AMD EPYC 9755 AMD P-State Testing

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 2410248-NE-EPYC9755A92
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:

C++ Boost Tests 2 Tests
Timed Code Compilation 5 Tests
C/C++ Compiler Tests 9 Tests
CPU Massive 13 Tests
Creator Workloads 6 Tests
Database Test Suite 4 Tests
Encoding 2 Tests
Fortran Tests 2 Tests
HPC - High Performance Computing 8 Tests
Java Tests 2 Tests
Common Kernel Benchmarks 2 Tests
Machine Learning 4 Tests
Molecular Dynamics 4 Tests
Multi-Core 17 Tests
NVIDIA GPU Compute 2 Tests
Intel oneAPI 3 Tests
OpenMPI Tests 4 Tests
Programmer / Developer System Benchmarks 5 Tests
Python Tests 6 Tests
Raytracing 2 Tests
Renderers 3 Tests
Scientific Computing 4 Tests
Server 6 Tests
Server CPU Tests 10 Tests
Video Encoding 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

Additional Graphs

Show Perf Per Clock Calculation Graphs Where Applicable

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
acpi-cpufreq schedutil
October 23
  17 Hours, 13 Minutes
acpi-cpufreq performance
October 23
  16 Hours, 9 Minutes
amd-pstate-epp powersave, EPP power
October 22
  14 Hours, 53 Minutes
amd-pstate-epp performance
October 22
  16 Hours, 12 Minutes
Invert Hiding All Results Option
  16 Hours, 7 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):


AMD EPYC 9755 AMD P-State TestingProcessorMotherboardChipsetMemoryDiskGraphicsNetworkOSKernelCompilerFile-SystemScreen Resolutionacpi-cpufreq schedutilacpi-cpufreq performanceamd-pstate-epp powersave, EPP poweramd-pstate-epp performance2 x AMD EPYC 9755 128-Core @ 2.70GHz (256 Cores / 512 Threads)AMD VOLCANO (RVOT1001B BIOS)AMD Device 153a1520GB3201GB Micron_7450_MTFDKCB3T2TFS + 512GB SAMSUNG MZVL2512HCJQ-00B00ASPEEDBroadcom NetXtreme BCM5720 PCIeUbuntu 24.046.12.0-rc4-amd-pstate-phx (x86_64)GCC 13.2.0 + Clang 18.1.3ext41024x7682 x AMD EPYC 9755 128-Core @ 4.12GHz (256 Cores / 512 Threads)512GB SAMSUNG MZVL2512HCJQ-00B00 + 3201GB Micron_7450_MTFDKCB3T2TFS3201GB Micron_7450_MTFDKCB3T2TFS + 512GB SAMSUNG MZVL2512HCJQ-00B00OpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseCompiler Details- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-uJ7kn6/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-uJ7kn6/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v Processor Details- acpi-cpufreq schedutil: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xb002116- acpi-cpufreq performance: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xb002116- amd-pstate-epp powersave, EPP power: Scaling Governor: amd-pstate-epp powersave (Boost: Enabled EPP: power) - CPU Microcode: 0xb002116- amd-pstate-epp performance: Scaling Governor: amd-pstate-epp performance (Boost: Enabled EPP: performance) - CPU Microcode: 0xb002116Java Details- OpenJDK Runtime Environment (build 21.0.4+7-Ubuntu-1ubuntu224.04)Python Details- Python 3.12.3Security Details- gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Vulnerable + spectre_v1: Vulnerable: __user pointer sanitization and usercopy barriers only; no swapgs barriers + spectre_v2: Vulnerable; IBPB: disabled; STIBP: disabled; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected

acpi-cpufreq schedutilacpi-cpufreq performanceamd-pstate-epp powersave, EPP poweramd-pstate-epp performanceResult OverviewPhoronix Test Suite100%131%162%193%XNNPACKClickHouseDaCapo BenchmarkSVT-AV1Apache HTTP ServerKvazaareasyWave7-Zip CompressionTimed Gem5 CompilationTimed Linux Kernel CompilationApache CassandraTimed Wasmer CompilationOpenFOAMTimed Node.js CompilationStockfishGROMACSBlenderPyTorchTensorFlowPostgreSQLSPECFEM3DnginxOSPRay StudioTimed LLVM CompilationNAMDMemcachedCP2K Molecular DynamicsoneDNNOSPRayLiteRT

acpi-cpufreq schedutilacpi-cpufreq performanceamd-pstate-epp powersave, EPP poweramd-pstate-epp performancePer Watt Result OverviewPhoronix Test Suite100%111%121%132%Apache HTTP ServerClickHouseKvazaarSVT-AV1Apache CassandraTensorFlowGROMACS7-Zip CompressionNAMDStockfishPyTorchnginxMemcachedOSPRayP.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

AMD EPYC 9755 AMD P-State Testingopenfoam: drivaerFastback, Large Mesh Size - Execution Timeopenfoam: drivaerFastback, Large Mesh Size - Mesh Timexnnpack: QS8MobileNetV2xnnpack: FP16MobileNetV3Smallxnnpack: FP16MobileNetV3Largexnnpack: FP16MobileNetV2xnnpack: FP16MobileNetV1xnnpack: FP32MobileNetV3Smallxnnpack: FP32MobileNetV3Largexnnpack: FP32MobileNetV2xnnpack: FP32MobileNetV1svt-av1: Preset 3 - Beauty 4K 10-biteasywave: e2Asean Grid + BengkuluSept2007 Source - 2400stockfish: Chess Benchmarklitert: NASNet Mobiledacapobench: Apache Lucene Search Enginelitert: Inception V4litert: Inception ResNet V2tensorflow: CPU - 512 - ResNet-50litert: DeepLab V3litert: SqueezeNetlitert: Mobilenet Floatdacapobench: Tradebeanscassandra: Writescompress-7zip: Decompression Ratingcompress-7zip: Compression Ratingclickhouse: 100M Rows Hits Dataset, Third Runclickhouse: 100M Rows Hits Dataset, Second Runclickhouse: 100M Rows Hits Dataset, First Run / Cold Cachelitert: Quantized COCO SSD MobileNet v1svt-av1: Preset 5 - Beauty 4K 10-bitsvt-av1: Preset 3 - Bosphorus 4Klitert: Mobilenet Quanteasywave: e2Asean Grid + BengkuluSept2007 Source - 1200build-llvm: Unix Makefilescp2k: H20-256svt-av1: Preset 8 - Beauty 4K 10-bitonednn: Recurrent Neural Network Training - CPUospray: particle_volume/pathtracer/real_timepgbench: 100 - 1000 - Read Write - Average Latencypgbench: 100 - 1000 - Read Writepgbench: 100 - 1000 - Read Only - Average Latencypgbench: 100 - 1000 - Read Onlybuild-linux-kernel: allmodconfigspecfem3d: Layered Halfspacebuild-gem5: Time To Compilespecfem3d: Tomographic Modeldacapobench: H2 Database Enginespecfem3d: Water-layered Halfspacespecfem3d: Homogeneous Halfspacepytorch: CPU - 512 - ResNet-50nginx: 1000build-nodejs: Time To Compileapache: 1000namd: STMV with 1,066,628 Atomsbuild-linux-kernel: defconfigsvt-av1: Preset 13 - Beauty 4K 10-bitspecfem3d: Mount St. Helensdacapobench: Spring Bootopenfoam: drivaerFastback, Medium Mesh Size - Execution Timeopenfoam: drivaerFastback, Medium Mesh Size - Mesh Timegromacs: MPI CPU - water_GMX50_baredacapobench: Tradesoapmemcached: 1:100memcached: 1:10build-llvm: Ninjaospray-studio: 3 - 4K - 32 - Path Tracer - CPUospray: gravity_spheres_volume/dim_512/ao/real_timeospray-studio: 3 - 4K - 1 - Path Tracer - CPUsvt-av1: Preset 5 - Bosphorus 4Kospray-studio: 1 - 4K - 1 - Path Tracer - CPUospray-studio: 1 - 4K - 32 - Path Tracer - CPUdacapobench: PMD Source Code Analyzerblender: Barbershop - CPU-Onlydacapobench: Apache Lucene Search Indexdacapobench: Eclipsedacapobench: Apache Tomcatbuild-wasmer: Time To Compilesvt-av1: Preset 8 - Bosphorus 4Kkvazaar: Bosphorus 4K - Mediumdacapobench: Avrora AVR Simulation Frameworkdacapobench: Apache Xalan XSLTdacapobench: GraphChisvt-av1: Preset 13 - Bosphorus 4Kdacapobench: Apache Kafkadacapobench: jMonkeyEnginedacapobench: BioJava Biological Data Frameworkopenfoam: drivaerFastback, Small Mesh Size - Execution Timeopenfoam: drivaerFastback, Small Mesh Size - Mesh Timedacapobench: Zxing 1D/2D Barcode Image Processingkvazaar: Bosphorus 4K - Ultra Fastdacapobench: Jythonkvazaar: Bosphorus 4K - Slowblender: Junkshop - CPU-Onlykvazaar: Bosphorus 4K - Super Fastkvazaar: Bosphorus 4K - Very Fastonednn: Deconvolution Batch shapes_3d - CPUblender: BMW27 - CPU-Onlydacapobench: Batik SVG Toolkitdacapobench: FOP Print Formatteracpi-cpufreq schedutilacpi-cpufreq performanceamd-pstate-epp powersave, EPP poweramd-pstate-epp performance1950.6432673.2227222675719298421429316074579312215755266450173546716421.734105.839817516428129461835871389419509163220.94130544.568551.049708.31784928398613912801116731451.86448.23443.0470075.46.75112.75748466.040.957161.140140.5838.865794.378211.52782.456121290.2394188802142.1286.562910608121.8343.89110830953357.6219602294.58841229122.10378838.7890.22794660.929.6439919.26613.7983.532643624617375.778003126.7564532.457943412033636.834375833.9163.4891237977.024539244.04433110463357747.2629158279252927.09986.39754.37541516542754280.45062786908487815.3181725.02287330183.61467454.157.7082.3183.090.4458435.4811685091945.1227693.853012434162617403603382451351111382420393147802153121007581.74997.316815785362137402725814366367571935220.77131016.571822.050891.9854729364113781381229419661.18651.07641.4365692.86.97214.27447789.540.062161.314140.3429.400775.254210.85378.012128210.2384194532132.2106.867102458118.5993.65602007633267.2655254684.62541687021.71382110.6889.02892874.559.5332218.97515.9043.569244243376472.330969128.7205333.634407312296822.614374101.4663.9271236776.897439050.65833010423244347.0228517604161527.170114.67783.3027009572579403.59960426837471914.52308921.17363328294.05458183.217.5491.5190.760.4479625.3411314661936.5044632.53958260199222091377009201775893493211763102422089751070051.605102.907843797846131312432490383528570944214.00108089.477253.451073.9196852728001309549976708444.99440.20427.3573932.85.06110.98942023.442.646164.489140.9696.808789.088212.02981.554122650.2414152805135.9106.877590691134.9543.78499246847677.8555356694.76184245222.40373848.4793.39172820.629.5847221.87812.6053.504113348566272.775617139.310133.1071044712108995.334349758.6963.7241242976.857539134.01533110507372247.5030208845261828.62381.89876.93452515963732295.01962966982489914.88434719.04859436982.14482976.897.9181.2781.280.4482385.5912475331934.5134730.31069303065306868316859235660946402814483064962390941029761.749133.818850211688144068626275420326556066218.14122224.667141.056226.71109629759413739281265124674.14666.68653.0573505.06.99414.25644440.645.982160.717141.6449.387778.122211.46679.961125060.2394195019131.846.841081733116.9534.05080255032157.9444859644.71703731921.67381450.9988.84389729.529.6616018.75815.9393.290452902502970.930591127.4497632.404487012237534.644364726.0163.3091239677.110839149.95733010441271947.0428507719177126.792112.67582.43319312902613312.20560486835478514.99365919.98389426691.40461381.947.5289.8888.900.4487295.331149483OpenBenchmarking.org

OpenFOAM

OpenFOAM is the leading free, open-source software for computational fluid dynamics (CFD). This test profile currently uses the drivaerFastback test case for analyzing automotive aerodynamics or alternatively the older motorBike input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 10Input: drivaerFastback, Large Mesh Size - Execution Timeacpi-cpufreq schedutilacpi-cpufreq performanceamd-pstate-epp powersave, EPP poweramd-pstate-epp performance4008001200160020001950.641945.121936.501934.511. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfiniteVolume -lmeshTools -lparallel -llagrangian -lregionModels -lgenericPatchFields -lOpenFOAM -ldl -lm

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 10Input: drivaerFastback, Large Mesh Size - Mesh Timeamd-pstate-epp performanceacpi-cpufreq performanceacpi-cpufreq schedutilamd-pstate-epp powersave, EPP power160320480640800730.31693.85673.22632.541. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfiniteVolume -lmeshTools -lparallel -llagrangian -lregionModels -lgenericPatchFields -lOpenFOAM -ldl -lm

XNNPACK

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: QS8MobileNetV2amd-pstate-epp performanceamd-pstate-epp powersave, EPP poweracpi-cpufreq performanceacpi-cpufreq schedutil60K120K180K240K300KSE +/- 32620.26, N = 9SE +/- 28688.65, N = 6SE +/- 16900.30, N = 9SE +/- 29629.90, N = 93030652601992434162267571. (CXX) g++ options: -O3 -lrt -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP16MobileNetV3Smallamd-pstate-epp performanceacpi-cpufreq performanceamd-pstate-epp powersave, EPP poweracpi-cpufreq schedutil70K140K210K280K350KSE +/- 30695.56, N = 9SE +/- 20904.41, N = 9SE +/- 40655.76, N = 6SE +/- 15922.86, N = 93068682617402220911929841. (CXX) g++ options: -O3 -lrt -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP16MobileNetV3Largeamd-pstate-epp powersave, EPP poweracpi-cpufreq performanceamd-pstate-epp performanceacpi-cpufreq schedutil80K160K240K320K400KSE +/- 25113.17, N = 6SE +/- 39829.75, N = 9SE +/- 43034.08, N = 9SE +/- 10694.83, N = 93770093603383168592142931. (CXX) g++ options: -O3 -lrt -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP16MobileNetV2acpi-cpufreq performanceamd-pstate-epp performanceamd-pstate-epp powersave, EPP poweracpi-cpufreq schedutil50K100K150K200K250KSE +/- 26727.99, N = 9SE +/- 14007.04, N = 9SE +/- 28872.01, N = 6SE +/- 12388.73, N = 92451352356602017751607451. (CXX) g++ options: -O3 -lrt -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP16MobileNetV1acpi-cpufreq performanceamd-pstate-epp performanceamd-pstate-epp powersave, EPP poweracpi-cpufreq schedutil20K40K60K80K100KSE +/- 12603.55, N = 9SE +/- 7816.51, N = 9SE +/- 9815.30, N = 6SE +/- 9175.57, N = 91111389464089349793121. (CXX) g++ options: -O3 -lrt -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP32MobileNetV3Smallamd-pstate-epp powersave, EPP poweramd-pstate-epp performanceacpi-cpufreq performanceacpi-cpufreq schedutil70K140K210K280K350KSE +/- 42494.15, N = 6SE +/- 26742.74, N = 9SE +/- 34522.88, N = 9SE +/- 23141.95, N = 93211762814482420392157551. (CXX) g++ options: -O3 -lrt -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP32MobileNetV3Largeacpi-cpufreq performanceamd-pstate-epp powersave, EPP poweramd-pstate-epp performanceacpi-cpufreq schedutil70K140K210K280K350KSE +/- 39735.87, N = 9SE +/- 46863.64, N = 6SE +/- 37083.78, N = 9SE +/- 31970.03, N = 93147803102423064962664501. (CXX) g++ options: -O3 -lrt -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP32MobileNetV2amd-pstate-epp performanceacpi-cpufreq performanceamd-pstate-epp powersave, EPP poweracpi-cpufreq schedutil50K100K150K200K250KSE +/- 12562.08, N = 9SE +/- 24307.32, N = 9SE +/- 34560.66, N = 6SE +/- 18587.31, N = 92390942153122089751735461. (CXX) g++ options: -O3 -lrt -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP32MobileNetV1amd-pstate-epp powersave, EPP poweramd-pstate-epp performanceacpi-cpufreq performanceacpi-cpufreq schedutil20K40K60K80K100KSE +/- 11140.48, N = 6SE +/- 10333.77, N = 9SE +/- 8272.73, N = 9SE +/- 9091.20, N = 9107005102976100758716421. (CXX) g++ options: -O3 -lrt -lm

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.2Encoder Mode: Preset 3 - Input: Beauty 4K 10-bitamd-pstate-epp powersave, EPP poweracpi-cpufreq schedutilacpi-cpufreq performanceamd-pstate-epp performance0.39350.7871.18051.5741.9675SE +/- 0.002, N = 3SE +/- 0.003, N = 3SE +/- 0.003, N = 3SE +/- 0.002, N = 31.6051.7341.7491.749

easyWave

The easyWave software allows simulating tsunami generation and propagation in the context of early warning systems. EasyWave supports making use of OpenMP for CPU multi-threading and there are also GPU ports available but not currently incorporated as part of this test profile. The easyWave tsunami generation software is run with one of the example/reference input files for measuring the CPU execution time. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BettereasyWave r34Input: e2Asean Grid + BengkuluSept2007 Source - Time: 2400amd-pstate-epp performanceacpi-cpufreq schedutilamd-pstate-epp powersave, EPP poweracpi-cpufreq performance306090120150SE +/- 17.00, N = 12SE +/- 8.75, N = 15SE +/- 4.51, N = 12SE +/- 6.52, N = 15133.82105.84102.9197.321. (CXX) g++ options: -O3 -fopenmp

Stockfish

OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 17Chess Benchmarkacpi-cpufreq performanceacpi-cpufreq schedutilamd-pstate-epp powersave, EPP poweramd-pstate-epp performance200M400M600M800M1000MSE +/- 8305519.75, N = 15SE +/- 16235003.15, N = 15SE +/- 10216439.99, N = 4SE +/- 9684095.43, N = 38157853628175164288437978468502116881. (CXX) g++ options: -lgcov -m64 -lpthread -fno-exceptions -std=c++17 -fno-peel-loops -fno-tracer -pedantic -O3 -funroll-loops -msse -msse3 -mpopcnt -mavx2 -mbmi -mavx512f -mavx512bw -mavx512vnni -mavx512dq -mavx512vl -msse4.1 -mssse3 -msse2 -mbmi2 -flto -flto-partition=one -flto=jobserver

LiteRT

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: NASNet Mobileamd-pstate-epp performanceacpi-cpufreq performanceamd-pstate-epp powersave, EPP poweracpi-cpufreq schedutil300K600K900K1200K1500KSE +/- 95737.22, N = 12SE +/- 49109.78, N = 15SE +/- 99525.90, N = 12SE +/- 87991.61, N = 121440686137402713131241294618

DaCapo Benchmark

This test runs the DaCapo Benchmarks written in Java and intended to test system/CPU performance of various popular real-world Java workloads. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Apache Lucene Search Engineacpi-cpufreq schedutilamd-pstate-epp powersave, EPP poweramd-pstate-epp performanceacpi-cpufreq performance8K16K24K32K40KSE +/- 372.57, N = 5SE +/- 416.23, N = 15SE +/- 304.27, N = 15SE +/- 94.84, N = 335871324902627525814

LiteRT

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: Inception V4amd-pstate-epp performanceacpi-cpufreq schedutilamd-pstate-epp powersave, EPP poweracpi-cpufreq performance90K180K270K360K450KSE +/- 15462.87, N = 15SE +/- 19452.42, N = 15SE +/- 22160.81, N = 15SE +/- 19097.36, N = 15420326389419383528366367

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: Inception ResNet V2acpi-cpufreq performanceamd-pstate-epp powersave, EPP poweramd-pstate-epp performanceacpi-cpufreq schedutil120K240K360K480K600KSE +/- 40000.94, N = 15SE +/- 31545.86, N = 15SE +/- 23232.48, N = 15SE +/- 27055.81, N = 14571935570944556066509163

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 512 - Model: ResNet-50amd-pstate-epp powersave, EPP poweramd-pstate-epp performanceacpi-cpufreq performanceacpi-cpufreq schedutil50100150200250SE +/- 2.71, N = 3SE +/- 2.86, N = 3SE +/- 0.61, N = 3SE +/- 0.41, N = 3214.00218.14220.77220.94

LiteRT

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: DeepLab V3acpi-cpufreq performanceacpi-cpufreq schedutilamd-pstate-epp performanceamd-pstate-epp powersave, EPP power30K60K90K120K150KSE +/- 10503.47, N = 15SE +/- 11465.93, N = 15SE +/- 6547.94, N = 12SE +/- 4100.21, N = 15131016.5130544.5122224.6108089.4

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: SqueezeNetamd-pstate-epp powersave, EPP poweracpi-cpufreq performanceacpi-cpufreq schedutilamd-pstate-epp performance17K34K51K68K85KSE +/- 5257.47, N = 15SE +/- 4734.31, N = 15SE +/- 2486.13, N = 15SE +/- 4024.45, N = 1277253.471822.068551.067141.0

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: Mobilenet Floatamd-pstate-epp performanceamd-pstate-epp powersave, EPP poweracpi-cpufreq performanceacpi-cpufreq schedutil12K24K36K48K60KSE +/- 1980.12, N = 15SE +/- 4493.17, N = 15SE +/- 2999.48, N = 15SE +/- 1776.80, N = 1256226.751073.950891.949708.3

DaCapo Benchmark

This test runs the DaCapo Benchmarks written in Java and intended to test system/CPU performance of various popular real-world Java workloads. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Tradebeansamd-pstate-epp powersave, EPP poweracpi-cpufreq schedutilamd-pstate-epp performanceacpi-cpufreq performance4K8K12K16K20KSE +/- 794.76, N = 15SE +/- 618.67, N = 12SE +/- 235.77, N = 15SE +/- 136.02, N = 121968517849110968547

Apache Cassandra

OpenBenchmarking.orgOp/s, More Is BetterApache Cassandra 5.0Test: Writesamd-pstate-epp powersave, EPP poweracpi-cpufreq schedutilacpi-cpufreq performanceamd-pstate-epp performance60K120K180K240K300KSE +/- 3185.16, N = 3SE +/- 2802.92, N = 12SE +/- 1496.11, N = 3SE +/- 3195.31, N = 3272800283986293641297594

7-Zip Compression

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 24.05Test: Decompression Ratingamd-pstate-epp powersave, EPP poweramd-pstate-epp performanceacpi-cpufreq performanceacpi-cpufreq schedutil300K600K900K1200K1500KSE +/- 8783.54, N = 15SE +/- 4515.54, N = 13SE +/- 5780.94, N = 15SE +/- 8370.72, N = 1513095491373928137813813912801. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 24.05Test: Compression Ratingamd-pstate-epp powersave, EPP poweracpi-cpufreq schedutilacpi-cpufreq performanceamd-pstate-epp performance300K600K900K1200K1500KSE +/- 6703.84, N = 15SE +/- 8145.95, N = 15SE +/- 8577.67, N = 15SE +/- 8457.21, N = 139767081116731122941912651241. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

ClickHouse

ClickHouse is an open-source, high performance OLAP data management system. This test profile uses ClickHouse's standard benchmark recommendations per https://clickhouse.com/docs/en/operations/performance-test/ / https://github.com/ClickHouse/ClickBench/tree/main/clickhouse with the 100 million rows web analytics dataset. The reported value is the query processing time using the geometric mean of all separate queries performed as an aggregate. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse 22.12.3.5100M Rows Hits Dataset, Third Runamd-pstate-epp powersave, EPP poweracpi-cpufreq schedutilacpi-cpufreq performanceamd-pstate-epp performance150300450600750SE +/- 7.12, N = 3SE +/- 3.49, N = 3SE +/- 4.24, N = 3SE +/- 3.44, N = 6444.99451.86661.18674.14MIN: 109.69 / MAX: 2857.14MIN: 102.21 / MAX: 4285.71MIN: 121.21 / MAX: 6666.67MIN: 119.52 / MAX: 7500

OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse 22.12.3.5100M Rows Hits Dataset, Second Runamd-pstate-epp powersave, EPP poweracpi-cpufreq schedutilacpi-cpufreq performanceamd-pstate-epp performance140280420560700SE +/- 2.93, N = 3SE +/- 4.54, N = 3SE +/- 5.99, N = 3SE +/- 6.02, N = 6440.20448.23651.07666.68MIN: 105.45 / MAX: 3157.89MIN: 107.72 / MAX: 4285.71MIN: 120.72 / MAX: 6000MIN: 121.95 / MAX: 7500

OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse 22.12.3.5100M Rows Hits Dataset, First Run / Cold Cacheamd-pstate-epp powersave, EPP poweracpi-cpufreq schedutilacpi-cpufreq performanceamd-pstate-epp performance140280420560700SE +/- 1.84, N = 3SE +/- 2.09, N = 3SE +/- 8.80, N = 3SE +/- 6.62, N = 6427.35443.04641.43653.05MIN: 101.18 / MAX: 3333.33MIN: 105.26 / MAX: 4285.71MIN: 120.72 / MAX: 6666.67MIN: 118.81 / MAX: 6666.67

LiteRT

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: Quantized COCO SSD MobileNet v1amd-pstate-epp powersave, EPP poweramd-pstate-epp performanceacpi-cpufreq schedutilacpi-cpufreq performance16K32K48K64K80KSE +/- 3443.21, N = 15SE +/- 3239.30, N = 15SE +/- 833.30, N = 3SE +/- 2619.06, N = 1573932.873505.070075.465692.8

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.2Encoder Mode: Preset 5 - Input: Beauty 4K 10-bitamd-pstate-epp powersave, EPP poweracpi-cpufreq schedutilacpi-cpufreq performanceamd-pstate-epp performance246810SE +/- 0.015, N = 3SE +/- 0.016, N = 3SE +/- 0.009, N = 3SE +/- 0.016, N = 35.0616.7516.9726.994

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.2Encoder Mode: Preset 3 - Input: Bosphorus 4Kamd-pstate-epp powersave, EPP poweracpi-cpufreq schedutilamd-pstate-epp performanceacpi-cpufreq performance48121620SE +/- 0.03, N = 3SE +/- 0.10, N = 3SE +/- 0.05, N = 3SE +/- 0.03, N = 310.9912.7614.2614.27

LiteRT

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: Mobilenet Quantacpi-cpufreq schedutilacpi-cpufreq performanceamd-pstate-epp performanceamd-pstate-epp powersave, EPP power10K20K30K40K50KSE +/- 3098.66, N = 12SE +/- 3671.98, N = 12SE +/- 98.25, N = 3SE +/- 1628.59, N = 1548466.047789.544440.642023.4

easyWave

The easyWave software allows simulating tsunami generation and propagation in the context of early warning systems. EasyWave supports making use of OpenMP for CPU multi-threading and there are also GPU ports available but not currently incorporated as part of this test profile. The easyWave tsunami generation software is run with one of the example/reference input files for measuring the CPU execution time. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BettereasyWave r34Input: e2Asean Grid + BengkuluSept2007 Source - Time: 1200amd-pstate-epp performanceamd-pstate-epp powersave, EPP poweracpi-cpufreq schedutilacpi-cpufreq performance1020304050SE +/- 2.77, N = 12SE +/- 1.57, N = 12SE +/- 1.90, N = 12SE +/- 0.99, N = 1245.9842.6540.9640.061. (CXX) g++ options: -O3 -fopenmp

Timed LLVM Compilation

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 16.0Build System: Unix Makefilesamd-pstate-epp powersave, EPP poweracpi-cpufreq performanceacpi-cpufreq schedutilamd-pstate-epp performance4080120160200SE +/- 0.07, N = 3SE +/- 0.19, N = 3SE +/- 0.35, N = 3SE +/- 0.16, N = 3164.49161.31161.14160.72

CP2K Molecular Dynamics

OpenBenchmarking.orgSeconds, Fewer Is BetterCP2K Molecular Dynamics 2024.3Input: H20-256amd-pstate-epp performanceamd-pstate-epp powersave, EPP poweracpi-cpufreq schedutilacpi-cpufreq performance306090120150SE +/- 0.65, N = 3SE +/- 0.78, N = 3SE +/- 0.26, N = 3SE +/- 0.60, N = 3141.64140.97140.58140.341. (F9X) gfortran options: -fopenmp -march=native -mtune=native -O3 -funroll-loops -fbacktrace -ffree-form -fimplicit-none -std=f2008 -lcp2kstart -lcp2kmc -lcp2kswarm -lcp2kmotion -lcp2kthermostat -lcp2kemd -lcp2ktmc -lcp2kmain -lcp2kdbt -lcp2ktas -lcp2kgrid -lcp2kgriddgemm -lcp2kgridcpu -lcp2kgridref -lcp2kgridcommon -ldbcsrarnoldi -ldbcsrx -lcp2kdbx -lcp2kdbm -lcp2kshg_int -lcp2keri_mme -lcp2kminimax -lcp2khfxbase -lcp2ksubsys -lcp2kxc -lcp2kao -lcp2kpw_env -lcp2kinput -lcp2kpw -lcp2kgpu -lcp2kfft -lcp2kfpga -lcp2kfm -lcp2kcommon -lcp2koffload -lcp2kmpiwrap -lcp2kbase -ldbcsr -lsirius -lspla -lspfft -lsymspg -lvdwxc -l:libhdf5_fortran.a -l:libhdf5.a -lz -lgsl -lelpa_openmp -lcosma -lcosta -lscalapack -lxsmmf -lxsmm -ldl -lpthread -llibgrpp -lxcf03 -lxc -lint2 -lfftw3_mpi -lfftw3 -lfftw3_omp -lmpi_cxx -lmpi -l:libopenblas.a -lvori -lstdc++ -lmpi_usempif08 -lmpi_mpifh -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.2Encoder Mode: Preset 8 - Input: Beauty 4K 10-bitamd-pstate-epp powersave, EPP poweracpi-cpufreq schedutilamd-pstate-epp performanceacpi-cpufreq performance3691215SE +/- 0.025, N = 3SE +/- 0.004, N = 3SE +/- 0.022, N = 3SE +/- 0.022, N = 36.8088.8659.3879.400

oneDNN

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.6Harness: Recurrent Neural Network Training - Engine: CPUacpi-cpufreq schedutilamd-pstate-epp powersave, EPP poweramd-pstate-epp performanceacpi-cpufreq performance2004006008001000SE +/- 15.98, N = 14SE +/- 8.20, N = 3SE +/- 3.59, N = 3SE +/- 0.95, N = 3794.38789.09778.12775.25MIN: 749.39MIN: 750.44MIN: 745.1MIN: 748.251. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -fcf-protection=full -pie -ldl -lpthread

OSPRay

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 3.2Benchmark: particle_volume/pathtracer/real_timeacpi-cpufreq performanceamd-pstate-epp performanceacpi-cpufreq schedutilamd-pstate-epp powersave, EPP power50100150200250SE +/- 1.13, N = 3SE +/- 0.29, N = 3SE +/- 0.42, N = 3SE +/- 0.73, N = 3210.85211.47211.53212.03

PostgreSQL

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 17Scaling Factor: 100 - Clients: 1000 - Mode: Read Write - Average Latencyacpi-cpufreq schedutilamd-pstate-epp powersave, EPP poweramd-pstate-epp performanceacpi-cpufreq performance20406080100SE +/- 0.53, N = 3SE +/- 0.93, N = 3SE +/- 0.27, N = 3SE +/- 0.80, N = 382.4681.5579.9678.011. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpq -lpgcommon -lpgport -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 17Scaling Factor: 100 - Clients: 1000 - Mode: Read Writeacpi-cpufreq schedutilamd-pstate-epp powersave, EPP poweramd-pstate-epp performanceacpi-cpufreq performance3K6K9K12K15KSE +/- 77.18, N = 3SE +/- 138.02, N = 3SE +/- 42.62, N = 3SE +/- 129.70, N = 3121291226512506128211. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpq -lpgcommon -lpgport -lm

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 17Scaling Factor: 100 - Clients: 1000 - Mode: Read Only - Average Latencyamd-pstate-epp powersave, EPP poweramd-pstate-epp performanceacpi-cpufreq schedutilacpi-cpufreq performance0.05420.10840.16260.21680.271SE +/- 0.003, N = 3SE +/- 0.002, N = 3SE +/- 0.001, N = 3SE +/- 0.001, N = 30.2410.2390.2390.2381. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpq -lpgcommon -lpgport -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 17Scaling Factor: 100 - Clients: 1000 - Mode: Read Onlyamd-pstate-epp powersave, EPP poweracpi-cpufreq schedutilacpi-cpufreq performanceamd-pstate-epp performance900K1800K2700K3600K4500KSE +/- 51419.26, N = 3SE +/- 15318.86, N = 3SE +/- 17412.45, N = 3SE +/- 31939.88, N = 341528054188802419453241950191. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpq -lpgcommon -lpgport -lm

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 6.8Build: allmodconfigacpi-cpufreq schedutilamd-pstate-epp powersave, EPP poweracpi-cpufreq performanceamd-pstate-epp performance306090120150SE +/- 0.41, N = 3SE +/- 0.79, N = 3SE +/- 0.62, N = 3SE +/- 0.37, N = 3142.13135.91132.21131.84

SPECFEM3D

simulates acoustic (fluid), elastic (solid), coupled acoustic/elastic, poroelastic or seismic wave propagation in any type of conforming mesh of hexahedra. This test profile currently relies on CPU-based execution for SPECFEM3D and using a variety of their built-in examples/models for benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.1.1Model: Layered Halfspaceamd-pstate-epp powersave, EPP poweracpi-cpufreq performanceamd-pstate-epp performanceacpi-cpufreq schedutil246810SE +/- 0.213651076, N = 12SE +/- 0.119672870, N = 15SE +/- 0.089357142, N = 15SE +/- 0.061937588, N = 156.8775906916.8671024586.8410817336.5629106081. (F9X) gfortran options: -O2 -fopenmp -std=f2008 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

Timed Gem5 Compilation

This test times how long it takes to compile Gem5. Gem5 is a simulator for computer system architecture research. Gem5 is widely used for computer architecture research within the industry, academia, and more. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Gem5 Compilation 23.0.1Time To Compileamd-pstate-epp powersave, EPP poweracpi-cpufreq schedutilacpi-cpufreq performanceamd-pstate-epp performance306090120150SE +/- 0.53, N = 3SE +/- 0.58, N = 3SE +/- 1.24, N = 3SE +/- 0.48, N = 3134.95121.83118.60116.95

SPECFEM3D

simulates acoustic (fluid), elastic (solid), coupled acoustic/elastic, poroelastic or seismic wave propagation in any type of conforming mesh of hexahedra. This test profile currently relies on CPU-based execution for SPECFEM3D and using a variety of their built-in examples/models for benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.1.1Model: Tomographic Modelamd-pstate-epp performanceacpi-cpufreq schedutilamd-pstate-epp powersave, EPP poweracpi-cpufreq performance0.91141.82282.73423.64564.557SE +/- 0.146285208, N = 15SE +/- 0.129512298, N = 15SE +/- 0.100983661, N = 15SE +/- 0.069494966, N = 154.0508025503.8911083093.7849924683.6560200761. (F9X) gfortran options: -O2 -fopenmp -std=f2008 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

DaCapo Benchmark

This test runs the DaCapo Benchmarks written in Java and intended to test system/CPU performance of various popular real-world Java workloads. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: H2 Database Engineacpi-cpufreq schedutilamd-pstate-epp powersave, EPP poweracpi-cpufreq performanceamd-pstate-epp performance11002200330044005500SE +/- 66.08, N = 4SE +/- 55.32, N = 3SE +/- 33.64, N = 15SE +/- 34.65, N = 155335476733263215

SPECFEM3D

simulates acoustic (fluid), elastic (solid), coupled acoustic/elastic, poroelastic or seismic wave propagation in any type of conforming mesh of hexahedra. This test profile currently relies on CPU-based execution for SPECFEM3D and using a variety of their built-in examples/models for benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.1.1Model: Water-layered Halfspaceamd-pstate-epp performanceamd-pstate-epp powersave, EPP poweracpi-cpufreq schedutilacpi-cpufreq performance246810SE +/- 0.120836417, N = 15SE +/- 0.137117072, N = 15SE +/- 0.092706238, N = 15SE +/- 0.092456998, N = 37.9444859647.8555356697.6219602297.2655254681. (F9X) gfortran options: -O2 -fopenmp -std=f2008 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.1.1Model: Homogeneous Halfspaceamd-pstate-epp powersave, EPP poweramd-pstate-epp performanceacpi-cpufreq performanceacpi-cpufreq schedutil1.07142.14283.21424.28565.357SE +/- 0.117098618, N = 15SE +/- 0.166702204, N = 12SE +/- 0.125540742, N = 12SE +/- 0.121781767, N = 154.7618424524.7170373194.6254168704.5884122911. (F9X) gfortran options: -O2 -fopenmp -std=f2008 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

PyTorch

This is a benchmark of PyTorch making use of pytorch-benchmark [https://github.com/LukasHedegaard/pytorch-benchmark]. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 512 - Model: ResNet-50amd-pstate-epp performanceacpi-cpufreq performanceacpi-cpufreq schedutilamd-pstate-epp powersave, EPP power510152025SE +/- 0.12, N = 3SE +/- 0.30, N = 3SE +/- 0.27, N = 3SE +/- 0.21, N = 321.6721.7122.1022.40MIN: 17.67 / MAX: 25.57MIN: 20.56 / MAX: 22.75MIN: 13.05 / MAX: 23.43MIN: 20.39 / MAX: 25.7

nginx

This is a benchmark of the lightweight Nginx HTTP(S) web-server. This Nginx web server benchmark test profile makes use of the wrk program for facilitating the HTTP requests over a fixed period time with a configurable number of concurrent clients/connections. HTTPS with a self-signed OpenSSL certificate is used by this test for local benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.23.2Connections: 1000amd-pstate-epp powersave, EPP poweracpi-cpufreq schedutilamd-pstate-epp performanceacpi-cpufreq performance80K160K240K320K400KSE +/- 935.65, N = 3SE +/- 675.70, N = 3SE +/- 1924.75, N = 3SE +/- 1096.44, N = 3373848.47378838.78381450.99382110.681. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2

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 21.7.2Time To Compileamd-pstate-epp powersave, EPP poweracpi-cpufreq schedutilacpi-cpufreq performanceamd-pstate-epp performance20406080100SE +/- 0.13, N = 3SE +/- 0.67, N = 3SE +/- 0.08, N = 3SE +/- 0.31, N = 393.3990.2389.0388.84

Apache HTTP Server

This is a test of the Apache HTTPD web server. This Apache HTTPD web server benchmark test profile makes use of the wrk program for facilitating the HTTP requests over a fixed period time with a configurable number of concurrent clients. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterApache HTTP Server 2.4.56Concurrent Requests: 1000amd-pstate-epp powersave, EPP poweramd-pstate-epp performanceacpi-cpufreq performanceacpi-cpufreq schedutil20K40K60K80K100KSE +/- 77.98, N = 3SE +/- 78.02, N = 3SE +/- 135.49, N = 3SE +/- 48.19, N = 372820.6289729.5292874.5594660.921. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2

NAMD

OpenBenchmarking.orgns/day, More Is BetterNAMD 3.0Input: STMV with 1,066,628 Atomsacpi-cpufreq performanceamd-pstate-epp powersave, EPP poweracpi-cpufreq schedutilamd-pstate-epp performance3691215SE +/- 0.00175, N = 3SE +/- 0.03993, N = 3SE +/- 0.03107, N = 3SE +/- 0.01893, N = 39.533229.584729.643999.66160

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 6.8Build: defconfigamd-pstate-epp powersave, EPP poweracpi-cpufreq schedutilacpi-cpufreq performanceamd-pstate-epp performance510152025SE +/- 0.20, N = 15SE +/- 0.14, N = 11SE +/- 0.13, N = 13SE +/- 0.15, N = 1221.8819.2718.9818.76

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.2Encoder Mode: Preset 13 - Input: Beauty 4K 10-bitamd-pstate-epp powersave, EPP poweracpi-cpufreq schedutilacpi-cpufreq performanceamd-pstate-epp performance48121620SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 312.6113.8015.9015.94

SPECFEM3D

simulates acoustic (fluid), elastic (solid), coupled acoustic/elastic, poroelastic or seismic wave propagation in any type of conforming mesh of hexahedra. This test profile currently relies on CPU-based execution for SPECFEM3D and using a variety of their built-in examples/models for benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.1.1Model: Mount St. Helensacpi-cpufreq performanceacpi-cpufreq schedutilamd-pstate-epp powersave, EPP poweramd-pstate-epp performance0.80311.60622.40933.21244.0155SE +/- 0.088223419, N = 12SE +/- 0.104394989, N = 15SE +/- 0.063875374, N = 15SE +/- 0.040023214, N = 33.5692442433.5326436243.5041133483.2904529021. (F9X) gfortran options: -O2 -fopenmp -std=f2008 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

DaCapo Benchmark

This test runs the DaCapo Benchmarks written in Java and intended to test system/CPU performance of various popular real-world Java workloads. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Spring Bootacpi-cpufreq schedutilamd-pstate-epp powersave, EPP poweramd-pstate-epp performanceacpi-cpufreq performance13002600390052006500SE +/- 205.67, N = 12SE +/- 101.19, N = 15SE +/- 42.19, N = 3SE +/- 160.15, N = 156173566250293764

OpenFOAM

OpenFOAM is the leading free, open-source software for computational fluid dynamics (CFD). This test profile currently uses the drivaerFastback test case for analyzing automotive aerodynamics or alternatively the older motorBike input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 10Input: drivaerFastback, Medium Mesh Size - Execution Timeacpi-cpufreq schedutilamd-pstate-epp powersave, EPP poweracpi-cpufreq performanceamd-pstate-epp performance2040608010075.7872.7872.3370.931. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfiniteVolume -lmeshTools -lparallel -llagrangian -lregionModels -lgenericPatchFields -lOpenFOAM -ldl -lm

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 10Input: drivaerFastback, Medium Mesh Size - Mesh Timeamd-pstate-epp powersave, EPP poweracpi-cpufreq performanceamd-pstate-epp performanceacpi-cpufreq schedutil306090120150139.31128.72127.45126.761. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfiniteVolume -lmeshTools -lparallel -llagrangian -lregionModels -lgenericPatchFields -lOpenFOAM -ldl -lm

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 2024Implementation: MPI CPU - Input: water_GMX50_bareamd-pstate-epp performanceacpi-cpufreq schedutilamd-pstate-epp powersave, EPP poweracpi-cpufreq performance816243240SE +/- 0.33, N = 6SE +/- 0.31, N = 3SE +/- 0.24, N = 15SE +/- 0.24, N = 332.4032.4633.1133.631. (CXX) g++ options: -O3 -lm

DaCapo Benchmark

This test runs the DaCapo Benchmarks written in Java and intended to test system/CPU performance of various popular real-world Java workloads. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Tradesoapamd-pstate-epp powersave, EPP poweracpi-cpufreq schedutilamd-pstate-epp performanceacpi-cpufreq performance2K4K6K8K10KSE +/- 115.47, N = 3SE +/- 51.19, N = 3SE +/- 76.30, N = 15SE +/- 29.34, N = 1210447943448704073

Memcached

Memcached is a high performance, distributed memory object caching system. This Memcached test profiles makes use of memtier_benchmark for excuting this CPU/memory-focused server benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOps/sec, More Is BetterMemcached 1.6.19Set To Get Ratio: 1:100acpi-cpufreq schedutilamd-pstate-epp powersave, EPP poweramd-pstate-epp performanceacpi-cpufreq performance3M6M9M12M15MSE +/- 96851.07, N = 3SE +/- 115313.62, N = 3SE +/- 30429.78, N = 3SE +/- 82510.27, N = 312033636.8312108995.3312237534.6412296822.611. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

OpenBenchmarking.orgOps/sec, More Is BetterMemcached 1.6.19Set To Get Ratio: 1:10amd-pstate-epp powersave, EPP poweramd-pstate-epp performanceacpi-cpufreq performanceacpi-cpufreq schedutil900K1800K2700K3600K4500KSE +/- 11855.14, N = 3SE +/- 7025.74, N = 3SE +/- 9726.52, N = 3SE +/- 3296.60, N = 34349758.694364726.014374101.464375833.911. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

Timed LLVM Compilation

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 16.0Build System: Ninjaacpi-cpufreq performanceamd-pstate-epp powersave, EPP poweracpi-cpufreq schedutilamd-pstate-epp performance1428425670SE +/- 0.81, N = 3SE +/- 0.32, N = 3SE +/- 0.61, N = 3SE +/- 0.24, N = 363.9363.7263.4963.31

OSPRay Studio

Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity 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.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 3 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPUamd-pstate-epp powersave, EPP poweramd-pstate-epp performanceacpi-cpufreq schedutilacpi-cpufreq performance3K6K9K12K15KSE +/- 35.18, N = 3SE +/- 2.19, N = 3SE +/- 21.36, N = 3SE +/- 46.41, N = 312429123961237912367

OSPRay

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 3.2Benchmark: gravity_spheres_volume/dim_512/ao/real_timeamd-pstate-epp powersave, EPP poweracpi-cpufreq performanceacpi-cpufreq schedutilamd-pstate-epp performance20406080100SE +/- 0.39, N = 3SE +/- 0.10, N = 3SE +/- 0.13, N = 3SE +/- 0.17, N = 376.8676.9077.0277.11

OSPRay Studio

Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity 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.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 3 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPUacpi-cpufreq schedutilamd-pstate-epp performanceamd-pstate-epp powersave, EPP poweracpi-cpufreq performance90180270360450SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3392391391390

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.2Encoder Mode: Preset 5 - Input: Bosphorus 4Kamd-pstate-epp powersave, EPP poweracpi-cpufreq schedutilamd-pstate-epp performanceacpi-cpufreq performance1122334455SE +/- 0.46, N = 3SE +/- 0.18, N = 3SE +/- 0.13, N = 3SE +/- 0.19, N = 334.0244.0449.9650.66

OSPRay Studio

Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity 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.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 1 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPUamd-pstate-epp powersave, EPP poweracpi-cpufreq schedutilamd-pstate-epp performanceacpi-cpufreq performance70140210280350SE +/- 0.33, N = 3SE +/- 0.67, N = 3SE +/- 0.67, N = 3SE +/- 0.00, N = 3331331330330

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 1 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPUamd-pstate-epp powersave, EPP poweracpi-cpufreq schedutilamd-pstate-epp performanceacpi-cpufreq performance2K4K6K8K10KSE +/- 35.62, N = 3SE +/- 5.21, N = 3SE +/- 39.27, N = 3SE +/- 19.55, N = 310507104631044110423

DaCapo Benchmark

This test runs the DaCapo Benchmarks written in Java and intended to test system/CPU performance of various popular real-world Java workloads. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: PMD Source Code Analyzeramd-pstate-epp powersave, EPP poweracpi-cpufreq schedutilamd-pstate-epp performanceacpi-cpufreq performance8001600240032004000SE +/- 69.08, N = 15SE +/- 29.17, N = 4SE +/- 96.35, N = 12SE +/- 66.47, N = 153722357727192443

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.2Blend File: Barbershop - Compute: CPU-Onlyamd-pstate-epp powersave, EPP poweracpi-cpufreq schedutilamd-pstate-epp performanceacpi-cpufreq performance1122334455SE +/- 0.05, N = 3SE +/- 0.14, N = 3SE +/- 0.08, N = 3SE +/- 0.06, N = 347.5047.2647.0447.02

DaCapo Benchmark

This test runs the DaCapo Benchmarks written in Java and intended to test system/CPU performance of various popular real-world Java workloads. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Apache Lucene Search Indexamd-pstate-epp powersave, EPP poweracpi-cpufreq schedutilacpi-cpufreq performanceamd-pstate-epp performance6001200180024003000SE +/- 18.65, N = 14SE +/- 17.95, N = 3SE +/- 14.45, N = 3SE +/- 15.21, N = 33020291528512850

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Eclipseamd-pstate-epp powersave, EPP poweracpi-cpufreq schedutilamd-pstate-epp performanceacpi-cpufreq performance2K4K6K8K10KSE +/- 17.69, N = 3SE +/- 30.63, N = 3SE +/- 79.54, N = 5SE +/- 74.30, N = 38845827977197604

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Apache Tomcatamd-pstate-epp powersave, EPP poweracpi-cpufreq schedutilamd-pstate-epp performanceacpi-cpufreq performance6001200180024003000SE +/- 21.23, N = 15SE +/- 16.89, N = 5SE +/- 14.52, N = 5SE +/- 28.63, N = 122618252917711615

Timed Wasmer Compilation

This test times how long it takes to compile Wasmer. Wasmer is written in the Rust programming language and is a WebAssembly runtime implementation that supports WASI and EmScripten. This test profile builds Wasmer with the Cranelift and Singlepast compiler features enabled. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Wasmer Compilation 2.3Time To Compileamd-pstate-epp powersave, EPP poweracpi-cpufreq performanceacpi-cpufreq schedutilamd-pstate-epp performance714212835SE +/- 0.12, N = 3SE +/- 0.17, N = 3SE +/- 0.22, N = 3SE +/- 0.03, N = 328.6227.1727.1026.791. (CC) gcc options: -m64 -ldl -lgcc_s -lutil -lrt -lpthread -lm -lc -pie -nodefaultlibs

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.2Encoder Mode: Preset 8 - Input: Bosphorus 4Kamd-pstate-epp powersave, EPP poweracpi-cpufreq schedutilamd-pstate-epp performanceacpi-cpufreq performance306090120150SE +/- 0.21, N = 3SE +/- 0.34, N = 3SE +/- 0.22, N = 3SE +/- 0.64, N = 381.9086.40112.68114.68

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 2.2Video Input: Bosphorus 4K - Video Preset: Mediumacpi-cpufreq schedutilamd-pstate-epp powersave, EPP poweramd-pstate-epp performanceacpi-cpufreq performance20406080100SE +/- 0.43, N = 15SE +/- 0.50, N = 6SE +/- 0.50, N = 6SE +/- 0.21, N = 654.3776.9382.4383.301. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

DaCapo Benchmark

This test runs the DaCapo Benchmarks written in Java and intended to test system/CPU performance of various popular real-world Java workloads. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Avrora AVR Simulation Frameworkacpi-cpufreq schedutilamd-pstate-epp powersave, EPP poweramd-pstate-epp performanceacpi-cpufreq performance12002400360048006000SE +/- 32.32, N = 3SE +/- 39.23, N = 4SE +/- 42.45, N = 15SE +/- 8.86, N = 55415452531932700

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Apache Xalan XSLTacpi-cpufreq schedutilamd-pstate-epp powersave, EPP poweramd-pstate-epp performanceacpi-cpufreq performance400800120016002000SE +/- 20.87, N = 15SE +/- 32.56, N = 15SE +/- 7.22, N = 7SE +/- 25.65, N = 15165415961290957

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: GraphChiamd-pstate-epp powersave, EPP poweracpi-cpufreq schedutilamd-pstate-epp performanceacpi-cpufreq performance8001600240032004000SE +/- 15.10, N = 3SE +/- 21.79, N = 4SE +/- 22.50, N = 4SE +/- 20.35, N = 93732275426132579

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.2Encoder Mode: Preset 13 - Input: Bosphorus 4Kacpi-cpufreq schedutilamd-pstate-epp powersave, EPP poweramd-pstate-epp performanceacpi-cpufreq performance90180270360450SE +/- 1.63, N = 5SE +/- 1.40, N = 5SE +/- 3.02, N = 15SE +/- 2.95, N = 6280.45295.02312.21403.60

DaCapo Benchmark

This test runs the DaCapo Benchmarks written in Java and intended to test system/CPU performance of various popular real-world Java workloads. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Apache Kafkaamd-pstate-epp powersave, EPP poweracpi-cpufreq schedutilamd-pstate-epp performanceacpi-cpufreq performance13002600390052006500SE +/- 30.37, N = 3SE +/- 24.69, N = 3SE +/- 29.54, N = 3SE +/- 14.62, N = 36296627860486042

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: jMonkeyEngineamd-pstate-epp powersave, EPP poweracpi-cpufreq schedutilacpi-cpufreq performanceamd-pstate-epp performance15003000450060007500SE +/- 0.58, N = 3SE +/- 1.86, N = 3SE +/- 0.33, N = 3SE +/- 1.73, N = 36982690868376835

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: BioJava Biological Data Frameworkamd-pstate-epp powersave, EPP poweracpi-cpufreq schedutilamd-pstate-epp performanceacpi-cpufreq performance11002200330044005500SE +/- 39.44, N = 4SE +/- 13.33, N = 4SE +/- 11.01, N = 4SE +/- 41.96, N = 44899487847854719

OpenFOAM

OpenFOAM is the leading free, open-source software for computational fluid dynamics (CFD). This test profile currently uses the drivaerFastback test case for analyzing automotive aerodynamics or alternatively the older motorBike input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 10Input: drivaerFastback, Small Mesh Size - Execution Timeacpi-cpufreq schedutilamd-pstate-epp performanceamd-pstate-epp powersave, EPP poweracpi-cpufreq performance4812162015.3214.9914.8814.521. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfiniteVolume -lmeshTools -lparallel -llagrangian -lregionModels -lgenericPatchFields -lOpenFOAM -ldl -lm

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 10Input: drivaerFastback, Small Mesh Size - Mesh Timeacpi-cpufreq schedutilacpi-cpufreq performanceamd-pstate-epp performanceamd-pstate-epp powersave, EPP power61218243025.0221.1719.9819.051. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfiniteVolume -lmeshTools -lparallel -llagrangian -lregionModels -lgenericPatchFields -lOpenFOAM -ldl -lm

DaCapo Benchmark

This test runs the DaCapo Benchmarks written in Java and intended to test system/CPU performance of various popular real-world Java workloads. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Zxing 1D/2D Barcode Image Processingamd-pstate-epp powersave, EPP poweracpi-cpufreq schedutilacpi-cpufreq performanceamd-pstate-epp performance80160240320400SE +/- 7.30, N = 15SE +/- 7.16, N = 15SE +/- 6.97, N = 15SE +/- 7.47, N = 15369301282266

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 2.2Video Input: Bosphorus 4K - Video Preset: Ultra Fastamd-pstate-epp powersave, EPP poweracpi-cpufreq schedutilamd-pstate-epp performanceacpi-cpufreq performance20406080100SE +/- 0.50, N = 6SE +/- 0.57, N = 15SE +/- 0.74, N = 6SE +/- 0.31, N = 682.1483.6191.4094.051. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

DaCapo Benchmark

This test runs the DaCapo Benchmarks written in Java and intended to test system/CPU performance of various popular real-world Java workloads. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Jythonamd-pstate-epp powersave, EPP poweracpi-cpufreq schedutilamd-pstate-epp performanceacpi-cpufreq performance10002000300040005000SE +/- 25.42, N = 3SE +/- 11.72, N = 3SE +/- 21.18, N = 4SE +/- 9.70, N = 44829467446134581

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 2.2Video Input: Bosphorus 4K - Video Preset: Slowacpi-cpufreq schedutilamd-pstate-epp powersave, EPP poweramd-pstate-epp performanceacpi-cpufreq performance20406080100SE +/- 0.57, N = 5SE +/- 0.33, N = 6SE +/- 0.39, N = 6SE +/- 0.47, N = 654.1576.8981.9483.211. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.2Blend File: Junkshop - Compute: CPU-Onlyamd-pstate-epp powersave, EPP poweracpi-cpufreq schedutilacpi-cpufreq performanceamd-pstate-epp performance246810SE +/- 0.03, N = 5SE +/- 0.03, N = 6SE +/- 0.02, N = 6SE +/- 0.01, N = 67.917.707.547.52

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 2.2Video Input: Bosphorus 4K - Video Preset: Super Fastamd-pstate-epp powersave, EPP poweracpi-cpufreq schedutilamd-pstate-epp performanceacpi-cpufreq performance20406080100SE +/- 0.53, N = 6SE +/- 0.69, N = 8SE +/- 0.89, N = 6SE +/- 0.84, N = 681.2782.3189.8891.511. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: Very Fastamd-pstate-epp powersave, EPP poweracpi-cpufreq schedutilamd-pstate-epp performanceacpi-cpufreq performance20406080100SE +/- 0.31, N = 6SE +/- 0.79, N = 6SE +/- 0.50, N = 6SE +/- 0.73, N = 681.2883.0988.9090.761. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

oneDNN

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.6Harness: Deconvolution Batch shapes_3d - Engine: CPUamd-pstate-epp performanceamd-pstate-epp powersave, EPP poweracpi-cpufreq performanceacpi-cpufreq schedutil0.1010.2020.3030.4040.505SE +/- 0.006065, N = 15SE +/- 0.003691, N = 9SE +/- 0.008627, N = 15SE +/- 0.008672, N = 150.4487290.4482380.4479620.445843MIN: 0.39MIN: 0.39MIN: 0.4MIN: 0.391. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -fcf-protection=full -pie -ldl -lpthread

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.2Blend File: BMW27 - Compute: CPU-Onlyamd-pstate-epp powersave, EPP poweracpi-cpufreq schedutilacpi-cpufreq performanceamd-pstate-epp performance1.25782.51563.77345.03126.289SE +/- 0.03, N = 7SE +/- 0.02, N = 7SE +/- 0.02, N = 7SE +/- 0.02, N = 75.595.485.345.33

DaCapo Benchmark

This test runs the DaCapo Benchmarks written in Java and intended to test system/CPU performance of various popular real-world Java workloads. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Batik SVG Toolkitamd-pstate-epp powersave, EPP poweracpi-cpufreq schedutilamd-pstate-epp performanceacpi-cpufreq performance30060090012001500SE +/- 9.68, N = 7SE +/- 6.67, N = 7SE +/- 8.82, N = 10SE +/- 4.79, N = 71247116811491131

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: FOP Print Formatteramd-pstate-epp powersave, EPP poweracpi-cpufreq schedutilamd-pstate-epp performanceacpi-cpufreq performance120240360480600SE +/- 8.80, N = 15SE +/- 2.68, N = 9SE +/- 3.80, N = 10SE +/- 1.71, N = 10533509483466

100 Results Shown

OpenFOAM:
  drivaerFastback, Large Mesh Size - Execution Time
  drivaerFastback, Large Mesh Size - Mesh Time
XNNPACK:
  QS8MobileNetV2
  FP16MobileNetV3Small
  FP16MobileNetV3Large
  FP16MobileNetV2
  FP16MobileNetV1
  FP32MobileNetV3Small
  FP32MobileNetV3Large
  FP32MobileNetV2
  FP32MobileNetV1
SVT-AV1
easyWave
Stockfish
LiteRT
DaCapo Benchmark
LiteRT:
  Inception V4
  Inception ResNet V2
TensorFlow
LiteRT:
  DeepLab V3
  SqueezeNet
  Mobilenet Float
DaCapo Benchmark
Apache Cassandra
7-Zip Compression:
  Decompression Rating
  Compression Rating
ClickHouse:
  100M Rows Hits Dataset, Third Run
  100M Rows Hits Dataset, Second Run
  100M Rows Hits Dataset, First Run / Cold Cache
LiteRT
SVT-AV1:
  Preset 5 - Beauty 4K 10-bit
  Preset 3 - Bosphorus 4K
LiteRT
easyWave
Timed LLVM Compilation
CP2K Molecular Dynamics
SVT-AV1
oneDNN
OSPRay
PostgreSQL:
  100 - 1000 - Read Write - Average Latency
  100 - 1000 - Read Write
  100 - 1000 - Read Only - Average Latency
  100 - 1000 - Read Only
Timed Linux Kernel Compilation
SPECFEM3D
Timed Gem5 Compilation
SPECFEM3D
DaCapo Benchmark
SPECFEM3D:
  Water-layered Halfspace
  Homogeneous Halfspace
PyTorch
nginx
Timed Node.js Compilation
Apache HTTP Server
NAMD
Timed Linux Kernel Compilation
SVT-AV1
SPECFEM3D
DaCapo Benchmark
OpenFOAM:
  drivaerFastback, Medium Mesh Size - Execution Time
  drivaerFastback, Medium Mesh Size - Mesh Time
GROMACS
DaCapo Benchmark
Memcached:
  1:100
  1:10
Timed LLVM Compilation
OSPRay Studio
OSPRay
OSPRay Studio
SVT-AV1
OSPRay Studio:
  1 - 4K - 1 - Path Tracer - CPU
  1 - 4K - 32 - Path Tracer - CPU
DaCapo Benchmark
Blender
DaCapo Benchmark:
  Apache Lucene Search Index
  Eclipse
  Apache Tomcat
Timed Wasmer Compilation
SVT-AV1
Kvazaar
DaCapo Benchmark:
  Avrora AVR Simulation Framework
  Apache Xalan XSLT
  GraphChi
SVT-AV1
DaCapo Benchmark:
  Apache Kafka
  jMonkeyEngine
  BioJava Biological Data Framework
OpenFOAM:
  drivaerFastback, Small Mesh Size - Execution Time
  drivaerFastback, Small Mesh Size - Mesh Time
DaCapo Benchmark
Kvazaar
DaCapo Benchmark
Kvazaar
Blender
Kvazaar:
  Bosphorus 4K - Super Fast
  Bosphorus 4K - Very Fast
oneDNN
Blender
DaCapo Benchmark:
  Batik SVG Toolkit
  FOP Print Formatter