.97 / Max: 305.86Min: 153.66 / Avg: 242.98 / Max: 320.92Min: 160.27 / Avg: 246.19 / Max: 325.31

OpenBenchmarking.orgMegahertz, More Is BetterArrayFire 3.7CPU Peak Freq (Highest CPU Core Frequency) MonitorP-State performanceintel_cpufreq performanceintel_cpufreq schedutilP-State powersave6001200180024003000Min: 3403 / Avg: 3404 / Max: 3408Min: 3403 / Avg: 3403.96 / Max: 3410Min: 2303 / Avg: 3284.24 / Max: 3405Min: 801 / Avg: 2569.52 / Max: 3405

OpenBenchmarking.orgms, Fewer Is BetterArrayFire 3.7Test: Conjugate Gradient CPUintel_cpufreq performanceP-State powersaveP-State performanceintel_cpufreq schedutil246810SE +/- 0.128, N = 15SE +/- 0.067, N = 15SE +/- 0.068, N = 15SE +/- 0.088, N = 154.0054.2926.1316.4541. (CXX) g++ options: -rdynamic

NAS Parallel Benchmarks

OpenBenchmarking.orgCelsius, Fewer Is BetterNAS Parallel Benchmarks 3.4CPU Temperature MonitorP-State powersaveintel_cpufreq schedutilintel_cpufreq performanceP-State performance1326395265Min: 39 / Avg: 44.96 / Max: 53Min: 41 / Avg: 46.59 / Max: 55Min: 52 / Avg: 54.96 / Max: 67Min: 53 / Avg: 56.04 / Max: 67

OpenBenchmarking.orgWatts, Fewer Is BetterNAS Parallel Benchmarks 3.4CPU Power Consumption MonitorP-State powersaveintel_cpufreq schedutilintel_cpufreq performanceP-State performance70140210280350Min: 68.72 / Avg: 141.99 / Max: 325.63Min: 102.97 / Avg: 198.35 / Max: 382.36Min: 175 / Avg: 266.53 / Max: 346.89Min: 166.22 / Avg: 274.74 / Max: 393.59

OpenBenchmarking.orgMegahertz, More Is BetterNAS Parallel Benchmarks 3.4CPU Peak Freq (Highest CPU Core Frequency) Monitorintel_cpufreq performanceP-State performanceintel_cpufreq schedutilP-State powersave6001200180024003000Min: 3400 / Avg: 3402.61 / Max: 3409Min: 3110 / Avg: 3381.08 / Max: 3410Min: 1971 / Avg: 2875.93 / Max: 3404Min: 801 / Avg: 1875.67 / Max: 3000

OpenBenchmarking.orgTotal Mop/s Per Watt, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.CP-State powersaveintel_cpufreq schedutilintel_cpufreq performanceP-State performance102030405042.6231.0428.9127.70

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.Cintel_cpufreq performanceP-State performanceintel_cpufreq schedutilP-State powersave17003400510068008500SE +/- 128.21, N = 15SE +/- 165.19, N = 15SE +/- 121.94, N = 15SE +/- 109.82, N = 127705.447610.186157.586051.901. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.1.0

Geometric Mean Of All Test Results

OpenBenchmarking.orgGeometric Mean, More Is BetterGeometric Mean Of All Test ResultsResult Composite - Xeon Scalable Ice Lake P-State Governorintel_cpufreq performanceP-State performanceintel_cpufreq schedutilP-State powersave50100150200250226.10225.06190.19177.93

150 Results Shown

Zstd Compression
Kvazaar
AOM AV1:
  Speed 6 Realtime - Bosphorus 4K
  Speed 8 Realtime - Bosphorus 4K
PostgreSQL pgbench:
  1000 - 250 - Read Write - Average Latency
  1000 - 250 - Read Write
AOM AV1
PJSIP
PostgreSQL pgbench:
  1000 - 100 - Read Write - Average Latency
  1000 - 100 - Read Write
Kvazaar
SVT-HEVC
SVT-VP9:
  PSNR/SSIM Optimized - Bosphorus 1080p
  VMAF Optimized - Bosphorus 1080p
Darmstadt Automotive Parallel Heterogeneous Suite
SVT-AV1
SVT-HEVC
Timed Godot Game Engine Compilation
OpenVKL:
  vklBenchmarkStructuredVolume
  vklBenchmarkVdbVolume
libavif avifenc
Darmstadt Automotive Parallel Heterogeneous Suite
OpenVKL
TensorFlow Lite
Timed Linux Kernel Compilation
OSPray
Timed Node.js Compilation
Embree
NAS Parallel Benchmarks
OSPray
NAS Parallel Benchmarks:
  SP.B
  LU.C
Zstd Compression
Quantum ESPRESSO
Zstd Compression
Intel Open Image Denoise
Blender
Embree
Timed LLVM Compilation
OpenFOAM
NAS Parallel Benchmarks
OpenVKL
NAS Parallel Benchmarks
OSPray
Blender
NAS Parallel Benchmarks:
  IS.D
  MG.C
TensorFlow Lite
Timed Mesa Compilation
Embree
Rodinia
PJSIP
ONNX Runtime
NAS Parallel Benchmarks
Intel Open Image Denoise
High Performance Conjugate Gradient
Zstd Compression
Stockfish
Rodinia
ONNX Runtime
Timed LLVM Compilation
ONNX Runtime
Intel Open Image Denoise
Blender
ArrayFire
Rodinia
Xcompact3d Incompact3d
Zstd Compression
GROMACS
LAMMPS Molecular Dynamics Simulator
OpenFOAM
Liquid-DSP:
  160 - 256 - 57
  128 - 256 - 57
OSPray:
  XFrog Forest - Path Tracer
  San Miguel - Path Tracer
NAMD
NAS Parallel Benchmarks
NWChem
RELION
Rodinia
TensorFlow Lite
WRF
Xcompact3d Incompact3d
OSPray:
  NASA Streamlines - Path Tracer
  XFrog Forest - SciVis
CPU Temperature Monitor:
  Phoronix Test Suite System Monitoring:
    Celsius
    Watts
    Megahertz
  CPU Temp Monitor:
    Celsius
  CPU Power Consumption Monitor:
    Watts
  CPU Peak Freq (Highest CPU Core Frequency) Monitor:
    Megahertz
PostgreSQL pgbench:
  1000 - 250 - Read Only - Average Latency
  1000 - 250 - Read Only
PostgreSQL pgbench:
  CPU Temp Monitor
  CPU Power Consumption Monitor
  CPU Peak Freq (Highest CPU Core Frequency) Monitor
PostgreSQL pgbench:
  1000 - 100 - Read Only - Average Latency
  1000 - 100 - Read Only
Liquid-DSP:
  CPU Temp Monitor
  CPU Power Consumption Monitor
  CPU Peak Freq (Highest CPU Core Frequency) Monitor
  64 - 256 - 57
Liquid-DSP
PJSIP:
  CPU Temp Monitor
  CPU Power Consumption Monitor
  CPU Peak Freq (Highest CPU Core Frequency) Monitor
  INVITE
PJSIP
libavif avifenc:
  CPU Temp Monitor
  CPU Power Consumption Monitor
  CPU Peak Freq (Highest CPU Core Frequency) Monitor
libavif avifenc
libavif avifenc:
  CPU Temp Monitor
  CPU Power Consumption Monitor
  CPU Peak Freq (Highest CPU Core Frequency) Monitor
libavif avifenc
AOM AV1:
  CPU Temp Monitor
  CPU Power Consumption Monitor
  CPU Peak Freq (Highest CPU Core Frequency) Monitor
  Speed 6 Two-Pass - Bosphorus 4K
AOM AV1
Rodinia:
  CPU Temp Monitor
  CPU Power Consumption Monitor
  CPU Peak Freq (Highest CPU Core Frequency) Monitor
Rodinia
Darmstadt Automotive Parallel Heterogeneous Suite:
  CPU Temp Monitor
  CPU Power Consumption Monitor
  CPU Peak Freq (Highest CPU Core Frequency) Monitor
  OpenMP - NDT Mapping
Darmstadt Automotive Parallel Heterogeneous Suite
ONNX Runtime:
  CPU Temp Monitor
  CPU Power Consumption Monitor
  CPU Peak Freq (Highest CPU Core Frequency) Monitor
  bertsquad-10 - OpenMP CPU
ONNX Runtime
ONNX Runtime:
  CPU Temp Monitor
  CPU Power Consumption Monitor
  CPU Peak Freq (Highest CPU Core Frequency) Monitor
  super-resolution-10 - OpenMP CPU
ONNX Runtime
ArrayFire:
  CPU Temp Monitor
  CPU Power Consumption Monitor
  CPU Peak Freq (Highest CPU Core Frequency) Monitor
ArrayFire
NAS Parallel Benchmarks:
  CPU Temp Monitor
  CPU Power Consumption Monitor
  CPU Peak Freq (Highest CPU Core Frequency) Monitor
  EP.C
NAS Parallel Benchmarks
Geometric Mean Of All Test Results