AMD EPYC 4124P CPU Review Benchmarks

Benchmarks preparing for a future article on Phoronix.com by Michael Larabel.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2405238-NE-MERGE298576
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 2 Tests
C++ Boost Tests 4 Tests
Chess Test Suite 2 Tests
Timed Code Compilation 10 Tests
C/C++ Compiler Tests 18 Tests
Compression Tests 3 Tests
CPU Massive 34 Tests
Creator Workloads 26 Tests
Cryptography 4 Tests
Database Test Suite 7 Tests
Encoding 9 Tests
Fortran Tests 6 Tests
Game Development 6 Tests
HPC - High Performance Computing 20 Tests
Imaging 3 Tests
Java 3 Tests
Common Kernel Benchmarks 4 Tests
Machine Learning 6 Tests
Molecular Dynamics 7 Tests
MPI Benchmarks 7 Tests
Multi-Core 50 Tests
NVIDIA GPU Compute 4 Tests
Intel oneAPI 7 Tests
OpenMPI Tests 12 Tests
Programmer / Developer System Benchmarks 13 Tests
Python 2 Tests
Raytracing 2 Tests
Renderers 6 Tests
Scientific Computing 10 Tests
Software Defined Radio 2 Tests
Server 13 Tests
Server CPU Tests 25 Tests
Single-Threaded 3 Tests
Texture Compression 2 Tests
Video Encoding 9 Tests
Common Workstation Benchmarks 3 Tests

Statistics

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

Graph Settings

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

Additional Graphs

Show Perf Per Core/Thread Calculation Graphs Where Applicable
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
Xeon E-2488
April 01
  1 Day, 22 Hours, 13 Minutes
EPYC 4124P
May 20
  2 Days, 9 Hours, 21 Minutes
EPYC 4244P
May 12
  1 Day, 16 Hours, 20 Minutes
EPYC 4344P
May 08
  1 Day, 11 Hours, 13 Minutes
EPYC 4364P
April 28
  1 Day, 17 Hours, 57 Minutes
EPYC 4464P
May 17
  1 Day, 11 Hours, 26 Minutes
EPYC 4484PX
May 10
  1 Day, 14 Hours, 16 Minutes
EPYC 4564P
April 27
  1 Day, 8 Hours, 35 Minutes
EPYC 4584PX
May 15
  1 Day, 9 Hours, 50 Minutes
Invert Hiding All Results Option
  1 Day, 16 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):


AMD EPYC 4124P CPU Review BenchmarksProcessorMotherboardChipsetMemoryDiskGraphicsNetworkAudioOSKernelDesktopDisplay ServerCompilerFile-SystemScreen ResolutionXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124PIntel Xeon E E-2488 @ 3.20GHz (8 Cores / 16 Threads)Supermicro Super Server X13SCL-F v0123456789 (1.1 BIOS)Intel Raptor Lake-S PCH2 x 32GB DRAM-4800MT/s Micron MTC20C2085S1EC48BA13201GB Micron_7450_MTFDKCC3T2TFS + 960GB Micron_7450_MTFDKBA960TFRASPEED2 x Intel I210Ubuntu 24.046.8.0-11-generic (x86_64)GNOME Shell 45.3X Server 1.21.1.11GCC 13.2.0ext41920x1080AMD EPYC 4564P 16-Core @ 5.88GHz (16 Cores / 32 Threads)Supermicro AS-3015A-I H13SAE-MF v1.00 (1.1 BIOS)AMD Device 14d82 x 32GB DRAM-5200MT/sAMD Rembrandt Radeon HD AudioAMD EPYC 4364P 8-Core @ 5.57GHz (8 Cores / 16 Threads)AMD EPYC 4344P 8-Core @ 5.39GHz (8 Cores / 16 Threads)AMD EPYC 4484PX 12-Core @ 5.66GHz (12 Cores / 24 Threads)AMD EPYC 4244P 6-Core @ 5.17GHz (6 Cores / 12 Threads)AMD EPYC 4584PX 16-Core @ 5.76GHz (16 Cores / 32 Threads)AMD EPYC 4464P 12-Core @ 5.48GHz (12 Cores / 24 Threads)AMD EPYC 4124P 4-Core @ 5.17GHz (4 Cores / 8 Threads)OpenBenchmarking.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-fxIygj/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-fxIygj/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 Disk Details- Xeon E-2488: NONE / errors=remount-ro,relatime,rw,stripe=64 / Block Size: 4096Processor Details- Xeon E-2488: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0x122 - Thermald 2.5.6- EPYC 4564P: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xa601203- EPYC 4364P: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xa601203- EPYC 4344P: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xa601203- EPYC 4484PX: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xa601203- EPYC 4244P: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xa601203- EPYC 4584PX: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xa601203- EPYC 4464P: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xa601203- EPYC 4124P: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xa601203Java Details- OpenJDK Runtime Environment (build 21.0.2+13-Ubuntu-2)Python Details- Python 3.12.2Security Details- Xeon E-2488: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected- EPYC 4564P: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Vulnerable: Safe RET no microcode + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected - EPYC 4364P: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Vulnerable: Safe RET no microcode + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected - EPYC 4344P: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Vulnerable: Safe RET no microcode + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected - EPYC 4484PX: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Vulnerable: Safe RET no microcode + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected - EPYC 4244P: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Vulnerable: Safe RET no microcode + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected - EPYC 4584PX: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Vulnerable: Safe RET no microcode + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected - EPYC 4464P: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Vulnerable: Safe RET no microcode + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected - EPYC 4124P: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Vulnerable: Safe RET no microcode + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124PResult OverviewPhoronix Test Suite100%197%295%392%490%ACES DGEMMPostgreSQLStockfishNAMDminiBUDEChaos Group V-RAYJava JMHBlenderAircrack-ngASTC EncoderLuxCoreRenderOpenSSLStress-NGEmbreeCpuminer-Optm-queensQuantLibCoremarkHelsingOSPRay StudioTimed Node.js CompilationPrimesieveJohn The RipperOpenVKLIntel Open Image DenoisenginxMemcachedOSPRayTimed LLVM CompilationBRL-CAD7-Zip CompressionTimed Linux Kernel CompilationParallel BZIP2 CompressionTimed Godot Game Engine CompilationSVT-HEVCRocksDBASKAPAppleseedTimed FFmpeg CompilationCockroachDBHeFFTe - Highly Efficient FFT for ExascaleSpeedbuvg266Timed Mesa CompilationSPECFEM3DTimed Gem5 CompilationGROMACSLAMMPS Molecular Dynamics SimulatorScyllaDBGraphicsMagickOpenVINOKvazaaroneDNNSVT-VP9JPEG-XL libjxllibavif avifencx265Y-CruncherDaCapo BenchmarkPennantSVT-AV1TensorFlowMariaDBTimed PHP CompilationZstd CompressionVVenCNAS Parallel BenchmarksOpenRadiossGPAWOpenFOAMTimed Wasmer CompilationCloverLeafDuckDBPyTorchXcompact3d Incompact3dONNX RuntimeApache IoTDBsrsRAN ProjectClickHouseLiquid-DSPPyBenchTimed CPython CompilationGoogle DracoFFmpegMariaDB mariadb-slapZ3 Theorem ProverNumpy BenchmarkGNU Octave Benchmark

Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124PPer Watt Result OverviewPhoronix Test Suite100%163%225%288%350%NAMDminiBUDEJohn The RipperStockfish7-Zip CompressionJava JMHHeFFTe - Highly Efficient FFT for ExascaleEmbreeACES DGEMMASKAPCoremarkOpenSSLASTC EncoderChaos Group V-RAYSVT-HEVCnginxLuxCoreRenderStress-NGOpenVKLBRL-CADQuantLibuvg266Cpuminer-OptMemcachedIntel Open Image DenoiseOSPRayAircrack-ngNumpy BenchmarkRocksDBKvazaarClickHouseJPEG-XL libjxlSVT-VP9GROMACSSpeedbsrsRAN ProjectLAMMPS Molecular Dynamics Simulatorx265SVT-AV1TensorFlowNAS Parallel BenchmarksPyTorchLiquid-DSPCockroachDBGraphicsMagickScyllaDBMariaDB mariadb-slapFFmpegVVenCMariaDBP.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.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.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 4124P CPU Review Benchmarkspgbench: 100 - 500 - Read Only - Average Latencypgbench: 100 - 500 - Read Onlypgbench: 100 - 800 - Read Only - Average Latencypgbench: 100 - 800 - Read Onlyjohn-the-ripper: WPA PSKluxcorerender: Danish Mood - CPUopenvino: Weld Porosity Detection FP16 - CPUopenvino: Face Detection FP16 - CPUopenvino: Handwritten English Recognition FP16 - CPUopenssl: RSA4096srsran: PDSCH Processor Benchmark, Throughput Totalopenvino: Person Re-Identification Retail FP16 - CPUopenvino: Age Gender Recognition Retail 0013 FP16 - CPUluxcorerender: LuxCore Benchmark - CPUopenvino: Handwritten English Recognition FP16-INT8 - CPUospray-studio: 2 - 1080p - 16 - Path Tracer - CPUospray-studio: 3 - 1080p - 16 - Path Tracer - CPUjohn-the-ripper: MD5ospray-studio: 1 - 1080p - 16 - Path Tracer - CPUjohn-the-ripper: HMAC-SHA512namd: ATPase with 327,506 Atomsopenvino: Person Re-Identification Retail FP16 - CPUopenvino: Vehicle Detection FP16 - CPUopenvino: Face Detection Retail FP16 - CPUospray-studio: 3 - 1080p - 1 - Path Tracer - CPUospray-studio: 2 - 1080p - 1 - Path Tracer - CPUopenvino: Road Segmentation ADAS FP16 - CPUospray-studio: 1 - 1080p - 1 - Path Tracer - CPUstockfish: Chess Benchmarkcpuminer-opt: Quad SHA-256, Pyritestress-ng: Vector Floating Pointembree: Pathtracer ISPC - Crownopenvino: Machine Translation EN To DE FP16 - CPUospray-studio: 3 - 1080p - 32 - Path Tracer - CPUminibude: OpenMP - BM1minibude: OpenMP - BM1openvino: Vehicle Detection FP16-INT8 - CPUopenvino: Face Detection Retail FP16 - CPUospray-studio: 2 - 1080p - 32 - Path Tracer - CPUopenvino: Person Vehicle Bike Detection FP16 - CPUminibude: OpenMP - BM2minibude: OpenMP - BM2blender: Barbershop - CPU-Onlyospray-studio: 1 - 1080p - 32 - Path Tracer - CPUopenvino: Noise Suppression Poconet-Like FP16 - CPUblender: Pabellon Barcelona - CPU-Onlyv-ray: CPUjava-jmh: Throughputopenssl: ChaCha20openvino: Weld Porosity Detection FP16-INT8 - CPUopenssl: ChaCha20-Poly1305blender: Junkshop - CPU-Onlyastcenc: Thoroughopenvino: Face Detection FP16-INT8 - CPUastcenc: Mediumopenssl: AES-128-GCMopenssl: RSA4096blender: BMW27 - CPU-Onlyastcenc: Fastaircrack-ng: ospray: particle_volume/scivis/real_timeopenvino: Face Detection Retail FP16-INT8 - CPUcpuminer-opt: Triple SHA-256, Onecoinospray: particle_volume/ao/real_timestress-ng: Floating Pointblender: Fishy Cat - CPU-Onlyopenssl: AES-256-GCMastcenc: Very Thoroughospray: gravity_spheres_volume/dim_512/pathtracer/real_timeopenssl: SHA512cpuminer-opt: Skeincoinblender: Classroom - CPU-Onlyrocksdb: Read While Writingastcenc: Exhaustivesvt-hevc: 1 - Bosphorus 4Kcpuminer-opt: LBC, LBRY Creditsospray: gravity_spheres_volume/dim_512/ao/real_timedacapobench: Apache Tomcatstress-ng: Vector Shuffleopenssl: SHA256cpuminer-opt: Deepcoinospray: gravity_spheres_volume/dim_512/scivis/real_timesvt-hevc: 1 - Bosphorus 1080pcpuminer-opt: Blake-2 Sstress-ng: AVX-512 VNNIhelsing: 12 digitm-queens: Time To Solvecompress-7zip: Decompression Ratingspeedb: Rand Readcpuminer-opt: Magicpuminer-opt: Myriad-Groestlopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUquantlib: Multi-Threadedrocksdb: Rand Readcoremark: CoreMark Size 666 - Iterations Per Secondcpuminer-opt: Garlicoinembree: Pathtracer ISPC - Asian Dragon Objstress-ng: Wide Vector Mathjohn-the-ripper: Blowfishcpuminer-opt: Ringcoincpuminer-opt: scryptstress-ng: Fused Multiply-Addjohn-the-ripper: bcrypthelsing: 14 digitnamd: STMV with 1,066,628 Atomsembree: Pathtracer ISPC - Asian Dragonopenvino: Road Segmentation ADAS FP16-INT8 - CPUaskap: tConvolve OpenMP - Griddingnginx: 1000primesieve: 1e12build-nodejs: Time To Compileprimesieve: 1e13openvkl: vklBenchmarkCPU ISPCgraphics-magick: Sharpengraphics-magick: Enhancedbuild-linux-kernel: allmodconfigmemcached: 1:100build-llvm: Ninjaoidn: RT.ldr_alb_nrm.3840x2160 - CPU-Onlyoidn: RT.hdr_alb_nrm.3840x2160 - CPU-Onlyuvg266: Bosphorus 4K - Mediumspeedb: Read While Writingappleseed: Disney Materialluxcorerender: DLSC - CPUopenvino: Vehicle Detection FP16-INT8 - CPUnginx: 500luxcorerender: Orange Juice - CPUgraphics-magick: Swirldacapobench: Zxing 1D/2D Barcode Image Processingtensorflow: CPU - 512 - AlexNetbrl-cad: VGR Performance Metricoidn: RTLightmap.hdr.4096x4096 - CPU-Onlynginx: 200appleseed: Emilyonednn: IP Shapes 1D - CPUmemcached: 1:10tensorflow: CPU - 256 - AlexNetcompress-pbzip2: FreeBSD-13.0-RELEASE-amd64-memstick.img Compressionbuild-godot: Time To Compilesvt-hevc: 7 - Bosphorus 1080puvg266: Bosphorus 4K - Super Fastsvt-hevc: 7 - Bosphorus 4Kbuild-llvm: Unix Makefileskvazaar: Bosphorus 4K - Mediumonednn: Recurrent Neural Network Inference - CPUonednn: Recurrent Neural Network Training - CPUpgbench: 100 - 800 - Read Writepgbench: 100 - 800 - Read Write - Average Latencyuvg266: Bosphorus 4K - Very Fastuvg266: Bosphorus 4K - Ultra Fastopenvino: Person Detection FP32 - CPUspecfem3d: Tomographic Modelopenvino: Person Detection FP16 - CPUbuild-linux-kernel: defconfigcompress-7zip: Compression Ratingbuild-ffmpeg: Time To Compilecockroach: KV, 95% Reads - 128specfem3d: Homogeneous Halfspaceaskap: tConvolve OpenMP - Degriddingjpegxl: PNG - 100openfoam: drivaerFastback, Small Mesh Size - Execution Timecockroach: KV, 60% Reads - 128onednn: Deconvolution Batch shapes_3d - CPUjpegxl: JPEG - 100cockroach: KV, 50% Reads - 128kvazaar: Bosphorus 4K - Super Fastpgbench: 100 - 500 - Read Writepgbench: 100 - 500 - Read Write - Average Latencycompress-zstd: 8, Long Mode - Compression Speedbuild-mesa: Time To Compilex265: Bosphorus 4Kbuild-gem5: Time To Compilecompress-zstd: 8 - Compression Speedgromacs: MPI CPU - water_GMX50_baresvt-av1: Preset 8 - Bosphorus 4Ksvt-hevc: 10 - Bosphorus 1080pspecfem3d: Layered Halfspacespecfem3d: Mount St. Helenssvt-vp9: Visual Quality Optimized - Bosphorus 1080ponnx: super-resolution-10 - CPU - Parallelkvazaar: Bosphorus 4K - Very Fastluxcorerender: Rainbow Colors and Prism - CPUtensorflow: CPU - 64 - AlexNetuvg266: Bosphorus 1080p - Super Fastkvazaar: Bosphorus 4K - Ultra Fastonednn: IP Shapes 3D - CPUsvt-vp9: Visual Quality Optimized - Bosphorus 4Kavifenc: 6appleseed: Material Testerscylladb: Writesspecfem3d: Water-layered Halfspaceliquid-dsp: 16 - 256 - 512uvg266: Bosphorus 1080p - Very Fastopenvino: Weld Porosity Detection FP16 - CPUnpb: EP.Cgraphics-magick: Noise-Gaussianlammps: Rhodopsin Proteinsvt-vp9: PSNR/SSIM Optimized - Bosphorus 1080popenvino: Face Detection FP16 - CPUkvazaar: Bosphorus 1080p - Super Fastsvt-vp9: VMAF Optimized - Bosphorus 1080psvt-hevc: 10 - Bosphorus 4Kuvg266: Bosphorus 1080p - Mediumtensorflow: CPU - 32 - GoogLeNetuvg266: Bosphorus 1080p - Ultra Fastopenvino: Handwritten English Recognition FP16 - CPUavifenc: 0tensorflow: CPU - 64 - GoogLeNetnpb: SP.Bonnx: ArcFace ResNet-100 - CPU - Parallelopenvino: Road Segmentation ADAS FP16-INT8 - CPUopenvino: Age Gender Recognition Retail 0013 FP16 - CPUtensorflow: CPU - 512 - GoogLeNettensorflow: CPU - 256 - GoogLeNety-cruncher: 1Bsvt-av1: Preset 12 - Bosphorus 4Konednn: Deconvolution Batch shapes_1d - CPUkvazaar: Bosphorus 1080p - Very Fastopenvino: Machine Translation EN To DE FP16 - CPUkvazaar: Bosphorus 1080p - Mediumsvt-vp9: PSNR/SSIM Optimized - Bosphorus 4Kmariadb: oltp_write_only - 64openradioss: INIVOL and Fluid Structure Interaction Drop Containertensorflow: CPU - 32 - AlexNetsvt-av1: Preset 4 - Bosphorus 4Krocksdb: Read Rand Write Randkvazaar: Bosphorus 1080p - Ultra Fastcompress-zstd: 12 - Compression Speedopenvino: Handwritten English Recognition FP16-INT8 - CPUpennant: leblancbigonnx: bertsquad-12 - CPU - Parallelgraphics-magick: Resizingy-cruncher: 500Mvvenc: Bosphorus 4K - Fastavifenc: 2svt-vp9: VMAF Optimized - Bosphorus 4Konnx: yolov4 - CPU - Parallelopenradioss: Bird Strike on Windshieldpennant: sedovbigavifenc: 6, Losslessopenvino: Vehicle Detection FP16 - CPUvvenc: Bosphorus 4K - Fasteronednn: Convolution Batch Shapes Auto - CPUmariadb: oltp_read_write - 64openvino: Road Segmentation ADAS FP16 - CPUsvt-av1: Preset 8 - Bosphorus 1080ponnx: ResNet50 v1-12-int8 - CPU - Paralleljpegxl: PNG - 90apache-iotdb: 800 - 100 - 800 - 400tensorflow: CPU - 512 - ResNet-50apache-iotdb: 800 - 100 - 800 - 400npb: BT.Capache-iotdb: 800 - 100 - 800 - 100liquid-dsp: 16 - 256 - 32build-php: Time To Compilejpegxl: JPEG - 90openvino: Person Vehicle Bike Detection FP16 - CPUonnx: CaffeNet 12-int8 - CPU - Paralleltensorflow: CPU - 32 - ResNet-50tensorflow: CPU - 64 - ResNet-50tensorflow: CPU - 256 - ResNet-50apache-iotdb: 800 - 100 - 800 - 100svt-av1: Preset 12 - Bosphorus 1080pspeedb: Read Rand Write Randospray: particle_volume/pathtracer/real_timemariadb: oltp_update_non_index - 64gpaw: Carbon Nanotubeincompact3d: input.i3d 129 Cells Per Directionopenvino: Face Detection FP16-INT8 - CPUvvenc: Bosphorus 1080p - Fastonnx: fcn-resnet101-11 - CPU - Parallelbuild-wasmer: Time To Compilex265: Bosphorus 1080ppytorch: CPU - 64 - ResNet-50dacapobench: H2 Database Enginesvt-av1: Preset 4 - Bosphorus 1080pcloverleaf: clover_bmmariadb: oltp_update_index - 64openradioss: Bumper Beamopenvino: Person Detection FP32 - CPUopenvino: Noise Suppression Poconet-Like FP16 - CPUopenvino: Person Detection FP16 - CPUopenfoam: drivaerFastback, Medium Mesh Size - Mesh Timevvenc: Bosphorus 1080p - Fasterduckdb: IMDBdacapobench: Apache Lucene Search Engineapache-iotdb: 800 - 100 - 500 - 100srsran: PUSCH Processor Benchmark, Throughput Totalapache-iotdb: 500 - 100 - 800 - 100npb: LU.Capache-iotdb: 800 - 100 - 500 - 100openfoam: drivaerFastback, Medium Mesh Size - Execution Timeapache-iotdb: 500 - 100 - 800 - 100clickhouse: 100M Rows Hits Dataset, Second Runopenradioss: Chrysler Neon 1Mapache-iotdb: 500 - 100 - 800 - 400apache-iotdb: 800 - 100 - 500 - 400apache-iotdb: 800 - 100 - 500 - 400dacapobench: PMD Source Code Analyzerclickhouse: 100M Rows Hits Dataset, Third Runopenfoam: drivaerFastback, Small Mesh Size - Mesh Timeclickhouse: 100M Rows Hits Dataset, First Run / Cold Cacheapache-iotdb: 500 - 100 - 800 - 400pytorch: CPU - 1 - ResNet-50graphics-magick: HWB Color Spacebuild-python: Defaultnpb: SP.Ccompress-zstd: 19 - Compression Speedopenvino: Face Detection Retail FP16-INT8 - CPUincompact3d: input.i3d 193 Cells Per Directiontensorflow: CPU - 1 - GoogLeNetapache-iotdb: 500 - 100 - 500 - 100apache-iotdb: 500 - 100 - 500 - 100apache-iotdb: 500 - 100 - 500 - 400apache-iotdb: 500 - 100 - 500 - 400compress-zstd: 19, Long Mode - Compression Speedonnx: T5 Encoder - CPU - Standardpybench: Total For Average Test Timesdraco: Church Facadetensorflow: CPU - 1 - ResNet-50openvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUffmpeg: libx265 - Uploadonnx: T5 Encoder - CPU - Parallelopenvino: Weld Porosity Detection FP16-INT8 - CPUffmpeg: libx265 - Video On Demandffmpeg: libx265 - Platformmysqlslap: 128onnx: GPT-2 - CPU - Standardmysqlslap: 64z3: 2.smt2srsran: PDSCH Processor Benchmark, Throughput Threadffmpeg: libx265 - Liveonnx: Faster R-CNN R-50-FPN-int8 - CPU - Parallelonnx: GPT-2 - CPU - Parallelliquid-dsp: 1 - 256 - 32renaissance: Savina Reactors.IObuild-python: Released Build, PGO + LTO Optimizednumpy: srsran: PUSCH Processor Benchmark, Throughput Threadoctave-benchmark: liquid-dsp: 1 - 256 - 512onnx: T5 Encoder - CPU - Parallelonnx: T5 Encoder - CPU - Standardonnx: Faster R-CNN R-50-FPN-int8 - CPU - Parallelonnx: CaffeNet 12-int8 - CPU - Parallelonnx: ResNet50 v1-12-int8 - CPU - Parallelonnx: ResNet50 v1-12-int8 - CPU - Standardonnx: ResNet50 v1-12-int8 - CPU - Standardonnx: ArcFace ResNet-100 - CPU - Parallelonnx: GPT-2 - CPU - Parallelonnx: GPT-2 - CPU - Standardonnx: bertsquad-12 - CPU - Parallelonnx: super-resolution-10 - CPU - Parallelonnx: fcn-resnet101-11 - CPU - Parallelonnx: yolov4 - CPU - Parallelsvt-av1: Preset 13 - Bosphorus 4Kopenradioss: Cell Phone Drop Testopenradioss: Rubber O-Ring Seal Installationheffte: r2c - FFTW - double - 128heffte: r2c - FFTW - float - 128askap: tConvolve MPI - Griddingaskap: tConvolve MPI - Degriddinglammps: 20k Atomsmt-dgemm: Sustained Floating-Point RateXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P0.8995558731.852431962295601.45265.832.65150.643000.22908.518.227499.471.69174.92422754892991979141514407210000.65977437.96249.029.7628842474101.212441168982912652728846.0613.388333.749544712.452311.310500.86816.1782403401.42313.73712.5501281.5481236523.02411.152006036765943472.268346518558001022.1023800263020173.1712.230710.4189.140064812725680195618.8123.51205.932135441.7075.886401559.06388475.931614740.28165.00561932491901.46393.79539442939716013933336.9419427600.87412.266037.262.7349666879138.29123365572633294.492.638519.16561601125583.014.08072.8526152757824426278.094843.7218507.3137214.447512260430017.4605831356.3114.5499576480.15188411437.47119.8629762395.5718787437.4140.2056516.5757219.862556.2287132.2221.095915.937245.67428836491508.0423048853.56697.9370.420.426.622548837174.9489672.1315.9592582.293.581301053192.281941270.2198692.95323.2705932.914083072373.87189.146.612486364.422168.3920.1747.98719.3929.281548.712931.953448623.19818.9724.6929.7152.89378166329.83108.3389499050.05183987.567.1149295084282.1813.650242.9447963021.44.9479213.48459866.628.644241211.791504.132.51519.48468.378485.61.43436.140383.64144.53953717553.287162292221.3375.880323.059.35173.7896.3339.597.5969559.566.260173.408541104832135.41673524215927000089.3130.051470.81707.236295.691506.63139.72289.26101.8336.5978.79115.4053.07133.56778.1712750.9723.043636.351.0076.1376.8433.891105.2806.85318103.04118.4550.4783.19296034538.42160.524.3481976533197.51170.645.7032.8676511.537224414.9264.97561.84379.858.09421259.8855.896478.96916.0411.7686.3805318641839.48120.533214.54731.814524.1322.985649449928326.36137.9271105000054.44932.5069.94557.40823.1923.1023.0756035278548.0422120915157.969220068228.89919.7521490384.0915.4631.04281238.13484.3332.25212815.91864.58187089153.90134.5415.21133.99225.9549140.06799.575311377.241068.9119.4940491.56618423882260.988162558098249.50983.5464886364290.14626555491122249.9035.18608234.39382.4861.4931516.8511387.0516.35.0773.720361351.3380.565702839857760197275.148.91169.620415560713.710.428.89161.3137.7858.7558.75574126.674112863.076809.6178.1541.0093123.284632366673695.4197.921675.48153.66.462202550006.198765.9078624.38581.793474.660404.46170224.10643.39678.108647.8908086.687313.1792960.856123.593104.61493.26177.7426.478785.00626199.095146.337.5794.2041100.36113841660.72211082431606644.181362.0013.52729.8414289.712852.64.1134815.394.65795.0517285202834118000171161813310002.788461938.32701.842.3712651080317.251069442708586136059037.1431.3658136.734424749.9531248.8101653.693269.12381921556.071249.61949.985481.15379231587.74165.354387975134161573.0421298535264732672.519212962215072.7519.903826.46154.7202251224402513373632.353.25392.237792259.9538.981954734.27973408.983998199.6566.782153368476772.68418.978131104157992334640136.1142946311.63915.80161207.46649337016452.47339896522738356.747.3690923.101427532571394.822.01627.914170373134971626633.441133749485.3583365.1130693063951674.5064613179.3227.3873778238.33437953500.13308.2156410032.2543695200.7680.7564632.2209476.635073.23136360.726.691421.43082.4736035894714.3843844031.28354.7640.860.8615.92511989185.3179225.004.82154835.067.72250589425.473971380.41162348.33152.3017831.130003761626.61409.963.299879188.525311.9546.4199.61387.01122.02706.6451348.374952216.15742.6054.5488.3230.13223158088.8457.47217088825.301121061.739.5610713755172.4427.748183.2345195084.82.4615927.22392195.262.56565178.850797.017.46434.65273.493793.82.54372.744560.8183.97038588633.126776518364.90133.32248.1116.98322.53181.8381.233.88685100.003.421102.15238115172985.254370260292390000166.8111.722123.3711912.481419.26590.80248.39408.42158.9464.16135.30203.3921.8972.106133.2118660.9037.271416.730.41132.62132.1318.211170.2143.00636186.5658.4388.30111.01348099322.67242.497.8382915758301.57220.920.0929.5529715.55603388.6527.81836.331103.5211.5199183.6442.225655.89011.3617.4356.4071920118225.15189.413380.81848.525399.5641.027371602544844.13103.3779596666740.11048.5885.12829.19439.9940.2440.6874075244660.3362770195220.907233313154.98916.5884685301.7923.1901.7634929.443118.0643.38182624.17172.88198538108.6490.499.9089.98226.0110450.91482.377208060.661611.592.0847556.69776056272351.513579315319248.89891.8478454316235.16776589141053251.8030.765271227.39321.2965.6927814.13413374.3518.83.3373.883678457.3465.636985751969731166230.4110.7162.329533522414.930.2934.21156.7735.9669.8169.80612133.168118348.8771049.1186.4252.7214122.627530186673265.2193.465803.04183.55.780189644006.378066.1614518.96641.205042.625242.38299422.41726.82848.151557.5174464.28277.50080567.06586.8403165.28567.71110.0537.2403127.9317477.196642.9413.6919.5777530.9615205022.051390018855322.10723.137.14392.237697.37530.03.8718615.122.41417.6437900438302234333374581167703331.737641029.88472.572.2125262156224.432133231438583190330936.5016.462582.808420926.294657.345879.501781.6272250833.73658.93126.357925.3871530991.32315.132307838776376503.465683661088101417.3348542739663139.4810.208913.9779.6040133134074673194210.3101.72203.103948527.8154.618712495.55510874.638284251.39127.011139412588771.39794.66757579440530717983259.4625195940.85573.048389.153.9107064828556.72178763583374377.743.8213812.28745131371242.643.82853.5018894571648683330.625972.0926230.8543490.769408254499103.5029051674.9915.6889413926.82232431851.25162.8829927440.6923235375.9150.4934518.4511275.722739.3485990.1212.506739.343153.59833130501310.9622104490.55636.8320.480.488.613194971156.0695322.754.5394947.754.421391019240.232261980.23101214.88263.5110981.999862195688.49237.576.154460326.162178.2026.6557.23662.52212.491337.472491.143265724.49825.2531.8654.9849.57647068855.1197.40510357142.19583155.863.8652030423426.0316.661296.6009867506.73.8341216.51964052.738.824047312.355527.928.26317.61432.221520.31.54647.285361.05133.30904418551.286977035203.1691.585531.0411.93206.40119.8352.304.6784061.905.338142.93695894217129.332051612211670000111.7811.051169.68766.826251.44560.14168.08242.58109.0345.6393.71142.9720.37108.65492.3711152.3127.024714.480.491.9091.7725.455125.2773.91089129.0248.2664.6876.06265119585.75172.895.7422131122226.13171.019.1342.9394112.548325511.5895.69351.94271.489.29179266.6561.969168.1478.4413.1418.1680016859317.79148.336322.61036.024462.1430.706418256322935.27122.5573556666753.75537.1804.78677.58330.7930.5330.6362951458546.7062138776170.390201401205.87421.8746431285.9718.7731.1605436.90289.1245.11197719.89186.82177579145.3272.707.9572.52296.2109445.144100.627240968.161470.5105.5837149.88695614492827.878970305285236.471003.5971338740268.42691441641113232.4738.173004222.47347.9767.4825516.57610027.1118.03.1687.770342562.9970.706478128564655502243.6110.2139.477527508317.470.2831.95141.6295.6365.3565.26580123.952112448.6761061.5179.9950.5310120.280536590003042.0200.978808.62183.65.587196116677.060977.1675119.79101.475313.099053.09150323.38137.00258.311078.0638979.703710.9182864.561107.793122.90895.48162.0323.717977.51964256.283635.698.2155.3305000.9045533711.929414750841972.08693.786.90368.267335.27583.74.0718120.382.33395.1938690446742219333383341170726671.69120978.60436.412.3725752201171.632176218443433229328866.8816.091674.798574325.851646.263838.461659.0673858790.63647.13125.885942.2972930890.99323.682250538412521187.691665727746071356.6447254230173141.779.867413.3676.0119129046626940190537.1104.74192.658746525.7764.516502329.23499004.525524192.47130.421104255872531.35634.57222564435758317580267.8624898540.83132.948323.693.8169164858468.86174027128104280.913.7948811.90731301315000.023.96654.3868840969443011328.705929.5625613.2942668.667959360491021.6860411637.7215.6355402835.32234031806.87157.9129040929.2423407386.1550.4857018.3940237.303122.2984832.8212.937743.111158.44832730491319.9322056776.09644.7700.470.478.353189650160.0140772.674.7591569.874.301371041238.892217670.2297227.42264.6709891.979322163987.01235.475.701856330.824173.1926.0455.66669.64412.101310.592514.663228024.78524.6231.3052.2447.69474772552.3598.29110424842.93582706.259.6308952073420.8716.358275.0986566756.93.9488816.27763986.237.703954912.644532.328.61716.77438.615525.11.52245.951351.91133.47435036251.591441038198.4289.197630.1411.59204.83116.2150.714.5162960.975.436146.66750693342130.204350609206270000108.2111.511489.70738.715246.28579.07161.51237.22107.4744.4392.85138.9521.70110.45591.2111203.8326.860916.830.4190.1390.1926.159121.4953.93445123.8953.4462.7174.71260139494.79171.595.5632247481217.52177.920.2235.4791612.323925011.8615.55452.56470.349.22219238.1350.887078.2629.1312.8017.7920216606023.27142.839314.22935.084465.5130.496395417622976.53122.3371802000054.03835.6045.04672.34531.0030.6430.5063086247528.2272222556158.588197477203.43220.3888378299.0218.3001.1281036.90186.7843.89199219.55174.59173080124.7076.528.8376.36262.8387343.833101.969239168.581469.8105.7040284.23693423772781.236270293571230.37967.2071203893260.60701070301155233.3033.330642213.47350.0068.6724916.8210088.5018.33.3585.341122961.8871.666420103663451680250.9410.5143.501532498817.450.2931.73138.3725.8764.9264.77565134.740109547.7271071.0176.6349.8105121.291522516673060.5202.26804.51183.45.583193650007.226576.9674220.07681.486783.182062.91846343.17937.23168.242567.4212681.145711.2108886.830108.482119.56580.04127.3224.383976.27685875.195179.318.9515.3136490.5139742820.9008894241201392.811005.3810.00559.8810308.39792.54.3625279.973.12589.7725530311163030333251861445570000.654251372.19772.212.6218981589337.451590334537294519741113.8522.5701105.206468930.677766.9211191.722254.38542021124.06868.47034.739680.74534261465.71236.283139951157401824.36967122275001936.5568550488427101.1913.172419.12101.6138187736505370274041.476.39259.009467324.6826.056593338.38715176.068955977.7695.441606184412031.81646.09148805205130725583197.3830036161.11433.99118675.18570445912180.80246938223436229.265.1058915.891067901909466.062.77140.42110713792006421469.548480.4435169.3157419.489195028625696.1502682391.4421.7757568714.45328642586.65227.4542202851.9732882268.4410.2703925.5348366.704948.43120690.439.183482.795111.6254524164905.0322651410.81428.2540.640.6410.253781166118.616273.475.02124133.885.55163749327.412948910.30123864.16201.64811.935532658380.05294.914.408323225.987215.6831.2972.07453.30614.40962.2081890.003960820.20929.5336.7185.2952.22846332385.1170.29914156530.54990283.667.5585205338591.919.943168.9813173004.53.5106519.80769839.843.544585210.906888.721.04627.20320.093942.32.28856.958422.86113.16737172947.848594598281.5695.223734.7112.30248.73124.5256.282.7043080.874.469131.166945115980131.868301941230153333114.0811.911508.63879.525336.78597.79166.31330.16131.0547.98115.48146.0821.4091.588113.5125252.3529.365116.340.44114.12109.6219.349143.2773.34505125.3456.9863.8597.41279043421.96199.146.4131817775220.31273.120.3128.1378712.61182588.9696.45245.73393.568.98958229.4942.176397.1687.7514.6024.0293617226517.76156.675327.75138.719407.6436.237271059240212.65105.0371830666743.98540.0095.32769.69234.7834.7634.9573321638568.4061841970182.049185239191.34214.7612158313.0919.9441.4932730.47199.2241.34185020.74685.73159977138.9370.318.0970.44243.1003245.97587.839231360.521273.992.9143166.10778787022123.994179324034279.62978.5178204086237.32771721601101291.7033.649585258.37326.4961.3423615.21414130.3024.03.5370.705589855.8964.557075257369435597231.3913.2204.342602513214.760.3131.32187.7806.1763.7063.68561161.844107647.233908.8171.6048.1416137.918510310003515.9199.919791.79183.45.526191250005.324534.9005720.77051.298193.051352.66341378.25134.05367.246396.2052579.312510.5013669.803111.238140.08782.02148.2822.7023113.7417529.936140.899.5395.6045021.2074144852.525317051635661.46531.485.25272.465652.66218.25.1514005.461.68301.935033958442156833350055892176671.31921773.96364.222.9834302930146.622899166145172072020773.7012.334763.1511350119.094477.357644.501330.8197307603.92478.87219.1551244.7096023697.69421.361727328953646655.507497071748431040.1535429817183186.247.513610.1758.075398225529560144386.1136.83147.476235520.7293.447681804.90327103.455773175.54170.00840603212001.03273.49699427527546013390351.0618655210.63302.256265.102.9501086286403.87132207369133247.542.919519.12538701008567.365.17871.9796786853146372248.854487.2817920.7532626.851334146372162.8214211243.8812.2001307368.19176211364.32120.3922079544.9717654504.2650.3895614.3576187.282825.3166910.9316.827916.468205.20225323381730.8791567216.54815.0920.360.366.532400243210.1113762.066.1970866.423.301061380176.611703680.1775062.51341.3042622.606381651621.67174.067.617305415.397135.9920.3843.57840.9229.591615.383148.812544831.44419.2924.5944.4060.37583091544.17125.9958293353.88063936.277.2346781514370.0212.848307.0078851927.05.5525412.69649645.030.103160915.820482.935.70717.60540.892500.01.25336.700279.57166.97052221062.572651918173.3364.292124.228.88160.2888.4441.114.4940650.516.798191.20632678004156.90660120115643333384.3611.271168.35606.838213.44761.78126.08208.1286.7932.6374.93105.2322.01136.63173.7711155.6419.837421.310.4173.5873.3631.31998.4505.21462101.8063.2947.1763.76208039560.31139.364.5401781795167.39164.419.8641.708519.1545820214.1334.54264.14260.906.78226291.7959.0226910.02410.9410.4947.9345513314127.23119.760264.14629.652529.4425.365612224322331.46136.5854613666763.29830.1856.60583.98325.7025.5025.4356689052449.5661806410132.400162697237.23621.7994226393.1315.5380.95944142.11180.5834.88239416.54377.23142647140.7690.028.4990.50297.1713837.628115.643282976.691206.0117.1426620.69623488812944.551763541378211.231126.5262518245295.34624591951298214.0039.156514195.64406.8958.4922718.85110028.7418.03.2789.870366452.3679.645792524557190648275.6210.2152.179550516015.610.3229.17147.2785.7560.2060.23517134.446100949.3221073.6162.3846.5649118.958502723333288.4214.375773.69179.85.694184263336.789316.5726021.47461.712573.785313.43791291.70550.41268.404087.43468109.23515.55841042.41147.48497.60098.85157.4827.827176.43825963.544723.736.8383.9201680.36013872540.62812732941550444.151326.2413.19731.4813432.713807.24.2833111.824.55776.8418442215173825000174601709080002.911831863.361011.612.5113191155435.771140455425606006756703.0632.1775138.504690448.8211220.5261588.303099.90390891560.991240.06049.602481.39401421882.34168.044376766629443540.871278572903502563.799068645010372.7818.617525.54143.3020246764339927363062.654.64365.317288626.4518.499454486.58939708.498697928.2067.992117266560872.56368.668321066335681333693139.5743345931.57065.63157777.30748338416010.74329138068108225.267.1447022.111404672511125.722.11728.533167201132843992617.791120746506.7580769.4130006737923331.4847683149.4329.1655749237.41418893424.57298.1555781750.8441961204.0150.7576834.2365516.906603.67150874.917.030395.43685.3086065792710.7893756154.98345.3460.840.8415.07526262887.702084.885.01158717.747.65243620409.893841830.40160748.18153.6486521.166743693215.30396.853.521565184.513297.0343.8997.77379.71920.65694.5151355.105102215.68340.1551.6396.1028.06273272095.9557.47817712525.249118066.736.3144335388830.7726.408141.456496269.12.7078225.90790314.058.25584058.563961.217.66634.02267.077970.72.68269.960554.1681.87915742831.121479799357.60120.35144.5916.43315.45168.1374.962.89087100.053.568104.32436114553378.378737947282563333154.0212.042051.6011511.766419.93605.15224.02410.42162.4759.48139.11187.7321.8574.061135.7824785.6534.716415.450.43130.80131.3417.729166.3743.11307169.8157.6880.52114.88346495324.46239.937.2962929561271.84248.020.5722.9716514.76643258.3737.49437.107107.5311.0380168.3934.640046.1747.8916.8204.2453219719418.32175.205374.22945.383398.7640.487457989647856.87101.0277261666740.09947.0535.10895.93040.3740.4940.3376031850631.9422706385209.224227813154.85213.8228168312.5221.7231.7658829.502109.5746.20171522.17447.02196283117.9983.188.4083.30204.5984748.86083.716212759.611592.392.2748014.86791594412040.354779999611293.87823.2680189263232.67786008191051291.2629.689215265.18316.2668.8026814.58515940.6122.53.5165.106554760.1464.527089646970817373227.3412.9199.254571397815.120.332.14183.8226.2165.2465.49582140.352112447.573907.5176.6953.1497139.017495846673350.9198.056746.24183.65.480191190675.439505.0182418.81961.115522.671292.41341418.46728.80377.190057.1210067.75788.30854566.85090.6426162.00267.88106.0150.2806139.0639760.758364.0714.68010.5916510.5059906760.9618324151124612.77934.249.24510.629585.510640.84.6423774.883.12541.9224972329682807000247191363440002.205601286.31681.132.718311562304.221554297721834250741241.4521.9896102.356193734.598864.9621120.772184.94537261059.99866.22834.649697.15528721274.27242.013088554316120272.103927251611671835.7865832975290103.2513.295318.09101.8002176018765593270736.078.09258.378062286.1956.238003221.20678206.254185850.5997.841513138244271.83276.31605781478597024937199.3131309341.12373.96116235.34753444111892.69238762116135939.525.2733315.711008531758023.973.00439.64511850794750279453.878184.4433784.7456873.291726942648144.0033572229.5721.2409539442.24314402468.43210.6439475809.7831119291.5090.6081325.0086351.234438.01108719.129.943524.511120.8584464167976.2022749241.80464.5060.640.6410.413783719120.9147933.485.33116236.165.55181781315.302751670.30118177.50202.5309061.973622762180.28305.224.447904246.663216.6731.6771.64491.50214.661036.151973.993983020.09029.8237.2274.2239.28207429173.5175.25013993533.02992280.750.6996218764566.4220.743210.3926375445.73.4546120.52871721.144.464667110.714745.522.12327.43339.220798.42.12357.233428.68103.73082045839.010788519284.34102.60035.2312.70256.65127.6957.683.8069380.934.437129.085729112383104.124424270233596667117.1212.821542.11899.266337.46647.10172.91331.83130.3849.24111.99150.5123.4789.625110.5217215.9230.185217.050.46109.73109.3620.254145.0423.57568131.1358.5666.4797.27273914403.46204.706.5262278556231.05221.222.1131.8558512.76242849.4146.49044.34292.079.18340202.2749.179277.2158.7814.5366.4635716962519.68162.424336.91140.177421.8335.017022686837547.76108.8172846000045.58641.7705.64719.98534.7234.6834.7970544979581.6722166699193.968191756177.01617.2911479331.3720.2101.4134932.556103.2539.53191421.50569.98168313118.5280.799.2881.56254.7731646.15690.030237462.301351.995.0941255.98756701512407.899877434011256.89936.3476232185244.44747235791109259.3532.846554233.74333.4156.9625815.05511606.2220.03.6475.680231754.4966.496873598568771814231.5511.5168.616526503714.760.3232.40155.8776.4965.8765.82586140.979113150.4581034.9177.9349.5481121.994531470003338.2197.975812.29183.65.815180782006.414515.9320720.18401.387922.966922.67554373.66833.14188.192537.0924078.39269.74591707.631108.948141.76875.83126.0335.0223107.74107389.246270.8210.3937.1870622.5531959054.409181532426000.81349.323.51185.853738.54054.67.969649.231.01179.64779079088598609476379607986670.89678500.05228.814.5354724662107.084584106224851444714008.647.838344.2717773512.914322.862412.37879.05152187391.89323.42312.9371914.77149914479.34648.211123819260371856.72533291996640686.8723686058987282.785.12066.8139.85606597453469096458.7206.18101.366923895.2752.331761232.02253372.339072137.33256.10562917695500.70142.3472628874161579066.90519.8211352610.42941.524228.171.95862128404319.5889284630072205.101.945046.1137810681157.037.609105.3024518935829300168.373016.7013170.1222228.034885633254797.571641851.657.8364209322.7411819944.9783.2915250467.4111818740.5610.274259.2948140.591801.1541180.8124.4961444.308300.41016716262563.9141068869.521240.8560.240.244.471477767303.4285611.419.6845317.162.21722033123.631156530.1247788.24514.7043733.817531117437.50121.8511.097420618.87093.0113.8529.821262.9106.642274.054388.641569750.97113.1416.8631.5990.58281309431.71182.4565615579.58438555.5112.8664236912841.958.999432.882931458.97.512868.95930433.220.751939325.783323.051.96811.66787.863330.30.91424.872192.92237.97918709289.476485638127.2346.594316.825.95113.0263.9628.755.0336735.859.471281.66631555249214.48750870110696000061.1911.43781.24444.618155.851135.6192.91154.1461.0824.2952.8377.3521.51187.64152.849885.3214.820828.430.453.1753.0743.94768.8417.4227275.9790.3336.1047.01142651786.89100.573.2631219968126.17114.322.2454.784846.5304614219.8003.31185.38945.964.93035390.3080.1054513.44717.467.7429.055469023237.3086.468174.40922.238860.7519.063472448922316.95216.4037171333385.80422.70710.18420.70119.0119.1119.2436052182313.4271323685105.663113348318.66628.4063104585.2311.4250.87115659.46658.6223.04343812.18292.42101087210.60126.508.26126.06387.8830927.354152.6753854109.52881.5167.0326610.49439340083645.54344828435165.391462.6045355429406.06451178521824168.4150.903037155.72531.8841.0919023.2049840.1314.93.23104.21818139.38103.024506583745226559346.659.00142.205552570812.180.2924.42134.7385.8051.0751.11449119.46087856.8591023.8141.0342.0364107.58350277333233.268710.18183.45.880182076677.420797.0317123.78742.376355.732935.18098193.84567.47159.292458.40332153.15221.47621175.76202.82968.465138.72254.8817.247644.08943226.622623.964.7802.161795OpenBenchmarking.org

PostgreSQL

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

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 500 - Mode: Read Only - Average LatencyXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P0.57441.14881.72322.29762.872SE +/- 0.003, N = 3SE +/- 0.001, N = 3SE +/- 0.012, N = 3SE +/- 0.009, N = 3SE +/- 0.001, N = 3SE +/- 0.014, N = 3SE +/- 0.001, N = 3SE +/- 0.001, N = 3SE +/- 0.025, N = 60.8990.3610.9610.9040.5131.2070.3600.5052.5531. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 500 - Mode: Read OnlyXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P300K600K900K1200K1500KSE +/- 1617.01, N = 3SE +/- 3948.07, N = 3SE +/- 6448.13, N = 3SE +/- 5619.73, N = 3SE +/- 2685.11, N = 3SE +/- 4829.64, N = 3SE +/- 3546.18, N = 3SE +/- 2177.66, N = 3SE +/- 1920.28, N = 6555873138416652050255337197428241448513872549906761959051. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 800 - Mode: Read Only - Average LatencyXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P0.9921.9842.9763.9684.96SE +/- 0.005, N = 3SE +/- 0.006, N = 3SE +/- 0.023, N = 3SE +/- 0.010, N = 3SE +/- 0.012, N = 3SE +/- 0.021, N = 9SE +/- 0.002, N = 3SE +/- 0.007, N = 3SE +/- 0.054, N = 41.8520.7222.0511.9290.9002.5250.6280.9614.4091. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 800 - Mode: Read OnlyXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P300K600K900K1200K1500KSE +/- 1154.98, N = 3SE +/- 8757.92, N = 3SE +/- 4300.20, N = 3SE +/- 2047.43, N = 3SE +/- 11913.26, N = 3SE +/- 2616.05, N = 9SE +/- 4344.86, N = 3SE +/- 6188.19, N = 3SE +/- 2208.37, N = 4431962110824339001841475088942431705112732948324151815321. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

John The Ripper

This is a benchmark of John The Ripper, which is a password cracker. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: WPA PSKXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P30K60K90K120K150KSE +/- 135.70, N = 3SE +/- 425.10, N = 3SE +/- 221.78, N = 3SE +/- 166.40, N = 3SE +/- 115.44, N = 3SE +/- 52.29, N = 3SE +/- 585.52, N = 3SE +/- 646.01, N = 3SE +/- 49.33, N = 329560160664855328419712013963566155044112461426001. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -lm -lrt -lz -ldl -lcrypt -lbz2

LuxCoreRender

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

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.6Scene: Danish Mood - Acceleration: CPUXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P0.94051.8812.82153.7624.7025SE +/- 0.01, N = 15SE +/- 0.04, N = 3SE +/- 0.02, N = 11SE +/- 0.02, N = 3SE +/- 0.03, N = 5SE +/- 0.02, N = 5SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 41.454.182.102.082.811.464.152.770.81MIN: 0.39 / MAX: 1.82MIN: 1.81 / MAX: 4.75MIN: 0.64 / MAX: 2.54MIN: 0.66 / MAX: 2.47MIN: 1.01 / MAX: 3.32MIN: 0.38 / MAX: 1.85MIN: 1.74 / MAX: 4.72MIN: 0.99 / MAX: 3.25MIN: 0.17 / MAX: 1.12

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Weld Porosity Detection FP16 - Device: CPUXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P30060090012001500SE +/- 0.54, N = 3SE +/- 1.37, N = 3SE +/- 0.13, N = 3SE +/- 0.27, N = 3SE +/- 0.16, N = 3SE +/- 0.14, N = 3SE +/- 0.25, N = 3SE +/- 0.30, N = 3SE +/- 0.29, N = 3265.831362.00723.13693.781005.38531.481326.24934.24349.321. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Face Detection FP16 - Device: CPUXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P3691215SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 32.6513.527.146.9010.005.2513.199.243.511. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Handwritten English Recognition FP16 - Device: CPUXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P160320480640800SE +/- 0.33, N = 3SE +/- 3.18, N = 3SE +/- 1.00, N = 3SE +/- 3.35, N = 3SE +/- 1.93, N = 3SE +/- 3.75, N = 3SE +/- 0.36, N = 3SE +/- 0.66, N = 3SE +/- 0.70, N = 3150.64729.84392.23368.26559.88272.46731.48510.62185.851. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenSSL

OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test profile makes use of the built-in "openssl speed" benchmarking capabilities. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgsign/s, More Is BetterOpenSSL 3.3Algorithm: RSA4096Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P3K6K9K12K15KSE +/- 28.09, N = 3SE +/- 5.90, N = 3SE +/- 2.36, N = 3SE +/- 2.72, N = 3SE +/- 14.97, N = 3SE +/- 3.91, N = 3SE +/- 2.41, N = 3SE +/- 3.17, N = 3SE +/- 5.33, N = 33000.214289.77697.37335.210308.35652.613432.79585.53738.51. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

srsRAN Project

srsRAN Project is a complete ORAN-native 5G RAN solution created by Software Radio Systems (SRS). The srsRAN Project radio suite was formerly known as srsLTE and can be used for building your own software-defined radio (SDR) 4G/5G mobile network. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMbps, More Is BettersrsRAN Project 23.10.1-20240325Test: PDSCH Processor Benchmark, Throughput TotalXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P3K6K9K12K15KSE +/- 5.11, N = 5SE +/- 51.53, N = 6SE +/- 38.56, N = 7SE +/- 11.93, N = 7SE +/- 99.73, N = 6SE +/- 13.19, N = 7SE +/- 68.24, N = 6SE +/- 22.68, N = 6SE +/- 3.81, N = 72908.512852.67530.07583.79792.56218.213807.210640.84054.6-mavx512f -mavx512cd -mavx512bw -mavx512dq-mavx512f -mavx512cd -mavx512bw -mavx512dq-mavx512f -mavx512cd -mavx512bw -mavx512dq-mavx512f -mavx512cd -mavx512bw -mavx512dq-mavx512f -mavx512cd -mavx512bw -mavx512dq-mavx512f -mavx512cd -mavx512bw -mavx512dq-mavx512f -mavx512cd -mavx512bw -mavx512dq-mavx512f -mavx512cd -mavx512bw -mavx512dq1. (CXX) g++ options: -O3 -march=native -mavx2 -mavx -msse4.1 -mfma -fno-trapping-math -fno-math-errno -ldl

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Person Re-Identification Retail FP16 - Device: CPUXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P48121620SE +/- 0.11, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 318.224.113.874.074.365.154.284.647.96MIN: 10.36 / MAX: 177.58MIN: 2.45 / MAX: 41.27MIN: 2.38 / MAX: 13.89MIN: 2.41 / MAX: 9.33MIN: 2.55 / MAX: 15.23MIN: 3.03 / MAX: 14.81MIN: 2.63 / MAX: 16.2MIN: 2.6 / MAX: 15.94MIN: 4.52 / MAX: 22.421. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Age Gender Recognition Retail 0013 FP16 - Device: CPUXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P7K14K21K28K35KSE +/- 31.71, N = 3SE +/- 16.51, N = 3SE +/- 8.32, N = 3SE +/- 12.32, N = 3SE +/- 16.68, N = 3SE +/- 1.45, N = 3SE +/- 29.98, N = 3SE +/- 16.45, N = 3SE +/- 7.10, N = 37499.4734815.3918615.1218120.3825279.9714005.4633111.8223774.889649.231. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

LuxCoreRender

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

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.6Scene: LuxCore Benchmark - Acceleration: CPUXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P1.04632.09263.13894.18525.2315SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 31.694.652.412.333.121.684.553.121.01MIN: 0.51 / MAX: 2.04MIN: 2.03 / MAX: 5.27MIN: 0.82 / MAX: 2.85MIN: 0.78 / MAX: 2.76MIN: 1.17 / MAX: 3.62MIN: 0.5 / MAX: 2.06MIN: 1.97 / MAX: 5.16MIN: 1.19 / MAX: 3.62MIN: 0.25 / MAX: 1.3

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Handwritten English Recognition FP16-INT8 - Device: CPUXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P2004006008001000SE +/- 0.45, N = 3SE +/- 1.22, N = 3SE +/- 0.59, N = 3SE +/- 0.81, N = 3SE +/- 1.97, N = 3SE +/- 1.40, N = 3SE +/- 0.33, N = 3SE +/- 0.61, N = 3SE +/- 0.15, N = 3174.92795.05417.64395.19589.77301.93776.84541.92179.641. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

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: 2 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPUXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P20K40K60K80K100KSE +/- 172.31, N = 3SE +/- 19.75, N = 3SE +/- 127.68, N = 3SE +/- 87.29, N = 3SE +/- 293.34, N = 3SE +/- 199.64, N = 3SE +/- 3.84, N = 3SE +/- 39.63, N = 3SE +/- 134.02, N = 3422751728537900386902553050339184422497277907

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 3 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPUXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P20K40K60K80K100KSE +/- 115.84, N = 3SE +/- 29.87, N = 3SE +/- 62.68, N = 3SE +/- 85.35, N = 3SE +/- 529.04, N = 15SE +/- 91.50, N = 3SE +/- 45.16, N = 3SE +/- 102.05, N = 3SE +/- 186.30, N = 3489292028343830446743111658442215173296890885

John The Ripper

This is a benchmark of John The Ripper, which is a password cracker. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: MD5Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P900K1800K2700K3600K4500KSE +/- 2504.83, N = 3SE +/- 11590.23, N = 3SE +/- 7423.69, N = 3SE +/- 666.67, N = 3SE +/- 333.33, N = 3SE +/- 17071.74, N = 3SE +/- 17559.42, N = 3SE +/- 8082.90, N = 3SE +/- 151.74, N = 391979141180002234333221933330303331568333382500028070009860941. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -lm -lrt -lz -ldl -lcrypt -lbz2

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: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPUXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P16K32K48K64K80KSE +/- 112.38, N = 3SE +/- 33.74, N = 3SE +/- 43.80, N = 3SE +/- 55.41, N = 3SE +/- 280.33, N = 3SE +/- 80.90, N = 3SE +/- 12.67, N = 3SE +/- 16.70, N = 3SE +/- 181.95, N = 3415141711637458383342518650055174602471976379

John The Ripper

This is a benchmark of John The Ripper, which is a password cracker. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: HMAC-SHA512Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P40M80M120M160M200MSE +/- 518797.01, N = 3SE +/- 580393.26, N = 3SE +/- 411753.30, N = 3SE +/- 110045.95, N = 3SE +/- 58043.09, N = 3SE +/- 24875.24, N = 3SE +/- 243467.31, N = 3SE +/- 1126651.23, N = 3SE +/- 38480.88, N = 34072100018133100011677033311707266714455700089217667170908000136344000607986671. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -lm -lrt -lz -ldl -lcrypt -lbz2

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.orgns/day, More Is BetterNAMD 3.0b6Input: ATPase with 327,506 AtomsXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P0.65521.31041.96562.62083.276SE +/- 0.00164, N = 3SE +/- 0.03311, N = 4SE +/- 0.00212, N = 3SE +/- 0.00076, N = 3SE +/- 0.01721, N = 15SE +/- 0.00340, N = 3SE +/- 0.00837, N = 3SE +/- 0.00983, N = 3SE +/- 0.00275, N = 30.659772.788461.737641.691200.654251.319212.911832.205600.89678

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Person Re-Identification Retail FP16 - Device: CPUXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P400800120016002000SE +/- 2.58, N = 3SE +/- 0.22, N = 3SE +/- 0.99, N = 3SE +/- 1.30, N = 3SE +/- 1.33, N = 3SE +/- 0.80, N = 3SE +/- 0.50, N = 3SE +/- 0.33, N = 3SE +/- 0.38, N = 3437.961938.321029.88978.601372.19773.961863.361286.31500.051. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Vehicle Detection FP16 - Device: CPUXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P2004006008001000SE +/- 0.14, N = 3SE +/- 2.53, N = 3SE +/- 1.08, N = 3SE +/- 0.47, N = 3SE +/- 1.18, N = 3SE +/- 2.00, N = 3SE +/- 2.08, N = 3SE +/- 0.50, N = 3SE +/- 0.62, N = 3249.02701.84472.57436.41772.21364.221011.61681.13228.811. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Face Detection Retail FP16 - Device: CPUXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P3691215SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 39.762.372.212.372.622.982.512.704.53MIN: 4.34 / MAX: 46.89MIN: 1.27 / MAX: 12.75MIN: 1.23 / MAX: 13.12MIN: 1.25 / MAX: 6.4MIN: 1.36 / MAX: 13.53MIN: 1.64 / MAX: 9.56MIN: 1.32 / MAX: 13.29MIN: 1.33 / MAX: 14.55MIN: 2.48 / MAX: 9.871. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

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: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPUXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P12002400360048006000SE +/- 0.88, N = 3SE +/- 0.33, N = 3SE +/- 4.04, N = 3SE +/- 2.52, N = 3SE +/- 2.33, N = 3SE +/- 5.49, N = 3SE +/- 15.53, N = 4SE +/- 3.18, N = 3SE +/- 0.33, N = 3288412652526257518983430131918315472

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 2 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPUXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P10002000300040005000SE +/- 2.33, N = 3SE +/- 2.08, N = 3SE +/- 0.33, N = 3SE +/- 0.67, N = 3SE +/- 9.29, N = 3SE +/- 3.28, N = 3SE +/- 0.58, N = 3SE +/- 0.58, N = 3SE +/- 7.84, N = 3247410802156220115892930115515624662

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Road Segmentation ADAS FP16 - Device: CPUXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P90180270360450SE +/- 0.22, N = 3SE +/- 0.46, N = 3SE +/- 1.10, N = 3SE +/- 0.84, N = 3SE +/- 1.33, N = 3SE +/- 0.31, N = 3SE +/- 1.74, N = 3SE +/- 0.76, N = 3SE +/- 0.63, N = 3101.21317.25224.43171.63337.45146.62435.77304.22107.081. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

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: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPUXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P10002000300040005000SE +/- 0.88, N = 3SE +/- 1.00, N = 3SE +/- 1.76, N = 3SE +/- 1.86, N = 3SE +/- 16.15, N = 3SE +/- 1.45, N = 3SE +/- 1.53, N = 3SE +/- 1.45, N = 3SE +/- 8.25, N = 3244110692133217615902899114015544584

Stockfish

This is a test of Stockfish, an advanced open-source C++11 chess benchmark that can scale up to 1024 CPU threads. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 16.1Chess BenchmarkXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P10M20M30M40M50MSE +/- 121681.53, N = 15SE +/- 574948.55, N = 15SE +/- 160295.89, N = 3SE +/- 191557.41, N = 3SE +/- 379095.21, N = 4SE +/- 169306.09, N = 3SE +/- 611568.23, N = 15SE +/- 353999.00, N = 15SE +/- 100541.00, N = 15168982914427085823143858218443433345372916614517455425602977218310622485-mavx512f -mavx512bw -mavx512vnni -mavx512dq -mavx512vl-mavx512f -mavx512bw -mavx512vnni -mavx512dq -mavx512vl-mavx512f -mavx512bw -mavx512vnni -mavx512dq -mavx512vl-mavx512f -mavx512bw -mavx512vnni -mavx512dq -mavx512vl-mavx512f -mavx512bw -mavx512vnni -mavx512dq -mavx512vl-mavx512f -mavx512bw -mavx512vnni -mavx512dq -mavx512vl-mavx512f -mavx512bw -mavx512vnni -mavx512dq -mavx512vl-mavx512f -mavx512bw -mavx512vnni -mavx512dq -mavx512vl1. (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 -msse4.1 -mssse3 -msse2 -mbmi2 -flto -flto-partition=one -flto=jobserver

Cpuminer-Opt

Cpuminer-Opt is a fork of cpuminer-multi that carries a wide range of CPU performance optimizations for measuring the potential cryptocurrency mining performance of the CPU/processor with a wide variety of cryptocurrencies. The benchmark reports the hash speed for the CPU mining performance for the selected cryptocurrency. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 23.5Algorithm: Quad SHA-256, PyriteXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P13K26K39K52K65KSE +/- 3.33, N = 3SE +/- 331.71, N = 3SE +/- 78.81, N = 3SE +/- 38.44, N = 3SE +/- 26.67, N = 3SE +/- 58.59, N = 3SE +/- 454.25, N = 3SE +/- 3.33, N = 3SE +/- 143.80, N = 32652761360319033229345197207206006742507144471. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

Stress-NG

Stress-NG is a Linux stress tool developed by Colin Ian King. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Vector Floating PointXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P13K26K39K52K65KSE +/- 378.33, N = 3SE +/- 261.75, N = 3SE +/- 415.80, N = 3SE +/- 129.67, N = 3SE +/- 59.97, N = 3SE +/- 108.35, N = 3SE +/- 280.00, N = 3SE +/- 284.33, N = 3SE +/- 17.31, N = 328846.0659037.1430936.5028866.8841113.8520773.7056703.0641241.4514008.641. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -lEGL -ljpeg -lmpfr -lpthread -lrt -lsctp -lz

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs (and GPUs via SYCL) 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 4.3Binary: Pathtracer ISPC - Model: CrownXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P714212835SE +/- 0.0081, N = 3SE +/- 0.0172, N = 3SE +/- 0.0298, N = 3SE +/- 0.0091, N = 3SE +/- 0.0256, N = 3SE +/- 0.0104, N = 3SE +/- 0.0431, N = 3SE +/- 0.0059, N = 3SE +/- 0.0041, N = 313.388331.365816.462516.091622.570112.334732.177521.98967.8383MIN: 13.27 / MAX: 16.49MIN: 30.96 / MAX: 32.3MIN: 16.24 / MAX: 16.97MIN: 15.93 / MAX: 16.53MIN: 22.22 / MAX: 23.17MIN: 12.21 / MAX: 12.61MIN: 31.73 / MAX: 33MIN: 21.74 / MAX: 22.75MIN: 7.77 / MAX: 8.03

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Machine Translation EN To DE FP16 - Device: CPUXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P306090120150SE +/- 0.02, N = 3SE +/- 0.06, N = 3SE +/- 0.17, N = 3SE +/- 0.34, N = 3SE +/- 0.10, N = 3SE +/- 0.39, N = 3SE +/- 0.12, N = 3SE +/- 0.13, N = 3SE +/- 0.49, N = 433.74136.7382.8074.79105.2063.15138.50102.3544.271. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

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: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPUXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P40K80K120K160K200KSE +/- 76.92, N = 3SE +/- 101.69, N = 3SE +/- 273.73, N = 3SE +/- 185.23, N = 3SE +/- 84.90, N = 3SE +/- 16.70, N = 3SE +/- 195.52, N = 3SE +/- 30.37, N = 3SE +/- 162.34, N = 395447442478420985743646891135014690461937177735

miniBUDE

MiniBUDE is a mini application for the the core computation of the Bristol University Docking Engine (BUDE). This test profile currently makes use of the OpenMP implementation of miniBUDE for CPU benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBillion Interactions/s, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM1Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P1122334455SE +/- 0.06, N = 3SE +/- 0.03, N = 4SE +/- 0.10, N = 3SE +/- 0.01, N = 3SE +/- 0.26, N = 3SE +/- 0.00, N = 3SE +/- 0.17, N = 4SE +/- 0.10, N = 3SE +/- 0.00, N = 312.4549.9526.2925.8530.6819.0948.8234.6012.911. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm

OpenBenchmarking.orgGFInst/s, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM1Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P30060090012001500SE +/- 1.56, N = 3SE +/- 0.84, N = 4SE +/- 2.56, N = 3SE +/- 0.15, N = 3SE +/- 6.54, N = 3SE +/- 0.09, N = 3SE +/- 4.13, N = 4SE +/- 2.41, N = 3SE +/- 0.06, N = 3311.311248.81657.35646.26766.92477.361220.53864.96322.861. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Vehicle Detection FP16-INT8 - Device: CPUXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P400800120016002000SE +/- 1.52, N = 3SE +/- 1.19, N = 3SE +/- 0.43, N = 3SE +/- 2.16, N = 3SE +/- 1.23, N = 3SE +/- 1.34, N = 3SE +/- 0.49, N = 3SE +/- 0.37, N = 3SE +/- 0.52, N = 3500.861653.69879.50838.461191.72644.501588.301120.77412.371. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Face Detection Retail FP16 - Device: CPUXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P7001400210028003500SE +/- 1.96, N = 3SE +/- 6.25, N = 3SE +/- 0.66, N = 3SE +/- 1.26, N = 3SE +/- 2.38, N = 3SE +/- 3.43, N = 3SE +/- 1.96, N = 3SE +/- 0.82, N = 3SE +/- 2.00, N = 3816.173269.121781.621659.062254.381330.813099.902184.94879.051. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

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: 2 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPUXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P30K60K90K120K150KSE +/- 34.91, N = 3SE +/- 61.02, N = 3SE +/- 152.10, N = 3SE +/- 84.09, N = 3SE +/- 95.50, N = 3SE +/- 222.81, N = 3SE +/- 140.94, N = 3SE +/- 126.62, N = 3SE +/- 575.91, N = 38240338192722507385854202973073908953726152187

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Person Vehicle Bike Detection FP16 - Device: CPUXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P30060090012001500SE +/- 0.87, N = 3SE +/- 2.52, N = 3SE +/- 0.80, N = 3SE +/- 5.03, N = 3SE +/- 5.46, N = 3SE +/- 2.84, N = 3SE +/- 2.21, N = 3SE +/- 0.91, N = 3SE +/- 0.95, N = 3401.421556.07833.73790.631124.06603.921560.991059.99391.891. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

miniBUDE

MiniBUDE is a mini application for the the core computation of the Bristol University Docking Engine (BUDE). This test profile currently makes use of the OpenMP implementation of miniBUDE for CPU benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFInst/s, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM2Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P30060090012001500SE +/- 0.15, N = 3SE +/- 1.54, N = 3SE +/- 0.13, N = 3SE +/- 0.07, N = 3SE +/- 0.75, N = 3SE +/- 0.06, N = 3SE +/- 2.18, N = 3SE +/- 0.58, N = 3SE +/- 0.04, N = 3313.741249.62658.93647.13868.47478.871240.06866.23323.421. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm

OpenBenchmarking.orgBillion Interactions/s, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM2Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P1122334455SE +/- 0.01, N = 3SE +/- 0.06, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.09, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 312.5549.9926.3625.8934.7419.1649.6034.6512.941. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles performance with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported as well as HIP for AMD Radeon GPUs and Intel oneAPI for Intel Graphics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.1Blend File: Barbershop - Compute: CPU-OnlyXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P400800120016002000SE +/- 4.06, N = 3SE +/- 0.46, N = 3SE +/- 0.87, N = 3SE +/- 1.01, N = 3SE +/- 0.50, N = 3SE +/- 0.31, N = 3SE +/- 0.24, N = 3SE +/- 0.89, N = 3SE +/- 1.15, N = 31281.54481.15925.38942.29680.741244.70481.39697.151914.77

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: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPUXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P30K60K90K120K150KSE +/- 135.20, N = 3SE +/- 168.15, N = 3SE +/- 145.56, N = 3SE +/- 106.16, N = 3SE +/- 40.93, N = 3SE +/- 217.15, N = 3SE +/- 55.84, N = 3SE +/- 35.09, N = 3SE +/- 101.66, N = 38123637923715307293053426960234014252872149914

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Noise Suppression Poconet-Like FP16 - Device: CPUXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P400800120016002000SE +/- 1.17, N = 3SE +/- 1.23, N = 3SE +/- 0.86, N = 3SE +/- 1.25, N = 3SE +/- 1.93, N = 3SE +/- 1.27, N = 3SE +/- 2.01, N = 3SE +/- 0.77, N = 3SE +/- 0.42, N = 3523.021587.74991.32890.991465.71697.691882.341274.27479.341. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles performance with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported as well as HIP for AMD Radeon GPUs and Intel oneAPI for Intel Graphics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.1Blend File: Pabellon Barcelona - Compute: CPU-OnlyXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P140280420560700SE +/- 1.05, N = 3SE +/- 0.18, N = 3SE +/- 0.40, N = 3SE +/- 0.34, N = 3SE +/- 0.05, N = 3SE +/- 0.44, N = 3SE +/- 0.14, N = 3SE +/- 0.08, N = 3SE +/- 0.83, N = 3411.15165.35315.13323.68236.28421.36168.04242.01648.21

Chaos Group V-RAY

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

OpenBenchmarking.orgvsamples, More Is BetterChaos Group V-RAY 6.0Mode: CPUXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P9K18K27K36K45KSE +/- 16.84, N = 3SE +/- 204.38, N = 3SE +/- 11.00, N = 3SE +/- 22.00, N = 3SE +/- 54.69, N = 3SE +/- 50.00, N = 3SE +/- 96.96, N = 3SE +/- 61.57, N = 3SE +/- 5.33, N = 3200604387923078225053139917273437673088511238

Java JMH

This very basic test profile runs the stock benchmark of the Java JMH benchmark via Maven. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOps/s, More Is BetterJava JMHThroughputXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P16000M32000M48000M64000M80000M36765943472.2775134161573.0438776376503.4738412521187.6951157401824.3628953646655.5166629443540.8754316120272.1019260371856.73

OpenSSL

OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test profile makes use of the built-in "openssl speed" benchmarking capabilities. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.3Algorithm: ChaCha20Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P30000M60000M90000M120000M150000MSE +/- 7700475.42, N = 3SE +/- 13732325.68, N = 3SE +/- 32786296.71, N = 3SE +/- 10772886.17, N = 3SE +/- 26095977.93, N = 3SE +/- 41193652.45, N = 3SE +/- 45400804.32, N = 3SE +/- 14660801.77, N = 3SE +/- 18396330.78, N = 3346518558001298535264736836610881066572774607967122275004970717484312785729035092725161167332919966401. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Weld Porosity Detection FP16-INT8 - Device: CPUXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P6001200180024003000SE +/- 2.31, N = 3SE +/- 4.11, N = 3SE +/- 0.60, N = 3SE +/- 0.44, N = 3SE +/- 1.19, N = 3SE +/- 0.80, N = 3SE +/- 0.50, N = 3SE +/- 0.27, N = 3SE +/- 0.30, N = 31022.102672.511417.331356.641936.551040.152563.791835.78686.871. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenSSL

OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test profile makes use of the built-in "openssl speed" benchmarking capabilities. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.3Algorithm: ChaCha20-Poly1305Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P20000M40000M60000M80000M100000MSE +/- 5622113.45, N = 3SE +/- 63328398.60, N = 3SE +/- 11858939.41, N = 3SE +/- 18319786.28, N = 3SE +/- 21541900.76, N = 3SE +/- 14961656.63, N = 3SE +/- 37115945.76, N = 3SE +/- 17029222.81, N = 3SE +/- 35385699.13, N = 32380026302092129622150485427396634725423017368550488427354298171839068645010365832975290236860589871. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles performance with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported as well as HIP for AMD Radeon GPUs and Intel oneAPI for Intel Graphics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.1Blend File: Junkshop - Compute: CPU-OnlyXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P60120180240300SE +/- 0.02, N = 3SE +/- 0.17, N = 3SE +/- 0.43, N = 3SE +/- 0.48, N = 3SE +/- 0.15, N = 3SE +/- 0.25, N = 3SE +/- 0.10, N = 3SE +/- 0.08, N = 3SE +/- 0.62, N = 3173.1772.75139.48141.77101.19186.2472.78103.25282.78

ASTC Encoder

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

OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 4.7Preset: ThoroughXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P510152025SE +/- 0.3204, N = 12SE +/- 0.0627, N = 3SE +/- 0.0128, N = 3SE +/- 0.0050, N = 3SE +/- 0.0127, N = 3SE +/- 0.0018, N = 3SE +/- 0.0075, N = 3SE +/- 0.0021, N = 3SE +/- 0.0100, N = 312.230719.903810.20899.867413.17247.513618.617513.29535.12061. (CXX) g++ options: -O3 -flto -pthread

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Face Detection FP16-INT8 - Device: CPUXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P612182430SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 310.4126.4613.9713.3619.1210.1725.5418.096.811. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

ASTC Encoder

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

OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 4.7Preset: MediumXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P306090120150SE +/- 0.00, N = 3SE +/- 0.18, N = 5SE +/- 0.04, N = 4SE +/- 0.04, N = 4SE +/- 0.07, N = 4SE +/- 0.02, N = 3SE +/- 0.06, N = 5SE +/- 0.03, N = 4SE +/- 0.03, N = 389.14154.7279.6076.01101.6158.08143.30101.8039.861. (CXX) g++ options: -O3 -flto -pthread

OpenSSL

OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test profile makes use of the built-in "openssl speed" benchmarking capabilities. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.3Algorithm: AES-128-GCMXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P50000M100000M150000M200000M250000MSE +/- 45687236.99, N = 3SE +/- 197196146.33, N = 3SE +/- 48206635.82, N = 3SE +/- 18100529.72, N = 3SE +/- 100195492.71, N = 3SE +/- 30766844.46, N = 3SE +/- 834503022.99, N = 3SE +/- 82240254.30, N = 3SE +/- 11806687.23, N = 36481272568025122440251313313407467312904662694018773650537098225529560246764339927176018765593659745346901. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

OpenBenchmarking.orgverify/s, More Is BetterOpenSSL 3.3Algorithm: RSA4096Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P80K160K240K320K400KSE +/- 1626.68, N = 3SE +/- 143.01, N = 3SE +/- 20.61, N = 3SE +/- 13.93, N = 3SE +/- 923.26, N = 3SE +/- 34.43, N = 3SE +/- 494.21, N = 3SE +/- 313.76, N = 3SE +/- 24.26, N = 3195618.8373632.3194210.3190537.1274041.4144386.1363062.6270736.096458.71. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles performance with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported as well as HIP for AMD Radeon GPUs and Intel oneAPI for Intel Graphics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.1Blend File: BMW27 - Compute: CPU-OnlyXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P50100150200250SE +/- 0.18, N = 3SE +/- 0.05, N = 3SE +/- 0.33, N = 3SE +/- 0.10, N = 3SE +/- 0.17, N = 3SE +/- 0.46, N = 3SE +/- 0.14, N = 3SE +/- 0.16, N = 3SE +/- 0.26, N = 3123.5153.25101.72104.7476.39136.8354.6478.09206.18

ASTC Encoder

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

OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 4.7Preset: FastXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P90180270360450SE +/- 0.04, N = 3SE +/- 0.54, N = 4SE +/- 0.29, N = 3SE +/- 0.39, N = 3SE +/- 0.09, N = 3SE +/- 0.12, N = 3SE +/- 0.31, N = 4SE +/- 0.15, N = 3SE +/- 0.06, N = 3205.93392.24203.10192.66259.01147.48365.32258.38101.371. (CXX) g++ options: -O3 -flto -pthread

Aircrack-ng

Aircrack-ng is a tool for assessing WiFi/WLAN network security. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgk/s, More Is BetterAircrack-ng 1.7Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P20K40K60K80K100KSE +/- 17.95, N = 3SE +/- 153.97, N = 3SE +/- 45.75, N = 3SE +/- 20.41, N = 3SE +/- 41.76, N = 3SE +/- 28.81, N = 3SE +/- 75.15, N = 3SE +/- 7.31, N = 3SE +/- 2.21, N = 335441.7192259.9548527.8246525.7867324.6835520.7388626.4562286.2023895.281. (CXX) g++ options: -std=gnu++17 -O3 -fvisibility=hidden -fcommon -rdynamic -lnl-3 -lnl-genl-3 -lpcre -lsqlite3 -lpthread -lz -lssl -lcrypto -lhwloc -ldl -lm -pthread

OSPRay

Intel OSPRay is a portable ray-tracing engine for high-performance, high-fidelity 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.orgItems Per Second, More Is BetterOSPRay 3.1Benchmark: particle_volume/scivis/real_timeXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P3691215SE +/- 0.00749, N = 3SE +/- 0.00296, N = 3SE +/- 0.00347, N = 3SE +/- 0.00135, N = 3SE +/- 0.00208, N = 3SE +/- 0.00497, N = 3SE +/- 0.00215, N = 3SE +/- 0.00310, N = 3SE +/- 0.00090, N = 35.886408.981954.618714.516506.056593.447688.499456.238002.33176

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Face Detection Retail FP16-INT8 - Device: CPUXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P10002000300040005000SE +/- 3.53, N = 3SE +/- 1.99, N = 3SE +/- 1.63, N = 3SE +/- 2.13, N = 3SE +/- 2.70, N = 3SE +/- 0.53, N = 3SE +/- 3.97, N = 3SE +/- 1.50, N = 3SE +/- 4.76, N = 31559.064734.272495.552329.233338.381804.904486.583221.201232.021. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

Cpuminer-Opt

Cpuminer-Opt is a fork of cpuminer-multi that carries a wide range of CPU performance optimizations for measuring the potential cryptocurrency mining performance of the CPU/processor with a wide variety of cryptocurrencies. The benchmark reports the hash speed for the CPU mining performance for the selected cryptocurrency. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 23.5Algorithm: Triple SHA-256, OnecoinXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P20K40K60K80K100KSE +/- 3.33, N = 3SE +/- 146.40, N = 3SE +/- 8.82, N = 3SE +/- 25.17, N = 3SE +/- 188.09, N = 3SE +/- 11.55, N = 3SE +/- 20.82, N = 3SE +/- 72.11, N = 3SE +/- 166.77, N = 33884797340510874990071517327109397067820253371. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

OSPRay

Intel OSPRay is a portable ray-tracing engine for high-performance, high-fidelity 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.orgItems Per Second, More Is BetterOSPRay 3.1Benchmark: particle_volume/ao/real_timeXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P3691215SE +/- 0.00839, N = 3SE +/- 0.00600, N = 3SE +/- 0.00129, N = 3SE +/- 0.00247, N = 3SE +/- 0.00892, N = 3SE +/- 0.00096, N = 3SE +/- 0.00180, N = 3SE +/- 0.00160, N = 3SE +/- 0.00263, N = 35.931618.983994.638284.525526.068953.455778.498696.254182.33907

Stress-NG

Stress-NG is a Linux stress tool developed by Colin Ian King. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Floating PointXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P2K4K6K8K10KSE +/- 7.41, N = 3SE +/- 15.20, N = 3SE +/- 6.00, N = 3SE +/- 0.05, N = 3SE +/- 2.90, N = 3SE +/- 1.77, N = 3SE +/- 8.85, N = 3SE +/- 1.22, N = 3SE +/- 1.85, N = 34740.288199.654251.394192.475977.763175.547928.205850.592137.331. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -lEGL -ljpeg -lmpfr -lpthread -lrt -lsctp -lz

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles performance with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported as well as HIP for AMD Radeon GPUs and Intel oneAPI for Intel Graphics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.1Blend File: Fishy Cat - Compute: CPU-OnlyXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P60120180240300SE +/- 0.24, N = 3SE +/- 0.06, N = 3SE +/- 0.39, N = 3SE +/- 0.16, N = 3SE +/- 0.02, N = 3SE +/- 0.15, N = 3SE +/- 0.12, N = 3SE +/- 0.16, N = 3SE +/- 0.25, N = 3165.0066.78127.01130.4295.44170.0067.9997.84256.10

OpenSSL

OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test profile makes use of the built-in "openssl speed" benchmarking capabilities. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.3Algorithm: AES-256-GCMXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P50000M100000M150000M200000M250000MSE +/- 5611535.27, N = 3SE +/- 27189836.88, N = 3SE +/- 101608115.02, N = 3SE +/- 28146850.41, N = 3SE +/- 51787792.79, N = 3SE +/- 23525395.17, N = 3SE +/- 124036322.98, N = 3SE +/- 10292339.65, N = 3SE +/- 6624573.52, N = 35619324919021533684767711394125887711042558725316061844120384060321200211726656087151313824427562917695501. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

ASTC Encoder

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

OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 4.7Preset: Very ThoroughXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P0.60391.20781.81172.41563.0195SE +/- 0.0116, N = 3SE +/- 0.0093, N = 3SE +/- 0.0010, N = 3SE +/- 0.0004, N = 3SE +/- 0.0004, N = 3SE +/- 0.0004, N = 3SE +/- 0.0008, N = 3SE +/- 0.0009, N = 3SE +/- 0.0007, N = 31.46392.68411.39791.35631.81641.03272.56361.83270.70141. (CXX) g++ options: -O3 -flto -pthread

OSPRay

Intel OSPRay is a portable ray-tracing engine for high-performance, high-fidelity 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.orgItems Per Second, More Is BetterOSPRay 3.1Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_timeXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P3691215SE +/- 0.00822, N = 3SE +/- 0.00353, N = 3SE +/- 0.00236, N = 3SE +/- 0.00576, N = 3SE +/- 0.00278, N = 3SE +/- 0.00315, N = 3SE +/- 0.00316, N = 3SE +/- 0.00517, N = 3SE +/- 0.00113, N = 33.795398.978134.667574.572226.091483.496998.668326.316052.34726

OpenSSL

OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test profile makes use of the built-in "openssl speed" benchmarking capabilities. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.3Algorithm: SHA512Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P2000M4000M6000M8000M10000MSE +/- 2787035.99, N = 3SE +/- 2951460.39, N = 3SE +/- 749962.39, N = 3SE +/- 485369.37, N = 3SE +/- 7000138.46, N = 3SE +/- 432194.03, N = 3SE +/- 5901271.36, N = 3SE +/- 1960683.64, N = 3SE +/- 3598429.85, N = 3442939716011041579923579440530756443575838052051307427527546010663356813781478597028874161571. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

Cpuminer-Opt

Cpuminer-Opt is a fork of cpuminer-multi that carries a wide range of CPU performance optimizations for measuring the potential cryptocurrency mining performance of the CPU/processor with a wide variety of cryptocurrencies. The benchmark reports the hash speed for the CPU mining performance for the selected cryptocurrency. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 23.5Algorithm: SkeincoinXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P7K14K21K28K35KSE +/- 139.08, N = 3SE +/- 11.55, N = 3SE +/- 39.30, N = 3SE +/- 11.55, N = 3SE +/- 134.45, N = 3SE +/- 11.55, N = 3SE +/- 8.82, N = 3SE +/- 42.56, N = 3SE +/- 5.33, N = 313933.0034640.0017983.0017580.0025583.0013390.0033693.0024937.009066.901. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles performance with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported as well as HIP for AMD Radeon GPUs and Intel oneAPI for Intel Graphics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.1Blend File: Classroom - Compute: CPU-OnlyXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P110220330440550SE +/- 1.57, N = 3SE +/- 0.07, N = 3SE +/- 0.07, N = 3SE +/- 0.28, N = 3SE +/- 0.13, N = 3SE +/- 0.40, N = 3SE +/- 0.33, N = 3SE +/- 0.27, N = 3SE +/- 0.71, N = 3336.94136.11259.46267.86197.38351.06139.57199.31519.82

RocksDB

This is a benchmark of Meta/Facebook's RocksDB as an embeddable persistent key-value store for fast storage based on Google's LevelDB. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Read While WritingXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P900K1800K2700K3600K4500KSE +/- 3646.67, N = 3SE +/- 7045.87, N = 3SE +/- 22460.23, N = 3SE +/- 6544.07, N = 3SE +/- 24911.17, N = 3SE +/- 20912.63, N = 3SE +/- 23577.88, N = 3SE +/- 10561.84, N = 3SE +/- 3157.59, N = 31942760429463125195942489854300361618655214334593313093411352611. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

ASTC Encoder

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

OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 4.7Preset: ExhaustiveXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P0.36880.73761.10641.47521.844SE +/- 0.0051, N = 3SE +/- 0.0020, N = 3SE +/- 0.0000, N = 3SE +/- 0.0003, N = 3SE +/- 0.0003, N = 3SE +/- 0.0004, N = 3SE +/- 0.0003, N = 3SE +/- 0.0001, N = 3SE +/- 0.0002, N = 30.87411.63910.85570.83131.11430.63301.57061.12370.42941. (CXX) g++ options: -O3 -flto -pthread

SVT-HEVC

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

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 1 - Input: Bosphorus 4KXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P1.3052.613.9155.226.525SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 32.265.803.042.943.992.255.633.961.521. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

Cpuminer-Opt

Cpuminer-Opt is a fork of cpuminer-multi that carries a wide range of CPU performance optimizations for measuring the potential cryptocurrency mining performance of the CPU/processor with a wide variety of cryptocurrencies. The benchmark reports the hash speed for the CPU mining performance for the selected cryptocurrency. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 23.5Algorithm: LBC, LBRY CreditsXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P3K6K9K12K15KSE +/- 15.18, N = 3SE +/- 5.77, N = 3SE +/- 7.26, N = 3SE +/- 27.28, N = 3SE +/- 3.33, N = 3SE +/- 2.97, N = 3SE +/- 106.67, N = 3SE +/- 3.33, N = 3SE +/- 2.03, N = 36037.2616120.008389.158323.6911867.006265.1015777.0011623.004228.171. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

OSPRay

Intel OSPRay is a portable ray-tracing engine for high-performance, high-fidelity 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.orgItems Per Second, More Is BetterOSPRay 3.1Benchmark: gravity_spheres_volume/dim_512/ao/real_timeXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P246810SE +/- 0.00479, N = 3SE +/- 0.00259, N = 3SE +/- 0.00682, N = 3SE +/- 0.00148, N = 3SE +/- 0.01719, N = 3SE +/- 0.00463, N = 3SE +/- 0.03021, N = 3SE +/- 0.00993, N = 3SE +/- 0.00310, N = 32.734967.466493.910703.816915.185702.950107.307485.347531.95862

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 TomcatXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P3K6K9K12K15KSE +/- 14.71, N = 3SE +/- 2.95, N = 4SE +/- 9.21, N = 3SE +/- 6.08, N = 3SE +/- 5.15, N = 4SE +/- 4.16, N = 3SE +/- 2.87, N = 4SE +/- 4.80, N = 4SE +/- 11.72, N = 36687337064826485445986283384444112840

Stress-NG

Stress-NG is a Linux stress tool developed by Colin Ian King. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Vector ShuffleXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P4K8K12K16K20KSE +/- 104.90, N = 3SE +/- 12.57, N = 3SE +/- 2.63, N = 3SE +/- 1.05, N = 3SE +/- 4.46, N = 3SE +/- 3.05, N = 3SE +/- 37.39, N = 3SE +/- 1.99, N = 3SE +/- 1.14, N = 39138.2916452.478556.728468.8612180.806403.8716010.7411892.694319.581. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -lEGL -ljpeg -lmpfr -lpthread -lrt -lsctp -lz

OpenSSL

OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test profile makes use of the built-in "openssl speed" benchmarking capabilities. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.3Algorithm: SHA256Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P7000M14000M21000M28000M35000MSE +/- 27097230.48, N = 3SE +/- 7892274.19, N = 3SE +/- 8102567.82, N = 3SE +/- 7769960.49, N = 3SE +/- 9363717.55, N = 3SE +/- 4935253.44, N = 3SE +/- 8957910.25, N = 3SE +/- 5636428.54, N = 3SE +/- 10799214.46, N = 3123365572633398965227317876358337174027128102469382234313220736913329138068102387621161389284630071. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

Cpuminer-Opt

Cpuminer-Opt is a fork of cpuminer-multi that carries a wide range of CPU performance optimizations for measuring the potential cryptocurrency mining performance of the CPU/processor with a wide variety of cryptocurrencies. The benchmark reports the hash speed for the CPU mining performance for the selected cryptocurrency. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 23.5Algorithm: DeepcoinXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P2K4K6K8K10KSE +/- 36.27, N = 3SE +/- 5.77, N = 3SE +/- 3.02, N = 3SE +/- 1.63, N = 3SE +/- 23.29, N = 3SE +/- 1.04, N = 3SE +/- 18.11, N = 3SE +/- 7.14, N = 3SE +/- 1.80, N = 33294.498356.744377.744280.916229.263247.548225.265939.522205.101. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

OSPRay

Intel OSPRay is a portable ray-tracing engine for high-performance, high-fidelity 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.orgItems Per Second, More Is BetterOSPRay 3.1Benchmark: gravity_spheres_volume/dim_512/scivis/real_timeXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P246810SE +/- 0.00622, N = 3SE +/- 0.02548, N = 3SE +/- 0.00260, N = 3SE +/- 0.01618, N = 3SE +/- 0.01525, N = 3SE +/- 0.01153, N = 3SE +/- 0.00808, N = 3SE +/- 0.01288, N = 3SE +/- 0.00828, N = 32.638517.369093.821383.794885.105892.919517.144705.273331.94504

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 YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 1 - Input: Bosphorus 1080pXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P612182430SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 39.1623.1012.2811.9015.899.1222.1115.716.111. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

Cpuminer-Opt

Cpuminer-Opt is a fork of cpuminer-multi that carries a wide range of CPU performance optimizations for measuring the potential cryptocurrency mining performance of the CPU/processor with a wide variety of cryptocurrencies. The benchmark reports the hash speed for the CPU mining performance for the selected cryptocurrency. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 23.5Algorithm: Blake-2 SXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P30K60K90K120K150KSE +/- 460.90, N = 3SE +/- 99.39, N = 3SE +/- 29.06, N = 3SE +/- 20.82, N = 3SE +/- 40.41, N = 3SE +/- 30.00, N = 3SE +/- 41.77, N = 3SE +/- 103.98, N = 3SE +/- 28.87, N = 356160142753745137313010679053870140467100853378101. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

Stress-NG

Stress-NG is a Linux stress tool developed by Colin Ian King. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: AVX-512 VNNIXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P600K1200K1800K2400K3000KSE +/- 5501.16, N = 3SE +/- 2539.18, N = 3SE +/- 1225.91, N = 3SE +/- 340.15, N = 3SE +/- 1104.16, N = 3SE +/- 655.92, N = 3SE +/- 5242.51, N = 3SE +/- 97.63, N = 3SE +/- 94.80, N = 31125583.012571394.821371242.641315000.021909466.061008567.362511125.721758023.97681157.031. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -lEGL -ljpeg -lmpfr -lpthread -lrt -lsctp -lz

Helsing

Helsing is an open-source POSIX vampire number generator. This test profile measures the time it takes to generate vampire numbers between varying numbers of digits. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterHelsing 1.0-betaDigit Range: 12 digitXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P246810SE +/- 0.028, N = 15SE +/- 0.003, N = 11SE +/- 0.004, N = 8SE +/- 0.003, N = 8SE +/- 0.003, N = 10SE +/- 0.002, N = 7SE +/- 0.003, N = 11SE +/- 0.003, N = 9SE +/- 0.016, N = 64.0802.0163.8283.9662.7715.1782.1173.0047.6091. (CC) gcc options: -O2 -pthread

m-queens

A solver for the N-queens problem with multi-threading support via the OpenMP library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is Betterm-queens 1.2Time To SolveXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P20406080100SE +/- 0.62, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.08, N = 3SE +/- 0.03, N = 3SE +/- 0.05, N = 3SE +/- 0.04, N = 372.8527.9153.5054.3940.4271.9828.5339.65105.301. (CXX) g++ options: -fopenmp -O2 -march=native

7-Zip Compression

This is a test of 7-Zip compression/decompression with its integrated benchmark feature. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 22.01Test: Decompression RatingXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P40K80K120K160K200KSE +/- 900.25, N = 3SE +/- 369.09, N = 3SE +/- 299.70, N = 3SE +/- 107.68, N = 3SE +/- 503.79, N = 3SE +/- 31.18, N = 3SE +/- 83.27, N = 3SE +/- 184.46, N = 3SE +/- 61.13, N = 361527170373889458840910713767868167201118507451891. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

Speedb

Speedb is a next-generation key value storage engine that is RocksDB compatible and aiming for stability, efficiency, and performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOp/s, More Is BetterSpeedb 2.7Test: Random ReadXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P30M60M90M120M150MSE +/- 170759.02, N = 3SE +/- 286737.26, N = 3SE +/- 34435.41, N = 3SE +/- 63522.73, N = 3SE +/- 202059.67, N = 3SE +/- 43642.52, N = 3SE +/- 806005.16, N = 3SE +/- 36870.14, N = 3SE +/- 186103.10, N = 3578244261349716267164868369443011920064215314637213284399294750279358293001. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

Cpuminer-Opt

Cpuminer-Opt is a fork of cpuminer-multi that carries a wide range of CPU performance optimizations for measuring the potential cryptocurrency mining performance of the CPU/processor with a wide variety of cryptocurrencies. The benchmark reports the hash speed for the CPU mining performance for the selected cryptocurrency. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 23.5Algorithm: MagiXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P140280420560700SE +/- 0.39, N = 3SE +/- 0.26, N = 3SE +/- 0.30, N = 3SE +/- 2.02, N = 3SE +/- 0.52, N = 3SE +/- 1.33, N = 3SE +/- 0.22, N = 3SE +/- 0.16, N = 3SE +/- 1.24, N = 3278.09633.44330.62328.70469.54248.85617.79453.87168.371. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 23.5Algorithm: Myriad-GroestlXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P2K4K6K8K10KSE +/- 30.23, N = 3SE +/- 13.33, N = 3SE +/- 6.11, N = 3SE +/- 3.31, N = 3SE +/- 5.30, N = 3SE +/- 8.61, N = 3SE +/- 3.33, N = 3SE +/- 39.39, N = 3SE +/- 0.25, N = 34843.7211337.005972.095929.568480.444487.2811207.008184.443016.701. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P11K22K33K44K55KSE +/- 38.88, N = 3SE +/- 47.80, N = 3SE +/- 19.90, N = 3SE +/- 5.77, N = 3SE +/- 42.38, N = 3SE +/- 103.84, N = 3SE +/- 32.19, N = 3SE +/- 68.04, N = 3SE +/- 57.65, N = 318507.3149485.3526230.8525613.2935169.3117920.7546506.7533784.7413170.121. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

QuantLib

QuantLib is an open-source library/framework around quantitative finance for modeling, trading and risk management scenarios. QuantLib is written in C++ with Boost and its built-in benchmark used reports the QuantLib Benchmark Index benchmark score. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMFLOPS, More Is BetterQuantLib 1.32Configuration: Multi-ThreadedXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P20K40K60K80K100KSE +/- 294.52, N = 3SE +/- 169.22, N = 3SE +/- 49.82, N = 3SE +/- 12.44, N = 3SE +/- 315.31, N = 3SE +/- 41.80, N = 3SE +/- 255.88, N = 3SE +/- 164.89, N = 3SE +/- 39.28, N = 337214.483365.143490.742668.657419.432626.880769.456873.222228.01. (CXX) g++ options: -O3 -march=native -fPIE -pie

RocksDB

This is a benchmark of Meta/Facebook's RocksDB as an embeddable persistent key-value store for fast storage based on Google's LevelDB. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Random ReadXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P30M60M90M120M150MSE +/- 236765.68, N = 3SE +/- 780691.20, N = 3SE +/- 144351.01, N = 3SE +/- 68428.53, N = 3SE +/- 342211.57, N = 3SE +/- 45665.92, N = 3SE +/- 276158.53, N = 3SE +/- 74109.11, N = 3SE +/- 11708.73, N = 3475122601306930636940825467959360891950285133414613000673791726942348856331. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

Coremark

This is a test of EEMBC CoreMark processor benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations/Sec, More Is BetterCoremark 1.0CoreMark Size 666 - Iterations Per SecondXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P200K400K600K800K1000KSE +/- 3256.58, N = 15SE +/- 9073.63, N = 3SE +/- 1076.82, N = 3SE +/- 4350.78, N = 3SE +/- 7061.60, N = 3SE +/- 954.28, N = 3SE +/- 1179.52, N = 3SE +/- 7794.37, N = 3SE +/- 165.60, N = 3430017.46951674.51499103.50491021.69625696.15372162.82923331.48648144.00254797.571. (CC) gcc options: -O2 -lrt" -lrt

Cpuminer-Opt

Cpuminer-Opt is a fork of cpuminer-multi that carries a wide range of CPU performance optimizations for measuring the potential cryptocurrency mining performance of the CPU/processor with a wide variety of cryptocurrencies. The benchmark reports the hash speed for the CPU mining performance for the selected cryptocurrency. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 23.5Algorithm: GarlicoinXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P7001400210028003500SE +/- 4.51, N = 3SE +/- 4.61, N = 3SE +/- 1.43, N = 3SE +/- 2.95, N = 3SE +/- 11.09, N = 3SE +/- 1.62, N = 3SE +/- 0.76, N = 3SE +/- 3.95, N = 3SE +/- 0.39, N = 31356.313179.321674.991637.722391.441243.883149.432229.57851.651. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs (and GPUs via SYCL) 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 4.3Binary: Pathtracer ISPC - Model: Asian Dragon ObjXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P714212835SE +/- 0.1018, N = 3SE +/- 0.0167, N = 3SE +/- 0.0082, N = 3SE +/- 0.0102, N = 3SE +/- 0.0104, N = 3SE +/- 0.0041, N = 3SE +/- 0.0196, N = 3SE +/- 0.0248, N = 3SE +/- 0.0121, N = 314.549927.387315.688915.635521.775712.200129.165521.24097.8364MIN: 14.14 / MAX: 16.68MIN: 27.11 / MAX: 28.25MIN: 15.56 / MAX: 16.03MIN: 15.52 / MAX: 15.91MIN: 21.53 / MAX: 22.24MIN: 12.12 / MAX: 12.41MIN: 28.89 / MAX: 30.01MIN: 21.05 / MAX: 21.73MIN: 7.78 / MAX: 7.97

Stress-NG

Stress-NG is a Linux stress tool developed by Colin Ian King. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Wide Vector MathXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P200K400K600K800K1000KSE +/- 373.64, N = 3SE +/- 1811.04, N = 3SE +/- 205.90, N = 3SE +/- 84.63, N = 3SE +/- 164.21, N = 3SE +/- 31.25, N = 3SE +/- 875.08, N = 3SE +/- 1009.32, N = 3SE +/- 117.98, N = 3576480.15778238.33413926.82402835.32568714.45307368.19749237.41539442.24209322.741. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -lEGL -ljpeg -lmpfr -lpthread -lrt -lsctp -lz

John The Ripper

This is a benchmark of John The Ripper, which is a password cracker. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: BlowfishXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P9K18K27K36K45KSE +/- 68.54, N = 3SE +/- 39.87, N = 3SE +/- 44.47, N = 3SE +/- 3.00, N = 3SE +/- 7.77, N = 3SE +/- 17.13, N = 3SE +/- 175.99, N = 3SE +/- 156.57, N = 3SE +/- 1.00, N = 31884143795232432340332864176214188931440118191. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -lm -lrt -lz -ldl -lcrypt -lbz2

Cpuminer-Opt

Cpuminer-Opt is a fork of cpuminer-multi that carries a wide range of CPU performance optimizations for measuring the potential cryptocurrency mining performance of the CPU/processor with a wide variety of cryptocurrencies. The benchmark reports the hash speed for the CPU mining performance for the selected cryptocurrency. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 23.5Algorithm: RingcoinXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P8001600240032004000SE +/- 3.73, N = 3SE +/- 20.59, N = 3SE +/- 4.79, N = 3SE +/- 2.14, N = 3SE +/- 2.15, N = 3SE +/- 1.54, N = 3SE +/- 6.91, N = 3SE +/- 2.43, N = 3SE +/- 9.66, N = 31437.473500.131851.251806.872586.651364.323424.572468.43944.971. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 23.5Algorithm: scryptXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P70140210280350SE +/- 0.08, N = 3SE +/- 1.34, N = 3SE +/- 0.10, N = 3SE +/- 0.16, N = 3SE +/- 1.04, N = 3SE +/- 0.13, N = 3SE +/- 1.22, N = 3SE +/- 0.11, N = 3SE +/- 0.14, N = 3119.86308.21162.88157.91227.45120.39298.15210.6483.291. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

Stress-NG

Stress-NG is a Linux stress tool developed by Colin Ian King. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Fused Multiply-AddXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P12M24M36M48M60MSE +/- 267691.10, N = 3SE +/- 500794.58, N = 3SE +/- 252666.10, N = 3SE +/- 319716.71, N = 3SE +/- 58656.32, N = 3SE +/- 283045.68, N = 3SE +/- 54521.03, N = 3SE +/- 28005.99, N = 3SE +/- 14786.84, N = 329762395.5756410032.2529927440.6929040929.2442202851.9722079544.9755781750.8439475809.7815250467.411. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -lEGL -ljpeg -lmpfr -lpthread -lrt -lsctp -lz

John The Ripper

This is a benchmark of John The Ripper, which is a password cracker. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: bcryptXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P9K18K27K36K45KSE +/- 127.68, N = 3SE +/- 104.20, N = 3SE +/- 43.32, N = 3SE +/- 7.88, N = 3SE +/- 12.90, N = 3SE +/- 12.53, N = 3SE +/- 89.13, N = 3SE +/- 157.44, N = 3SE +/- 3.71, N = 31878743695232352340732882176544196131119118181. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -lm -lrt -lz -ldl -lcrypt -lbz2

Helsing

Helsing is an open-source POSIX vampire number generator. This test profile measures the time it takes to generate vampire numbers between varying numbers of digits. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterHelsing 1.0-betaDigit Range: 14 digitXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P160320480640800SE +/- 0.23, N = 3SE +/- 0.37, N = 3SE +/- 0.18, N = 3SE +/- 0.31, N = 3SE +/- 0.10, N = 3SE +/- 0.52, N = 3SE +/- 0.19, N = 3SE +/- 0.29, N = 3SE +/- 0.11, N = 3437.41200.77375.92386.16268.44504.27204.02291.51740.561. (CC) gcc options: -O2 -pthread

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.orgns/day, More Is BetterNAMD 3.0b6Input: STMV with 1,066,628 AtomsXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P0.17050.3410.51150.6820.8525SE +/- 0.00016, N = 3SE +/- 0.00230, N = 3SE +/- 0.00059, N = 3SE +/- 0.00019, N = 3SE +/- 0.00185, N = 3SE +/- 0.00046, N = 3SE +/- 0.00443, N = 3SE +/- 0.00106, N = 3SE +/- 0.00019, N = 30.205650.756460.493450.485700.270390.389560.757680.608130.27425

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs (and GPUs via SYCL) 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 4.3Binary: Pathtracer ISPC - Model: Asian DragonXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P816243240SE +/- 0.1189, N = 3SE +/- 0.0349, N = 3SE +/- 0.0104, N = 3SE +/- 0.0055, N = 3SE +/- 0.0168, N = 3SE +/- 0.0065, N = 3SE +/- 0.0606, N = 3SE +/- 0.0156, N = 3SE +/- 0.0183, N = 316.575732.220918.451118.394025.534814.357634.236525.00869.2948MIN: 16.29 / MAX: 19.34MIN: 31.88 / MAX: 33.23MIN: 18.3 / MAX: 18.87MIN: 18.28 / MAX: 18.74MIN: 25.23 / MAX: 26.17MIN: 14.27 / MAX: 14.68MIN: 33.88 / MAX: 35.24MIN: 24.79 / MAX: 25.66MIN: 9.21 / MAX: 9.46

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Road Segmentation ADAS FP16-INT8 - Device: CPUXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P110220330440550SE +/- 0.28, N = 3SE +/- 1.94, N = 3SE +/- 0.50, N = 3SE +/- 1.13, N = 3SE +/- 0.69, N = 3SE +/- 0.12, N = 3SE +/- 0.32, N = 3SE +/- 0.40, N = 3SE +/- 1.16, N = 9219.86476.63275.72237.30366.70187.28516.90351.23140.591. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

ASKAP

ASKAP is a set of benchmarks from the Australian SKA Pathfinder. The principal ASKAP benchmarks are the Hogbom Clean Benchmark (tHogbomClean) and Convolutional Resamping Benchmark (tConvolve) as well as some previous ASKAP benchmarks being included as well for OpenCL and CUDA execution of tConvolve. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 1.0Test: tConvolve OpenMP - GriddingXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P14002800420056007000SE +/- 25.17, N = 5SE +/- 41.40, N = 6SE +/- 24.04, N = 8SE +/- 21.74, N = 15SE +/- 49.58, N = 6SE +/- 25.19, N = 7SE +/- 55.23, N = 6SE +/- 19.10, N = 6SE +/- 19.19, N = 152556.225073.232739.343122.294948.432825.316603.674438.011801.151. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

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: 1000Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P30K60K90K120K150KSE +/- 46.60, N = 3SE +/- 301.50, N = 3SE +/- 98.21, N = 3SE +/- 87.10, N = 3SE +/- 194.32, N = 3SE +/- 150.02, N = 3SE +/- 280.22, N = 3SE +/- 117.22, N = 3SE +/- 247.36, N = 387132.22136360.7285990.1284832.82120690.4366910.93150874.91108719.1241180.811. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2

Primesieve

Primesieve generates prime numbers using a highly optimized sieve of Eratosthenes implementation. Primesieve primarily benchmarks the CPU's L1/L2 cache performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPrimesieve 12.1Length: 1e12Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P612182430SE +/- 0.302, N = 3SE +/- 0.007, N = 6SE +/- 0.007, N = 4SE +/- 0.013, N = 4SE +/- 0.005, N = 5SE +/- 0.014, N = 3SE +/- 0.009, N = 6SE +/- 0.007, N = 5SE +/- 0.014, N = 321.0956.69112.50612.9379.18316.8277.0309.94324.4961. (CXX) g++ options: -O3

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 CompileXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P30060090012001500SE +/- 1.08, N = 3SE +/- 0.68, N = 3SE +/- 0.38, N = 3SE +/- 0.61, N = 3SE +/- 0.11, N = 3SE +/- 0.13, N = 3SE +/- 0.55, N = 3SE +/- 0.29, N = 3SE +/- 0.89, N = 3915.94421.43739.34743.11482.80916.47395.44524.511444.31

Primesieve

Primesieve generates prime numbers using a highly optimized sieve of Eratosthenes implementation. Primesieve primarily benchmarks the CPU's L1/L2 cache performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPrimesieve 12.1Length: 1e13Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P70140210280350SE +/- 0.18, N = 3SE +/- 0.20, N = 3SE +/- 0.15, N = 3SE +/- 0.11, N = 3SE +/- 0.05, N = 3SE +/- 0.10, N = 3SE +/- 0.07, N = 3SE +/- 0.08, N = 3SE +/- 0.18, N = 3245.6782.47153.60158.45111.63205.2085.31120.86300.411. (CXX) g++ options: -O3

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 2.0.0Benchmark: vklBenchmarkCPU ISPCXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P130260390520650SE +/- 0.33, N = 3SE +/- 0.67, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.00, N = 3SE +/- 0.33, N = 3SE +/- 0.67, N = 3SE +/- 0.00, N = 3288603331327452253606446167MIN: 20 / MAX: 4338MIN: 48 / MAX: 8450MIN: 25 / MAX: 4820MIN: 24 / MAX: 4788MIN: 34 / MAX: 5835MIN: 19 / MAX: 3690MIN: 47 / MAX: 8240MIN: 34 / MAX: 6230MIN: 12 / MAX: 2373

GraphicsMagick

This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample high resolution (currently 15400 x 6940) JPEG image. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.43Operation: SharpenXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P1326395265SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 33658303041235741161. (CC) gcc options: -fopenmp -O2 -ltiff -ljbig -lsharpyuv -lwebp -lwebpmux -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lxml2 -lzstd -llzma -lbz2 -lz -lm -lpthread -lgomp

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.43Operation: EnhancedXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P20406080100SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 34994504964389267261. (CC) gcc options: -fopenmp -O2 -ltiff -ljbig -lsharpyuv -lwebp -lwebpmux -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lxml2 -lzstd -llzma -lbz2 -lz -lm -lpthread -lgomp

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: allmodconfigXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P6001200180024003000SE +/- 0.63, N = 3SE +/- 0.38, N = 3SE +/- 0.32, N = 3SE +/- 0.16, N = 3SE +/- 0.76, N = 3SE +/- 0.90, N = 3SE +/- 0.27, N = 3SE +/- 1.21, N = 3SE +/- 0.88, N = 31508.04714.381310.961319.93905.031730.88710.79976.202563.91

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: 1:100Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P800K1600K2400K3200K4000KSE +/- 11523.53, N = 3SE +/- 5665.65, N = 3SE +/- 1471.26, N = 3SE +/- 390.53, N = 3SE +/- 4210.88, N = 3SE +/- 2895.46, N = 3SE +/- 8167.06, N = 3SE +/- 2341.26, N = 3SE +/- 1131.60, N = 33048853.563844031.282104490.552056776.092651410.811567216.543756154.982749241.801068869.521. (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: NinjaXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P30060090012001500SE +/- 0.51, N = 3SE +/- 0.24, N = 3SE +/- 0.77, N = 3SE +/- 0.10, N = 3SE +/- 0.34, N = 3SE +/- 0.14, N = 3SE +/- 0.47, N = 3SE +/- 0.48, N = 3SE +/- 0.99, N = 3697.94354.76636.83644.77428.25815.09345.35464.511240.86

Intel Open Image Denoise

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

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 2.2Run: RT.ldr_alb_nrm.3840x2160 - Device: CPU-OnlyXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P0.19350.3870.58050.7740.9675SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.420.860.480.470.640.360.840.640.24

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 2.2Run: RT.hdr_alb_nrm.3840x2160 - Device: CPU-OnlyXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P0.19350.3870.58050.7740.9675SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.420.860.480.470.640.360.840.640.24

uvg266

uvg266 is an open-source VVC/H.266 (Versatile Video Coding) encoder based on Kvazaar as part of the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: MediumXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P48121620SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 36.6215.928.618.3510.256.5315.0710.414.47

Speedb

Speedb is a next-generation key value storage engine that is RocksDB compatible and aiming for stability, efficiency, and performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOp/s, More Is BetterSpeedb 2.7Test: Read While WritingXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P1.1M2.2M3.3M4.4M5.5MSE +/- 20209.24, N = 3SE +/- 26941.48, N = 3SE +/- 14207.26, N = 3SE +/- 24740.75, N = 15SE +/- 55041.91, N = 13SE +/- 17743.52, N = 15SE +/- 35376.76, N = 15SE +/- 18321.18, N = 3SE +/- 10363.63, N = 152548837511989131949713189650378116624002435262628378371914777671. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

Appleseed

Appleseed is an open-source production renderer focused on physically-based global illumination rendering engine primarily designed for animation and visual effects. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterAppleseed 2.0 BetaScene: Disney MaterialXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P70140210280350174.9585.32156.07160.01118.62210.1187.70120.91303.43

LuxCoreRender

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

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.6Scene: DLSC - Acceleration: CPUXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P1.1252.253.3754.55.625SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 32.135.002.752.673.472.064.883.481.41MIN: 2.03 / MAX: 2.65MIN: 4.85 / MAX: 5.35MIN: 2.66 / MAX: 2.86MIN: 2.59 / MAX: 2.76MIN: 3.38 / MAX: 3.64MIN: 2 / MAX: 2.12MIN: 4.77 / MAX: 5.16MIN: 3.39 / MAX: 3.64MIN: 1.37 / MAX: 1.44

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Vehicle Detection FP16-INT8 - Device: CPUXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P48121620SE +/- 0.05, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 315.954.824.534.755.026.195.015.339.68MIN: 9.85 / MAX: 70.28MIN: 2.78 / MAX: 17.83MIN: 2.65 / MAX: 17.47MIN: 2.76 / MAX: 10.38MIN: 2.86 / MAX: 11.09MIN: 3.5 / MAX: 13.93MIN: 2.78 / MAX: 17.17MIN: 2.88 / MAX: 17.76MIN: 5.18 / MAX: 21.131. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

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: 500Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P30K60K90K120K150KSE +/- 173.47, N = 3SE +/- 288.60, N = 3SE +/- 191.32, N = 3SE +/- 64.09, N = 3SE +/- 88.44, N = 3SE +/- 14.73, N = 3SE +/- 336.44, N = 3SE +/- 41.74, N = 3SE +/- 166.47, N = 392582.29154835.0694947.7591569.87124133.8870866.42158717.74116236.1645317.161. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2

LuxCoreRender

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

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.6Scene: Orange Juice - Acceleration: CPUXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P246810SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 33.587.724.424.305.553.307.655.552.21MIN: 3.44 / MAX: 4.42MIN: 6.87 / MAX: 8.15MIN: 4.32 / MAX: 4.49MIN: 4.24 / MAX: 4.36MIN: 5.19 / MAX: 5.69MIN: 3.26 / MAX: 3.33MIN: 6.89 / MAX: 7.99MIN: 5.2 / MAX: 5.66MIN: 2.13 / MAX: 2.24

GraphicsMagick

This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample high resolution (currently 15400 x 6940) JPEG image. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.43Operation: SwirlXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P50100150200250SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.33, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3130250139137163106243181721. (CC) gcc options: -fopenmp -O2 -ltiff -ljbig -lsharpyuv -lwebp -lwebpmux -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lxml2 -lzstd -llzma -lbz2 -lz -lm -lpthread -lgomp

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 ProcessingXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P400800120016002000SE +/- 30.56, N = 15SE +/- 4.09, N = 9SE +/- 2.37, N = 8SE +/- 2.15, N = 8SE +/- 3.68, N = 9SE +/- 10.99, N = 7SE +/- 3.84, N = 9SE +/- 2.11, N = 9SE +/- 3.20, N = 610535891019104174913806207812033

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: AlexNetXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P90180270360450SE +/- 0.02, N = 3SE +/- 1.74, N = 3SE +/- 0.55, N = 3SE +/- 0.04, N = 3SE +/- 0.08, N = 3SE +/- 0.09, N = 3SE +/- 0.06, N = 3SE +/- 0.04, N = 3SE +/- 0.05, N = 3192.28425.47240.23238.89327.41176.61409.89315.30123.63

BRL-CAD

BRL-CAD is a cross-platform, open-source solid modeling system with built-in benchmark mode. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgVGR Performance Metric, More Is BetterBRL-CAD 7.38.2VGR Performance MetricXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P90K180K270K360K450K1941273971382261982217672948911703683841832751671156531. (CXX) g++ options: -std=c++17 -pipe -fvisibility=hidden -fno-strict-aliasing -fno-common -fexceptions -ftemplate-depth-128 -m64 -ggdb3 -O3 -fipa-pta -fstrength-reduce -finline-functions -flto -ltcl8.6 -lnetpbm -lregex_brl -lz_brl -lassimp -ldl -lm -ltk8.6

Intel Open Image Denoise

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

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 2.2Run: RTLightmap.hdr.4096x4096 - Device: CPU-OnlyXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P0.09230.18460.27690.36920.4615SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.210.410.230.220.300.170.400.300.12

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: 200Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P30K60K90K120K150KSE +/- 231.66, N = 3SE +/- 150.85, N = 3SE +/- 127.61, N = 3SE +/- 78.04, N = 3SE +/- 32.54, N = 3SE +/- 50.61, N = 3SE +/- 28.66, N = 3SE +/- 69.09, N = 3SE +/- 66.30, N = 398692.95162348.33101214.8897227.42123864.1675062.51160748.18118177.5047788.241. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2

Appleseed

Appleseed is an open-source production renderer focused on physically-based global illumination rendering engine primarily designed for animation and visual effects. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterAppleseed 2.0 BetaScene: EmilyXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P110220330440550323.27152.30263.51264.67201.65341.30153.65202.53514.70

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.4Harness: IP Shapes 1D - Engine: CPUXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P0.85891.71782.57673.43564.2945SE +/- 0.01544, N = 4SE +/- 0.00269, N = 4SE +/- 0.00536, N = 4SE +/- 0.00137, N = 4SE +/- 0.00037, N = 4SE +/- 0.00010, N = 4SE +/- 0.00331, N = 4SE +/- 0.00923, N = 4SE +/- 0.00057, N = 42.914081.130001.999861.979321.935532.606381.166741.973623.81753MIN: 2.51MIN: 1.03MIN: 1.85MIN: 1.91MIN: 1.91MIN: 2.57MIN: 1.08MIN: 1.82MIN: 3.741. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

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: 1:10Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P800K1600K2400K3200K4000KSE +/- 7388.22, N = 3SE +/- 5303.54, N = 3SE +/- 2761.61, N = 3SE +/- 2995.56, N = 3SE +/- 4264.77, N = 3SE +/- 1442.09, N = 3SE +/- 5211.99, N = 3SE +/- 1507.35, N = 3SE +/- 2338.48, N = 33072373.873761626.612195688.492163987.012658380.051651621.673693215.302762180.281117437.501. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

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: 256 - Model: AlexNetXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P90180270360450SE +/- 0.06, N = 3SE +/- 0.09, N = 3SE +/- 0.09, N = 3SE +/- 0.05, N = 3SE +/- 0.35, N = 3SE +/- 0.14, N = 3SE +/- 0.23, N = 3SE +/- 0.07, N = 3SE +/- 0.04, N = 3189.14409.96237.57235.47294.91174.06396.85305.22121.85

Parallel BZIP2 Compression

This test measures the time needed to compress a file (FreeBSD-13.0-RELEASE-amd64-memstick.img) using Parallel BZIP2 compression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterParallel BZIP2 Compression 1.1.13FreeBSD-13.0-RELEASE-amd64-memstick.img CompressionXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P3691215SE +/- 0.044479, N = 6SE +/- 0.025811, N = 10SE +/- 0.045809, N = 15SE +/- 0.051557, N = 7SE +/- 0.036366, N = 9SE +/- 0.047798, N = 6SE +/- 0.022219, N = 15SE +/- 0.044427, N = 15SE +/- 0.094483, N = 56.6124863.2998796.1544605.7018564.4083237.6173053.5215654.44790411.0974201. (CXX) g++ options: -O2 -pthread -lbz2 -lpthread

Timed Godot Game Engine Compilation

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Godot Game Engine Compilation 4.0Time To CompileXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P130260390520650SE +/- 0.34, N = 3SE +/- 0.40, N = 3SE +/- 0.15, N = 3SE +/- 0.16, N = 3SE +/- 0.51, N = 3SE +/- 0.05, N = 3SE +/- 0.60, N = 3SE +/- 0.49, N = 3SE +/- 0.23, N = 3364.42188.53326.16330.82225.99415.40184.51246.66618.87

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 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 1080pXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P70140210280350SE +/- 2.05, N = 15SE +/- 0.26, N = 10SE +/- 0.21, N = 8SE +/- 0.17, N = 8SE +/- 0.22, N = 9SE +/- 0.13, N = 7SE +/- 0.40, N = 10SE +/- 0.24, N = 9SE +/- 0.07, N = 6168.39311.95178.20173.19215.68135.99297.03216.6793.011. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

uvg266

uvg266 is an open-source VVC/H.266 (Versatile Video Coding) encoder based on Kvazaar as part of the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Super FastXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P1122334455SE +/- 0.08, N = 3SE +/- 0.07, N = 4SE +/- 0.05, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 4SE +/- 0.02, N = 3SE +/- 0.01, N = 320.1746.4126.6526.0431.2920.3843.8931.6713.85

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 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 4KXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P20406080100SE +/- 0.08, N = 4SE +/- 0.06, N = 6SE +/- 0.04, N = 5SE +/- 0.04, N = 4SE +/- 0.07, N = 5SE +/- 0.02, N = 4SE +/- 0.15, N = 6SE +/- 0.05, N = 5SE +/- 0.03, N = 347.9899.6157.2355.6672.0743.5797.7771.6429.821. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

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 MakefilesXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P30060090012001500SE +/- 0.50, N = 3SE +/- 1.00, N = 3SE +/- 0.38, N = 3SE +/- 0.24, N = 3SE +/- 0.93, N = 3SE +/- 0.63, N = 3SE +/- 2.07, N = 3SE +/- 0.73, N = 3SE +/- 1.10, N = 3719.39387.01662.52669.64453.31840.92379.72491.501262.91

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: MediumXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P510152025SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.05, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 39.2822.0212.4912.1014.409.5920.6514.666.641. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.4Harness: Recurrent Neural Network Inference - Engine: CPUXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P5001000150020002500SE +/- 6.38, N = 3SE +/- 1.91, N = 3SE +/- 7.18, N = 3SE +/- 0.53, N = 3SE +/- 0.47, N = 3SE +/- 0.51, N = 3SE +/- 2.47, N = 3SE +/- 1.03, N = 3SE +/- 0.34, N = 31548.71706.651337.471310.59962.211615.38694.521036.152274.05MIN: 1512.56MIN: 679.48MIN: 1299.81MIN: 1303.57MIN: 959.35MIN: 1610.14MIN: 671.73MIN: 1006.91MIN: 2268.031. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.4Harness: Recurrent Neural Network Training - Engine: CPUXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P9001800270036004500SE +/- 9.27, N = 3SE +/- 1.43, N = 3SE +/- 1.64, N = 3SE +/- 3.47, N = 3SE +/- 1.07, N = 3SE +/- 0.60, N = 3SE +/- 1.75, N = 3SE +/- 2.12, N = 3SE +/- 1.52, N = 32931.951348.372491.142514.661890.003148.811355.101973.994388.64MIN: 2882.15MIN: 1314.05MIN: 2459.9MIN: 2499.44MIN: 1885.76MIN: 3143.3MIN: 1323.99MIN: 1936.17MIN: 4379.531. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

PostgreSQL

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

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 800 - Mode: Read WriteXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P11K22K33K44K55KSE +/- 85.58, N = 3SE +/- 481.81, N = 3SE +/- 123.75, N = 3SE +/- 206.50, N = 3SE +/- 369.77, N = 7SE +/- 280.73, N = 3SE +/- 549.43, N = 3SE +/- 454.20, N = 3SE +/- 116.46, N = 33448649522326573228039608254485102239830156971. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 800 - Mode: Read Write - Average LatencyXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P1122334455SE +/- 0.06, N = 3SE +/- 0.16, N = 3SE +/- 0.09, N = 3SE +/- 0.16, N = 3SE +/- 0.19, N = 7SE +/- 0.34, N = 3SE +/- 0.17, N = 3SE +/- 0.23, N = 3SE +/- 0.38, N = 323.2016.1624.5024.7920.2131.4415.6820.0950.971. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

uvg266

uvg266 is an open-source VVC/H.266 (Versatile Video Coding) encoder based on Kvazaar as part of the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Very FastXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P1020304050SE +/- 0.06, N = 3SE +/- 0.08, N = 4SE +/- 0.05, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 4SE +/- 0.03, N = 3SE +/- 0.00, N = 318.9742.6025.2524.6229.5319.2940.1529.8213.14

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Ultra FastXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P1224364860SE +/- 0.01, N = 3SE +/- 0.08, N = 5SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 4SE +/- 0.01, N = 3SE +/- 0.17, N = 4SE +/- 0.01, N = 4SE +/- 0.03, N = 324.6954.5431.8631.3036.7124.5951.6337.2216.86

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Person Detection FP32 - Device: CPUXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P20406080100SE +/- 0.17, N = 3SE +/- 0.47, N = 3SE +/- 0.09, N = 3SE +/- 0.13, N = 3SE +/- 0.07, N = 3SE +/- 0.20, N = 3SE +/- 0.44, N = 3SE +/- 0.35, N = 3SE +/- 0.06, N = 329.7188.3254.9852.2485.2944.4096.1074.2231.591. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

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 ModelXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P20406080100SE +/- 0.06, N = 3SE +/- 0.20, N = 15SE +/- 0.48, N = 3SE +/- 0.53, N = 3SE +/- 0.25, N = 3SE +/- 0.26, N = 3SE +/- 0.34, N = 3SE +/- 0.32, N = 3SE +/- 0.34, N = 352.8930.1349.5847.6952.2360.3828.0639.2890.581. (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

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Person Detection FP16 - Device: CPUXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P20406080100SE +/- 0.16, N = 3SE +/- 0.98, N = 3SE +/- 0.11, N = 3SE +/- 0.04, N = 3SE +/- 0.10, N = 3SE +/- 0.06, N = 3SE +/- 0.52, N = 3SE +/- 0.08, N = 3SE +/- 0.14, N = 329.8388.8455.1152.3585.1144.1795.9573.5131.711. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

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: defconfigXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P4080120160200SE +/- 0.45, N = 3SE +/- 0.36, N = 3SE +/- 0.32, N = 3SE +/- 0.40, N = 3SE +/- 0.38, N = 3SE +/- 0.29, N = 3SE +/- 0.35, N = 3SE +/- 0.47, N = 3SE +/- 0.30, N = 3108.3457.4797.4198.2970.30126.0057.4875.25182.46

7-Zip Compression

This is a test of 7-Zip compression/decompression with its integrated benchmark feature. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 22.01Test: Compression RatingXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P40K80K120K160K200KSE +/- 436.66, N = 3SE +/- 313.05, N = 3SE +/- 195.02, N = 3SE +/- 134.28, N = 3SE +/- 350.41, N = 3SE +/- 155.58, N = 3SE +/- 738.67, N = 3SE +/- 160.29, N = 3SE +/- 61.73, N = 39499017088810357110424814156582933177125139935561551. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

Timed FFmpeg Compilation

This test times how long it takes to build the FFmpeg multimedia library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed FFmpeg Compilation 6.1Time To CompileXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P20406080100SE +/- 0.33, N = 3SE +/- 0.12, N = 3SE +/- 0.02, N = 3SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.13, N = 3SE +/- 0.06, N = 3SE +/- 0.17, N = 3SE +/- 0.07, N = 350.0525.3042.2042.9430.5553.8825.2533.0379.58

CockroachDB

CockroachDB is a cloud-native, distributed SQL database for data intensive applications. This test profile uses a server-less CockroachDB configuration to test various Coackroach workloads on the local host with a single node. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgops/s, More Is BetterCockroachDB 22.2Workload: KV, 95% Reads - Concurrency: 128Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P30K60K90K120K150KSE +/- 237.27, N = 3SE +/- 765.52, N = 3SE +/- 302.28, N = 3SE +/- 276.11, N = 3SE +/- 391.29, N = 3SE +/- 73.92, N = 3SE +/- 158.53, N = 3SE +/- 58.24, N = 3SE +/- 88.19, N = 383987.5121061.783155.882706.290283.663936.2118066.792280.738555.5

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: Homogeneous HalfspaceXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P306090120150SE +/- 0.41, N = 3SE +/- 0.28, N = 3SE +/- 0.35, N = 3SE +/- 0.54, N = 3SE +/- 0.43, N = 3SE +/- 1.09, N = 3SE +/- 0.48, N = 3SE +/- 0.57, N = 3SE +/- 1.30, N = 367.1139.5663.8759.6367.5677.2336.3150.70112.871. (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

ASKAP

ASKAP is a set of benchmarks from the Australian SKA Pathfinder. The principal ASKAP benchmarks are the Hogbom Clean Benchmark (tHogbomClean) and Convolutional Resamping Benchmark (tConvolve) as well as some previous ASKAP benchmarks being included as well for OpenCL and CUDA execution of tConvolve. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 1.0Test: tConvolve OpenMP - DegriddingXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P2K4K6K8K10KSE +/- 41.03, N = 5SE +/- 49.85, N = 6SE +/- 27.18, N = 8SE +/- 18.97, N = 15SE +/- 71.64, N = 6SE +/- 154.63, N = 7SE +/- 90.51, N = 6SE +/- 42.40, N = 6SE +/- 16.62, N = 154282.185172.443426.033420.878591.904370.028830.774566.422841.951. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

JPEG-XL libjxl

The JPEG XL Image Coding System is designed to provide next-generation JPEG image capabilities with JPEG XL offering better image quality and compression over legacy JPEG. This test profile is currently focused on the multi-threaded JPEG XL image encode performance using the reference libjxl library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMP/s, More Is BetterJPEG-XL libjxl 0.10.1Input: PNG - Quality: 100Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P714212835SE +/- 0.066, N = 3SE +/- 0.037, N = 3SE +/- 0.016, N = 3SE +/- 0.006, N = 3SE +/- 0.008, N = 3SE +/- 0.006, N = 3SE +/- 0.020, N = 3SE +/- 0.022, N = 3SE +/- 0.002, N = 313.65027.74816.66116.35819.94312.84826.40820.7438.9991. (CXX) g++ options: -fno-rtti -O3 -fPIE -pie -lm

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 TimeXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P90180270360450242.94183.23296.60275.10168.98307.01141.46210.39432.881. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfoamToVTK -ldynamicMesh -llagrangian -lgenericPatchFields -lfileFormats -lOpenFOAM -ldl -lm

CockroachDB

CockroachDB is a cloud-native, distributed SQL database for data intensive applications. This test profile uses a server-less CockroachDB configuration to test various Coackroach workloads on the local host with a single node. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgops/s, More Is BetterCockroachDB 22.2Workload: KV, 60% Reads - Concurrency: 128Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P20K40K60K80K100KSE +/- 198.29, N = 3SE +/- 156.58, N = 3SE +/- 47.09, N = 3SE +/- 105.77, N = 3SE +/- 72.81, N = 3SE +/- 116.97, N = 3SE +/- 462.84, N = 3SE +/- 132.40, N = 3SE +/- 20.64, N = 363021.495084.867506.766756.973004.551927.096269.175445.731458.9

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.4Harness: Deconvolution Batch shapes_3d - Engine: CPUXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P246810SE +/- 0.10597, N = 15SE +/- 0.00405, N = 9SE +/- 0.00661, N = 9SE +/- 0.00062, N = 9SE +/- 0.00129, N = 9SE +/- 0.00099, N = 9SE +/- 0.00476, N = 9SE +/- 0.00652, N = 9SE +/- 0.00081, N = 94.947922.461593.834123.948883.510655.552542.707823.454617.51286MIN: 4.45MIN: 2.35MIN: 3.58MIN: 3.84MIN: 3.46MIN: 5.53MIN: 2.61MIN: 3.24MIN: 7.51. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

JPEG-XL libjxl

The JPEG XL Image Coding System is designed to provide next-generation JPEG image capabilities with JPEG XL offering better image quality and compression over legacy JPEG. This test profile is currently focused on the multi-threaded JPEG XL image encode performance using the reference libjxl library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMP/s, More Is BetterJPEG-XL libjxl 0.10.1Input: JPEG - Quality: 100Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P612182430SE +/- 0.037, N = 3SE +/- 0.005, N = 3SE +/- 0.006, N = 3SE +/- 0.012, N = 3SE +/- 0.037, N = 3SE +/- 0.007, N = 3SE +/- 0.034, N = 3SE +/- 0.026, N = 3SE +/- 0.002, N = 313.48427.22316.51916.27719.80712.69625.90720.5288.9591. (CXX) g++ options: -fno-rtti -O3 -fPIE -pie -lm

CockroachDB

CockroachDB is a cloud-native, distributed SQL database for data intensive applications. This test profile uses a server-less CockroachDB configuration to test various Coackroach workloads on the local host with a single node. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgops/s, More Is BetterCockroachDB 22.2Workload: KV, 50% Reads - Concurrency: 128Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P20K40K60K80K100KSE +/- 189.35, N = 3SE +/- 831.25, N = 3SE +/- 264.18, N = 3SE +/- 75.55, N = 3SE +/- 233.77, N = 3SE +/- 67.60, N = 3SE +/- 58.30, N = 3SE +/- 37.01, N = 3SE +/- 100.60, N = 359866.692195.264052.763986.269839.849645.090314.071721.130433.2

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 FastXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P1428425670SE +/- 0.31, N = 4SE +/- 0.07, N = 5SE +/- 0.05, N = 4SE +/- 0.05, N = 4SE +/- 0.03, N = 4SE +/- 0.04, N = 3SE +/- 0.03, N = 5SE +/- 0.04, N = 4SE +/- 0.01, N = 328.6462.5638.8237.7043.5430.1058.2544.4620.751. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

PostgreSQL

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

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 500 - Mode: Read WriteXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P13K26K39K52K65KSE +/- 362.37, N = 3SE +/- 699.92, N = 3SE +/- 256.18, N = 3SE +/- 304.71, N = 3SE +/- 339.91, N = 3SE +/- 246.90, N = 3SE +/- 609.40, N = 3SE +/- 263.22, N = 3SE +/- 9.63, N = 34241256517404733954945852316095840546671193931. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 500 - Mode: Read Write - Average LatencyXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P612182430SE +/- 0.101, N = 3SE +/- 0.109, N = 3SE +/- 0.078, N = 3SE +/- 0.098, N = 3SE +/- 0.080, N = 3SE +/- 0.123, N = 3SE +/- 0.089, N = 3SE +/- 0.061, N = 3SE +/- 0.013, N = 311.7918.85012.35512.64410.90615.8208.56310.71425.7831. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

Zstd Compression

This test measures the time needed to compress/decompress a sample file (silesia.tar) using Zstd (Zstandard) compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 8, Long Mode - Compression SpeedXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P2004006008001000SE +/- 1.12, N = 3SE +/- 3.49, N = 3SE +/- 0.95, N = 3SE +/- 0.50, N = 3SE +/- 3.16, N = 3SE +/- 1.62, N = 3SE +/- 3.15, N = 3SE +/- 1.33, N = 3SE +/- 0.48, N = 3504.1797.0527.9532.3888.7482.9961.2745.5323.01. (CC) gcc options: -O3 -pthread -lz -llzma

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 24.0Time To CompileXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P1224364860SE +/- 0.07, N = 3SE +/- 0.21, N = 3SE +/- 0.11, N = 3SE +/- 0.11, N = 3SE +/- 0.04, N = 3SE +/- 0.16, N = 3SE +/- 0.01, N = 3SE +/- 0.08, N = 3SE +/- 0.12, N = 332.5217.4628.2628.6221.0535.7117.6722.1251.97

x265

This is a simple test of the x265 encoder run on the CPU with 1080p and 4K options for H.265 video encode performance with x265. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.4Video Input: Bosphorus 4KXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P816243240SE +/- 0.17, N = 3SE +/- 0.08, N = 3SE +/- 0.15, N = 15SE +/- 0.22, N = 3SE +/- 0.11, N = 3SE +/- 0.19, N = 3SE +/- 0.20, N = 3SE +/- 0.16, N = 3SE +/- 0.04, N = 319.4834.6517.6116.7727.2017.6034.0227.4311.661. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

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 CompileXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P2004006008001000SE +/- 0.89, N = 3SE +/- 0.80, N = 3SE +/- 0.34, N = 3SE +/- 0.25, N = 3SE +/- 1.50, N = 3SE +/- 0.50, N = 3SE +/- 3.30, N = 4SE +/- 1.21, N = 3SE +/- 0.48, N = 3468.38273.49432.22438.62320.09540.89267.08339.22787.86

Zstd Compression

This test measures the time needed to compress/decompress a sample file (silesia.tar) using Zstd (Zstandard) compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 8 - Compression SpeedXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P2004006008001000SE +/- 3.15, N = 3SE +/- 6.27, N = 9SE +/- 1.88, N = 3SE +/- 1.07, N = 3SE +/- 6.53, N = 3SE +/- 2.29, N = 3SE +/- 2.98, N = 3SE +/- 2.23, N = 3SE +/- 0.98, N = 3485.6793.8520.3525.1942.3500.0970.7798.4330.31. (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 2024Implementation: MPI CPU - Input: water_GMX50_bareXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P0.60351.2071.81052.4143.0175SE +/- 0.000, N = 3SE +/- 0.001, N = 3SE +/- 0.002, N = 3SE +/- 0.002, N = 3SE +/- 0.001, N = 3SE +/- 0.001, N = 3SE +/- 0.002, N = 3SE +/- 0.008, N = 3SE +/- 0.001, N = 31.4342.5431.5461.5222.2881.2532.6822.1230.9141. (CXX) g++ options: -O3 -lm

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 2.0Encoder Mode: Preset 8 - Input: Bosphorus 4KXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P1632486480SE +/- 0.30, N = 3SE +/- 0.15, N = 5SE +/- 0.10, N = 4SE +/- 0.07, N = 4SE +/- 0.07, N = 4SE +/- 0.11, N = 3SE +/- 0.11, N = 5SE +/- 0.05, N = 4SE +/- 0.06, N = 336.1472.7447.2945.9556.9636.7069.9657.2324.871. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

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 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 1080pXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P120240360480600SE +/- 4.53, N = 15SE +/- 1.04, N = 12SE +/- 0.24, N = 11SE +/- 0.44, N = 11SE +/- 0.39, N = 11SE +/- 0.23, N = 10SE +/- 0.81, N = 12SE +/- 0.29, N = 11SE +/- 0.16, N = 9383.64560.81361.05351.91422.86279.57554.16428.68192.921. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

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 HalfspaceXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P50100150200250SE +/- 1.26, N = 3SE +/- 0.14, N = 3SE +/- 0.49, N = 3SE +/- 1.33, N = 3SE +/- 0.40, N = 3SE +/- 1.62, N = 3SE +/- 0.13, N = 3SE +/- 0.17, N = 3SE +/- 0.46, N = 3144.5483.97133.31133.47113.17166.9781.88103.73237.981. (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: Mount St. HelensXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P20406080100SE +/- 0.34, N = 3SE +/- 0.29, N = 15SE +/- 0.25, N = 3SE +/- 0.47, N = 3SE +/- 0.12, N = 3SE +/- 0.61, N = 5SE +/- 0.35, N = 5SE +/- 0.26, N = 3SE +/- 0.10, N = 353.2933.1351.2951.5947.8562.5731.1239.0189.481. (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

SVT-VP9

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

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: Visual Quality Optimized - Input: Bosphorus 1080pXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P80160240320400SE +/- 3.49, N = 15SE +/- 1.71, N = 15SE +/- 0.76, N = 9SE +/- 0.69, N = 9SE +/- 1.06, N = 10SE +/- 0.64, N = 9SE +/- 2.24, N = 11SE +/- 1.08, N = 10SE +/- 0.47, N = 7221.33364.90203.16198.42281.56173.33357.60284.34127.231. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

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 Model Zoo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: super-resolution-10 - Device: CPU - Executor: ParallelXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P306090120150SE +/- 0.57, N = 3SE +/- 1.10, N = 3SE +/- 0.18, N = 3SE +/- 0.21, N = 3SE +/- 0.43, N = 3SE +/- 0.80, N = 3SE +/- 0.51, N = 3SE +/- 0.21, N = 3SE +/- 0.32, N = 1575.88133.3291.5989.2095.2264.29120.35102.6046.591. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

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: Very FastXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P1122334455SE +/- 0.19, N = 3SE +/- 0.09, N = 4SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 4SE +/- 0.08, N = 3SE +/- 0.00, N = 323.0548.1131.0430.1434.7124.2244.5935.2316.821. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

LuxCoreRender

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

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.6Scene: Rainbow Colors and Prism - Acceleration: CPUXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P48121620SE +/- 0.03, N = 3SE +/- 0.06, N = 5SE +/- 0.04, N = 4SE +/- 0.03, N = 4SE +/- 0.03, N = 4SE +/- 0.01, N = 3SE +/- 0.05, N = 5SE +/- 0.05, N = 4SE +/- 0.01, N = 39.3516.9811.9311.5912.308.8816.4312.705.95MIN: 8.52 / MAX: 10.72MIN: 15.46 / MAX: 17.3MIN: 11.1 / MAX: 12.12MIN: 10.79 / MAX: 11.71MIN: 11.45 / MAX: 12.4MIN: 8.44 / MAX: 8.94MIN: 15.06 / MAX: 16.65MIN: 11.78 / MAX: 12.96MIN: 5.75 / MAX: 5.99

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: 64 - Model: AlexNetXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P70140210280350SE +/- 0.21, N = 3SE +/- 0.34, N = 3SE +/- 0.21, N = 3SE +/- 0.08, N = 3SE +/- 0.15, N = 3SE +/- 0.07, N = 3SE +/- 0.33, N = 3SE +/- 0.15, N = 3SE +/- 0.04, N = 3173.78322.53206.40204.83248.73160.28315.45256.65113.02

uvg266

uvg266 is an open-source VVC/H.266 (Versatile Video Coding) encoder based on Kvazaar as part of the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 1080p - Video Preset: Super FastXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P4080120160200SE +/- 0.97, N = 15SE +/- 0.16, N = 9SE +/- 0.08, N = 7SE +/- 0.05, N = 7SE +/- 0.09, N = 8SE +/- 0.03, N = 6SE +/- 0.07, N = 9SE +/- 0.05, N = 8SE +/- 0.04, N = 596.33181.83119.83116.21124.5288.44168.13127.6963.96

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 FastXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P20406080100SE +/- 0.30, N = 10SE +/- 0.07, N = 6SE +/- 0.04, N = 4SE +/- 0.04, N = 4SE +/- 0.06, N = 5SE +/- 0.02, N = 4SE +/- 0.04, N = 6SE +/- 0.03, N = 5SE +/- 0.03, N = 339.5981.2352.3050.7156.2841.1174.9657.6828.751. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.4Harness: IP Shapes 3D - Engine: CPUXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P246810SE +/- 0.01930, N = 5SE +/- 0.00611, N = 5SE +/- 0.00833, N = 5SE +/- 0.00237, N = 5SE +/- 0.00680, N = 5SE +/- 0.00220, N = 5SE +/- 0.01016, N = 5SE +/- 0.00774, N = 5SE +/- 0.00492, N = 57.596953.886854.678404.516292.704304.494062.890873.806935.03367MIN: 7.29MIN: 3.57MIN: 4.46MIN: 4.45MIN: 2.66MIN: 4.45MIN: 2.68MIN: 3.54MIN: 4.941. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

SVT-VP9

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

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: Visual Quality Optimized - Input: Bosphorus 4KXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P20406080100SE +/- 0.47, N = 15SE +/- 1.42, N = 15SE +/- 0.56, N = 5SE +/- 0.64, N = 5SE +/- 0.75, N = 15SE +/- 0.51, N = 5SE +/- 1.39, N = 15SE +/- 0.79, N = 15SE +/- 0.42, N = 359.56100.0061.9060.9780.8750.51100.0580.9335.851. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

libavif avifenc

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

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 1.0Encoder Speed: 6Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P3691215SE +/- 0.088, N = 15SE +/- 0.010, N = 9SE +/- 0.014, N = 7SE +/- 0.005, N = 7SE +/- 0.008, N = 8SE +/- 0.010, N = 6SE +/- 0.018, N = 9SE +/- 0.014, N = 8SE +/- 0.010, N = 56.2603.4215.3385.4364.4696.7983.5684.4379.4711. (CXX) g++ options: -O3 -fPIC -lm

Appleseed

Appleseed is an open-source production renderer focused on physically-based global illumination rendering engine primarily designed for animation and visual effects. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterAppleseed 2.0 BetaScene: Material TesterXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P60120180240300173.41102.15142.94146.67131.17191.21104.32129.09281.67

ScyllaDB

This is a benchmark of ScyllaDB and is making use of Apache Cassandra's cassandra-stress for conducting the benchmark. ScyllaDB is an open-source distributed NoSQL data store that is compatible with Apache Cassandra while focusing on higher throughput and lower latency. ScyllaDB uses a sharded design on each node. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOp/s, More Is BetterScyllaDB 5.2.9Test: WritesXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P30K60K90K120K150KSE +/- 395.91, N = 3SE +/- 255.51, N = 3SE +/- 60.93, N = 3SE +/- 140.30, N = 3SE +/- 415.80, N = 3SE +/- 110.37, N = 3SE +/- 369.77, N = 3SE +/- 83.55, N = 3SE +/- 158.89, N = 310483215172994217933421159807800414553311238355249

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 HalfspaceXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P50100150200250SE +/- 0.21, N = 3SE +/- 0.06, N = 3SE +/- 0.42, N = 3SE +/- 0.81, N = 3SE +/- 0.24, N = 3SE +/- 0.07, N = 3SE +/- 0.54, N = 3SE +/- 0.52, N = 3SE +/- 0.51, N = 3135.4285.25129.33130.20131.87156.9178.38104.12214.491. (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

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 1.6Threads: 16 - Buffer Length: 256 - Filter Length: 512Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P60M120M180M240M300MSE +/- 1245404.89, N = 3SE +/- 520000.00, N = 3SE +/- 75055.53, N = 3SE +/- 170098.01, N = 3SE +/- 168358.08, N = 3SE +/- 138604.15, N = 3SE +/- 2913213.19, N = 3SE +/- 1274497.72, N = 3SE +/- 125033.33, N = 31592700002923900002116700002062700002301533331564333332825633332335966671069600001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

uvg266

uvg266 is an open-source VVC/H.266 (Versatile Video Coding) encoder based on Kvazaar as part of the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 1080p - Video Preset: Very FastXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P4080120160200SE +/- 0.95, N = 15SE +/- 0.11, N = 9SE +/- 0.14, N = 7SE +/- 0.04, N = 7SE +/- 0.08, N = 7SE +/- 0.04, N = 6SE +/- 0.18, N = 8SE +/- 0.05, N = 7SE +/- 0.05, N = 589.31166.81111.78108.21114.0884.36154.02117.1261.19

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Weld Porosity Detection FP16 - Device: CPUXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P714212835SE +/- 0.06, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 330.0511.7211.0511.5111.9111.2712.0412.8211.43MIN: 17.38 / MAX: 87.99MIN: 6 / MAX: 26.83MIN: 5.83 / MAX: 23.56MIN: 5.95 / MAX: 21.47MIN: 6.32 / MAX: 23.15MIN: 5.84 / MAX: 21.18MIN: 6.3 / MAX: 25.96MIN: 6.57 / MAX: 26.61MIN: 5.89 / MAX: 21.521. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

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.CXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P5001000150020002500SE +/- 55.41, N = 15SE +/- 13.01, N = 8SE +/- 41.08, N = 15SE +/- 11.50, N = 10SE +/- 11.67, N = 7SE +/- 8.87, N = 6SE +/- 13.19, N = 8SE +/- 21.84, N = 15SE +/- 7.98, N = 51470.812123.371169.681489.701508.631168.352051.601542.11781.241. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.6

GraphicsMagick

This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample high resolution (currently 15400 x 6940) JPEG image. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.43Operation: Noise-GaussianXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P306090120150SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 1.00, N = 3SE +/- 0.58, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.33, N = 3SE +/- 0.00, N = 3701197673876011589441. (CC) gcc options: -fopenmp -O2 -ltiff -ljbig -lsharpyuv -lwebp -lwebpmux -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lxml2 -lzstd -llzma -lbz2 -lz -lm -lpthread -lgomp

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 23Jun2022Model: Rhodopsin ProteinXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P3691215SE +/- 0.250, N = 15SE +/- 0.059, N = 11SE +/- 0.055, N = 9SE +/- 0.035, N = 10SE +/- 0.126, N = 15SE +/- 0.004, N = 9SE +/- 0.045, N = 11SE +/- 0.178, N = 15SE +/- 0.003, N = 87.23612.4816.8268.7159.5256.83811.7669.2664.6181. (CXX) g++ options: -O3 -lm -ldl

SVT-VP9

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-VP9 CPU-based multi-threaded video encoder for the VP9 video format with a sample 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 1080pXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P90180270360450SE +/- 0.53, N = 10SE +/- 0.42, N = 11SE +/- 0.28, N = 10SE +/- 0.35, N = 10SE +/- 0.48, N = 10SE +/- 0.22, N = 9SE +/- 0.58, N = 11SE +/- 0.37, N = 11SE +/- 0.23, N = 8295.69419.26251.44246.28336.78213.44419.93337.46155.851. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Face Detection FP16 - Device: CPUXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P30060090012001500SE +/- 8.08, N = 3SE +/- 1.73, N = 3SE +/- 0.52, N = 3SE +/- 0.62, N = 3SE +/- 0.35, N = 3SE +/- 0.60, N = 3SE +/- 0.56, N = 3SE +/- 0.16, N = 3SE +/- 1.02, N = 31506.63590.80560.14579.07597.79761.78605.15647.101135.61MIN: 1180.01 / MAX: 1642.12MIN: 555.5 / MAX: 623.22MIN: 538 / MAX: 581.72MIN: 564.55 / MAX: 589.31MIN: 574.7 / MAX: 616.24MIN: 744.08 / MAX: 774.48MIN: 570.99 / MAX: 624.11MIN: 540.69 / MAX: 688.06MIN: 1110.52 / MAX: 1148.031. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

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 1080p - Video Preset: Super FastXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P50100150200250SE +/- 2.29, N = 15SE +/- 0.26, N = 10SE +/- 0.09, N = 9SE +/- 0.04, N = 9SE +/- 0.10, N = 9SE +/- 0.06, N = 8SE +/- 0.14, N = 10SE +/- 0.12, N = 9SE +/- 0.12, N = 6139.72248.39168.08161.51166.31126.08224.02172.9192.911. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -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: VMAF Optimized - Input: Bosphorus 1080pXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P90180270360450SE +/- 0.18, N = 10SE +/- 0.58, N = 11SE +/- 0.20, N = 10SE +/- 0.18, N = 10SE +/- 0.34, N = 10SE +/- 0.18, N = 9SE +/- 1.10, N = 11SE +/- 0.25, N = 10SE +/- 0.15, N = 8289.26408.42242.58237.22330.16208.12410.42331.83154.141. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

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 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 4KXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P4080120160200SE +/- 1.10, N = 15SE +/- 0.14, N = 8SE +/- 0.12, N = 6SE +/- 0.10, N = 6SE +/- 0.17, N = 7SE +/- 0.10, N = 6SE +/- 0.31, N = 8SE +/- 0.15, N = 7SE +/- 0.02, N = 5101.83158.94109.03107.47131.0586.79162.47130.3861.081. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

uvg266

uvg266 is an open-source VVC/H.266 (Versatile Video Coding) encoder based on Kvazaar as part of the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 1080p - Video Preset: MediumXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P1428425670SE +/- 0.14, N = 4SE +/- 0.07, N = 5SE +/- 0.03, N = 4SE +/- 0.03, N = 4SE +/- 0.06, N = 4SE +/- 0.04, N = 3SE +/- 0.10, N = 5SE +/- 0.06, N = 4SE +/- 0.03, N = 336.5964.1645.6344.4347.9832.6359.4849.2424.29

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: 32 - Model: GoogLeNetXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P306090120150SE +/- 0.10, N = 3SE +/- 0.14, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.13, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 3SE +/- 0.06, N = 3SE +/- 0.02, N = 378.79135.3093.7192.85115.4874.93139.11111.9952.83

uvg266

uvg266 is an open-source VVC/H.266 (Versatile Video Coding) encoder based on Kvazaar as part of the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 1080p - Video Preset: Ultra FastXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P4080120160200SE +/- 1.21, N = 15SE +/- 0.20, N = 9SE +/- 0.06, N = 8SE +/- 0.16, N = 8SE +/- 0.14, N = 8SE +/- 0.06, N = 7SE +/- 0.12, N = 9SE +/- 0.12, N = 8SE +/- 0.06, N = 6115.40203.39142.97138.95146.08105.23187.73150.5177.35

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Handwritten English Recognition FP16 - Device: CPUXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P1224364860SE +/- 0.12, N = 3SE +/- 0.09, N = 3SE +/- 0.05, N = 3SE +/- 0.20, N = 3SE +/- 0.08, N = 3SE +/- 0.30, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.08, N = 353.0721.8920.3721.7021.4022.0121.8523.4721.51MIN: 35.4 / MAX: 130.32MIN: 14.64 / MAX: 40.37MIN: 14.74 / MAX: 35.54MIN: 16.33 / MAX: 33.88MIN: 14.65 / MAX: 31.23MIN: 13.52 / MAX: 35.51MIN: 15.94 / MAX: 38.89MIN: 17.04 / MAX: 41.98MIN: 14.59 / MAX: 33.421. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

libavif avifenc

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

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 1.0Encoder Speed: 0Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P4080120160200SE +/- 0.49, N = 3SE +/- 0.33, N = 3SE +/- 0.18, N = 3SE +/- 0.27, N = 3SE +/- 1.17, N = 3SE +/- 0.29, N = 3SE +/- 0.77, N = 5SE +/- 0.10, N = 3SE +/- 0.07, N = 3133.5772.11108.65110.4691.59136.6374.0689.63187.641. (CXX) g++ options: -O3 -fPIC -lm

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: 64 - Model: GoogLeNetXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P306090120150SE +/- 0.03, N = 3SE +/- 0.07, N = 3SE +/- 0.04, N = 3SE +/- 0.05, N = 3SE +/- 0.08, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.08, N = 3SE +/- 0.02, N = 378.17133.2192.3791.21113.5173.77135.78110.5252.84

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.BXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P5K10K15K20K25KSE +/- 44.80, N = 3SE +/- 253.63, N = 3SE +/- 12.84, N = 3SE +/- 9.02, N = 3SE +/- 51.70, N = 4SE +/- 2.11, N = 3SE +/- 245.10, N = 4SE +/- 246.27, N = 15SE +/- 3.80, N = 312750.9718660.9011152.3111203.8325252.3511155.6424785.6517215.929885.321. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.6

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 Model Zoo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: ArcFace ResNet-100 - Device: CPU - Executor: ParallelXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P918273645SE +/- 0.11, N = 3SE +/- 0.05, N = 3SE +/- 0.11, N = 3SE +/- 0.18, N = 3SE +/- 0.08, N = 3SE +/- 0.12, N = 3SE +/- 0.12, N = 3SE +/- 0.27, N = 7SE +/- 0.01, N = 323.0437.2727.0226.8629.3719.8434.7230.1914.821. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Road Segmentation ADAS FP16-INT8 - Device: CPUXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P816243240SE +/- 0.05, N = 3SE +/- 0.07, N = 3SE +/- 0.03, N = 3SE +/- 0.08, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.23, N = 936.3516.7314.4816.8316.3421.3115.4517.0528.43MIN: 24.38 / MAX: 96.4MIN: 9.66 / MAX: 30.96MIN: 8.91 / MAX: 26.44MIN: 8.78 / MAX: 22.96MIN: 9.56 / MAX: 24.55MIN: 11.09 / MAX: 25.08MIN: 9.45 / MAX: 28.8MIN: 9.42 / MAX: 28.42MIN: 16.13 / MAX: 41.371. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Age Gender Recognition Retail 0013 FP16 - Device: CPUXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P0.2250.450.6750.91.125SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 31.000.410.400.410.440.410.430.460.40MIN: 0.4 / MAX: 10.73MIN: 0.21 / MAX: 10.02MIN: 0.2 / MAX: 7.69MIN: 0.21 / MAX: 8.32MIN: 0.22 / MAX: 7.12MIN: 0.22 / MAX: 5.13MIN: 0.22 / MAX: 7.53MIN: 0.22 / MAX: 9.38MIN: 0.22 / MAX: 4.511. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

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: GoogLeNetXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P306090120150SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.05, N = 3SE +/- 0.02, N = 376.13132.6291.9090.13114.1273.58130.80109.7353.17

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 256 - Model: GoogLeNetXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P306090120150SE +/- 0.05, N = 3SE +/- 0.08, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.08, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.00, N = 376.84132.1391.7790.19109.6273.36131.34109.3653.07

Y-Cruncher

Y-Cruncher is a multi-threaded Pi benchmark capable of computing Pi to trillions of digits. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterY-Cruncher 0.8.3Pi Digits To Calculate: 1BXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P1020304050SE +/- 0.21, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.07, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.01, N = 333.8918.2125.4626.1619.3531.3217.7320.2543.95

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 2.0Encoder Mode: Preset 12 - Input: Bosphorus 4KXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P4080120160200SE +/- 1.00, N = 15SE +/- 0.33, N = 8SE +/- 0.14, N = 7SE +/- 0.12, N = 7SE +/- 0.18, N = 7SE +/- 0.10, N = 6SE +/- 0.17, N = 8SE +/- 0.26, N = 7SE +/- 0.06, N = 5105.28170.21125.28121.50143.2898.45166.37145.0468.841. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.4Harness: Deconvolution Batch shapes_1d - Engine: CPUXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P246810SE +/- 0.02381, N = 3SE +/- 0.01295, N = 3SE +/- 0.00421, N = 3SE +/- 0.00446, N = 3SE +/- 0.01511, N = 3SE +/- 0.00480, N = 3SE +/- 0.01094, N = 3SE +/- 0.02716, N = 3SE +/- 0.00779, N = 36.853183.006363.910893.934453.345055.214623.113073.575687.42272MIN: 3.93MIN: 2.4MIN: 3.5MIN: 3.52MIN: 2.98MIN: 4.63MIN: 2.51MIN: 2.86MIN: 6.881. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

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 1080p - Video Preset: Very FastXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P4080120160200SE +/- 0.87, N = 7SE +/- 0.25, N = 9SE +/- 0.10, N = 8SE +/- 0.09, N = 7SE +/- 0.16, N = 8SE +/- 0.06, N = 7SE +/- 0.11, N = 9SE +/- 0.06, N = 8SE +/- 0.05, N = 6103.04186.56129.02123.89125.34101.80169.81131.1375.971. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Machine Translation EN To DE FP16 - Device: CPUXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P306090120150SE +/- 0.08, N = 3SE +/- 0.03, N = 3SE +/- 0.10, N = 3SE +/- 0.24, N = 3SE +/- 0.06, N = 3SE +/- 0.39, N = 3SE +/- 0.05, N = 3SE +/- 0.07, N = 3SE +/- 0.99, N = 4118.4558.4348.2653.4456.9863.2957.6858.5690.33MIN: 68.57 / MAX: 244.71MIN: 31.85 / MAX: 94.55MIN: 29.16 / MAX: 69.56MIN: 25.81 / MAX: 61.36MIN: 40.42 / MAX: 73.08MIN: 45.67 / MAX: 70.41MIN: 32.9 / MAX: 82.05MIN: 42.61 / MAX: 80.74MIN: 51.71 / MAX: 101.441. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

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 1080p - Video Preset: MediumXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P20406080100SE +/- 0.37, N = 4SE +/- 0.08, N = 6SE +/- 0.04, N = 5SE +/- 0.05, N = 5SE +/- 0.10, N = 5SE +/- 0.05, N = 4SE +/- 0.13, N = 6SE +/- 0.05, N = 5SE +/- 0.03, N = 450.4788.3064.6862.7163.8547.1780.5266.4736.101. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -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 4KXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P306090120150SE +/- 0.64, N = 10SE +/- 0.13, N = 6SE +/- 0.08, N = 5SE +/- 0.09, N = 5SE +/- 0.15, N = 6SE +/- 0.05, N = 5SE +/- 0.16, N = 6SE +/- 0.11, N = 6SE +/- 0.01, N = 483.19111.0176.0674.7197.4163.76114.8897.2747.011. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

MariaDB

This is a MariaDB MySQL database server benchmark making use of sysbench rather than the existing pts/mysqlslap test profile that uses MariaDB with mysqlslap/mariadb-slap as the benchmark driver. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 11.5Test: oltp_write_only - Threads: 64Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P70K140K210K280K350KSE +/- 798.38, N = 3SE +/- 56.85, N = 3SE +/- 419.19, N = 3SE +/- 204.75, N = 3SE +/- 971.36, N = 3SE +/- 493.89, N = 3SE +/- 391.18, N = 3SE +/- 431.10, N = 3SE +/- 535.09, N = 3296034348099265119260139279043208039346495273914142651-lnuma -lpcre2-8 -lcrypt -laio -lssl -lcrypto-shared -lrt -lstdc++-shared -lrt -lstdc++-shared -lrt -lstdc++-shared -lrt -lstdc++-shared -lrt -lstdc++-shared -lrt -lstdc++-shared -lrt -lstdc++-shared -lrt -lstdc++1. (CXX) g++ options: -pie -fPIC -fstack-protector -O3 -lz -lm -lpthread -ldl

OpenRadioss

OpenRadioss is an open-source AGPL-licensed finite element solver for dynamic event analysis OpenRadioss is based on Altair Radioss and open-sourced in 2022. This open-source finite element solver is benchmarked with various example models available from https://www.openradioss.org/models/ and https://github.com/OpenRadioss/ModelExchange/tree/main/Examples. This test is currently using a reference OpenRadioss binary build offered via GitHub. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2023.09.15Model: INIVOL and Fluid Structure Interaction Drop ContainerXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P2004006008001000SE +/- 8.95, N = 9SE +/- 2.52, N = 3SE +/- 5.87, N = 9SE +/- 4.81, N = 6SE +/- 4.68, N = 5SE +/- 0.28, N = 3SE +/- 4.35, N = 9SE +/- 9.39, N = 6SE +/- 1.30, N = 3538.42322.67585.75494.79421.96560.31324.46403.46786.89

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: 32 - Model: AlexNetXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P50100150200250SE +/- 1.37, N = 3SE +/- 0.14, N = 4SE +/- 0.23, N = 3SE +/- 0.06, N = 3SE +/- 0.25, N = 3SE +/- 0.15, N = 3SE +/- 0.35, N = 4SE +/- 0.20, N = 3SE +/- 0.05, N = 3160.52242.49172.89171.59199.14139.36239.93204.70100.57

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 2.0Encoder Mode: Preset 4 - Input: Bosphorus 4KXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P246810SE +/- 0.024, N = 3SE +/- 0.009, N = 3SE +/- 0.016, N = 3SE +/- 0.008, N = 3SE +/- 0.004, N = 3SE +/- 0.005, N = 3SE +/- 0.030, N = 3SE +/- 0.019, N = 3SE +/- 0.004, N = 34.3487.8385.7425.5636.4134.5407.2966.5263.2631. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

RocksDB

This is a benchmark of Meta/Facebook's RocksDB as an embeddable persistent key-value store for fast storage based on Google's LevelDB. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Read Random Write RandomXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P600K1200K1800K2400K3000KSE +/- 17144.87, N = 3SE +/- 24549.22, N = 3SE +/- 5891.62, N = 3SE +/- 1649.04, N = 3SE +/- 1307.98, N = 3SE +/- 24161.52, N = 3SE +/- 8693.67, N = 3SE +/- 16096.70, N = 3SE +/- 11016.21, N = 31976533291575821311222247481181777517817952929561227855612199681. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

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 1080p - Video Preset: Ultra FastXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P70140210280350SE +/- 4.30, N = 15SE +/- 0.21, N = 11SE +/- 0.14, N = 10SE +/- 0.14, N = 10SE +/- 0.16, N = 10SE +/- 0.11, N = 9SE +/- 0.34, N = 10SE +/- 0.14, N = 10SE +/- 0.09, N = 8197.51301.57226.13217.52220.31167.39271.84231.05126.171. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

Zstd Compression

This test measures the time needed to compress/decompress a sample file (silesia.tar) using Zstd (Zstandard) compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 12 - Compression SpeedXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P60120180240300SE +/- 2.27, N = 3SE +/- 2.97, N = 3SE +/- 0.92, N = 3SE +/- 0.62, N = 3SE +/- 1.66, N = 3SE +/- 0.43, N = 3SE +/- 6.73, N = 15SE +/- 2.73, N = 3SE +/- 0.15, N = 3170.6220.9171.0177.9273.1164.4248.0221.2114.31. (CC) gcc options: -O3 -pthread -lz -llzma

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Handwritten English Recognition FP16-INT8 - Device: CPUXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P1020304050SE +/- 0.12, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.07, N = 3SE +/- 0.09, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 345.7020.0919.1320.2220.3119.8620.5722.1122.24MIN: 32.92 / MAX: 117.92MIN: 13.66 / MAX: 38.02MIN: 12.57 / MAX: 34MIN: 14.54 / MAX: 30.69MIN: 14.76 / MAX: 29.79MIN: 13.85 / MAX: 30.49MIN: 14.62 / MAX: 37.71MIN: 14.68 / MAX: 40.04MIN: 14.31 / MAX: 32.881. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

Pennant

Pennant is an application focused on hydrodynamics on general unstructured meshes in 2D. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgHydro Cycle Time - Seconds, Fewer Is BetterPennant 1.0.1Test: leblancbigXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P1224364860SE +/- 1.09, N = 12SE +/- 0.27, N = 3SE +/- 0.88, N = 15SE +/- 0.00, N = 3SE +/- 0.35, N = 3SE +/- 0.11, N = 3SE +/- 0.17, N = 3SE +/- 0.42, N = 15SE +/- 0.08, N = 332.8729.5542.9435.4828.1441.7122.9731.8654.781. (CXX) g++ options: -fopenmp -lmpi_cxx -lmpi

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 Model Zoo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: bertsquad-12 - Device: CPU - Executor: ParallelXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P48121620SE +/- 0.10358, N = 3SE +/- 0.05371, N = 3SE +/- 0.11789, N = 3SE +/- 0.06035, N = 3SE +/- 0.15346, N = 3SE +/- 0.02536, N = 3SE +/- 0.09843, N = 14SE +/- 0.10273, N = 9SE +/- 0.05918, N = 311.5372015.5560012.5483012.3239012.611809.1545814.7664012.762406.530461. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

GraphicsMagick

This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample high resolution (currently 15400 x 6940) JPEG image. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.43Operation: ResizingXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P70140210280350SE +/- 1.86, N = 3SE +/- 1.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.33, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.88, N = 3SE +/- 0.00, N = 32443382552502582023252841421. (CC) gcc options: -fopenmp -O2 -ltiff -ljbig -lsharpyuv -lwebp -lwebpmux -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lxml2 -lzstd -llzma -lbz2 -lz -lm -lpthread -lgomp

Y-Cruncher

Y-Cruncher is a multi-threaded Pi benchmark capable of computing Pi to trillions of digits. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterY-Cruncher 0.8.3Pi Digits To Calculate: 500MXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P510152025SE +/- 0.124, N = 4SE +/- 0.010, N = 5SE +/- 0.036, N = 4SE +/- 0.038, N = 4SE +/- 0.012, N = 5SE +/- 0.082, N = 4SE +/- 0.010, N = 5SE +/- 0.009, N = 5SE +/- 0.020, N = 314.9268.65211.58911.8618.96914.1338.3739.41419.800

VVenC

VVenC is the Fraunhofer Versatile Video Encoder as a fast/efficient H.266/VVC encoder. The vvenc encoder makes use of SIMD Everywhere (SIMDe). The vvenc software is published under the Clear BSD License. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.11Video Input: Bosphorus 4K - Video Preset: FastXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P246810SE +/- 0.018, N = 3SE +/- 0.058, N = 3SE +/- 0.021, N = 3SE +/- 0.031, N = 3SE +/- 0.034, N = 3SE +/- 0.017, N = 3SE +/- 0.045, N = 3SE +/- 0.029, N = 3SE +/- 0.004, N = 34.9757.8185.6935.5546.4524.5427.4946.4903.3111. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects

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 1.0Encoder Speed: 2Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P20406080100SE +/- 0.18, N = 3SE +/- 0.03, N = 3SE +/- 0.13, N = 3SE +/- 0.03, N = 3SE +/- 0.56, N = 4SE +/- 0.23, N = 3SE +/- 0.33, N = 7SE +/- 0.18, N = 3SE +/- 0.03, N = 361.8436.3351.9452.5645.7364.1437.1144.3485.391. (CXX) g++ options: -O3 -fPIC -lm

SVT-VP9

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

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: VMAF Optimized - Input: Bosphorus 4KXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P20406080100SE +/- 0.46, N = 15SE +/- 0.15, N = 6SE +/- 0.09, N = 5SE +/- 0.03, N = 5SE +/- 0.12, N = 6SE +/- 0.11, N = 5SE +/- 0.18, N = 6SE +/- 0.08, N = 6SE +/- 0.04, N = 479.85103.5271.4870.3493.5660.90107.5392.0745.961. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

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 Model Zoo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: yolov4 - Device: CPU - Executor: ParallelXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P3691215SE +/- 0.11600, N = 3SE +/- 0.13812, N = 4SE +/- 0.10193, N = 15SE +/- 0.11284, N = 4SE +/- 0.01052, N = 3SE +/- 0.08117, N = 3SE +/- 0.09061, N = 9SE +/- 0.06480, N = 12SE +/- 0.01891, N = 38.0942111.519909.291799.222198.989586.7822611.038009.183404.930351. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenRadioss

OpenRadioss is an open-source AGPL-licensed finite element solver for dynamic event analysis OpenRadioss is based on Altair Radioss and open-sourced in 2022. This open-source finite element solver is benchmarked with various example models available from https://www.openradioss.org/models/ and https://github.com/OpenRadioss/ModelExchange/tree/main/Examples. This test is currently using a reference OpenRadioss binary build offered via GitHub. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2023.09.15Model: Bird Strike on WindshieldXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P80160240320400SE +/- 3.59, N = 9SE +/- 2.93, N = 12SE +/- 7.66, N = 9SE +/- 0.53, N = 3SE +/- 1.41, N = 3SE +/- 0.57, N = 3SE +/- 3.16, N = 9SE +/- 4.67, N = 12SE +/- 0.92, N = 3259.88183.64266.65238.13229.49291.79168.39202.27390.30

Pennant

Pennant is an application focused on hydrodynamics on general unstructured meshes in 2D. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgHydro Cycle Time - Seconds, Fewer Is BetterPennant 1.0.1Test: sedovbigXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P20406080100SE +/- 0.67, N = 4SE +/- 0.35, N = 8SE +/- 0.59, N = 6SE +/- 0.05, N = 3SE +/- 0.43, N = 3SE +/- 0.22, N = 3SE +/- 0.12, N = 3SE +/- 0.18, N = 3SE +/- 0.09, N = 355.9042.2361.9750.8942.1859.0234.6449.1880.111. (CXX) g++ options: -fopenmp -lmpi_cxx -lmpi

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 1.0Encoder Speed: 6, LosslessXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P3691215SE +/- 0.014, N = 5SE +/- 0.044, N = 7SE +/- 0.021, N = 6SE +/- 0.006, N = 6SE +/- 0.038, N = 6SE +/- 0.012, N = 5SE +/- 0.051, N = 9SE +/- 0.018, N = 6SE +/- 0.014, N = 48.9695.8908.1478.2627.16810.0246.1747.21513.4471. (CXX) g++ options: -O3 -fPIC -lm

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Vehicle Detection FP16 - Device: CPUXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P48121620SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.06, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 316.0411.368.449.137.7510.947.898.7817.46MIN: 9.49 / MAX: 56.98MIN: 4.12 / MAX: 36.81MIN: 4.55 / MAX: 19.23MIN: 4.28 / MAX: 20.17MIN: 4.8 / MAX: 13.5MIN: 4.95 / MAX: 20.28MIN: 4.2 / MAX: 25.04MIN: 4.89 / MAX: 24.3MIN: 8.04 / MAX: 25.291. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

VVenC

VVenC is the Fraunhofer Versatile Video Encoder as a fast/efficient H.266/VVC encoder. The vvenc encoder makes use of SIMD Everywhere (SIMDe). The vvenc software is published under the Clear BSD License. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.11Video Input: Bosphorus 4K - Video Preset: FasterXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P48121620SE +/- 0.047, N = 3SE +/- 0.038, N = 3SE +/- 0.018, N = 3SE +/- 0.020, N = 3SE +/- 0.034, N = 3SE +/- 0.005, N = 3SE +/- 0.009, N = 3SE +/- 0.009, N = 3SE +/- 0.002, N = 311.76817.43513.14112.80114.60210.49416.82014.5367.7421. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.4Harness: Convolution Batch Shapes Auto - Engine: CPUXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P3691215SE +/- 0.04485, N = 7SE +/- 0.01415, N = 7SE +/- 0.00717, N = 7SE +/- 0.01592, N = 7SE +/- 0.00824, N = 7SE +/- 0.03028, N = 7SE +/- 0.00632, N = 7SE +/- 0.01722, N = 7SE +/- 0.00783, N = 76.380536.407198.168007.792024.029367.934554.245326.463579.05546MIN: 5.92MIN: 5.93MIN: 7.7MIN: 7.68MIN: 3.95MIN: 7.8MIN: 3.87MIN: 6.03MIN: 8.911. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

MariaDB

This is a MariaDB MySQL database server benchmark making use of sysbench rather than the existing pts/mysqlslap test profile that uses MariaDB with mysqlslap/mariadb-slap as the benchmark driver. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 11.5Test: oltp_read_write - Threads: 64Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P40K80K120K160K200KSE +/- 562.40, N = 3SE +/- 389.87, N = 3SE +/- 211.83, N = 3SE +/- 284.19, N = 3SE +/- 296.87, N = 3SE +/- 193.47, N = 3SE +/- 91.63, N = 3SE +/- 99.82, N = 3SE +/- 75.46, N = 318641820118216859316606017226513314119719416962590232-lnuma -lpcre2-8 -lcrypt -laio -lssl -lcrypto-shared -lrt -lstdc++-shared -lrt -lstdc++-shared -lrt -lstdc++-shared -lrt -lstdc++-shared -lrt -lstdc++-shared -lrt -lstdc++-shared -lrt -lstdc++-shared -lrt -lstdc++1. (CXX) g++ options: -pie -fPIC -fstack-protector -O3 -lz -lm -lpthread -ldl

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Road Segmentation ADAS FP16 - Device: CPUXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P918273645SE +/- 0.09, N = 3SE +/- 0.04, N = 3SE +/- 0.09, N = 3SE +/- 0.12, N = 3SE +/- 0.07, N = 3SE +/- 0.06, N = 3SE +/- 0.07, N = 3SE +/- 0.05, N = 3SE +/- 0.22, N = 339.4825.1517.7923.2717.7627.2318.3219.6837.30MIN: 22.02 / MAX: 90.7MIN: 11.63 / MAX: 50.5MIN: 9.38 / MAX: 30.36MIN: 8.9 / MAX: 35.88MIN: 11.78 / MAX: 28.07MIN: 12.7 / MAX: 33.19MIN: 10.07 / MAX: 36.96MIN: 10.8 / MAX: 33.75MIN: 30.15 / MAX: 46.261. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

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 2.0Encoder Mode: Preset 8 - Input: Bosphorus 1080pXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P4080120160200SE +/- 1.11, N = 15SE +/- 0.29, N = 9SE +/- 0.13, N = 8SE +/- 0.16, N = 8SE +/- 0.18, N = 8SE +/- 0.16, N = 7SE +/- 0.32, N = 8SE +/- 0.26, N = 8SE +/- 0.05, N = 6120.53189.41148.34142.84156.68119.76175.21162.4286.471. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

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 Model Zoo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: ResNet50 v1-12-int8 - Device: CPU - Executor: ParallelXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P80160240320400SE +/- 1.45, N = 3SE +/- 3.68, N = 3SE +/- 0.89, N = 3SE +/- 1.50, N = 3SE +/- 3.53, N = 4SE +/- 0.43, N = 3SE +/- 1.30, N = 3SE +/- 0.27, N = 3SE +/- 0.68, N = 3214.55380.82322.61314.23327.75264.15374.23336.91174.411. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

JPEG-XL libjxl

The JPEG XL Image Coding System is designed to provide next-generation JPEG image capabilities with JPEG XL offering better image quality and compression over legacy JPEG. This test profile is currently focused on the multi-threaded JPEG XL image encode performance using the reference libjxl library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMP/s, More Is BetterJPEG-XL libjxl 0.10.1Input: PNG - Quality: 90Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P1122334455SE +/- 0.19, N = 3SE +/- 0.28, N = 3SE +/- 0.36, N = 3SE +/- 0.16, N = 3SE +/- 0.30, N = 10SE +/- 0.08, N = 3SE +/- 0.24, N = 3SE +/- 0.44, N = 3SE +/- 0.07, N = 331.8148.5336.0235.0838.7229.6545.3840.1822.241. (CXX) g++ options: -fno-rtti -O3 -fPIE -pie -lm

Apache IoTDB

Apache IotDB is a time series database and this benchmark is facilitated using the IoT Benchmaark [https://github.com/thulab/iot-benchmark/]. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgAverage Latency, Fewer Is BetterApache IoTDB 1.2Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 400Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P2004006008001000SE +/- 1.92, N = 3SE +/- 4.31, N = 3SE +/- 4.56, N = 3SE +/- 3.04, N = 3SE +/- 1.07, N = 3SE +/- 8.54, N = 5SE +/- 1.42, N = 3SE +/- 4.87, N = 3SE +/- 6.01, N = 3524.13399.56462.14465.51407.64529.44398.76421.83860.75MAX: 26588.63MAX: 27980.82MAX: 27920.53MAX: 27554.23MAX: 26798.87MAX: 28194.55MAX: 26832.58MAX: 27011.65MAX: 28570.46

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-50Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P918273645SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.31, N = 8SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 322.9841.0230.7030.4936.2325.3640.4835.0119.06

Apache IoTDB

Apache IotDB is a time series database and this benchmark is facilitated using the IoT Benchmaark [https://github.com/thulab/iot-benchmark/]. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgpoint/sec, More Is BetterApache IoTDB 1.2Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 400Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P16M32M48M64M80MSE +/- 207001.08, N = 3SE +/- 597457.28, N = 3SE +/- 441409.11, N = 3SE +/- 178945.47, N = 3SE +/- 171497.11, N = 3SE +/- 580368.90, N = 5SE +/- 219419.50, N = 3SE +/- 367807.54, N = 3SE +/- 143283.84, N = 3564944997371602564182563639541767271059256122243745798967022686834724489

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.CXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P10K20K30K40K50KSE +/- 96.46, N = 3SE +/- 110.88, N = 3SE +/- 14.25, N = 3SE +/- 20.15, N = 3SE +/- 193.15, N = 3SE +/- 5.49, N = 3SE +/- 481.60, N = 5SE +/- 229.09, N = 3SE +/- 13.18, N = 328326.3644844.1322935.2722976.5340212.6522331.4647856.8737547.7622316.951. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.6

Apache IoTDB

Apache IotDB is a time series database and this benchmark is facilitated using the IoT Benchmaark [https://github.com/thulab/iot-benchmark/]. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgAverage Latency, Fewer Is BetterApache IoTDB 1.2Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 100Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P50100150200250SE +/- 0.51, N = 3SE +/- 0.21, N = 3SE +/- 0.48, N = 3SE +/- 0.64, N = 3SE +/- 0.27, N = 3SE +/- 0.11, N = 3SE +/- 0.15, N = 3SE +/- 0.12, N = 3SE +/- 0.96, N = 3137.92103.37122.55122.33105.03136.58101.02108.81216.40MAX: 23917.2MAX: 23852.59MAX: 23938.16MAX: 23948.29MAX: 23941.39MAX: 23944.74MAX: 23859.84MAX: 23915.13MAX: 24148.64

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 1.6Threads: 16 - Buffer Length: 256 - Filter Length: 32Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P200M400M600M800M1000MSE +/- 5153390.47, N = 3SE +/- 67412.49, N = 3SE +/- 812656.82, N = 3SE +/- 1997031.13, N = 3SE +/- 3918917.08, N = 3SE +/- 383507.21, N = 3SE +/- 1995247.13, N = 3SE +/- 956399.50, N = 3SE +/- 104774.89, N = 37110500007959666677355666677180200007183066675461366677726166677284600003717133331. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

Timed PHP Compilation

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed PHP Compilation 8.3.4Time To CompileXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P20406080100SE +/- 0.20, N = 3SE +/- 0.18, N = 3SE +/- 0.10, N = 3SE +/- 0.07, N = 3SE +/- 0.21, N = 3SE +/- 0.03, N = 3SE +/- 0.22, N = 3SE +/- 0.24, N = 3SE +/- 0.04, N = 354.4540.1153.7654.0443.9963.3040.1045.5985.80

JPEG-XL libjxl

The JPEG XL Image Coding System is designed to provide next-generation JPEG image capabilities with JPEG XL offering better image quality and compression over legacy JPEG. This test profile is currently focused on the multi-threaded JPEG XL image encode performance using the reference libjxl library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMP/s, More Is BetterJPEG-XL libjxl 0.10.1Input: JPEG - Quality: 90Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P1122334455SE +/- 0.09, N = 3SE +/- 0.37, N = 10SE +/- 0.30, N = 3SE +/- 0.01, N = 3SE +/- 0.38, N = 3SE +/- 0.13, N = 3SE +/- 0.47, N = 6SE +/- 0.46, N = 3SE +/- 0.07, N = 332.5148.5937.1835.6040.0130.1947.0541.7722.711. (CXX) g++ options: -fno-rtti -O3 -fPIE -pie -lm

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Person Vehicle Bike Detection FP16 - Device: CPUXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P3691215SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 39.945.124.785.045.326.605.105.6410.18MIN: 6.2 / MAX: 41.65MIN: 3.61 / MAX: 15.43MIN: 3.18 / MAX: 16.31MIN: 3.47 / MAX: 17.02MIN: 3.77 / MAX: 11.07MIN: 4.29 / MAX: 16.53MIN: 3.41 / MAX: 14.16MIN: 3.48 / MAX: 18.22MIN: 5.72 / MAX: 20.751. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

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 Model Zoo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: CaffeNet 12-int8 - Device: CPU - Executor: ParallelXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P2004006008001000SE +/- 3.86, N = 3SE +/- 8.14, N = 3SE +/- 7.12, N = 3SE +/- 2.32, N = 3SE +/- 5.20, N = 3SE +/- 5.55, N = 6SE +/- 8.12, N = 7SE +/- 7.33, N = 3SE +/- 1.46, N = 3557.41829.19677.58672.35769.69583.98895.93719.99420.701. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

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: 32 - Model: ResNet-50Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P918273645SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 323.1939.9930.7931.0034.7825.7040.3734.7219.01

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 64 - Model: ResNet-50Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P918273645SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 323.1040.2430.5330.6434.7625.5040.4934.6819.11

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 256 - Model: ResNet-50Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P918273645SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 323.0740.6830.6330.5034.9525.4340.3334.7919.24

Apache IoTDB

Apache IotDB is a time series database and this benchmark is facilitated using the IoT Benchmaark [https://github.com/thulab/iot-benchmark/]. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgpoint/sec, More Is BetterApache IoTDB 1.2Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 100Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P16M32M48M64M80MSE +/- 209117.79, N = 3SE +/- 205604.00, N = 3SE +/- 268932.10, N = 3SE +/- 302032.90, N = 3SE +/- 81989.58, N = 3SE +/- 45916.59, N = 3SE +/- 138400.03, N = 3SE +/- 59581.06, N = 3SE +/- 161259.81, N = 3560352787407524462951458630862477332163856689052760318507054497936052182

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 2.0Encoder Mode: Preset 12 - Input: Bosphorus 1080pXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P140280420560700SE +/- 0.76, N = 12SE +/- 1.66, N = 15SE +/- 0.74, N = 12SE +/- 0.93, N = 12SE +/- 0.82, N = 12SE +/- 0.74, N = 12SE +/- 1.39, N = 12SE +/- 1.70, N = 12SE +/- 0.40, N = 11548.04660.34546.71528.23568.41449.57631.94581.67313.431. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Speedb

Speedb is a next-generation key value storage engine that is RocksDB compatible and aiming for stability, efficiency, and performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOp/s, More Is BetterSpeedb 2.7Test: Read Random Write RandomXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P600K1200K1800K2400K3000KSE +/- 4914.43, N = 3SE +/- 2327.92, N = 3SE +/- 1406.43, N = 3SE +/- 1251.53, N = 3SE +/- 284.11, N = 3SE +/- 2410.81, N = 3SE +/- 1095.04, N = 3SE +/- 6109.05, N = 3SE +/- 5732.94, N = 32120915277019521387762222556184197018064102706385216669913236851. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

OSPRay

Intel OSPRay is a portable ray-tracing engine for high-performance, high-fidelity 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.orgItems Per Second, More Is BetterOSPRay 3.1Benchmark: particle_volume/pathtracer/real_timeXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P50100150200250SE +/- 0.42, N = 3SE +/- 0.68, N = 3SE +/- 0.61, N = 3SE +/- 0.28, N = 3SE +/- 1.13, N = 3SE +/- 0.31, N = 3SE +/- 1.24, N = 3SE +/- 0.64, N = 3SE +/- 0.27, N = 3157.97220.91170.39158.59182.05132.40209.22193.97105.66

MariaDB

This is a MariaDB MySQL database server benchmark making use of sysbench rather than the existing pts/mysqlslap test profile that uses MariaDB with mysqlslap/mariadb-slap as the benchmark driver. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 11.5Test: oltp_update_non_index - Threads: 64Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P50K100K150K200K250KSE +/- 516.32, N = 3SE +/- 290.99, N = 3SE +/- 295.88, N = 3SE +/- 120.42, N = 3SE +/- 1725.95, N = 9SE +/- 223.22, N = 3SE +/- 355.20, N = 3SE +/- 159.15, N = 3SE +/- 188.07, N = 3220068233313201401197477185239162697227813191756113348-lnuma -lpcre2-8 -lcrypt -laio -lssl -lcrypto-shared -lrt -lstdc++-shared -lrt -lstdc++-shared -lrt -lstdc++-shared -lrt -lstdc++-shared -lrt -lstdc++-shared -lrt -lstdc++-shared -lrt -lstdc++-shared -lrt -lstdc++1. (CXX) g++ options: -pie -fPIC -fstack-protector -O3 -lz -lm -lpthread -ldl

GPAW

GPAW is a density-functional theory (DFT) Python code based on the projector-augmented wave (PAW) method and the atomic simulation environment (ASE). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGPAW 23.6Input: Carbon NanotubeXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P70140210280350SE +/- 8.24, N = 12SE +/- 1.88, N = 3SE +/- 2.92, N = 3SE +/- 0.06, N = 3SE +/- 1.91, N = 3SE +/- 0.19, N = 3SE +/- 3.67, N = 10SE +/- 2.27, N = 3SE +/- 0.42, N = 3228.90154.99205.87203.43191.34237.24154.85177.02318.671. (CC) gcc options: -shared -fwrapv -O2 -lxc -lblas -lmpi

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 129 Cells Per DirectionXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P714212835SE +/- 0.22, N = 3SE +/- 0.12, N = 15SE +/- 0.18, N = 9SE +/- 0.03, N = 3SE +/- 0.15, N = 15SE +/- 0.02, N = 3SE +/- 0.11, N = 15SE +/- 0.17, N = 15SE +/- 0.04, N = 319.7516.5921.8720.3914.7621.8013.8217.2928.411. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Face Detection FP16-INT8 - Device: CPUXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P130260390520650SE +/- 0.59, N = 3SE +/- 0.24, N = 3SE +/- 0.15, N = 3SE +/- 0.10, N = 3SE +/- 0.11, N = 3SE +/- 0.03, N = 3SE +/- 0.41, N = 3SE +/- 0.33, N = 3SE +/- 0.48, N = 3384.09301.79285.97299.02313.09393.13312.52331.37585.23MIN: 285.45 / MAX: 543.49MIN: 278.87 / MAX: 327.8MIN: 150.08 / MAX: 303.22MIN: 288.59 / MAX: 303.77MIN: 291.27 / MAX: 322.77MIN: 378.57 / MAX: 400.92MIN: 167.86 / MAX: 330.96MIN: 179.64 / MAX: 354.6MIN: 563.46 / MAX: 593.111. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

VVenC

VVenC is the Fraunhofer Versatile Video Encoder as a fast/efficient H.266/VVC encoder. The vvenc encoder makes use of SIMD Everywhere (SIMDe). The vvenc software is published under the Clear BSD License. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.11Video Input: Bosphorus 1080p - Video Preset: FastXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P612182430SE +/- 0.06, N = 3SE +/- 0.07, N = 3SE +/- 0.08, N = 3SE +/- 0.06, N = 3SE +/- 0.10, N = 3SE +/- 0.02, N = 3SE +/- 0.10, N = 3SE +/- 0.08, N = 3SE +/- 0.02, N = 315.4623.1918.7718.3019.9415.5421.7220.2111.431. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects

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 Model Zoo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: fcn-resnet101-11 - Device: CPU - Executor: ParallelXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P0.39730.79461.19191.58921.9865SE +/- 0.013081, N = 14SE +/- 0.005924, N = 3SE +/- 0.018640, N = 15SE +/- 0.013735, N = 4SE +/- 0.014994, N = 3SE +/- 0.007958, N = 3SE +/- 0.015047, N = 15SE +/- 0.015352, N = 3SE +/- 0.035957, N = 121.0428121.7634901.1605401.1281001.4932700.9594411.7658801.4134900.8711561. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

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 CompileXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P1326395265SE +/- 0.23, N = 3SE +/- 0.13, N = 3SE +/- 0.23, N = 3SE +/- 0.14, N = 3SE +/- 0.14, N = 3SE +/- 0.12, N = 3SE +/- 0.25, N = 3SE +/- 0.36, N = 3SE +/- 0.39, N = 338.1329.4436.9036.9030.4742.1129.5032.5659.471. (CC) gcc options: -m64 -ldl -lgcc_s -lutil -lrt -lpthread -lm -lc -pie -nodefaultlibs

x265

This is a simple test of the x265 encoder run on the CPU with 1080p and 4K options for H.265 video encode performance with x265. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.4Video Input: Bosphorus 1080pXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P306090120150SE +/- 0.77, N = 15SE +/- 0.21, N = 7SE +/- 0.53, N = 6SE +/- 0.54, N = 6SE +/- 0.18, N = 7SE +/- 0.38, N = 6SE +/- 0.21, N = 7SE +/- 0.15, N = 7SE +/- 0.16, N = 584.33118.0689.1286.7899.2280.58109.57103.2558.621. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

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: 64 - Model: ResNet-50Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P1020304050SE +/- 1.58, N = 15SE +/- 0.94, N = 15SE +/- 0.16, N = 3SE +/- 0.14, N = 3SE +/- 0.01, N = 3SE +/- 0.17, N = 3SE +/- 0.34, N = 3SE +/- 0.17, N = 3SE +/- 0.23, N = 1232.2543.3845.1143.8941.3434.8846.2039.5323.04MIN: 23.14 / MAX: 40.93MIN: 34.95 / MAX: 46.71MIN: 43.61 / MAX: 45.86MIN: 42.37 / MAX: 45.05MIN: 30.45 / MAX: 41.8MIN: 21.67 / MAX: 35.54MIN: 43.63 / MAX: 47.16MIN: 38.01 / MAX: 40.46MIN: 15.25 / MAX: 23.79

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 EngineXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P7001400210028003500SE +/- 23.84, N = 3SE +/- 13.96, N = 3SE +/- 7.51, N = 3SE +/- 11.72, N = 3SE +/- 9.02, N = 3SE +/- 14.53, N = 3SE +/- 5.29, N = 3SE +/- 23.54, N = 4SE +/- 22.07, N = 3212818261977199218502394171519143438

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 2.0Encoder Mode: Preset 4 - Input: Bosphorus 1080pXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P612182430SE +/- 0.15, N = 5SE +/- 0.13, N = 6SE +/- 0.07, N = 5SE +/- 0.04, N = 5SE +/- 0.07, N = 6SE +/- 0.02, N = 5SE +/- 0.08, N = 6SE +/- 0.04, N = 6SE +/- 0.01, N = 415.9224.1719.8919.5520.7516.5422.1721.5112.181. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

CloverLeaf

CloverLeaf is a Lagrangian-Eulerian hydrodynamics benchmark. This test profile currently makes use of CloverLeaf's OpenMP version. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterCloverLeaf 1.3Input: clover_bmXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P20406080100SE +/- 0.27, N = 3SE +/- 0.45, N = 3SE +/- 0.21, N = 3SE +/- 0.05, N = 3SE +/- 0.10, N = 3SE +/- 0.13, N = 3SE +/- 0.47, N = 6SE +/- 0.28, N = 3SE +/- 0.21, N = 364.5872.8886.8274.5985.7377.2347.0269.9892.421. (F9X) gfortran options: -O3 -march=native -funroll-loops -fopenmp

MariaDB

This is a MariaDB MySQL database server benchmark making use of sysbench rather than the existing pts/mysqlslap test profile that uses MariaDB with mysqlslap/mariadb-slap as the benchmark driver. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 11.5Test: oltp_update_index - Threads: 64Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P40K80K120K160K200KSE +/- 250.58, N = 3SE +/- 282.52, N = 3SE +/- 308.54, N = 3SE +/- 133.22, N = 3SE +/- 173.91, N = 3SE +/- 254.61, N = 3SE +/- 412.73, N = 3SE +/- 411.40, N = 3SE +/- 107.36, N = 3187089198538177579173080159977142647196283168313101087-lnuma -lpcre2-8 -lcrypt -laio -lssl -lcrypto-shared -lrt -lstdc++-shared -lrt -lstdc++-shared -lrt -lstdc++-shared -lrt -lstdc++-shared -lrt -lstdc++-shared -lrt -lstdc++-shared -lrt -lstdc++-shared -lrt -lstdc++1. (CXX) g++ options: -pie -fPIC -fstack-protector -O3 -lz -lm -lpthread -ldl

OpenRadioss

OpenRadioss is an open-source AGPL-licensed finite element solver for dynamic event analysis OpenRadioss is based on Altair Radioss and open-sourced in 2022. This open-source finite element solver is benchmarked with various example models available from https://www.openradioss.org/models/ and https://github.com/OpenRadioss/ModelExchange/tree/main/Examples. This test is currently using a reference OpenRadioss binary build offered via GitHub. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2023.09.15Model: Bumper BeamXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P50100150200250SE +/- 2.49, N = 12SE +/- 1.49, N = 15SE +/- 3.91, N = 12SE +/- 0.23, N = 3SE +/- 1.43, N = 5SE +/- 0.20, N = 3SE +/- 1.50, N = 3SE +/- 2.01, N = 15SE +/- 0.17, N = 3153.90108.64145.32124.70138.93140.76117.99118.52210.60

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Person Detection FP32 - Device: CPUXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P306090120150SE +/- 0.77, N = 3SE +/- 0.48, N = 3SE +/- 0.13, N = 3SE +/- 0.18, N = 3SE +/- 0.06, N = 3SE +/- 0.39, N = 3SE +/- 0.38, N = 3SE +/- 0.38, N = 3SE +/- 0.18, N = 3134.5490.4972.7076.5270.3190.0283.1880.79126.50MIN: 98.92 / MAX: 233.45MIN: 55.81 / MAX: 127.95MIN: 40.38 / MAX: 84.07MIN: 52.86 / MAX: 94.9MIN: 50.95 / MAX: 96.87MIN: 43.62 / MAX: 98.59MIN: 38.33 / MAX: 120MIN: 30.58 / MAX: 108.27MIN: 102.39 / MAX: 136.91. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Noise Suppression Poconet-Like FP16 - Device: CPUXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P48121620SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 315.219.907.958.838.098.498.409.288.26MIN: 10.08 / MAX: 64.69MIN: 6.53 / MAX: 37.69MIN: 5 / MAX: 23.85MIN: 5.3 / MAX: 14.21MIN: 5.45 / MAX: 16.52MIN: 5.12 / MAX: 20.17MIN: 5.53 / MAX: 31MIN: 5.38 / MAX: 30.18MIN: 5.5 / MAX: 13.881. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Person Detection FP16 - Device: CPUXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P306090120150SE +/- 0.73, N = 3SE +/- 1.01, N = 3SE +/- 0.15, N = 3SE +/- 0.06, N = 3SE +/- 0.09, N = 3SE +/- 0.11, N = 3SE +/- 0.45, N = 3SE +/- 0.10, N = 3SE +/- 0.57, N = 3133.9989.9872.5276.3670.4490.5083.3081.56126.06MIN: 103.21 / MAX: 233.72MIN: 63.39 / MAX: 124.53MIN: 28.47 / MAX: 87.6MIN: 56.38 / MAX: 88.42MIN: 48.46 / MAX: 97.28MIN: 68.02 / MAX: 98.61MIN: 29.23 / MAX: 114.06MIN: 55.87 / MAX: 108.66MIN: 63.05 / MAX: 145.091. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

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 - Mesh TimeXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P80160240320400225.95226.01296.21262.84243.10297.17204.60254.77387.881. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfoamToVTK -ldynamicMesh -llagrangian -lgenericPatchFields -lfileFormats -lOpenFOAM -ldl -lm

VVenC

VVenC is the Fraunhofer Versatile Video Encoder as a fast/efficient H.266/VVC encoder. The vvenc encoder makes use of SIMD Everywhere (SIMDe). The vvenc software is published under the Clear BSD License. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.11Video Input: Bosphorus 1080p - Video Preset: FasterXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P1122334455SE +/- 0.25, N = 4SE +/- 0.11, N = 4SE +/- 0.04, N = 4SE +/- 0.12, N = 4SE +/- 0.07, N = 4SE +/- 0.06, N = 4SE +/- 0.12, N = 4SE +/- 0.10, N = 4SE +/- 0.02, N = 340.0750.9145.1443.8345.9837.6348.8646.1627.351. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects

DuckDB

DuckDB is an in-progress SQL OLAP database management system optimized for analytics and features a vectorized and parallel engine. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterDuckDB 0.9.1Benchmark: IMDBXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P306090120150SE +/- 0.14, N = 3SE +/- 0.05, N = 3SE +/- 0.06, N = 3SE +/- 0.07, N = 3SE +/- 0.05, N = 3SE +/- 0.05, N = 3SE +/- 0.07, N = 3SE +/- 0.29, N = 3SE +/- 0.01, N = 399.5882.38100.63101.9787.84115.6483.7290.03152.681. (CXX) g++ options: -O3 -rdynamic -lssl -lcrypto -ldl

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 EngineXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P8001600240032004000SE +/- 50.09, N = 15SE +/- 9.53, N = 5SE +/- 18.64, N = 5SE +/- 19.37, N = 5SE +/- 7.90, N = 5SE +/- 20.21, N = 5SE +/- 16.10, N = 5SE +/- 18.41, N = 5SE +/- 35.27, N = 4311320802409239123132829212723743854

Apache IoTDB

Apache IotDB is a time series database and this benchmark is facilitated using the IoT Benchmaark [https://github.com/thulab/iot-benchmark/]. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgAverage Latency, Fewer Is BetterApache IoTDB 1.2Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 100Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P20406080100SE +/- 0.20, N = 3SE +/- 0.29, N = 3SE +/- 0.29, N = 3SE +/- 0.05, N = 3SE +/- 0.13, N = 3SE +/- 0.12, N = 3SE +/- 0.05, N = 3SE +/- 0.07, N = 3SE +/- 0.49, N = 377.2460.6668.1668.5860.5276.6959.6162.30109.52MAX: 23891.04MAX: 23861.25MAX: 23889.9MAX: 23897.06MAX: 23884.06MAX: 23999.1MAX: 23860.38MAX: 23874.13MAX: 24035.02

srsRAN Project

srsRAN Project is a complete ORAN-native 5G RAN solution created by Software Radio Systems (SRS). The srsRAN Project radio suite was formerly known as srsLTE and can be used for building your own software-defined radio (SDR) 4G/5G mobile network. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMbps, More Is BettersrsRAN Project 23.10.1-20240325Test: PUSCH Processor Benchmark, Throughput TotalXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P30060090012001500SE +/- 9.26, N = 15SE +/- 0.05, N = 4SE +/- 0.10, N = 6SE +/- 0.05, N = 5SE +/- 0.05, N = 4SE +/- 0.65, N = 6SE +/- 18.52, N = 4SE +/- 0.14, N = 4SE +/- 2.54, N = 61068.91611.51470.51469.81273.91206.01592.31351.9881.5MIN: 637.2 / MAX: 1111.5-mavx512f -mavx512cd -mavx512bw -mavx512dq - MIN: 1019.4 / MAX: 1611.6-mavx512f -mavx512cd -mavx512bw -mavx512dq - MIN: 849.1 / MAX: 1470.7-mavx512f -mavx512cd -mavx512bw -mavx512dq - MIN: 849.1 / MAX: 1470-mavx512f -mavx512cd -mavx512bw -mavx512dq - MIN: 849.1 / MAX: 1274-mavx512f -mavx512cd -mavx512bw -mavx512dq - MIN: 763.8 / MAX: 1207.4-mavx512f -mavx512cd -mavx512bw -mavx512dq - MIN: 927.1 / MAX: 1610.9-mavx512f -mavx512cd -mavx512bw -mavx512dq - MIN: 955 / MAX: 1352.2-mavx512f -mavx512cd -mavx512bw -mavx512dq - MIN: 613.1 / MAX: 888.51. (CXX) g++ options: -O3 -march=native -mavx2 -mavx -msse4.1 -mfma -fno-trapping-math -fno-math-errno -ldl

Apache IoTDB

Apache IotDB is a time series database and this benchmark is facilitated using the IoT Benchmaark [https://github.com/thulab/iot-benchmark/]. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgAverage Latency, Fewer Is BetterApache IoTDB 1.2Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 100Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P4080120160200SE +/- 0.54, N = 3SE +/- 0.82, N = 3SE +/- 0.24, N = 3SE +/- 0.39, N = 3SE +/- 0.40, N = 3SE +/- 0.72, N = 3SE +/- 0.56, N = 3SE +/- 0.32, N = 3SE +/- 0.62, N = 3119.4992.08105.58105.7092.91117.1492.2795.09167.03MAX: 13845.12MAX: 11356.99MAX: 15103.61MAX: 13869.85MAX: 12607.68MAX: 15130.91MAX: 11332.45MAX: 12619.54MAX: 17738.52

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: LU.CXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P10K20K30K40K50KSE +/- 714.33, N = 15SE +/- 521.71, N = 15SE +/- 613.23, N = 15SE +/- 38.55, N = 3SE +/- 13.15, N = 3SE +/- 11.58, N = 3SE +/- 266.87, N = 3SE +/- 221.05, N = 3SE +/- 7.85, N = 340491.5647556.6937149.8840284.2343166.1026620.6948014.8641255.9826610.491. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.6

Apache IoTDB

Apache IotDB is a time series database and this benchmark is facilitated using the IoT Benchmaark [https://github.com/thulab/iot-benchmark/]. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgpoint/sec, More Is BetterApache IoTDB 1.2Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 100Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P20M40M60M80M100MSE +/- 232749.13, N = 3SE +/- 390613.00, N = 3SE +/- 296062.71, N = 3SE +/- 77775.76, N = 3SE +/- 198325.80, N = 3SE +/- 57777.29, N = 3SE +/- 118053.95, N = 3SE +/- 132686.57, N = 3SE +/- 188707.13, N = 3618423887760562769561449693423777787870262348881791594417567015143934008

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 TimeXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P80016002400320040002260.992351.512827.882781.242123.992944.552040.352407.903645.541. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfoamToVTK -ldynamicMesh -llagrangian -lgenericPatchFields -lfileFormats -lOpenFOAM -ldl -lm

Apache IoTDB

Apache IotDB is a time series database and this benchmark is facilitated using the IoT Benchmaark [https://github.com/thulab/iot-benchmark/]. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgpoint/sec, More Is BetterApache IoTDB 1.2Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 100Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P20M40M60M80M100MSE +/- 262085.32, N = 3SE +/- 368630.91, N = 3SE +/- 282897.65, N = 3SE +/- 216731.24, N = 3SE +/- 51778.51, N = 3SE +/- 200521.84, N = 3SE +/- 356287.02, N = 3SE +/- 105860.93, N = 3SE +/- 147160.66, N = 3625580987931531970305285702935717932403463541378799996117743401144828435

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, Second RunXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P60120180240300SE +/- 3.87, N = 3SE +/- 1.51, N = 5SE +/- 1.00, N = 3SE +/- 0.75, N = 3SE +/- 1.95, N = 3SE +/- 1.04, N = 3SE +/- 3.27, N = 3SE +/- 2.91, N = 3SE +/- 0.19, N = 3249.50248.89236.47230.37279.62211.23293.87256.89165.39MIN: 9.27 / MAX: 12000MIN: 15.92 / MAX: 8571.43MIN: 10.66 / MAX: 10000MIN: 10.32 / MAX: 10000MIN: 14.87 / MAX: 8571.43MIN: 7.98 / MAX: 10000MIN: 18.95 / MAX: 10000MIN: 13.95 / MAX: 10000MIN: 5.27 / MAX: 10000

OpenRadioss

OpenRadioss is an open-source AGPL-licensed finite element solver for dynamic event analysis OpenRadioss is based on Altair Radioss and open-sourced in 2022. This open-source finite element solver is benchmarked with various example models available from https://www.openradioss.org/models/ and https://github.com/OpenRadioss/ModelExchange/tree/main/Examples. This test is currently using a reference OpenRadioss binary build offered via GitHub. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2023.09.15Model: Chrysler Neon 1MXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P30060090012001500SE +/- 17.37, N = 7SE +/- 4.49, N = 3SE +/- 10.68, N = 9SE +/- 1.89, N = 3SE +/- 2.98, N = 3SE +/- 2.88, N = 3SE +/- 8.46, N = 9SE +/- 9.60, N = 3SE +/- 1.90, N = 3983.54891.841003.59967.20978.511126.52823.26936.341462.60

Apache IoTDB

Apache IotDB is a time series database and this benchmark is facilitated using the IoT Benchmaark [https://github.com/thulab/iot-benchmark/]. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgpoint/sec, More Is BetterApache IoTDB 1.2Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 400Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P20M40M60M80M100MSE +/- 922667.78, N = 3SE +/- 818556.17, N = 3SE +/- 255843.12, N = 3SE +/- 612351.99, N = 3SE +/- 707677.76, N = 3SE +/- 173074.65, N = 3SE +/- 243124.87, N = 3SE +/- 191894.24, N = 3SE +/- 492377.86, N = 5648863647845431671338740712038937820408662518245801892637623218545355429

OpenBenchmarking.orgAverage Latency, Fewer Is BetterApache IoTDB 1.2Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 400Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P90180270360450SE +/- 4.53, N = 3SE +/- 2.35, N = 3SE +/- 1.82, N = 3SE +/- 6.43, N = 3SE +/- 0.75, N = 3SE +/- 1.17, N = 3SE +/- 1.32, N = 3SE +/- 3.20, N = 3SE +/- 5.93, N = 3290.14235.16268.42260.60237.32295.34232.67244.44406.06MAX: 26535.45MAX: 26882.16MAX: 27440.82MAX: 26603.07MAX: 26320.16MAX: 26742.14MAX: 26680.29MAX: 26631.84MAX: 27165.87

OpenBenchmarking.orgpoint/sec, More Is BetterApache IoTDB 1.2Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 400Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P20M40M60M80M100MSE +/- 787042.09, N = 3SE +/- 360981.97, N = 3SE +/- 261270.67, N = 3SE +/- 676495.92, N = 3SE +/- 169341.63, N = 3SE +/- 77022.60, N = 3SE +/- 285870.90, N = 3SE +/- 718192.76, N = 3SE +/- 415945.47, N = 3626555497765891469144164701070307717216062459195786008197472357945117852

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 AnalyzerXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P400800120016002000SE +/- 8.96, N = 15SE +/- 5.68, N = 7SE +/- 9.55, N = 7SE +/- 8.67, N = 11SE +/- 9.69, N = 7SE +/- 9.62, N = 11SE +/- 3.44, N = 7SE +/- 7.50, N = 7SE +/- 8.71, N = 6112210531113115511011298105111091824

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 RunXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P60120180240300SE +/- 1.74, N = 3SE +/- 2.29, N = 5SE +/- 4.93, N = 3SE +/- 2.33, N = 3SE +/- 2.40, N = 3SE +/- 1.41, N = 3SE +/- 2.43, N = 3SE +/- 4.31, N = 3SE +/- 0.26, N = 3249.90251.80232.47233.30291.70214.00291.26259.35168.41MIN: 9.25 / MAX: 12000MIN: 15.75 / MAX: 10000MIN: 10.67 / MAX: 12000MIN: 10.46 / MAX: 10000MIN: 14.85 / MAX: 10000MIN: 7.95 / MAX: 10000MIN: 16.56 / MAX: 7500MIN: 13.75 / MAX: 10000MIN: 5.2 / MAX: 10000

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 - Mesh TimeXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P112233445535.1930.7738.1733.3333.6539.1629.6932.8550.901. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfoamToVTK -ldynamicMesh -llagrangian -lgenericPatchFields -lfileFormats -lOpenFOAM -ldl -lm

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, First Run / Cold CacheXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P60120180240300SE +/- 1.98, N = 3SE +/- 2.37, N = 5SE +/- 1.84, N = 3SE +/- 1.31, N = 3SE +/- 1.12, N = 3SE +/- 1.29, N = 3SE +/- 1.16, N = 3SE +/- 0.94, N = 3SE +/- 1.34, N = 3234.39227.39222.47213.47258.37195.64265.18233.74155.72MIN: 9.14 / MAX: 12000MIN: 13.31 / MAX: 10000MIN: 10.49 / MAX: 12000MIN: 10.21 / MAX: 8571.43MIN: 14.45 / MAX: 10000MIN: 7.8 / MAX: 10000MIN: 14.2 / MAX: 10000MIN: 13.67 / MAX: 10000MIN: 5.21 / MAX: 8571.43

Apache IoTDB

Apache IotDB is a time series database and this benchmark is facilitated using the IoT Benchmaark [https://github.com/thulab/iot-benchmark/]. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgAverage Latency, Fewer Is BetterApache IoTDB 1.2Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 400Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P110220330440550SE +/- 10.20, N = 3SE +/- 5.40, N = 3SE +/- 6.12, N = 3SE +/- 6.58, N = 3SE +/- 5.21, N = 3SE +/- 2.59, N = 3SE +/- 1.19, N = 3SE +/- 1.97, N = 3SE +/- 9.34, N = 5382.48321.29347.97350.00326.49406.89316.26333.41531.88MAX: 27376.22MAX: 27126.33MAX: 27085.8MAX: 27235.37MAX: 27383.3MAX: 27507.51MAX: 27135.69MAX: 26859.8MAX: 28595.84

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: 1 - Model: ResNet-50Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P1530456075SE +/- 1.37, N = 12SE +/- 0.90, N = 15SE +/- 1.84, N = 15SE +/- 0.65, N = 3SE +/- 0.30, N = 3SE +/- 0.26, N = 3SE +/- 0.68, N = 6SE +/- 0.11, N = 3SE +/- 0.16, N = 361.4965.6967.4868.6761.3458.4968.8056.9641.09MIN: 40.06 / MAX: 72.22MIN: 53.12 / MAX: 69.76MIN: 46.76 / MAX: 74.15MIN: 64.12 / MAX: 71.37MIN: 50.53 / MAX: 62.03MIN: 55.22 / MAX: 59.43MIN: 59.18 / MAX: 72.68MIN: 52.49 / MAX: 58MIN: 39.2 / MAX: 41.9

GraphicsMagick

This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample high resolution (currently 15400 x 6940) JPEG image. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.43Operation: HWB Color SpaceXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P70140210280350SE +/- 0.67, N = 3SE +/- 0.58, N = 3SE +/- 0.33, N = 3SE +/- 1.20, N = 3SE +/- 0.88, N = 3SE +/- 0.58, N = 3SE +/- 1.73, N = 3SE +/- 1.53, N = 3SE +/- 0.33, N = 33152782552492362272682581901. (CC) gcc options: -fopenmp -O2 -ltiff -ljbig -lsharpyuv -lwebp -lwebpmux -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lxml2 -lzstd -llzma -lbz2 -lz -lm -lpthread -lgomp

Timed CPython Compilation

This test times how long it takes to build the reference Python implementation, CPython, with optimizations and LTO enabled for a release build. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed CPython Compilation 3.10.6Build Configuration: DefaultXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P61218243016.8514.1316.5816.8215.2118.8514.5915.0623.20

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.CXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P3K6K9K12K15KSE +/- 4.20, N = 3SE +/- 146.76, N = 5SE +/- 1.44, N = 3SE +/- 5.49, N = 3SE +/- 10.77, N = 3SE +/- 7.67, N = 3SE +/- 188.19, N = 3SE +/- 27.04, N = 3SE +/- 7.32, N = 311387.0513374.3510027.1110088.5014130.3010028.7415940.6111606.229840.131. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.6

Zstd Compression

This test measures the time needed to compress/decompress a sample file (silesia.tar) using Zstd (Zstandard) compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 19 - Compression SpeedXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P612182430SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.09, N = 3SE +/- 0.23, N = 15SE +/- 0.09, N = 3SE +/- 0.48, N = 12SE +/- 0.17, N = 15SE +/- 0.18, N = 316.318.818.018.324.018.022.520.014.91. (CC) gcc options: -O3 -pthread -lz -llzma

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Face Detection Retail FP16-INT8 - Device: CPUXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P1.14082.28163.42244.56325.704SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 35.073.333.163.353.533.273.513.643.23MIN: 2.36 / MAX: 27.99MIN: 1.88 / MAX: 15.67MIN: 1.77 / MAX: 13.91MIN: 1.81 / MAX: 10.37MIN: 1.95 / MAX: 9.62MIN: 1.84 / MAX: 8.95MIN: 1.92 / MAX: 13.78MIN: 1.95 / MAX: 15.55MIN: 1.85 / MAX: 13.261. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

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 DirectionXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P20406080100SE +/- 0.87, N = 15SE +/- 0.58, N = 10SE +/- 0.27, N = 3SE +/- 0.30, N = 3SE +/- 0.60, N = 15SE +/- 0.07, N = 3SE +/- 0.83, N = 3SE +/- 0.40, N = 3SE +/- 0.03, N = 373.7273.8887.7785.3470.7189.8765.1175.68104.221. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

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: 1 - Model: GoogLeNetXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P1428425670SE +/- 0.05, N = 8SE +/- 0.18, N = 8SE +/- 0.10, N = 9SE +/- 0.09, N = 8SE +/- 0.18, N = 8SE +/- 0.15, N = 8SE +/- 0.18, N = 8SE +/- 0.08, N = 8SE +/- 0.04, N = 751.3357.3462.9961.8855.8952.3660.1454.4939.38

Apache IoTDB

Apache IotDB is a time series database and this benchmark is facilitated using the IoT Benchmaark [https://github.com/thulab/iot-benchmark/]. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgAverage Latency, Fewer Is BetterApache IoTDB 1.2Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 100Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P20406080100SE +/- 0.51, N = 3SE +/- 0.10, N = 3SE +/- 0.31, N = 3SE +/- 0.91, N = 3SE +/- 0.22, N = 3SE +/- 0.44, N = 3SE +/- 0.42, N = 3SE +/- 0.39, N = 3SE +/- 0.35, N = 380.5665.6370.7071.6664.5579.6464.5266.49103.02MAX: 15084.51MAX: 12576.01MAX: 13822.83MAX: 13850.52MAX: 15090.58MAX: 15110.81MAX: 12582.24MAX: 13829.28MAX: 13961.1

OpenBenchmarking.orgpoint/sec, More Is BetterApache IoTDB 1.2Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 100Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P15M30M45M60M75MSE +/- 205982.51, N = 3SE +/- 41672.18, N = 3SE +/- 42980.57, N = 3SE +/- 364826.83, N = 3SE +/- 128616.25, N = 3SE +/- 151013.56, N = 3SE +/- 248696.67, N = 3SE +/- 282335.19, N = 3SE +/- 87332.86, N = 3570283986985751964781285642010367075257357925245708964696873598545065837

OpenBenchmarking.orgpoint/sec, More Is BetterApache IoTDB 1.2Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 400Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P15M30M45M60M75MSE +/- 245819.57, N = 3SE +/- 489754.87, N = 3SE +/- 418677.10, N = 3SE +/- 402227.19, N = 3SE +/- 347434.46, N = 3SE +/- 374209.00, N = 3SE +/- 262014.17, N = 3SE +/- 162538.27, N = 3SE +/- 134066.50, N = 3577601976973116664655502634516806943559757190648708173736877181445226559

OpenBenchmarking.orgAverage Latency, Fewer Is BetterApache IoTDB 1.2Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 400Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P80160240320400SE +/- 1.91, N = 3SE +/- 3.67, N = 3SE +/- 2.74, N = 3SE +/- 3.35, N = 3SE +/- 3.51, N = 3SE +/- 3.65, N = 3SE +/- 1.59, N = 3SE +/- 1.22, N = 3SE +/- 2.44, N = 3275.14230.41243.61250.94231.39275.62227.34231.55346.65MAX: 27185.57MAX: 26735.87MAX: 26975.13MAX: 27118.82MAX: 27094.18MAX: 28062.74MAX: 26429.57MAX: 27011.78MAX: 27744.45

Zstd Compression

This test measures the time needed to compress/decompress a sample file (silesia.tar) using Zstd (Zstandard) compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 19, Long Mode - Compression SpeedXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P3691215SE +/- 0.01, N = 3SE +/- 0.09, N = 3SE +/- 0.00, N = 3SE +/- 0.06, N = 3SE +/- 0.15, N = 3SE +/- 0.00, N = 3SE +/- 0.14, N = 5SE +/- 0.15, N = 3SE +/- 0.04, N = 38.9110.7010.2010.5013.2010.2012.9011.509.001. (CC) gcc options: -O3 -pthread -lz -llzma

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 Model Zoo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: T5 Encoder - Device: CPU - Executor: StandardXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P4080120160200SE +/- 2.25, N = 15SE +/- 2.20, N = 3SE +/- 0.71, N = 3SE +/- 1.14, N = 3SE +/- 2.12, N = 15SE +/- 1.77, N = 4SE +/- 1.28, N = 3SE +/- 2.03, N = 4SE +/- 1.62, N = 3169.62162.33139.48143.50204.34152.18199.25168.62142.211. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

PyBench

This test profile reports the total time of the different average timed test results from PyBench. PyBench reports average test times for different functions such as BuiltinFunctionCalls and NestedForLoops, with this total result providing a rough estimate as to Python's average performance on a given system. This test profile runs PyBench each time for 20 rounds. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyBench 2018-02-16Total For Average Test TimesXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P130260390520650SE +/- 2.82, N = 5SE +/- 6.41, N = 4SE +/- 2.53, N = 4SE +/- 2.21, N = 4SE +/- 6.12, N = 4SE +/- 2.17, N = 4SE +/- 6.56, N = 15SE +/- 5.33, N = 4SE +/- 3.40, N = 4415533527532602550571526552

Google Draco

Draco is a library developed by Google for compressing/decompressing 3D geometric meshes and point clouds. This test profile uses some Artec3D PLY models as the sample 3D model input formats for Draco compression/decompression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterGoogle Draco 1.5.6Model: Church FacadeXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P12002400360048006000SE +/- 17.70, N = 6SE +/- 29.27, N = 6SE +/- 10.00, N = 7SE +/- 5.95, N = 7SE +/- 4.33, N = 6SE +/- 16.57, N = 6SE +/- 90.20, N = 15SE +/- 26.89, N = 7SE +/- 12.94, N = 65607522450834988513251603978503757081. (CXX) g++ options: -O3

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: 1 - Model: ResNet-50Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P48121620SE +/- 0.01, N = 5SE +/- 0.03, N = 5SE +/- 0.01, N = 5SE +/- 0.03, N = 5SE +/- 0.01, N = 5SE +/- 0.02, N = 5SE +/- 0.01, N = 5SE +/- 0.02, N = 5SE +/- 0.01, N = 413.7114.9317.4717.4514.7615.6115.1214.7612.18

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P0.090.180.270.360.45SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.400.290.280.290.310.320.300.320.29MIN: 0.18 / MAX: 8.35MIN: 0.16 / MAX: 8.63MIN: 0.15 / MAX: 7.71MIN: 0.16 / MAX: 5.09MIN: 0.16 / MAX: 7.6MIN: 0.16 / MAX: 7.47MIN: 0.16 / MAX: 8.01MIN: 0.16 / MAX: 9.37MIN: 0.16 / MAX: 4.311. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

FFmpeg

This is a benchmark of the FFmpeg multimedia framework. The FFmpeg test profile is making use of a modified version of vbench from Columbia University's Architecture and Design Lab (ARCADE) [http://arcade.cs.columbia.edu/vbench/] that is a benchmark for video-as-a-service workloads. The test profile offers the options of a range of vbench scenarios based on freely distributable video content and offers the options of using the x264 or x265 video encoders for transcoding. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.1Encoder: libx265 - Scenario: UploadXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P816243240SE +/- 0.08, N = 3SE +/- 0.07, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.06, N = 3SE +/- 0.05, N = 3SE +/- 0.01, N = 328.8934.2131.9531.7331.3229.1732.1432.4024.421. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

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 Model Zoo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: T5 Encoder - Device: CPU - Executor: ParallelXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P4080120160200SE +/- 0.97, N = 3SE +/- 0.69, N = 3SE +/- 1.35, N = 3SE +/- 0.50, N = 3SE +/- 0.37, N = 3SE +/- 0.12, N = 3SE +/- 0.57, N = 3SE +/- 0.51, N = 3SE +/- 0.17, N = 3161.31156.77141.63138.37187.78147.28183.82155.88134.741. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Weld Porosity Detection FP16-INT8 - Device: CPUXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P246810SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 37.785.965.635.876.175.756.216.495.80MIN: 3.64 / MAX: 44.07MIN: 3.08 / MAX: 18.52MIN: 2.98 / MAX: 16.09MIN: 3.03 / MAX: 15.22MIN: 3.21 / MAX: 15.44MIN: 3.02 / MAX: 14.8MIN: 3.24 / MAX: 18.16MIN: 3.31 / MAX: 18.52MIN: 3.05 / MAX: 14.451. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

FFmpeg

This is a benchmark of the FFmpeg multimedia framework. The FFmpeg test profile is making use of a modified version of vbench from Columbia University's Architecture and Design Lab (ARCADE) [http://arcade.cs.columbia.edu/vbench/] that is a benchmark for video-as-a-service workloads. The test profile offers the options of a range of vbench scenarios based on freely distributable video content and offers the options of using the x264 or x265 video encoders for transcoding. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.1Encoder: libx265 - Scenario: Video On DemandXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P1632486480SE +/- 0.02, N = 3SE +/- 0.13, N = 3SE +/- 0.09, N = 3SE +/- 0.05, N = 3SE +/- 0.09, N = 3SE +/- 0.08, N = 3SE +/- 0.10, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 358.7569.8165.3564.9263.7060.2065.2465.8751.071. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

OpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.1Encoder: libx265 - Scenario: PlatformXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P1632486480SE +/- 0.22, N = 3SE +/- 0.10, N = 3SE +/- 0.05, N = 3SE +/- 0.08, N = 3SE +/- 0.06, N = 3SE +/- 0.01, N = 3SE +/- 0.19, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 358.7569.8065.2664.7763.6860.2365.4965.8251.111. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

MariaDB mariadb-slap

This is a MariaDB MySQL database server benchmark making use of mysqlslap (mariadb-slap). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB mariadb-slap 11.5Clients: 128Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P130260390520650SE +/- 1.05, N = 3SE +/- 0.54, N = 3SE +/- 0.74, N = 3SE +/- 0.66, N = 3SE +/- 0.93, N = 3SE +/- 0.54, N = 3SE +/- 0.71, N = 3SE +/- 0.23, N = 3SE +/- 0.18, N = 3574612580565561517582586449-lnuma -lpcre2-8 -lcrypt -laio -lssl -lcrypto-shared -lrt -lstdc++-shared -lrt -lstdc++-shared -lrt -lstdc++-shared -lrt -lstdc++-shared -lrt -lstdc++-shared -lrt -lstdc++-shared -lrt -lstdc++-shared -lrt -lstdc++1. (CXX) g++ options: -pie -fPIC -fstack-protector -O3 -lz -lm -lpthread -ldl

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 Model Zoo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: GPT-2 - Device: CPU - Executor: StandardXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P4080120160200SE +/- 0.39, N = 3SE +/- 1.39, N = 15SE +/- 0.21, N = 3SE +/- 1.56, N = 4SE +/- 3.26, N = 12SE +/- 0.08, N = 3SE +/- 0.20, N = 3SE +/- 1.56, N = 4SE +/- 2.03, N = 15126.67133.17123.95134.74161.84134.45140.35140.98119.461. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

MariaDB mariadb-slap

This is a MariaDB MySQL database server benchmark making use of mysqlslap (mariadb-slap). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB mariadb-slap 11.5Clients: 64Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P30060090012001500SE +/- 4.64, N = 3SE +/- 4.85, N = 3SE +/- 5.66, N = 3SE +/- 3.26, N = 3SE +/- 5.80, N = 3SE +/- 3.77, N = 3SE +/- 4.14, N = 3SE +/- 7.01, N = 3SE +/- 2.10, N = 311281183112410951076100911241131878-lnuma -lpcre2-8 -lcrypt -laio -lssl -lcrypto-shared -lrt -lstdc++-shared -lrt -lstdc++-shared -lrt -lstdc++-shared -lrt -lstdc++-shared -lrt -lstdc++-shared -lrt -lstdc++-shared -lrt -lstdc++-shared -lrt -lstdc++1. (CXX) g++ options: -pie -fPIC -fstack-protector -O3 -lz -lm -lpthread -ldl

Z3 Theorem Prover

The Z3 Theorem Prover / SMT solver is developed by Microsoft Research under the MIT license. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterZ3 Theorem Prover 4.12.1SMT File: 2.smt2Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P1428425670SE +/- 0.51, N = 3SE +/- 0.53, N = 3SE +/- 0.27, N = 3SE +/- 0.40, N = 3SE +/- 0.51, N = 3SE +/- 0.33, N = 3SE +/- 0.02, N = 3SE +/- 0.39, N = 3SE +/- 0.22, N = 363.0848.8848.6847.7347.2349.3247.5750.4656.861. (CXX) g++ options: -lpthread -std=c++17 -fvisibility=hidden -mfpmath=sse -msse -msse2 -O3 -fPIC

srsRAN Project

srsRAN Project is a complete ORAN-native 5G RAN solution created by Software Radio Systems (SRS). The srsRAN Project radio suite was formerly known as srsLTE and can be used for building your own software-defined radio (SDR) 4G/5G mobile network. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMbps, More Is BettersrsRAN Project 23.10.1-20240325Test: PDSCH Processor Benchmark, Throughput ThreadXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P2004006008001000SE +/- 5.58, N = 9SE +/- 5.92, N = 10SE +/- 3.24, N = 10SE +/- 7.98, N = 10SE +/- 1.53, N = 9SE +/- 6.27, N = 10SE +/- 3.58, N = 9SE +/- 7.68, N = 9SE +/- 5.88, N = 9809.61049.11061.51071.0908.81073.6907.51034.91023.8-mavx512f -mavx512cd -mavx512bw -mavx512dq-mavx512f -mavx512cd -mavx512bw -mavx512dq-mavx512f -mavx512cd -mavx512bw -mavx512dq-mavx512f -mavx512cd -mavx512bw -mavx512dq-mavx512f -mavx512cd -mavx512bw -mavx512dq-mavx512f -mavx512cd -mavx512bw -mavx512dq-mavx512f -mavx512cd -mavx512bw -mavx512dq-mavx512f -mavx512cd -mavx512bw -mavx512dq1. (CXX) g++ options: -O3 -march=native -mavx2 -mavx -msse4.1 -mfma -fno-trapping-math -fno-math-errno -ldl

FFmpeg

This is a benchmark of the FFmpeg multimedia framework. The FFmpeg test profile is making use of a modified version of vbench from Columbia University's Architecture and Design Lab (ARCADE) [http://arcade.cs.columbia.edu/vbench/] that is a benchmark for video-as-a-service workloads. The test profile offers the options of a range of vbench scenarios based on freely distributable video content and offers the options of using the x264 or x265 video encoders for transcoding. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.1Encoder: libx265 - Scenario: LiveXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P4080120160200SE +/- 1.39, N = 3SE +/- 0.71, N = 3SE +/- 0.17, N = 3SE +/- 0.58, N = 3SE +/- 1.34, N = 3SE +/- 0.31, N = 3SE +/- 0.59, N = 3SE +/- 0.29, N = 3SE +/- 0.04, N = 3178.15186.42179.99176.63171.60162.38176.69177.93141.031. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

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 Model Zoo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: ParallelXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P1224364860SE +/- 0.30, N = 3SE +/- 0.21, N = 3SE +/- 0.43, N = 3SE +/- 0.32, N = 3SE +/- 0.08, N = 3SE +/- 0.15, N = 3SE +/- 0.57, N = 4SE +/- 0.46, N = 3SE +/- 0.02, N = 341.0152.7250.5349.8148.1446.5653.1549.5542.041. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: GPT-2 - Device: CPU - Executor: ParallelXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P306090120150SE +/- 0.46, N = 3SE +/- 0.12, N = 3SE +/- 0.41, N = 3SE +/- 0.23, N = 3SE +/- 0.48, N = 3SE +/- 0.05, N = 3SE +/- 0.89, N = 3SE +/- 0.39, N = 3SE +/- 0.12, N = 3123.28122.63120.28121.29137.92118.96139.02121.99107.581. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

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 1.6Threads: 1 - Buffer Length: 256 - Filter Length: 32Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P14M28M42M56M70MSE +/- 637003.49, N = 3SE +/- 318365.79, N = 3SE +/- 2645.75, N = 3SE +/- 1855.92, N = 3SE +/- 16522.71, N = 3SE +/- 2905.93, N = 3SE +/- 223381.09, N = 3SE +/- 26514.15, N = 3SE +/- 333.33, N = 36323666753018667536590005225166751031000502723334958466753147000502773331. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

Renaissance

Renaissance is a suite of benchmarks designed to test the Java JVM from Apache Spark to a Twitter-like service to Scala and other features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.14Test: Savina Reactors.IOXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464P8001600240032004000SE +/- 16.31, N = 3SE +/- 15.03, N = 3SE +/- 28.17, N = 3SE +/- 13.60, N = 3SE +/- 38.91, N = 4SE +/- 12.81, N = 3SE +/- 41.68, N = 3SE +/- 30.89, N = 33695.43265.23042.03060.53515.93288.43350.93338.2MIN: 3664.8 / MAX: 5363.87MIN: 3236.75 / MAX: 4741.82MIN: 3011.87 / MAX: 4321.7MIN: 3036.07 / MAX: 4235.11MIN: 3407.81 / MAX: 4967.72MIN: 3264.51 / MAX: 4523.94MIN: 3285.69 / MAX: 4786.32MIN: 3297.53 / MAX: 4743.03

Test: Savina Reactors.IO

EPYC 4124P: The test quit with a non-zero exit status. The test run did not produce a result. E: sh: 1: exec: ./renaissance: not found

Timed CPython Compilation

This test times how long it takes to build the reference Python implementation, CPython, with optimizations and LTO enabled for a release build. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed CPython Compilation 3.10.6Build Configuration: Released Build, PGO + LTO OptimizedXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P50100150200250197.92193.47200.98202.26199.92214.38198.06197.98233.27

Numpy Benchmark

This is a test to obtain the general Numpy performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterNumpy BenchmarkXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P2004006008001000SE +/- 1.43, N = 3SE +/- 2.05, N = 3SE +/- 3.59, N = 3SE +/- 1.60, N = 3SE +/- 0.68, N = 3SE +/- 2.19, N = 3SE +/- 3.03, N = 3SE +/- 0.83, N = 3SE +/- 1.58, N = 3675.48803.04808.62804.51791.79773.69746.24812.29710.18

srsRAN Project

srsRAN Project is a complete ORAN-native 5G RAN solution created by Software Radio Systems (SRS). The srsRAN Project radio suite was formerly known as srsLTE and can be used for building your own software-defined radio (SDR) 4G/5G mobile network. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMbps, More Is BettersrsRAN Project 23.10.1-20240325Test: PUSCH Processor Benchmark, Throughput ThreadXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P4080120160200SE +/- 7.12, N = 15SE +/- 0.00, N = 4SE +/- 0.00, N = 4SE +/- 0.00, N = 4SE +/- 0.03, N = 4SE +/- 3.58, N = 15SE +/- 0.00, N = 4SE +/- 0.00, N = 4SE +/- 0.00, N = 4153.6183.5183.6183.4183.4179.8183.6183.6183.4MIN: 105.1 / MAX: 182.1-mavx512f -mavx512cd -mavx512bw -mavx512dq - MIN: 105.9-mavx512f -mavx512cd -mavx512bw -mavx512dq - MIN: 106-mavx512f -mavx512cd -mavx512bw -mavx512dq - MIN: 105.9-mavx512f -mavx512cd -mavx512bw -mavx512dq - MIN: 105.8-mavx512f -mavx512cd -mavx512bw -mavx512dq - MIN: 105.9 / MAX: 183.4-mavx512f -mavx512cd -mavx512bw -mavx512dq - MIN: 106-mavx512f -mavx512cd -mavx512bw -mavx512dq - MIN: 106-mavx512f -mavx512cd -mavx512bw -mavx512dq - MIN: 105.91. (CXX) g++ options: -O3 -march=native -mavx2 -mavx -msse4.1 -mfma -fno-trapping-math -fno-math-errno -ldl

GNU Octave Benchmark

This test profile measures how long it takes to complete several reference GNU Octave files via octave-benchmark. GNU Octave is used for numerical computations and is an open-source alternative to MATLAB. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGNU Octave Benchmark 8.4.0Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P246810SE +/- 0.011, N = 6SE +/- 0.021, N = 7SE +/- 0.017, N = 7SE +/- 0.016, N = 7SE +/- 0.016, N = 7SE +/- 0.013, N = 7SE +/- 0.020, N = 7SE +/- 0.018, N = 7SE +/- 0.012, N = 76.4625.7805.5875.5835.5265.6945.4805.8155.880

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 1.6Threads: 1 - Buffer Length: 256 - Filter Length: 512Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P4M8M12M16M20MSE +/- 13650.40, N = 3SE +/- 410224.76, N = 15SE +/- 250051.55, N = 3SE +/- 189549.47, N = 3SE +/- 44508.43, N = 3SE +/- 150617.99, N = 3SE +/- 267438.19, N = 15SE +/- 421403.42, N = 15SE +/- 229945.89, N = 32025500018964400196116671936500019125000184263331911906718078200182076671. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

System Power Consumption Monitor

OpenBenchmarking.orgWattsSystem Power Consumption MonitorPhoronix Test Suite System MonitoringXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P60120180240300Min: 51.7 / Avg: 138.43 / Max: 338.5Min: 90.7 / Avg: 202.74 / Max: 301Min: 67.4 / Avg: 159.31 / Max: 212.3Min: 51.9 / Avg: 120.42 / Max: 144Min: 53.5 / Avg: 128.7 / Max: 186.1Min: 51.6 / Avg: 115.02 / Max: 143.1Min: 76.2 / Avg: 149.2 / Max: 222.4Min: 84.9 / Avg: 130.63 / Max: 143.7Min: 52.3 / Avg: 99.43 / Max: 139.4

CPU Power Consumption Monitor

OpenBenchmarking.orgWattsCPU Power Consumption MonitorPhoronix Test Suite System MonitoringXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P4080120160200Min: 18.57 / Avg: 89.22 / Max: 198.5Min: 48.93 / Avg: 138.83 / Max: 208.13Min: 29.45 / Avg: 105.15 / Max: 145.99Min: 13.54 / Avg: 75.17 / Max: 92.35Min: 16.44 / Avg: 80.5 / Max: 123.57Min: 12.24 / Avg: 71.17 / Max: 91.98Min: 37.24 / Avg: 95.52 / Max: 147.11Min: 46.51 / Avg: 84.39 / Max: 91.68Min: 13.29 / Avg: 57.94 / Max: 90.46

CPU Peak Freq (Highest CPU Core Frequency) Monitor

OpenBenchmarking.orgMegahertzCPU Peak Freq (Highest CPU Core Frequency) MonitorPhoronix Test Suite System MonitoringXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P10002000300040005000Min: 801 / Avg: 4466.33 / Max: 5638Min: 4577 / Avg: 5148.01 / Max: 5604Min: 4543 / Avg: 5178.15 / Max: 5518Min: 400 / Avg: 4794.94 / Max: 5417Min: 400 / Avg: 4831.8 / Max: 5638Min: 400 / Avg: 4805.55 / Max: 5230Min: 4296 / Avg: 4927.95 / Max: 5702Min: 3947 / Avg: 4915.82 / Max: 5476Min: 400 / Avg: 4694.07 / Max: 5214

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 Model Zoo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: ResNet50 v1-12-int8 - Device: CPU - Executor: StandardXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P1.16572.33143.49714.66285.8285SE +/- 0.03583, N = 3SE +/- 0.05300, N = 15SE +/- 0.00310, N = 3SE +/- 0.03376, N = 15SE +/- 0.05991, N = 15SE +/- 0.05218, N = 15SE +/- 0.06313, N = 15SE +/- 0.00434, N = 3SE +/- 0.09911, N = 154.461702.382993.091502.918462.663413.437912.413412.675545.180981. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: ResNet50 v1-12-int8 - Device: CPU - Executor: StandardXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P90180270360450SE +/- 1.81, N = 3SE +/- 9.29, N = 15SE +/- 0.32, N = 3SE +/- 3.81, N = 15SE +/- 9.13, N = 15SE +/- 4.18, N = 15SE +/- 11.38, N = 15SE +/- 0.61, N = 3SE +/- 3.30, N = 15224.11422.42323.38343.18378.25291.71418.47373.67193.851. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

SVT-AV1

OpenBenchmarking.orgWatts, Fewer Is BetterSVT-AV1 2.0System Power Consumption MonitorXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P50100150200250Min: 53.1 / Avg: 139.35 / Max: 291.4Min: 96.5 / Avg: 160.58 / Max: 257.9Min: 69.1 / Avg: 135.43 / Max: 201.7Min: 53.5 / Avg: 97.56 / Max: 137.6Min: 72.5 / Avg: 106.27 / Max: 142.7Min: 53.4 / Avg: 96.49 / Max: 135.9Min: 87.4 / Avg: 116.78 / Max: 160.7Min: 92.3 / Avg: 113.17 / Max: 139.5Min: 54.1 / Avg: 95.37 / Max: 124.9

OpenBenchmarking.orgWatts, Fewer Is BetterSVT-AV1 2.0CPU Power Consumption MonitorXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P306090120150Min: 19.94 / Avg: 83.67 / Max: 140.47Min: 61.36 / Avg: 107.18 / Max: 143.06Min: 34.97 / Avg: 84.95 / Max: 119.79Min: 17.72 / Avg: 52.81 / Max: 86.02Min: 38.02 / Avg: 61.03 / Max: 80.68Min: 14.86 / Avg: 57.04 / Max: 90.38Min: 49.32 / Avg: 71.24 / Max: 87.22Min: 59.15 / Avg: 72.4 / Max: 84.51Min: 16.5 / Avg: 55.09 / Max: 79.61

OpenBenchmarking.orgMegahertz, More Is BetterSVT-AV1 2.0CPU Peak Freq (Highest CPU Core Frequency) MonitorXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P10002000300040005000Min: 3900 / Avg: 4628.73 / Max: 5328Min: 5067 / Avg: 5341.77 / Max: 5536Min: 5050 / Avg: 5231 / Max: 5488Min: 400 / Avg: 4136 / Max: 5340Min: 4656 / Avg: 5022.46 / Max: 5265Min: 400 / Avg: 4090.6 / Max: 5140Min: 4665 / Avg: 5036.36 / Max: 5403Min: 4265 / Avg: 5014.54 / Max: 5440Min: 400 / Avg: 4456.22 / Max: 5141

OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 13 - Input: Bosphorus 4KXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P0.51661.03321.54982.06642.5831.2501.5421.4472.2642.2961.7112.2741.9581.243

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 13 - Input: Bosphorus 4KXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P4080120160200SE +/- 0.99, N = 15SE +/- 4.27, N = 15SE +/- 2.01, N = 15SE +/- 1.88, N = 15SE +/- 2.98, N = 15SE +/- 0.98, N = 15SE +/- 4.16, N = 15SE +/- 2.97, N = 15SE +/- 0.56, N = 9104.61165.29122.91119.57140.0997.60162.00141.7768.471. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenRadioss

OpenBenchmarking.orgWatts, Fewer Is BetterOpenRadioss 2023.09.15System Power Consumption MonitorXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P4080120160200Min: 53.3 / Avg: 144.2 / Max: 243.3Min: 101.4 / Avg: 218.96 / Max: 242.9Min: 75.4 / Avg: 167.23 / Max: 182.1Min: 54.8 / Avg: 132.78 / Max: 139.8Min: 74 / Avg: 139.83 / Max: 156.7Min: 53.6 / Avg: 129.23 / Max: 134.8Min: 83.3 / Avg: 163.91 / Max: 181.2Min: 98.8 / Avg: 136.53 / Max: 141.3Min: 53.7 / Avg: 107.6 / Max: 110.8

OpenBenchmarking.orgWatts, Fewer Is BetterOpenRadioss 2023.09.15CPU Power Consumption MonitorXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P306090120150Min: 21.15 / Avg: 92.95 / Max: 162.3Min: 60.58 / Avg: 150.83 / Max: 170.13Min: 37.57 / Avg: 110.73 / Max: 122.22Min: 17.82 / Avg: 83.68 / Max: 90.4Min: 37.66 / Avg: 89 / Max: 101.5Min: 16.53 / Avg: 81.61 / Max: 87.66Min: 46.07 / Avg: 106.05 / Max: 119.17Min: 60.63 / Avg: 87.4 / Max: 90.41Min: 16.48 / Avg: 64.71 / Max: 68.56

OpenBenchmarking.orgMegahertz, More Is BetterOpenRadioss 2023.09.15CPU Peak Freq (Highest CPU Core Frequency) MonitorXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P10002000300040005000Min: 3993 / Avg: 4423.44 / Max: 5416Min: 4862 / Avg: 5088.49 / Max: 5537Min: 4849 / Avg: 5158.27 / Max: 5515Min: 400 / Avg: 4730.46 / Max: 5340Min: 4692 / Avg: 4820.08 / Max: 5215Min: 400 / Avg: 4945.43 / Max: 5137Min: 4692 / Avg: 4785.46 / Max: 5203Min: 4651 / Avg: 4861.54 / Max: 5304Min: 400 / Avg: 5060.94 / Max: 5140

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2023.09.15Model: Cell Phone Drop TestXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P306090120150SE +/- 3.30, N = 15SE +/- 1.68, N = 12SE +/- 3.06, N = 15SE +/- 0.37, N = 3SE +/- 1.45, N = 15SE +/- 0.21, N = 3SE +/- 0.42, N = 3SE +/- 1.62, N = 15SE +/- 0.33, N = 393.2667.7195.4880.0482.0298.8567.8875.83138.72

OpenBenchmarking.orgWatts, Fewer Is BetterOpenRadioss 2023.09.15System Power Consumption MonitorXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P50100150200250Min: 54.2 / Avg: 143.97 / Max: 246.8Min: 101.3 / Avg: 241.39 / Max: 265.9Min: 75.2 / Avg: 176.99 / Max: 191.4Min: 55.4 / Avg: 132.86 / Max: 137.3Min: 74.2 / Avg: 146.13 / Max: 157Min: 54.7 / Avg: 132.03 / Max: 136Min: 83.7 / Avg: 174.36 / Max: 196.5Min: 99.5 / Avg: 135.16 / Max: 138.6Min: 54.4 / Avg: 109.75 / Max: 111.2

OpenBenchmarking.orgWatts, Fewer Is BetterOpenRadioss 2023.09.15CPU Power Consumption MonitorXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P306090120150Min: 21.95 / Avg: 94.12 / Max: 160.28Min: 60.42 / Avg: 171.03 / Max: 189.55Min: 37.54 / Avg: 119.54 / Max: 131.85Min: 18.71 / Avg: 86.78 / Max: 90.38Min: 38.31 / Avg: 95.37 / Max: 103.37Min: 16.47 / Avg: 87.18 / Max: 90.37Min: 38.85 / Avg: 115.17 / Max: 132.31Min: 58.52 / Avg: 88.53 / Max: 90.38Min: 16.99 / Avg: 67.89 / Max: 70.08

OpenBenchmarking.orgMegahertz, More Is BetterOpenRadioss 2023.09.15CPU Peak Freq (Highest CPU Core Frequency) MonitorXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P10002000300040005000Min: 4246 / Avg: 4387.56 / Max: 5400Min: 4952 / Avg: 5013.45 / Max: 5489Min: 5027 / Avg: 5110.05 / Max: 5489Min: 4875 / Avg: 4971.99 / Max: 5340Min: 4722 / Avg: 4793.95 / Max: 5190Min: 400 / Avg: 4962.57 / Max: 5186Min: 4704 / Avg: 4794.67 / Max: 5202Min: 4540 / Avg: 4751.02 / Max: 5429Min: 400 / Avg: 5102.19 / Max: 5143

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2023.09.15Model: Rubber O-Ring Seal InstallationXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P60120180240300SE +/- 5.45, N = 12SE +/- 1.00, N = 3SE +/- 8.68, N = 9SE +/- 0.24, N = 3SE +/- 3.80, N = 9SE +/- 0.54, N = 3SE +/- 3.75, N = 15SE +/- 7.92, N = 9SE +/- 0.45, N = 3177.74110.05162.03127.32148.28157.48106.01126.03254.88

HeFFTe - Highly Efficient FFT for Exascale

OpenBenchmarking.orgWatts, Fewer Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.4System Power Consumption MonitorXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P20406080100Min: 52.8 / Avg: 61.36 / Max: 82.7Min: 95.8 / Avg: 99.24 / Max: 114.7Min: 71.1 / Avg: 74.77 / Max: 84.5Min: 51.9 / Avg: 54.38 / Max: 65Min: 72.4 / Avg: 74.99 / Max: 83.7Min: 52.2 / Avg: 54.38 / Max: 61.2Min: 86.2 / Avg: 87.89 / Max: 89.1Min: 97.7 / Avg: 99.33 / Max: 104.6Min: 52.9 / Avg: 55.65 / Max: 62.6

OpenBenchmarking.orgWatts, Fewer Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.4CPU Power Consumption MonitorXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P1326395265Min: 21.18 / Avg: 25.08 / Max: 26.48Min: 50.14 / Avg: 61.56 / Max: 64.57Min: 38.68 / Avg: 39.26 / Max: 40.29Min: 19.23 / Avg: 20.27 / Max: 21.16Min: 38.39 / Avg: 39.98 / Max: 41.26Min: 17.18 / Avg: 18.45 / Max: 20.02Min: 48.18 / Avg: 50.59 / Max: 52.49Min: 51.07 / Avg: 60.47 / Max: 62.64Min: 17.39 / Avg: 18.43 / Max: 19.81

OpenBenchmarking.orgMegahertz, More Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.4CPU Peak Freq (Highest CPU Core Frequency) MonitorXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P10002000300040005000Min: 3930 / Avg: 4692 / Max: 5204Min: 5293 / Avg: 5472.62 / Max: 5536Min: 5263 / Avg: 5323.75 / Max: 5448Min: 400 / Avg: 2142.27 / Max: 5333Min: 5025 / Avg: 5211.54 / Max: 5240Min: 400 / Avg: 3114.9 / Max: 4941Min: 5016 / Avg: 5188.92 / Max: 5322Min: 5237 / Avg: 5250.46 / Max: 5268Min: 400 / Avg: 3048.75 / Max: 4942

OpenBenchmarking.orgGFLOP/s Per Watt, More Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.4Test: r2c - Backend: FFTW - Precision: double - X Y Z: 128Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P0.33930.67861.01791.35721.69651.0560.6050.6041.2030.5681.5080.9940.5790.936

OpenBenchmarking.orgGFLOP/s, More Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.4Test: r2c - Backend: FFTW - Precision: double - X Y Z: 128Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P1122334455SE +/- 0.39, N = 15SE +/- 0.58, N = 15SE +/- 0.15, N = 15SE +/- 0.13, N = 14SE +/- 0.52, N = 15SE +/- 0.06, N = 14SE +/- 1.39, N = 15SE +/- 0.59, N = 15SE +/- 0.18, N = 1526.4837.2423.7224.3822.7027.8350.2835.0217.251. (CXX) g++ options: -O3

OpenBenchmarking.orgWatts, Fewer Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.4System Power Consumption MonitorXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P20406080100Min: 53.5 / Avg: 59.35 / Max: 70.9Min: 95.4 / Avg: 99.75 / Max: 109.7Min: 71.5 / Avg: 73.41 / Max: 79.4Min: 52.2 / Avg: 54.78 / Max: 62.4Min: 73.2 / Avg: 73.51 / Max: 74Min: 52 / Avg: 54.02 / Max: 58.9Min: 83.2 / Avg: 85.68 / Max: 87.5Min: 99.1 / Avg: 99.42 / Max: 100.1Min: 54.5 / Avg: 56.15 / Max: 60.4

OpenBenchmarking.orgWatts, Fewer Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.4CPU Power Consumption MonitorXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P1224364860Min: 22.31 / Avg: 24.02 / Max: 25.79Min: 60.66 / Avg: 61.58 / Max: 63.13Min: 32.99 / Avg: 38.11 / Max: 39.6Min: 16.26 / Avg: 18.88 / Max: 21.72Min: 32.77 / Avg: 38.09 / Max: 39.13Min: 14.83 / Avg: 17.84 / Max: 20.5Min: 47.01 / Avg: 49.09 / Max: 50.56Min: 60.81 / Avg: 61.43 / Max: 62.08Min: 15.66 / Avg: 17.88 / Max: 18.87

OpenBenchmarking.orgMegahertz, More Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.4CPU Peak Freq (Highest CPU Core Frequency) MonitorXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P10002000300040005000Min: 4293 / Avg: 4852.31 / Max: 5224Min: 5434 / Avg: 5488.82 / Max: 5537Min: 5246 / Avg: 5314.36 / Max: 5350Min: 400 / Avg: 3317 / Max: 5164Min: 5088 / Avg: 5203.15 / Max: 5240Min: 400 / Avg: 1929.92 / Max: 5134Min: 5041 / Avg: 5231.64 / Max: 5462Min: 4985 / Avg: 5213.08 / Max: 5267Min: 400 / Avg: 3289.36 / Max: 4942

OpenBenchmarking.orgGFLOP/s Per Watt, More Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.4Test: r2c - Backend: FFTW - Precision: float - X Y Z: 128Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P0.96441.92882.89323.85764.8223.5402.0772.0344.0412.9864.2862.8331.7542.466

OpenBenchmarking.orgGFLOP/s, More Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.4Test: r2c - Backend: FFTW - Precision: float - X Y Z: 128Xeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P306090120150SE +/- 3.73, N = 15SE +/- 1.14, N = 15SE +/- 1.52, N = 15SE +/- 1.45, N = 15SE +/- 0.82, N = 15SE +/- 2.17, N = 15SE +/- 1.72, N = 15SE +/- 1.06, N = 15SE +/- 1.04, N = 1585.01127.9377.5276.28113.7476.44139.06107.7444.091. (CXX) g++ options: -O3

ASKAP

OpenBenchmarking.orgWatts, Fewer Is BetterASKAP 1.0System Power Consumption MonitorXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P50100150200250Min: 54.6 / Avg: 142.3 / Max: 224.5Min: 99.6 / Avg: 174.53 / Max: 252.9Min: 72.9 / Avg: 131.71 / Max: 175.2Min: 54.3 / Avg: 94.27 / Max: 115.1Min: 72.9 / Avg: 123.03 / Max: 156.5Min: 53.4 / Avg: 86.1 / Max: 108.4Min: 84.1 / Avg: 138.63 / Max: 191Min: 98.7 / Avg: 133.75 / Max: 140.5Min: 53.9 / Avg: 72.34 / Max: 84.1

OpenBenchmarking.orgWatts, Fewer Is BetterASKAP 1.0CPU Power Consumption MonitorXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P306090120150Min: 38.32 / Avg: 95.55 / Max: 124.72Min: 60.25 / Avg: 116.42 / Max: 162.58Min: 52.24 / Avg: 77.99 / Max: 92.16Min: 16.89 / Avg: 53.42 / Max: 64.66Min: 37.3 / Avg: 75.25 / Max: 93.98Min: 20.37 / Avg: 44.71 / Max: 54.1Min: 49.43 / Avg: 84.77 / Max: 112.51Min: 60.35 / Avg: 86.14 / Max: 90.4Min: 16.33 / Avg: 35.93 / Max: 43.94

OpenBenchmarking.orgMegahertz, More Is BetterASKAP 1.0CPU Peak Freq (Highest CPU Core Frequency) MonitorXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P10002000300040005000Min: 4480 / Avg: 5025.92 / Max: 5400Min: 4983 / Avg: 5274.91 / Max: 5500Min: 5052 / Avg: 5291.68 / Max: 5464Min: 400 / Avg: 4768.77 / Max: 5141Min: 4772 / Avg: 5034.85 / Max: 5190Min: 400 / Avg: 4571.25 / Max: 5136Min: 4782 / Avg: 5076.91 / Max: 5262Min: 4659 / Avg: 5160.76 / Max: 5268Min: 4937 / Avg: 4941.91 / Max: 4963

OpenBenchmarking.orgMpix/sec Per Watt, More Is BetterASKAP 1.0Test: tConvolve MPI - GriddingXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P30609012015064.8864.2354.57109.97100.06133.37115.1585.7889.81

OpenBenchmarking.orgMpix/sec, More Is BetterASKAP 1.0Test: tConvolve MPI - GriddingXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P2K4K6K8K10KSE +/- 48.43, N = 3SE +/- 298.02, N = 15SE +/- 180.65, N = 12SE +/- 44.18, N = 3SE +/- 175.34, N = 15SE +/- 0.00, N = 3SE +/- 384.12, N = 15SE +/- 528.48, N = 12SE +/- 26.67, N = 36199.097477.194256.285875.197529.935963.549760.757389.243226.621. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

OpenBenchmarking.orgMpix/sec, More Is BetterASKAP 1.0Test: tConvolve MPI - DegriddingXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P2K4K6K8K10KSE +/- 58.27, N = 3SE +/- 321.53, N = 15SE +/- 192.19, N = 12SE +/- 34.30, N = 3SE +/- 187.79, N = 15SE +/- 38.09, N = 3SE +/- 346.60, N = 15SE +/- 473.28, N = 12SE +/- 0.00, N = 35146.336642.943635.695179.316140.894723.738364.076270.822623.961. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

LAMMPS Molecular Dynamics Simulator

OpenBenchmarking.orgWatts, Fewer Is BetterLAMMPS Molecular Dynamics Simulator 23Jun2022System Power Consumption MonitorXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P50100150200250Min: 54.5 / Avg: 142.79 / Max: 236.4Min: 102.7 / Avg: 240.84 / Max: 257.1Min: 74.2 / Avg: 176.91 / Max: 190.1Min: 54.3 / Avg: 135.62 / Max: 136.3Min: 74.7 / Avg: 147.98 / Max: 151Min: 53.7 / Avg: 135.94 / Max: 137Min: 84.6 / Avg: 184.42 / Max: 189.6Min: 94.6 / Avg: 136.23 / Max: 137.3Min: 54 / Avg: 115.62 / Max: 116.7

OpenBenchmarking.orgWatts, Fewer Is BetterLAMMPS Molecular Dynamics Simulator 23Jun2022CPU Power Consumption MonitorXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P306090120150Min: 22.3 / Avg: 94.86 / Max: 139Min: 61.31 / Avg: 169.46 / Max: 180.85Min: 36.84 / Avg: 120.36 / Max: 131.88Min: 27.71 / Avg: 89.73 / Max: 90.38Min: 37.33 / Avg: 96.74 / Max: 100.04Min: 16.77 / Avg: 89.63 / Max: 90.39Min: 46.78 / Avg: 122.74 / Max: 127.89Min: 56.97 / Avg: 89.85 / Max: 90.41Min: 15.9 / Avg: 74.19 / Max: 75.58

OpenBenchmarking.orgMegahertz, More Is BetterLAMMPS Molecular Dynamics Simulator 23Jun2022CPU Peak Freq (Highest CPU Core Frequency) MonitorXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P10002000300040005000Min: 2400 / Avg: 4332.92 / Max: 5400Min: 4809 / Avg: 4965.28 / Max: 5499Min: 4897 / Avg: 5080.08 / Max: 5335Min: 400 / Avg: 4913.12 / Max: 5036Min: 4731 / Avg: 4794.5 / Max: 5215Min: 400 / Avg: 4973.27 / Max: 5113Min: 4714 / Avg: 4784.39 / Max: 5207Min: 4579 / Avg: 4728.74 / Max: 5260Min: 4941 / Avg: 5112.82 / Max: 5145

OpenBenchmarking.orgns/day Per Watt, More Is BetterLAMMPS Molecular Dynamics Simulator 23Jun2022Model: 20k AtomsXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P0.0270.0540.0810.1080.1350.0800.0810.0680.1000.0990.0760.1200.1160.064

OpenBenchmarking.orgns/day, More Is BetterLAMMPS Molecular Dynamics Simulator 23Jun2022Model: 20k AtomsXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P48121620SE +/- 0.177, N = 9SE +/- 0.297, N = 9SE +/- 0.174, N = 9SE +/- 0.004, N = 3SE +/- 0.108, N = 9SE +/- 0.014, N = 3SE +/- 0.298, N = 6SE +/- 0.191, N = 9SE +/- 0.008, N = 37.57913.6918.2158.9519.5396.83814.68010.3934.7801. (CXX) g++ options: -O3 -lm -ldl

ACES DGEMM

OpenBenchmarking.orgWatts, Fewer Is BetterACES DGEMM 1.0System Power Consumption MonitorXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P50100150200250Min: 53.1 / Avg: 140.86 / Max: 198.1Min: 94.4 / Avg: 192.48 / Max: 264.4Min: 72 / Avg: 147.16 / Max: 175.9Min: 53.9 / Avg: 124.65 / Max: 133.5Min: 74 / Avg: 118.09 / Max: 149Min: 53 / Avg: 98.91 / Max: 111.4Min: 83.9 / Avg: 158.95 / Max: 189Min: 87.9 / Avg: 126.29 / Max: 137.1Min: 54 / Avg: 85.7 / Max: 96.2

OpenBenchmarking.orgWatts, Fewer Is BetterACES DGEMM 1.0CPU Power Consumption MonitorXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P306090120150Min: 21.45 / Avg: 96.15 / Max: 139.58Min: 64.62 / Avg: 140.35 / Max: 184.02Min: 36.54 / Avg: 99.71 / Max: 121.4Min: 32.7 / Avg: 81.36 / Max: 90.56Min: 45.64 / Avg: 75.73 / Max: 96.66Min: 17.24 / Avg: 64.71 / Max: 73.16Min: 40.66 / Avg: 100.01 / Max: 127.23Min: 54.86 / Avg: 82.61 / Max: 90.52Min: 20.86 / Avg: 49.46 / Max: 58.28

OpenBenchmarking.orgMegahertz, More Is BetterACES DGEMM 1.0CPU Peak Freq (Highest CPU Core Frequency) MonitorXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P10002000300040005000Min: 4014 / Avg: 4857.43 / Max: 5452Min: 5089 / Avg: 5251.73 / Max: 5529Min: 5195 / Avg: 5279.57 / Max: 5489Min: 400 / Avg: 4974.8 / Max: 5340Min: 5014 / Avg: 5093.65 / Max: 5190Min: 400 / Avg: 4835.39 / Max: 5139Min: 4970 / Avg: 5072.5 / Max: 5247Min: 4850 / Avg: 5060.65 / Max: 5440Min: 4941 / Avg: 5117.02 / Max: 5141

OpenBenchmarking.orgGFLOP/s Per Watt, More Is BetterACES DGEMM 1.0Sustained Floating-Point RateXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P0.02390.04780.07170.09560.11950.0440.0680.0530.0650.0740.0610.1060.0870.044

OpenBenchmarking.orgGFLOP/s, More Is BetterACES DGEMM 1.0Sustained Floating-Point RateXeon E-2488EPYC 4564PEPYC 4364PEPYC 4344PEPYC 4484PXEPYC 4244PEPYC 4584PXEPYC 4464PEPYC 4124P3691215SE +/- 0.054700, N = 3SE +/- 0.258971, N = 12SE +/- 0.144416, N = 15SE +/- 0.037881, N = 3SE +/- 0.066520, N = 3SE +/- 0.039171, N = 3SE +/- 0.322380, N = 15SE +/- 0.115135, N = 15SE +/- 0.006425, N = 34.2041109.5777535.3305005.3136495.6045023.92016810.5916517.1870622.1617951. (CC) gcc options: -O3 -march=native -fopenmp

385 Results Shown

PostgreSQL:
  100 - 500 - Read Only - Average Latency
  100 - 500 - Read Only
  100 - 800 - Read Only - Average Latency
  100 - 800 - Read Only
John The Ripper
LuxCoreRender
OpenVINO:
  Weld Porosity Detection FP16 - CPU
  Face Detection FP16 - CPU
  Handwritten English Recognition FP16 - CPU
OpenSSL
srsRAN Project
OpenVINO:
  Person Re-Identification Retail FP16 - CPU
  Age Gender Recognition Retail 0013 FP16 - CPU
LuxCoreRender
OpenVINO
OSPRay Studio:
  2 - 1080p - 16 - Path Tracer - CPU
  3 - 1080p - 16 - Path Tracer - CPU
John The Ripper
OSPRay Studio
John The Ripper
NAMD
OpenVINO:
  Person Re-Identification Retail FP16 - CPU
  Vehicle Detection FP16 - CPU
  Face Detection Retail FP16 - CPU
OSPRay Studio:
  3 - 1080p - 1 - Path Tracer - CPU
  2 - 1080p - 1 - Path Tracer - CPU
OpenVINO
OSPRay Studio
Stockfish
Cpuminer-Opt
Stress-NG
Embree
OpenVINO
OSPRay Studio
miniBUDE:
  OpenMP - BM1:
    Billion Interactions/s
    GFInst/s
OpenVINO:
  Vehicle Detection FP16-INT8 - CPU
  Face Detection Retail FP16 - CPU
OSPRay Studio
OpenVINO
miniBUDE:
  OpenMP - BM2:
    GFInst/s
    Billion Interactions/s
Blender
OSPRay Studio
OpenVINO
Blender
Chaos Group V-RAY
Java JMH
OpenSSL
OpenVINO
OpenSSL
Blender
ASTC Encoder
OpenVINO
ASTC Encoder
OpenSSL:
  AES-128-GCM
  RSA4096
Blender
ASTC Encoder
Aircrack-ng
OSPRay
OpenVINO
Cpuminer-Opt
OSPRay
Stress-NG
Blender
OpenSSL
ASTC Encoder
OSPRay
OpenSSL
Cpuminer-Opt
Blender
RocksDB
ASTC Encoder
SVT-HEVC
Cpuminer-Opt
OSPRay
DaCapo Benchmark
Stress-NG
OpenSSL
Cpuminer-Opt
OSPRay
SVT-HEVC
Cpuminer-Opt
Stress-NG
Helsing
m-queens
7-Zip Compression
Speedb
Cpuminer-Opt:
  Magi
  Myriad-Groestl
OpenVINO
QuantLib
RocksDB
Coremark
Cpuminer-Opt
Embree
Stress-NG
John The Ripper
Cpuminer-Opt:
  Ringcoin
  scrypt
Stress-NG
John The Ripper
Helsing
NAMD
Embree
OpenVINO
ASKAP
nginx
Primesieve
Timed Node.js Compilation
Primesieve
OpenVKL
GraphicsMagick:
  Sharpen
  Enhanced
Timed Linux Kernel Compilation
Memcached
Timed LLVM Compilation
Intel Open Image Denoise:
  RT.ldr_alb_nrm.3840x2160 - CPU-Only
  RT.hdr_alb_nrm.3840x2160 - CPU-Only
uvg266
Speedb
Appleseed
LuxCoreRender
OpenVINO
nginx
LuxCoreRender
GraphicsMagick
DaCapo Benchmark
TensorFlow
BRL-CAD
Intel Open Image Denoise
nginx
Appleseed
oneDNN
Memcached
TensorFlow
Parallel BZIP2 Compression
Timed Godot Game Engine Compilation
SVT-HEVC
uvg266
SVT-HEVC
Timed LLVM Compilation
Kvazaar
oneDNN:
  Recurrent Neural Network Inference - CPU
  Recurrent Neural Network Training - CPU
PostgreSQL:
  100 - 800 - Read Write
  100 - 800 - Read Write - Average Latency
uvg266:
  Bosphorus 4K - Very Fast
  Bosphorus 4K - Ultra Fast
OpenVINO
SPECFEM3D
OpenVINO
Timed Linux Kernel Compilation
7-Zip Compression
Timed FFmpeg Compilation
CockroachDB
SPECFEM3D
ASKAP
JPEG-XL libjxl
OpenFOAM
CockroachDB
oneDNN
JPEG-XL libjxl
CockroachDB
Kvazaar
PostgreSQL:
  100 - 500 - Read Write
  100 - 500 - Read Write - Average Latency
Zstd Compression
Timed Mesa Compilation
x265
Timed Gem5 Compilation
Zstd Compression
GROMACS
SVT-AV1
SVT-HEVC
SPECFEM3D:
  Layered Halfspace
  Mount St. Helens
SVT-VP9
ONNX Runtime
Kvazaar
LuxCoreRender
TensorFlow
uvg266
Kvazaar
oneDNN
SVT-VP9
libavif avifenc
Appleseed
ScyllaDB
SPECFEM3D
Liquid-DSP
uvg266
OpenVINO
NAS Parallel Benchmarks
GraphicsMagick
LAMMPS Molecular Dynamics Simulator
SVT-VP9
OpenVINO
Kvazaar
SVT-VP9
SVT-HEVC
uvg266
TensorFlow
uvg266
OpenVINO
libavif avifenc
TensorFlow
NAS Parallel Benchmarks
ONNX Runtime
OpenVINO:
  Road Segmentation ADAS FP16-INT8 - CPU
  Age Gender Recognition Retail 0013 FP16 - CPU
TensorFlow:
  CPU - 512 - GoogLeNet
  CPU - 256 - GoogLeNet
Y-Cruncher
SVT-AV1
oneDNN
Kvazaar
OpenVINO
Kvazaar
SVT-VP9
MariaDB
OpenRadioss
TensorFlow
SVT-AV1
RocksDB
Kvazaar
Zstd Compression
OpenVINO
Pennant
ONNX Runtime
GraphicsMagick
Y-Cruncher
VVenC
libavif avifenc
SVT-VP9
ONNX Runtime
OpenRadioss
Pennant
libavif avifenc
OpenVINO
VVenC
oneDNN
MariaDB
OpenVINO
SVT-AV1
ONNX Runtime
JPEG-XL libjxl
Apache IoTDB
TensorFlow
Apache IoTDB
NAS Parallel Benchmarks
Apache IoTDB
Liquid-DSP
Timed PHP Compilation
JPEG-XL libjxl
OpenVINO
ONNX Runtime
TensorFlow:
  CPU - 32 - ResNet-50
  CPU - 64 - ResNet-50
  CPU - 256 - ResNet-50
Apache IoTDB
SVT-AV1
Speedb
OSPRay
MariaDB
GPAW
Xcompact3d Incompact3d
OpenVINO
VVenC
ONNX Runtime
Timed Wasmer Compilation
x265
PyTorch
DaCapo Benchmark
SVT-AV1
CloverLeaf
MariaDB
OpenRadioss
OpenVINO:
  Person Detection FP32 - CPU
  Noise Suppression Poconet-Like FP16 - CPU
  Person Detection FP16 - CPU
OpenFOAM
VVenC
DuckDB
DaCapo Benchmark
Apache IoTDB
srsRAN Project
Apache IoTDB
NAS Parallel Benchmarks
Apache IoTDB
OpenFOAM
Apache IoTDB
ClickHouse
OpenRadioss
Apache IoTDB:
  500 - 100 - 800 - 400
  800 - 100 - 500 - 400
  800 - 100 - 500 - 400
DaCapo Benchmark
ClickHouse
OpenFOAM
ClickHouse
Apache IoTDB
PyTorch
GraphicsMagick
Timed CPython Compilation
NAS Parallel Benchmarks
Zstd Compression
OpenVINO
Xcompact3d Incompact3d
TensorFlow
Apache IoTDB:
  500 - 100 - 500 - 100:
    Average Latency
    point/sec
  500 - 100 - 500 - 400:
    point/sec
    Average Latency
Zstd Compression
ONNX Runtime
PyBench
Google Draco
TensorFlow
OpenVINO
FFmpeg
ONNX Runtime
OpenVINO
FFmpeg:
  libx265 - Video On Demand
  libx265 - Platform
MariaDB mariadb-slap
ONNX Runtime
MariaDB mariadb-slap
Z3 Theorem Prover
srsRAN Project
FFmpeg
ONNX Runtime:
  Faster R-CNN R-50-FPN-int8 - CPU - Parallel
  GPT-2 - CPU - Parallel
Liquid-DSP
Renaissance
Timed CPython Compilation
Numpy Benchmark
srsRAN Project
GNU Octave Benchmark
Liquid-DSP
System Power Consumption Monitor:
  Phoronix Test Suite System Monitoring:
    Watts
    Watts
    Megahertz
ONNX Runtime:
  ResNet50 v1-12-int8 - CPU - Standard:
    Inference Time Cost (ms)
    Inferences Per Second
SVT-AV1:
  System Power Consumption Monitor
  CPU Power Consumption Monitor
  CPU Peak Freq (Highest CPU Core Frequency) Monitor
  Preset 13 - Bosphorus 4K
SVT-AV1
OpenRadioss:
  System Power Consumption Monitor
  CPU Power Consumption Monitor
  CPU Peak Freq (Highest CPU Core Frequency) Monitor
OpenRadioss
OpenRadioss:
  System Power Consumption Monitor
  CPU Power Consumption Monitor
  CPU Peak Freq (Highest CPU Core Frequency) Monitor
OpenRadioss
HeFFTe - Highly Efficient FFT for Exascale:
  System Power Consumption Monitor
  CPU Power Consumption Monitor
  CPU Peak Freq (Highest CPU Core Frequency) Monitor
  r2c - FFTW - double - 128
HeFFTe - Highly Efficient FFT for Exascale
HeFFTe - Highly Efficient FFT for Exascale:
  System Power Consumption Monitor
  CPU Power Consumption Monitor
  CPU Peak Freq (Highest CPU Core Frequency) Monitor
  r2c - FFTW - float - 128
HeFFTe - Highly Efficient FFT for Exascale
ASKAP:
  System Power Consumption Monitor
  CPU Power Consumption Monitor
  CPU Peak Freq (Highest CPU Core Frequency) Monitor
  tConvolve MPI - Gridding
ASKAP:
  tConvolve MPI - Gridding
  tConvolve MPI - Degridding
LAMMPS Molecular Dynamics Simulator:
  System Power Consumption Monitor
  CPU Power Consumption Monitor
  CPU Peak Freq (Highest CPU Core Frequency) Monitor
  20k Atoms
LAMMPS Molecular Dynamics Simulator
ACES DGEMM:
  System Power Consumption Monitor
  CPU Power Consumption Monitor
  CPU Peak Freq (Highest CPU Core Frequency) Monitor
  Sustained Floating-Point Rate
ACES DGEMM