EPYC 4004 Benchmarks

Benchmarks preparing for a future article upon launch 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 2405239-NE-4124P914394
Jump To Table - Results

View

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

Limit displaying results to tests within:

AV1 2 Tests
BLAS (Basic Linear Algebra Sub-Routine) Tests 3 Tests
C++ Boost Tests 5 Tests
Chess Test Suite 2 Tests
Timed Code Compilation 10 Tests
C/C++ Compiler Tests 19 Tests
Compression Tests 3 Tests
CPU Massive 39 Tests
Creator Workloads 29 Tests
Cryptocurrency Benchmarks, CPU Mining Tests 2 Tests
Cryptography 6 Tests
Database Test Suite 10 Tests
Encoding 9 Tests
Fortran Tests 9 Tests
Game Development 6 Tests
HPC - High Performance Computing 29 Tests
Imaging 5 Tests
Java 4 Tests
Common Kernel Benchmarks 5 Tests
Linear Algebra 2 Tests
Large Language Models 2 Tests
Machine Learning 9 Tests
Molecular Dynamics 10 Tests
MPI Benchmarks 10 Tests
Multi-Core 51 Tests
NVIDIA GPU Compute 4 Tests
Intel oneAPI 7 Tests
OpenMPI Tests 17 Tests
Programmer / Developer System Benchmarks 15 Tests
Python 2 Tests
Raytracing 2 Tests
Renderers 6 Tests
Scientific Computing 15 Tests
Software Defined Radio 2 Tests
Server 18 Tests
Server CPU Tests 26 Tests
Single-Threaded 5 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

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
EPYC 4124P @ DDR5-5200
May 20
  2 Days, 17 Hours, 6 Minutes
smoke
May 23
  19 Hours, 19 Minutes
Invert Hiding All Results Option
  1 Day, 18 Hours, 13 Minutes
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):

EPYC 4124P @ DDR5-5200

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --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
Processor Notes: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xa601203
Java Notes: OpenJDK Runtime Environment (build 21.0.2+13-Ubuntu-2)
Python Notes: Python 3.12.2
Security Notes: 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

smoke

Processor: AMD EPYC 4124P 4-Core @ 5.17GHz (4 Cores / 8 Threads), Motherboard: Supermicro AS-3015A-I H13SAE-MF v1.00 (1.1 BIOS), Chipset: AMD Device 14d8, Memory: 2 x 32GB DRAM-5200MT/s, Disk: 3201GB Micron_7450_MTFDKCC3T2TFS + 960GB SAMSUNG MZ1L2960HCJR-00A07, Graphics: ASPEED, Audio: AMD Rembrandt Radeon HD Audio, Monitor: VE228, Network: 2 x Intel I210

OS: Ubuntu 24.04, Kernel: 6.8.0-11-generic (x86_64), Desktop: GNOME Shell 45.3, Display Server: X Server 1.21.1.11, Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1080

EPYC 4004 BenchmarksOpenBenchmarking.orgPhoronix Test SuiteAMD EPYC 4124P 4-Core @ 5.17GHz (4 Cores / 8 Threads)Supermicro AS-3015A-I H13SAE-MF v1.00 (1.1 BIOS)AMD Device 14d82 x 32GB DRAM-5200MT/s3201GB Micron_7450_MTFDKCC3T2TFS + 960GB SAMSUNG MZ1L2960HCJR-00A07ASPEEDAMD Rembrandt Radeon HD AudioVE2282 x Intel I210Ubuntu 24.046.8.0-11-generic (x86_64)GNOME Shell 45.3X Server 1.21.1.11GCC 13.2.0ext41920x1080ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerCompilerFile-SystemScreen ResolutionEPYC 4004 Benchmarks PerformanceSystem Logs- Transparent Huge Pages: madvise- --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 - Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xa601203- OpenJDK Runtime Environment (build 21.0.2+13-Ubuntu-2)- Python 3.12.2- 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 @ DDR5-5200 vs. smoke ComparisonPhoronix Test SuiteBaseline+9.8%+9.8%+19.6%+19.6%+29.4%+29.4%7.8%7.4%6%5.7%5.7%4.1%4.1%3.8%3.2%3.2%3.1%3.1%3%2.9%2.7%2.7%2.6%2.5%2.2%4.5%4.6%3.5%fcn-resnet101-11 - CPU - Parallel39%F.R.C.R.5.F.i - CPU - Standard24%r2c - FFTW - float - 12822.6%Preset 13 - Bosphorus 1080p20.3%2 - 256 - 51218.7%ArcFace ResNet-100 - CPU - Parallel14.9%Preset 13 - Bosphorus 4K8.1%T5 Encoder - CPU - Standard7.9%llama-2-13b.Q4_0.ggufDanish Mood - CPU500H.E.R.F.I - CPUH.E.R.F.I - CPU500 - 100 - 500 - 1004.5%tConvolve OpenMP - GriddingGPT-2 - CPU - StandardtConvolve MT - Degridding4%bertsquad-12 - CPU - Standard800 - 100 - 800 - 1003.8%H.E.R.F - CPU3.8%H.E.R.F - CPU3.8%500 - 100 - 500 - 4003.8%500 - 100 - 500 - 4003.7%500 - 100 - 800 - 4003.7%800 - 100 - 800 - 1003.6%500 - 100 - 500 - 1003.5%800 - 100 - 500 - 1003.5%500 - 100 - 800 - 4003.5%A.G.R.R.0.F.I - CPU3.4%H.H3.4%P.P.B.T.T3.4%D.B.s - CPURead While WritingR.R.W.R3.2%100 - 500 - Read Only - Average Latency800 - 100 - 500 - 1003.1%100 - 500 - Read OnlyR.v.1.i - CPU - Standard4 - 256 - 512Rand Fill Sync2.8%r2c - FFTW - double - 1282.7%V.Q.O - Bosphorus 4K2.7%V.Q.O - Bosphorus 1080p2.7%1000HWB Color Space800 - 100 - 500 - 4002.5%Read While Writing2.5%d.S.M.S - Execution TimeA.G.R.R.0.F.I - CPU2.3%llama-2-70b-chat.Q5_0.ggufsimple-H2O2.1%800 - 100 - 800 - 4002%tConvolve MPI - Degridding2%F.R.C.R.5.F.i - CPU - Standard22.9%GPT-2 - CPU - Standardbertsquad-12 - CPU - StandardR.v.1.i - CPU - Standardfcn-resnet101-11 - CPU - Parallel35.7%T5 Encoder - CPU - Standard7.9%ArcFace ResNet-100 - CPU - Parallel14.9%ONNX RuntimeONNX RuntimeHeFFTe - Highly Efficient FFT for ExascaleSVT-AV1Liquid-DSPONNX RuntimeSVT-AV1ONNX RuntimeLlama.cppLuxCoreRenderApache HTTP ServerOpenVINOOpenVINOApache IoTDBASKAPONNX RuntimeASKAPONNX RuntimeApache IoTDBOpenVINOOpenVINOApache IoTDBApache IoTDBApache IoTDBApache IoTDBApache IoTDBApache IoTDBApache IoTDBOpenVINOSPECFEM3DsrsRAN ProjectoneDNNSpeedbRocksDBPostgreSQLApache IoTDBPostgreSQLONNX RuntimeLiquid-DSPSpeedbHeFFTe - Highly Efficient FFT for ExascaleNode.js V8 Web Tooling BenchmarkSVT-VP9SVT-VP9nginxGraphicsMagickApache IoTDBRocksDBOpenFOAMOpenVINOLlama.cppQMCPACKApache IoTDBASKAPONNX RuntimeONNX RuntimeONNX RuntimeONNX RuntimeONNX RuntimeONNX RuntimeONNX RuntimeEPYC 4124P @ DDR5-5200smoke

EPYC 4004 Benchmarkstensorflow: CPU - 512 - ResNet-50xmrig: GhostRider - 1Mbuild-linux-kernel: allmodconfigopenfoam: drivaerFastback, Medium Mesh Size - Execution Timeopenfoam: drivaerFastback, Medium Mesh Size - Mesh Timeblender: Barbershop - CPU-Onlylammps: 20k Atomsopenradioss: Chrysler Neon 1Mtensorflow: CPU - 256 - ResNet-50build-nodejs: Time To Compilebuild-llvm: Unix Makefilesbuild-llvm: Ninjahelsing: 14 digittensorflow: CPU - 512 - GoogLeNetstockfish: Chess Benchmarkopenradioss: INIVOL and Fluid Structure Interaction Drop Containerbuild-gem5: Time To Compileopenvkl: vklBenchmarkCPU ISPCblender: Pabellon Barcelona - CPU-Onlybuild-godot: Time To Compilellama-cpp: llama-2-70b-chat.Q5_0.gguftensorflow: CPU - 256 - GoogLeNetblender: Classroom - CPU-Onlyappleseed: Emilyapache-iotdb: 800 - 100 - 800 - 400apache-iotdb: 800 - 100 - 800 - 400apache-iotdb: 800 - 100 - 800 - 100apache-iotdb: 800 - 100 - 800 - 100tensorflow: CPU - 512 - AlexNetprimesieve: 1e13minibude: OpenMP - BM2minibude: OpenMP - BM2svt-hevc: 1 - Bosphorus 4Kopenradioss: Bird Strike on Windshieldpetsc: Streamsapache-iotdb: 500 - 100 - 800 - 400apache-iotdb: 500 - 100 - 800 - 400tensorflow: CPU - 64 - ResNet-50astcenc: Very Thoroughastcenc: Exhaustivegpaw: Carbon Nanotubeclickhouse: 100M Rows Hits Dataset, Third Runclickhouse: 100M Rows Hits Dataset, Second Runclickhouse: 100M Rows Hits Dataset, First Run / Cold Cacheappleseed: Disney Materialopenssl: RSA4096openssl: RSA4096mariadb: oltp_read_write - 32mariadb: oltp_write_only - 64mariadb: oltp_update_index - 32mariadb: oltp_update_non_index - 32mariadb: oltp_update_non_index - 64mariadb: oltp_read_write - 64mariadb: oltp_update_index - 64mariadb: oltp_write_only - 32securemark: SecureMark-TLSblender: Junkshop - CPU-Onlyappleseed: Material Testerbrl-cad: VGR Performance Metricapache-iotdb: 800 - 100 - 500 - 100apache-iotdb: 800 - 100 - 500 - 100apache-iotdb: 800 - 100 - 500 - 400apache-iotdb: 800 - 100 - 500 - 400apache-iotdb: 500 - 100 - 800 - 100apache-iotdb: 500 - 100 - 800 - 100oidn: RTLightmap.hdr.4096x4096 - CPU-Onlyblender: Fishy Cat - CPU-Onlyopenradioss: Rubber O-Ring Seal Installationjava-jmh: Throughputpytorch: CPU - 64 - ResNet-50specfem3d: Layered Halfspaceonnx: Faster R-CNN R-50-FPN-int8 - CPU - Standardonnx: Faster R-CNN R-50-FPN-int8 - CPU - Standardonnx: GPT-2 - CPU - Standardonnx: GPT-2 - CPU - Standardonnx: bertsquad-12 - CPU - Standardonnx: bertsquad-12 - CPU - Standardspeedb: Read While Writingonnx: ResNet50 v1-12-int8 - CPU - Standardonnx: ResNet50 v1-12-int8 - CPU - Standardopenfoam: drivaerFastback, Small Mesh Size - Execution Timeopenfoam: drivaerFastback, Small Mesh Size - Mesh Timeonnx: super-resolution-10 - CPU - Parallelonnx: super-resolution-10 - CPU - Parallelpgbench: 100 - 500 - Read Only - Average Latencypgbench: 100 - 500 - Read Onlytensorflow: CPU - 256 - AlexNetmysqlslap: 128specfem3d: Water-layered Halfspaceopenradioss: Bumper Beamblender: BMW27 - CPU-Onlyonnx: fcn-resnet101-11 - CPU - Parallelonnx: fcn-resnet101-11 - CPU - Parallelonnx: CaffeNet 12-int8 - CPU - Standardonnx: CaffeNet 12-int8 - CPU - Standardgromacs: MPI CPU - water_GMX50_bareduckdb: IMDBtensorflow: CPU - 32 - ResNet-50avifenc: 0ospray-studio: 3 - 1080p - 32 - Path Tracer - CPUapache-iotdb: 500 - 100 - 500 - 400apache-iotdb: 500 - 100 - 500 - 400build-linux-kernel: defconfigvvenc: Bosphorus 4K - Fastopenssl: ChaCha20-Poly1305openssl: ChaCha20openssl: AES-256-GCMopenssl: AES-128-GCMopenssl: SHA512openssl: SHA256apache-iotdb: 500 - 100 - 500 - 100apache-iotdb: 500 - 100 - 500 - 100cloverleaf: clover_bm64_shortpgbench: 100 - 800 - Read Only - Average Latencypgbench: 100 - 800 - Read Onlynamd: STMV with 1,066,628 Atomsospray: particle_volume/pathtracer/real_timeffmpeg: libx265 - Video On Demandffmpeg: libx265 - Platformospray-studio: 2 - 1080p - 32 - Path Tracer - CPUscylladb: Writesospray-studio: 1 - 1080p - 32 - Path Tracer - CPUffmpeg: libx265 - Uploadeasywave: e2Asean Grid + BengkuluSept2007 Source - 1200openvino: Road Segmentation ADAS FP16-INT8 - CPUopenvino: Road Segmentation ADAS FP16-INT8 - CPUnpb: SP.Cospray: particle_volume/scivis/real_timeopenradioss: Cell Phone Drop Testpgbench: 100 - 500 - Read Write - Average Latencypgbench: 100 - 500 - Read Writepgbench: 100 - 800 - Read Write - Average Latencypgbench: 100 - 800 - Read Writetensorflow: CPU - 64 - GoogLeNetuvg266: Bosphorus 4K - Mediumnpb: BT.Cllamafile: mistral-7b-instruct-v0.2.Q8_0 - CPUllamafile: wizardcoder-python-34b-v1.0.Q6_K - CPUoidn: RT.hdr_alb_nrm.3840x2160 - CPU-Onlyoidn: RT.ldr_alb_nrm.3840x2160 - CPU-Onlyspecfem3d: Homogeneous Halfspacebuild-python: Released Build, PGO + LTO Optimizedmysqlslap: 64mt-dgemm: Sustained Floating-Point Ratecockroach: KV, 50% Reads - 128cockroach: KV, 60% Reads - 128cockroach: KV, 95% Reads - 128m-queens: Time To Solvenumpy: incompact3d: input.i3d 193 Cells Per Directionhpcg: 104 104 104 - 60embree: Pathtracer ISPC - Asian Dragon Objsvt-hevc: 1 - Bosphorus 1080pospray-studio: 3 - 1080p - 16 - Path Tracer - CPUastcenc: Thoroughembree: Pathtracer ISPC - Crownspecfem3d: Tomographic Modelcloverleaf: clover_bmospray: particle_volume/ao/real_timespecfem3d: Mount St. Helenskvazaar: Bosphorus 4K - Mediumapache: 1000nginx: 1000apache: 500nginx: 500nginx: 200onednn: Recurrent Neural Network Training - CPUospray-studio: 3 - 1080p - 1 - Path Tracer - CPUbuild-php: Time To Compileospray-studio: 2 - 1080p - 16 - Path Tracer - CPUavifenc: 2ospray-studio: 1 - 1080p - 16 - Path Tracer - CPUospray-studio: 2 - 1080p - 1 - Path Tracer - CPUembree: Pathtracer ISPC - Asian Dragonpennant: sedovbigospray-studio: 1 - 1080p - 1 - Path Tracer - CPUllama-cpp: llama-2-13b.Q4_0.ggufbuild-ffmpeg: Time To Compileluxcorerender: Danish Mood - CPUcompress-zstd: 19, Long Mode - Decompression Speedcompress-zstd: 19, Long Mode - Compression Speedvvenc: Bosphorus 4K - Fastercoremark: CoreMark Size 666 - Iterations Per Secondonednn: Recurrent Neural Network Inference - CPUnpb: LU.Credis: SET - 500openvino: Machine Translation EN To DE FP16 - CPUopenvino: Machine Translation EN To DE FP16 - CPUcompress-zstd: 19 - Decompression Speedcompress-zstd: 19 - Compression Speedv-ray: CPUy-cruncher: 1Btensorflow: CPU - 32 - GoogLeNetdacapobench: Tradesoapdragonflydb: 10 - 1:100dragonflydb: 10 - 1:10memcached: 1:10memcached: 1:100luxcorerender: Orange Juice - CPUtensorflow: CPU - 64 - AlexNetgraphics-magick: Sharpenopenvino: Face Detection FP16 - CPUopenvino: Face Detection FP16 - CPUluxcorerender: LuxCore Benchmark - CPUcompress-zstd: 8, Long Mode - Decompression Speedcompress-zstd: 8, Long Mode - Compression Speedcompress-zstd: 12 - Decompression Speedcompress-zstd: 12 - Compression Speedopenvino: Face Detection FP16-INT8 - CPUopenvino: Face Detection FP16-INT8 - CPUcompress-zstd: 8 - Decompression Speedcompress-zstd: 8 - Compression Speedminibude: OpenMP - BM1minibude: OpenMP - BM1dacapobench: Apache Tomcatgraphics-magick: Enhancedonnx: Faster R-CNN R-50-FPN-int8 - CPU - Parallelonnx: Faster R-CNN R-50-FPN-int8 - CPU - Parallelonnx: GPT-2 - CPU - Parallelonnx: GPT-2 - CPU - Parallelonnx: yolov4 - CPU - Parallelonnx: yolov4 - CPU - Parallelonnx: bertsquad-12 - CPU - Parallelonnx: bertsquad-12 - CPU - Parallelonnx: yolov4 - CPU - Standardonnx: yolov4 - CPU - Standardluxcorerender: DLSC - CPUonnx: T5 Encoder - CPU - Standardonnx: T5 Encoder - CPU - Standardrawtherapee: Total Benchmark Timeonnx: ArcFace ResNet-100 - CPU - Parallelonnx: ArcFace ResNet-100 - CPU - Parallelopenvino: Person Detection FP32 - CPUopenvino: Person Detection FP32 - CPUonnx: T5 Encoder - CPU - Parallelonnx: T5 Encoder - CPU - Parallelopenvino: Person Detection FP16 - CPUopenvino: Person Detection FP16 - CPUopenvino: Noise Suppression Poconet-Like FP16 - CPUopenvino: Noise Suppression Poconet-Like FP16 - CPUgraphics-magick: Swirlopenvino: Person Vehicle Bike Detection FP16 - CPUopenvino: Person Vehicle Bike Detection FP16 - CPUopenvino: Road Segmentation ADAS FP16 - CPUopenvino: Road Segmentation ADAS FP16 - CPUopenvino: Person Re-Identification Retail FP16 - CPUopenvino: Person Re-Identification Retail FP16 - CPUgraphics-magick: Resizingopenvino: Vehicle Detection FP16-INT8 - CPUopenvino: Vehicle Detection FP16-INT8 - CPUspeedb: Rand Fill Syncspeedb: Rand Fillopenvino: Handwritten English Recognition FP16-INT8 - CPUopenvino: Handwritten English Recognition FP16-INT8 - CPUopenvino: Handwritten English Recognition FP16 - CPUopenvino: Handwritten English Recognition FP16 - CPUopenvino: Face Detection Retail FP16-INT8 - CPUopenvino: Face Detection Retail FP16-INT8 - CPUspeedb: Read Rand Write Randopenvino: Vehicle Detection FP16 - CPUopenvino: Vehicle Detection FP16 - CPUgraphics-magick: Noise-Gaussianopenvino: Weld Porosity Detection FP16 - CPUopenvino: Weld Porosity Detection FP16 - CPUspeedb: Update Randopenvino: Face Detection Retail FP16 - CPUopenvino: Face Detection Retail FP16 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUonnx: CaffeNet 12-int8 - CPU - Parallelonnx: CaffeNet 12-int8 - CPU - Paralleljohn-the-ripper: MD5graphics-magick: HWB Color Spaceopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUgraphics-magick: Rotaterocksdb: Rand Fillopenvino: Age Gender Recognition Retail 0013 FP16 - CPUopenvino: Age Gender Recognition Retail 0013 FP16 - CPUrocksdb: Rand Fill Synconnx: ResNet50 v1-12-int8 - CPU - Parallelonnx: ResNet50 v1-12-int8 - CPU - Parallelspeedb: Rand Readrocksdb: Read Rand Write Randrocksdb: Overwriterocksdb: Update Randrocksdb: Read While Writingjohn-the-ripper: HMAC-SHA512rocksdb: Rand Readbuild-wasmer: Time To Compilenpb: IS.Dz3: 2.smt2namd: ATPase with 327,506 Atomspennant: leblancbigjpegxl: PNG - 90jpegxl: PNG - 100jpegxl: JPEG - 100node-web-tooling: ospray: gravity_spheres_volume/dim_512/ao/real_timejpegxl: JPEG - 90vvenc: Bosphorus 1080p - Fastospray: gravity_spheres_volume/dim_512/scivis/real_timebuild-mesa: Time To Compileospray: gravity_spheres_volume/dim_512/pathtracer/real_timex265: Bosphorus 4Kffmpeg: libx265 - Livesvt-av1: Preset 4 - Bosphorus 4Kaircrack-ng: uvg266: Bosphorus 4K - Very Fastllama-cpp: llama-2-7b.Q4_0.ggufllamafile: llava-v1.5-7b-q4 - CPUaskap: tConvolve OpenMP - Degriddingaskap: tConvolve OpenMP - Griddingcpuminer-opt: Quad SHA-256, Pyritecpuminer-opt: Deepcoindacapobench: H2 Database Enginecpuminer-opt: Triple SHA-256, Onecoinliquid-dsp: 4 - 256 - 512stress-ng: Vector Floating Pointstress-ng: Floating Pointstress-ng: Matrix 3D Mathstress-ng: Vector Shufflestress-ng: System V Message Passingstress-ng: AVX-512 VNNIstress-ng: Wide Vector Mathstress-ng: Fused Multiply-Addstress-ng: x86_64 RdRandstress-ng: CPU Cachecpuminer-opt: Blake-2 Scpuminer-opt: scryptcpuminer-opt: Skeincoincpuminer-opt: Ringcoincpuminer-opt: Myriad-Groestlcpuminer-opt: Magicpuminer-opt: Garlicoincpuminer-opt: LBC, LBRY Creditsastcenc: Fastuvg266: Bosphorus 4K - Super Fastdacapobench: Eclipseminife: Smalljava-scimark2: Compositeprimesieve: 1e12tensorflow: CPU - 32 - AlexNetnpb: SP.Bquantlib: Multi-Threadedkvazaar: Bosphorus 4K - Very Fastuvg266: Bosphorus 4K - Ultra Fasthadoop: Create - 500 - 100000hadoop: Create - 100 - 100000dacapobench: jMonkeyEnginey-cruncher: 500Maskap: tConvolve MT - Degriddingaskap: tConvolve MT - Griddingdacapobench: Tradebeanswebp: Quality 100, Lossless, Highest Compressionjohn-the-ripper: WPA PSKjohn-the-ripper: bcryptjohn-the-ripper: Blowfishliquid-dsp: 16 - 256 - 512liquid-dsp: 16 - 256 - 32liquid-dsp: 2 - 256 - 512liquid-dsp: 8 - 256 - 512liquid-dsp: 2 - 256 - 32liquid-dsp: 8 - 256 - 32liquid-dsp: 4 - 256 - 32liquid-dsp: 1 - 256 - 512liquid-dsp: 1 - 256 - 32dacapobench: Spring Bootpytorch: CPU - 1 - ResNet-50dacapobench: BioJava Biological Data Frameworkkvazaar: Bosphorus 4K - Super Fastincompact3d: input.i3d 129 Cells Per Directiondacapobench: Apache Lucene Search Enginedacapobench: Jythondacapobench: GraphChiastcenc: Mediumdacapobench: Apache Lucene Search Indexluxcorerender: Rainbow Colors and Prism - CPUdacapobench: Apache Kafkaz3: 1.smt2svt-av1: Preset 8 - Bosphorus 4Kuvg266: Bosphorus 1080p - Mediumsvt-av1: Preset 13 - Bosphorus 4Kdacapobench: FOP Print Formatterdacapobench: Avrora AVR Simulation Frameworkdacapobench: PMD Source Code Analyzerdacapobench: Zxing 1D/2D Barcode Image Processinghelsing: 12 digitvvenc: Bosphorus 1080p - Fasteronednn: Deconvolution Batch shapes_1d - CPUsvt-hevc: 7 - Bosphorus 4Kkvazaar: Bosphorus 4K - Ultra Fastkvazaar: Bosphorus 1080p - Mediumquantlib: Single-Threadednpb: CG.Conednn: IP Shapes 1D - CPUdacapobench: Batik SVG Toolkitcompress-7zip: Decompression Ratingcompress-7zip: Compression Ratingsvt-vp9: Visual Quality Optimized - Bosphorus 4Ksvt-vp9: VMAF Optimized - Bosphorus 4Ksrsran: PUSCH Processor Benchmark, Throughput Threadqmcpack: simple-H2Oaskap: tConvolve MPI - Griddingaskap: tConvolve MPI - Degriddingsvt-vp9: PSNR/SSIM Optimized - Bosphorus 4Knpb: EP.Cdacapobench: Apache Xalan XSLTsvt-av1: Preset 4 - Bosphorus 1080pavifenc: 6, Losslesscompress-pbzip2: FreeBSD-13.0-RELEASE-amd64-memstick.img Compressiondolfyn: Computational Fluid Dynamicspybench: Total For Average Test Timessvt-hevc: 10 - Bosphorus 4Knpb: MG.Cx265: Bosphorus 1080ptensorflow: CPU - 1 - ResNet-50webp: Quality 100, Losslessuvg266: Bosphorus 1080p - Very Fasteasywave: e2Asean Grid + BengkuluSept2007 Source - 240avifenc: 6uvg266: Bosphorus 1080p - Super Fastsvt-av1: Preset 12 - Bosphorus 4Konednn: IP Shapes 3D - CPUkvazaar: Bosphorus 1080p - Very Fasttensorflow: CPU - 1 - AlexNetuvg266: Bosphorus 1080p - Ultra Fastrnnoise: 26 Minute Long Talking Samplesvt-av1: Preset 8 - Bosphorus 1080pdraco: Church Facadeonednn: Convolution Batch Shapes Auto - CPUsvt-hevc: 7 - Bosphorus 1080pamg: srsran: PDSCH Processor Benchmark, Throughput Totaloctave-benchmark: build-python: Defaultavifenc: 10, Losslessdraco: Lionkvazaar: Bosphorus 1080p - Super Fastsrsran: PUSCH Processor Benchmark, Throughput Totalkvazaar: Bosphorus 1080p - Ultra Fastsvt-vp9: Visual Quality Optimized - Bosphorus 1080ptensorflow: CPU - 1 - GoogLeNetwebp: Quality 100, Highest Compressionlammps: Rhodopsin Proteinsvt-vp9: VMAF Optimized - Bosphorus 1080psvt-vp9: PSNR/SSIM Optimized - Bosphorus 1080plulesh: svt-hevc: 10 - Bosphorus 1080ponednn: Deconvolution Batch shapes_3d - CPUsrsran: PDSCH Processor Benchmark, Throughput Threadsvt-av1: Preset 13 - Bosphorus 1080pwebp: Quality 100svt-av1: Preset 12 - Bosphorus 1080pwebp: Defaultheffte: r2c - FFTW - double - 128heffte: r2c - FFTW - float - 128java-scimark2: Dense LU Matrix Factorizationjava-scimark2: Monte Carlojava-scimark2: Jacobi Successive Over-Relaxationjava-scimark2: Fast Fourier TransformEPYC 4124P @ DDR5-5200smoke19.06766.32563.9143645.543387.883091914.774.7801462.6019.241444.3081262.9101240.856740.56153.1710622485786.89787.863167648.21618.8700.9253.07519.82514.704373860.7534724489216.4036052182123.63300.41012.937323.4231.52390.3015733.6488531.884535542919.110.70140.4294318.666168.41165.39155.72303.42856196458.73738.58507814265111631313146511334890232101087189593423994282.78281.666315115653109.5243934008406.0645117852167.03448284350.12256.10254.8819260371856.72523.04237.97918709219.450651.86188.40332119.46095.953510.4960514777675.18098193.845432.882950.90303721.476246.59432.553195905121.85449214.487508701210.60206.181175.760.8711562.07796481.4860.914152.67519.01187.641177735346.6545226559182.4563.3112368605898733291996640562917695506597453469028874161578928463007103.0245065837176.224.4091815320.27425105.66351.0751.111521875524914991424.42155.66428.43140.599840.132.33176138.7225.7831939350.9711569752.844.4722316.956.401.810.240.24112.866423691233.2688782.16179530433.231458.938555.5105.302710.18104.2181816.902827.83646.11908855.12067.838390.58281309492.422.3390789.4764856386.6448650.3041180.8153643.8645317.1647788.244388.64547285.8047790785.3897637946629.294880.1054545846.1779.5840.811810.39.007.742254797.5716412274.0526610.493976817.0290.3344.271904.714.91123843.94752.8320652629939.842629619.361117437.501068869.522.21113.02161135.613.511.012219.1323.02285.3114.3585.236.812206.8330.312.914322.862128402623.787442.03649.29245107.583202.8294.93035153.1526.53046136.3817.332311.417.03171142.20560.10867.471514.8208126.5031.597.42079134.738126.0631.718.26479.347210.18391.8937.30107.087.96500.051429.68412.377778175861622.24179.6421.51185.853.231232.02132368517.46228.814411.43349.324143354.53879.055.80686.872.37635420.7019860941900.2913170.121588629310.49649.23512675.73293174.4093582930012199688639964789801135261607986673488563359.4661207.1056.8590.8967854.7848422.2388.9998.95919.491.9586222.70711.4251.9450451.9682.3472611.66141.033.26323895.27513.1411.7810.572841.951801.15144472205.103438253377273080014008.642137.331960.754319.587212479.03681157.03209322.7415250467.412048750.683426267.823781083.299066.90944.973016.70168.37851.654228.17101.366913.8571097710.505276.0824.496100.579885.3222228.016.8216.865428466234681619.8001930.031327.1430500.78426001181811819106960000371713333369993331071833331003200003715366672003400001820766750277333257141.09450220.7528.406310438543913319439.856025995.95509725.71024.87224.2968.4655582486182420337.60927.3547.4227229.8228.7536.104281.87548.433.817531002451895615535.8545.96183.417.0473226.622623.9647.01781.2478212.18213.44711.09742010.97555261.0817132.7058.6212.182.0261.197.5569.47163.9668.8415.0336775.9714.5677.357.52586.46857089.0554693.013528494174054.65.88023.2045.710425392.91881.5126.17127.2339.385.054.618154.14155.851832.9940192.927.512861023.8384.17315.73313.42725.5817.247644.089417467.362487.912281.43353.8419.062605.8453712.4431387.03421923.654.7271461.5419.251454.831267.911242.82353.17790.15790.958167652.53620.3330.9453.09523.73511.479714877.3634038308224.6334807635123.9212.937323.4171.52387.1815935.1677550.434373199819.120.70010.429320.787167.40162.78154.32304.02459796005.83705.98422514254011667613299911521190208100223190255425060284.11281.365607114316113.3542629139413.8444005866169.95440427260.12258.36257.7823.34241.06375791323.900141.83628.03895124.3291.745510.899315248025.00552199.732422.517650.44233221.165547.24482.477201890121.97447216.893616069214.44208.341595.550.6267432.05766485.8470.91319187.696178542359.5243591311185.1823.2932371688666033253021830562942530906593246003028769651208909109090107.6543525563176.624.4231808810.27290107.48350.9650.931530065510514975124.34155.98128.77138.849837.142.33489139.0926.1241913950.9421570452.734.4422215.396.361.820.240.24116.671964064234.1248732.12796630471.731514.139041.2107.095711.32104.0388876.975177.8386.09913865.1057.801491.89357869392.652.3328691.0415713566.5848039.1542274.3356841.6246111.8648555.154389.74549786.537852285.5917712346869.275379.8557945916.6580.310.871785.48.97.697251757.0544422268.5626772.723982548.2591.4243.731895151118352.792634894.242598346.061112711.411061151.622.21112.77161134.753.5112234322.52263.7115.3581.536.852230.633312.909322.7322623.963441.7289.23953108.197206.5094.84234155.4556.43266136.157.34471.417.58396131.80460.04777.520112.8998125.8131.777.42529134.659126.4731.598.24480.277310.15393.1337.49106.557.99498.311439.66412.867568376248221.05189.922.32179.053.221233.45131396717.38229.764411.43349.24091904.5884.845.81686.262.37296421.2949835001950.312876.121608470990.49665.38510885.80287172.3063577409411824548636804755861107321607960003488205460.1111202.8756.3720.8875654.6622722.2128.9758.95120.011.964322.91811.371.943252.5882.3401511.52140.453.26713.1111.7710.682894.091875.0474827000101.103713.817731.49100.069844.5422101.216.7716.7554585650621855.441311.610.7842496117811175710654000037034000031179000106850000100430000370560000200250000185480005029300041.0420.7128.426965739.68676.0125.64124.95724.1463.3427.1927.1899529.7228.735.9642307555.243.81404451745624534.9245.7183.417.413199.952572.5147.09784.1712.2113.4311.19626110.96754661.1417172.1558.3512.232.0361.217.529.50763.968.9855.0422675.8414.676.667.56686.31656939.0328992.283529630004061.95.91423.4445.714424092.78852.8126.24123.9339.045.064.585154.06155.981846.39521927.513451039.4319.29115.79314.70525.6416.791735.9765OpenBenchmarking.org

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.

Test: Savina Reactors.IO

EPYC 4124P @ DDR5-5200: The test quit with a non-zero exit status. The test run did not produce a result. E: sh: 1: exec: ./renaissance: not found

TensorFlow

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 512 - Model: ResNet-50EPYC 4124P @ DDR5-5200smoke510152025SE +/- 0.01, N = 319.0619.06
OpenBenchmarking.orgimages/sec Per Watt, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 512 - Model: ResNet-50EPYC 4124P @ DDR5-5200smoke0.07040.14080.21120.28160.3520.3130.311
OpenBenchmarking.orgMegahertz, More Is BetterTensorFlow 2.16.1CPU Peak Freq (Highest CPU Core Frequency) MonitorEPYC 4124P @ DDR5-5200smoke9001800270036004500Min: 400 / Avg: 4935.69 / Max: 5141Min: 400 / Avg: 4930.31 / Max: 5140
OpenBenchmarking.orgWatts, Fewer Is BetterTensorFlow 2.16.1CPU Power Consumption MonitorEPYC 4124P @ DDR5-5200smoke1326395265Min: 16.79 / Avg: 60.86 / Max: 68.58Min: 16.34 / Avg: 61.33 / Max: 68.71. EPYC 4124P @ DDR5-5200: Approximate power consumption of 32116 Joules per run.
OpenBenchmarking.orgCelsius, Fewer Is BetterTensorFlow 2.16.1CPU Temperature MonitorEPYC 4124P @ DDR5-5200smoke1326395265Min: 41.38 / Avg: 59.76 / Max: 64.25Min: 42.5 / Avg: 62.08 / Max: 65.88
OpenBenchmarking.orgWatts, Fewer Is BetterTensorFlow 2.16.1System Power Consumption MonitorEPYC 4124P @ DDR5-5200smoke20406080100Min: 53.2 / Avg: 102.8 / Max: 117Min: 54.6 / Avg: 103.78 / Max: 117.21. EPYC 4124P @ DDR5-5200: Approximate power consumption of 54519 Joules per run.
OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 512 - Model: ResNet-50EPYC 4124P @ DDR5-5200smoke510152025Min: 19.04 / Avg: 19.06 / Max: 19.08

Xmrig

Xmrig is an open-source cross-platform CPU/GPU miner for RandomX, KawPow, CryptoNight and AstroBWT. This test profile is setup to measure the Xmrig CPU mining performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.21Variant: GhostRider - Hash Count: 1MEPYC 4124P @ DDR5-5200170340510680850SE +/- 9.65, N = 2766.31. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
OpenBenchmarking.orgH/s Per Watt, More Is BetterXmrig 6.21Variant: GhostRider - Hash Count: 1MEPYC 4124P @ DDR5-52004812162017.23
MinAvgMaxEPYC 4124P @ DDR5-520040050805141OpenBenchmarking.orgMegahertz, More Is BetterXmrig 6.21CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.144.545.5OpenBenchmarking.orgWatts, Fewer Is BetterXmrig 6.21CPU Power Consumption Monitor12243648601. EPYC 4124P @ DDR5-5200: Approximate power consumption of 20637 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520037.848.751.0OpenBenchmarking.orgCelsius, Fewer Is BetterXmrig 6.21CPU Temperature Monitor1530456075
MinAvgMaxEPYC 4124P @ DDR5-520054.081.682.5OpenBenchmarking.orgWatts, Fewer Is BetterXmrig 6.21System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 37985 Joules per run.

Timed Linux Kernel Compilation

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 6.8Build: allmodconfigEPYC 4124P @ DDR5-5200smoke6001200180024003000SE +/- 0.88, N = 32563.912605.85
OpenBenchmarking.orgMegahertz, More Is BetterTimed Linux Kernel Compilation 6.8CPU Peak Freq (Highest CPU Core Frequency) MonitorEPYC 4124P @ DDR5-5200smoke9001800270036004500Min: 4943 / Avg: 5063.98 / Max: 5141Min: 4941 / Avg: 5057 / Max: 5141
OpenBenchmarking.orgWatts, Fewer Is BetterTimed Linux Kernel Compilation 6.8CPU Power Consumption MonitorEPYC 4124P @ DDR5-5200smoke1530456075Min: 21.6 / Avg: 75.16 / Max: 77.12Min: 19.04 / Avg: 74.57 / Max: 76.621. EPYC 4124P @ DDR5-5200: Approximate power consumption of 34422 Joules per run.
OpenBenchmarking.orgCelsius, Fewer Is BetterTimed Linux Kernel Compilation 6.8CPU Temperature MonitorEPYC 4124P @ DDR5-5200smoke1530456075Min: 46.88 / Avg: 74.18 / Max: 76.63Min: 43.75 / Avg: 74.74 / Max: 76.63
OpenBenchmarking.orgWatts, Fewer Is BetterTimed Linux Kernel Compilation 6.8System Power Consumption MonitorEPYC 4124P @ DDR5-5200smoke20406080100Min: 53.8 / Avg: 119.47 / Max: 121.1Min: 54.6 / Avg: 119.2 / Max: 120.51. EPYC 4124P @ DDR5-5200: Approximate power consumption of 55076 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 6.8Build: allmodconfigEPYC 4124P @ DDR5-5200smoke5001000150020002500Min: 2562.18 / Avg: 2563.91 / Max: 2565.08

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 TimeEPYC 4124P @ DDR5-5200smoke80016002400320040003645.543712.441. (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
MinAvgMaxEPYC 4124P @ DDR5-5200477650675172smoke476250665170OpenBenchmarking.orgMegahertz, More Is BetterOpenFOAM 10CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.551.367.0smoke17.152.767.4OpenBenchmarking.orgWatts, Fewer Is BetterOpenFOAM 10CPU Power Consumption Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520039.653.974.9smoke45.061.478.0OpenBenchmarking.orgCelsius, Fewer Is BetterOpenFOAM 10CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.194.1113.1smoke54.997.1116.1OpenBenchmarking.orgWatts, Fewer Is BetterOpenFOAM 10System Power Consumption Monitor4080120160200

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 10Input: drivaerFastback, Medium Mesh Size - Mesh TimeEPYC 4124P @ DDR5-5200smoke80160240320400387.88387.031. (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

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.1Blend File: Barbershop - Compute: CPU-OnlyEPYC 4124P @ DDR5-5200smoke400800120016002000SE +/- 1.15, N = 31914.771923.65
MinAvgMaxEPYC 4124P @ DDR5-520040050475140smoke40050145085OpenBenchmarking.orgMegahertz, More Is BetterBlender 4.1CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.477.078.1smoke16.776.377.5OpenBenchmarking.orgWatts, Fewer Is BetterBlender 4.1CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 26296 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520044.574.779.8smoke46.875.379.4OpenBenchmarking.orgCelsius, Fewer Is BetterBlender 4.1CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520055.5122.1122.9smoke55.3121.7122.3OpenBenchmarking.orgWatts, Fewer Is BetterBlender 4.1System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 41946 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.1Blend File: Barbershop - Compute: CPU-OnlyEPYC 4124P @ DDR5-5200smoke30060090012001500Min: 1913.3 / Avg: 1914.77 / Max: 1917.03

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: 20k AtomsEPYC 4124P @ DDR5-5200smoke1.07552.1513.22654.3025.3775SE +/- 0.008, N = 34.7804.7271. (CXX) g++ options: -O3 -lm -ldl
OpenBenchmarking.orgns/day Per Watt, More Is BetterLAMMPS Molecular Dynamics Simulator 23Jun2022Model: 20k AtomsEPYC 4124P @ DDR5-5200smoke0.01460.02920.04380.05840.0730.0640.065
MinAvgMaxEPYC 4124P @ DDR5-5200494151135145smoke40050305100OpenBenchmarking.orgMegahertz, More Is BetterLAMMPS Molecular Dynamics Simulator 23Jun2022CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520015.974.275.6smoke16.472.273.9OpenBenchmarking.orgWatts, Fewer Is BetterLAMMPS Molecular Dynamics Simulator 23Jun2022CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 23841 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520041.569.970.8smoke45.074.374.9OpenBenchmarking.orgCelsius, Fewer Is BetterLAMMPS Molecular Dynamics Simulator 23Jun2022CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.0115.6116.7smoke55.3114.9115.8OpenBenchmarking.orgWatts, Fewer Is BetterLAMMPS Molecular Dynamics Simulator 23Jun2022System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 37384 Joules per run.
OpenBenchmarking.orgns/day, More Is BetterLAMMPS Molecular Dynamics Simulator 23Jun2022Model: 20k AtomsEPYC 4124P @ DDR5-5200smoke246810Min: 4.76 / Avg: 4.78 / Max: 4.791. (CXX) g++ options: -O3 -lm -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: Chrysler Neon 1MEPYC 4124P @ DDR5-5200smoke30060090012001500SE +/- 1.90, N = 31462.601461.54
MinAvgMaxEPYC 4124P @ DDR5-520040050845169smoke40050825148OpenBenchmarking.orgMegahertz, More Is BetterOpenRadioss 2023.09.15CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.457.659.2smoke16.160.264.4OpenBenchmarking.orgWatts, Fewer Is BetterOpenRadioss 2023.09.15CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 15173 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520040.556.959.5smoke45.864.069.8OpenBenchmarking.orgCelsius, Fewer Is BetterOpenRadioss 2023.09.15CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.3100.3104.7smoke55.5104.9107.4OpenBenchmarking.orgWatts, Fewer Is BetterOpenRadioss 2023.09.15System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 26542 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2023.09.15Model: Chrysler Neon 1MEPYC 4124P @ DDR5-5200smoke30060090012001500Min: 1459.42 / Avg: 1462.6 / Max: 1465.99

TensorFlow

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 256 - Model: ResNet-50EPYC 4124P @ DDR5-5200smoke510152025SE +/- 0.00, N = 319.2419.25
OpenBenchmarking.orgimages/sec Per Watt, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 256 - Model: ResNet-50EPYC 4124P @ DDR5-5200smoke0.07070.14140.21210.28280.35350.3140.312
MinAvgMaxEPYC 4124P @ DDR5-520040049275141smoke40049215136OpenBenchmarking.orgMegahertz, More Is BetterTensorFlow 2.16.1CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.061.267.5smoke17.161.768.0OpenBenchmarking.orgWatts, Fewer Is BetterTensorFlow 2.16.1CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 16071 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520041.960.664.1smoke43.063.366.6OpenBenchmarking.orgCelsius, Fewer Is BetterTensorFlow 2.16.1CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.7103.4114.9smoke54.1104.7115.7OpenBenchmarking.orgWatts, Fewer Is BetterTensorFlow 2.16.1System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 27252 Joules per run.
OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 256 - Model: ResNet-50EPYC 4124P @ DDR5-5200smoke510152025Min: 19.23 / Avg: 19.24 / Max: 19.24

Timed Node.js Compilation

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Node.js Compilation 21.7.2Time To CompileEPYC 4124P @ DDR5-5200smoke30060090012001500SE +/- 0.89, N = 31444.311454.83
MinAvgMaxEPYC 4124P @ DDR5-5200494151225142smoke40050945141OpenBenchmarking.orgMegahertz, More Is BetterTimed Node.js Compilation 21.7.2CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520023.166.275.8smoke17.066.175.4OpenBenchmarking.orgWatts, Fewer Is BetterTimed Node.js Compilation 21.7.2CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 17000 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520049.969.276.5smoke42.570.676.6OpenBenchmarking.orgCelsius, Fewer Is BetterTimed Node.js Compilation 21.7.2CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.7108.9119.2smoke67.1110.0119.1OpenBenchmarking.orgWatts, Fewer Is BetterTimed Node.js Compilation 21.7.2System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 28108 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Node.js Compilation 21.7.2Time To CompileEPYC 4124P @ DDR5-5200smoke30060090012001500Min: 1442.56 / Avg: 1444.31 / Max: 1445.43

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 MakefilesEPYC 4124P @ DDR5-5200smoke30060090012001500SE +/- 1.10, N = 31262.911267.91
MinAvgMaxEPYC 4124P @ DDR5-5200486951065143smoke494150985141OpenBenchmarking.orgMegahertz, More Is BetterTimed LLVM Compilation 16.0CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520022.069.874.5smoke16.869.873.4OpenBenchmarking.orgWatts, Fewer Is BetterTimed LLVM Compilation 16.0CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 15857 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520046.172.180.3smoke45.373.079.5OpenBenchmarking.orgCelsius, Fewer Is BetterTimed LLVM Compilation 16.0CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520053.5113.7119.0smoke54.9114.3119.4OpenBenchmarking.orgWatts, Fewer Is BetterTimed LLVM Compilation 16.0System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 26035 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 16.0Build System: Unix MakefilesEPYC 4124P @ DDR5-5200smoke2004006008001000Min: 1261.63 / Avg: 1262.91 / Max: 1265.09

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 16.0Build System: NinjaEPYC 4124P @ DDR5-5200smoke30060090012001500SE +/- 0.99, N = 31240.861242.82
MinAvgMaxEPYC 4124P @ DDR5-5200456851045140smoke494250945141OpenBenchmarking.orgMegahertz, More Is BetterTimed LLVM Compilation 16.0CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520021.270.875.2smoke22.370.574.6OpenBenchmarking.orgWatts, Fewer Is BetterTimed LLVM Compilation 16.0CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 15850 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520048.372.281.8smoke50.573.380.4OpenBenchmarking.orgCelsius, Fewer Is BetterTimed LLVM Compilation 16.0CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520053.9114.7118.2smoke53.8115.0118.1OpenBenchmarking.orgWatts, Fewer Is BetterTimed LLVM Compilation 16.0System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 25843 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 16.0Build System: NinjaEPYC 4124P @ DDR5-5200smoke2004006008001000Min: 1239.07 / Avg: 1240.86 / Max: 1242.49

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 digitEPYC 4124P @ DDR5-5200160320480640800SE +/- 0.11, N = 3740.561. (CC) gcc options: -O2 -pthread
MinAvgMaxEPYC 4124P @ DDR5-520040049344966OpenBenchmarking.orgMegahertz, More Is BetterHelsing 1.0-betaCPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.180.683.7OpenBenchmarking.orgWatts, Fewer Is BetterHelsing 1.0-betaCPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 10645 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520041.681.381.6OpenBenchmarking.orgCelsius, Fewer Is BetterHelsing 1.0-betaCPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.6125.1127.3OpenBenchmarking.orgWatts, Fewer Is BetterHelsing 1.0-betaSystem Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 16635 Joules per run.

TensorFlow

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 512 - Model: GoogLeNetEPYC 4124P @ DDR5-5200smoke1224364860SE +/- 0.02, N = 353.1753.17
OpenBenchmarking.orgimages/sec Per Watt, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 512 - Model: GoogLeNetEPYC 4124P @ DDR5-5200smoke0.20270.40540.60810.81081.01350.9010.893
MinAvgMaxEPYC 4124P @ DDR5-520040049285141smoke40049205140OpenBenchmarking.orgMegahertz, More Is BetterTensorFlow 2.16.1CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.759.061.5smoke15.759.662.0OpenBenchmarking.orgWatts, Fewer Is BetterTensorFlow 2.16.1CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 11052 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520038.955.957.5smoke41.858.860.5OpenBenchmarking.orgCelsius, Fewer Is BetterTensorFlow 2.16.1CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520053.399.4103.0smoke53.9100.6104.3OpenBenchmarking.orgWatts, Fewer Is BetterTensorFlow 2.16.1System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 18724 Joules per run.
OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 512 - Model: GoogLeNetEPYC 4124P @ DDR5-5200smoke1122334455Min: 53.15 / Avg: 53.17 / Max: 53.2

Stockfish

OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 16.1Chess BenchmarkEPYC 4124P @ DDR5-52002M4M6M8M10MSE +/- 100541.00, N = 15106224851. (CXX) g++ options: -lgcov -m64 -lpthread -fno-exceptions -std=c++17 -fno-peel-loops -fno-tracer -pedantic -O3 -funroll-loops -msse -msse3 -mpopcnt -mavx2 -mbmi -mavx512f -mavx512bw -mavx512vnni -mavx512dq -mavx512vl -msse4.1 -mssse3 -msse2 -mbmi2 -flto -flto-partition=one -flto=jobserver
OpenBenchmarking.orgNodes Per Second Per Watt, More Is BetterStockfish 16.1Chess BenchmarkEPYC 4124P @ DDR5-520030K60K90K120K150K124222.60
MinAvgMaxEPYC 4124P @ DDR5-520040049135066OpenBenchmarking.orgMegahertz, More Is BetterStockfish 16.1CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520021.285.590.5OpenBenchmarking.orgWatts, Fewer Is BetterStockfish 16.1CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1682 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520043.876.978.9OpenBenchmarking.orgCelsius, Fewer Is BetterStockfish 16.1CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520055.4132.8139.4OpenBenchmarking.orgWatts, Fewer Is BetterStockfish 16.1System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 2629 Joules per run.

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 ContainerEPYC 4124P @ DDR5-5200smoke2004006008001000SE +/- 1.30, N = 3786.89790.15
MinAvgMaxEPYC 4124P @ DDR5-5200494151355167smoke40050945178OpenBenchmarking.orgMegahertz, More Is BetterOpenRadioss 2023.09.15CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.865.166.4smoke17.067.168.5OpenBenchmarking.orgWatts, Fewer Is BetterOpenRadioss 2023.09.15CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 9173 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520041.462.569.3smoke45.569.274.4OpenBenchmarking.orgCelsius, Fewer Is BetterOpenRadioss 2023.09.15CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.8107.3108.5smoke55.4111.1112.5OpenBenchmarking.orgWatts, Fewer Is BetterOpenRadioss 2023.09.15System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 15241 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2023.09.15Model: INIVOL and Fluid Structure Interaction Drop ContainerEPYC 4124P @ DDR5-5200smoke140280420560700Min: 784.66 / Avg: 786.89 / Max: 789.17

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 CompileEPYC 4124P @ DDR5-5200smoke2004006008001000SE +/- 0.48, N = 3787.86790.96
MinAvgMaxEPYC 4124P @ DDR5-520040051015144smoke494150965140OpenBenchmarking.orgMegahertz, More Is BetterTimed Gem5 Compilation 23.0.1CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.268.574.2smoke17.268.073.7OpenBenchmarking.orgWatts, Fewer Is BetterTimed Gem5 Compilation 23.0.1CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 9711 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520042.570.176.8smoke43.571.276.6OpenBenchmarking.orgCelsius, Fewer Is BetterTimed Gem5 Compilation 23.0.1CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.9112.0118.0smoke54.2111.7117.9OpenBenchmarking.orgWatts, Fewer Is BetterTimed Gem5 Compilation 23.0.1System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 15906 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Gem5 Compilation 23.0.1Time To CompileEPYC 4124P @ DDR5-5200smoke140280420560700Min: 787.12 / Avg: 787.86 / Max: 788.77

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 ISPCEPYC 4124P @ DDR5-5200smoke4080120160200SE +/- 0.00, N = 3167167MIN: 12 / MAX: 2373MIN: 12 / MAX: 2361
OpenBenchmarking.orgItems / Sec Per Watt, More Is BetterOpenVKL 2.0.0Benchmark: vklBenchmarkCPU ISPCEPYC 4124P @ DDR5-5200smoke0.58661.17321.75982.34642.9332.6072.598
MinAvgMaxEPYC 4124P @ DDR5-520040050555142smoke471650535141OpenBenchmarking.orgMegahertz, More Is BetterOpenVKL 2.0.0CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.364.179.9smoke32.464.379.0OpenBenchmarking.orgWatts, Fewer Is BetterOpenVKL 2.0.0CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 7623 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520042.467.876.0smoke47.169.077.0OpenBenchmarking.orgCelsius, Fewer Is BetterOpenVKL 2.0.0CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.6105.2123.7smoke54.8106.7122.6OpenBenchmarking.orgWatts, Fewer Is BetterOpenVKL 2.0.0System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 12628 Joules per run.
OpenBenchmarking.orgItems / Sec, More Is BetterOpenVKL 2.0.0Benchmark: vklBenchmarkCPU ISPCEPYC 4124P @ DDR5-5200smoke306090120150Min: 167 / Avg: 167 / Max: 167

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.1Blend File: Pabellon Barcelona - Compute: CPU-OnlyEPYC 4124P @ DDR5-5200smoke140280420560700SE +/- 0.83, N = 3648.21652.53
MinAvgMaxEPYC 4124P @ DDR5-520040049785066smoke495349765054OpenBenchmarking.orgMegahertz, More Is BetterBlender 4.1CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.079.681.2smoke26.478.279.7OpenBenchmarking.orgWatts, Fewer Is BetterBlender 4.1CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 9230 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520043.976.677.5smoke68.178.378.9OpenBenchmarking.orgCelsius, Fewer Is BetterBlender 4.1CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520056.2124.1125.1smoke55.4122.9124.0OpenBenchmarking.orgWatts, Fewer Is BetterBlender 4.1System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 14515 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.1Blend File: Pabellon Barcelona - Compute: CPU-OnlyEPYC 4124P @ DDR5-5200smoke120240360480600Min: 647.09 / Avg: 648.21 / Max: 649.83

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 CompileEPYC 4124P @ DDR5-5200smoke130260390520650SE +/- 0.23, N = 3618.87620.33
MinAvgMaxEPYC 4124P @ DDR5-5200494150925142smoke494050705141OpenBenchmarking.orgMegahertz, More Is BetterTimed Godot Game Engine Compilation 4.0CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520018.271.476.1smoke16.470.374.9OpenBenchmarking.orgWatts, Fewer Is BetterTimed Godot Game Engine Compilation 4.0CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 7906 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520044.372.176.3smoke43.673.477.5OpenBenchmarking.orgCelsius, Fewer Is BetterTimed Godot Game Engine Compilation 4.0CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520053.5115.1119.6smoke65.0115.4119.6OpenBenchmarking.orgWatts, Fewer Is BetterTimed Godot Game Engine Compilation 4.0System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 12853 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Godot Game Engine Compilation 4.0Time To CompileEPYC 4124P @ DDR5-5200smoke110220330440550Min: 618.47 / Avg: 618.87 / Max: 619.27

Llama.cpp

Llama.cpp is a port of Facebook's LLaMA model in C/C++ developed by Georgi Gerganov. Llama.cpp allows the inference of LLaMA and other supported models in C/C++. For CPU inference Llama.cpp supports AVX2/AVX-512, ARM NEON, and other modern ISAs along with features like OpenBLAS usage. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b1808Model: llama-2-70b-chat.Q5_0.ggufEPYC 4124P @ DDR5-5200smoke0.21150.4230.63450.8461.0575SE +/- 0.00, N = 30.920.941. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -march=native -mtune=native -lopenblas
OpenBenchmarking.orgTokens Per Second Per Watt, More Is BetterLlama.cpp b1808Model: llama-2-70b-chat.Q5_0.ggufEPYC 4124P @ DDR5-5200smoke0.00360.00720.01080.01440.0180.0160.016
MinAvgMaxEPYC 4124P @ DDR5-520040049074983smoke40049045141OpenBenchmarking.orgMegahertz, More Is BetterLlama.cpp b1808CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.957.866.1smoke15.758.567.2OpenBenchmarking.orgWatts, Fewer Is BetterLlama.cpp b1808CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 5840 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520040.449.658.9smoke42.452.761.3OpenBenchmarking.orgCelsius, Fewer Is BetterLlama.cpp b1808CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520053.7101.1104.7smoke54.3102.2105.6OpenBenchmarking.orgWatts, Fewer Is BetterLlama.cpp b1808System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 10242 Joules per run.
OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b1808Model: llama-2-70b-chat.Q5_0.ggufEPYC 4124P @ DDR5-5200smoke246810Min: 0.91 / Avg: 0.92 / Max: 0.921. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -march=native -mtune=native -lopenblas

TensorFlow

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 256 - Model: GoogLeNetEPYC 4124P @ DDR5-5200smoke1224364860SE +/- 0.00, N = 353.0753.09
OpenBenchmarking.orgimages/sec Per Watt, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 256 - Model: GoogLeNetEPYC 4124P @ DDR5-5200smoke0.20180.40360.60540.80721.0090.8940.897
MinAvgMaxEPYC 4124P @ DDR5-520040049265140smoke40048985141OpenBenchmarking.orgMegahertz, More Is BetterTensorFlow 2.16.1CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.059.461.1smoke16.359.261.2OpenBenchmarking.orgWatts, Fewer Is BetterTensorFlow 2.16.1CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 5643 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520041.358.259.5smoke43.459.460.5OpenBenchmarking.orgCelsius, Fewer Is BetterTensorFlow 2.16.1CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520053.9100.2101.4smoke54.2100.7101.8OpenBenchmarking.orgWatts, Fewer Is BetterTensorFlow 2.16.1System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 9590 Joules per run.
OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 256 - Model: GoogLeNetEPYC 4124P @ DDR5-5200smoke1122334455Min: 53.07 / Avg: 53.07 / Max: 53.08

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.1Blend File: Classroom - Compute: CPU-OnlyEPYC 4124P @ DDR5-5200smoke110220330440550SE +/- 0.71, N = 3519.82523.73
MinAvgMaxEPYC 4124P @ DDR5-5200494050165054smoke493949794991OpenBenchmarking.orgMegahertz, More Is BetterBlender 4.1CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.578.880.5smoke16.676.878.5OpenBenchmarking.orgWatts, Fewer Is BetterBlender 4.1CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 7278 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520043.075.976.4smoke47.078.078.5OpenBenchmarking.orgCelsius, Fewer Is BetterBlender 4.1CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.9121.8122.9smoke54.6120.2121.9OpenBenchmarking.orgWatts, Fewer Is BetterBlender 4.1System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 11327 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.1Blend File: Classroom - Compute: CPU-OnlyEPYC 4124P @ DDR5-5200smoke90180270360450Min: 518.78 / Avg: 519.82 / Max: 521.19

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: EmilyEPYC 4124P @ DDR5-5200smoke110220330440550514.70511.48
MinAvgMaxEPYC 4124P @ DDR5-5200494050375138smoke494050515139OpenBenchmarking.orgMegahertz, More Is BetterAppleseed 2.0 BetaCPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.674.176.4smoke16.874.576.9OpenBenchmarking.orgWatts, Fewer Is BetterAppleseed 2.0 BetaCPU Power Consumption Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520045.475.777.4smoke44.575.376.9OpenBenchmarking.orgCelsius, Fewer Is BetterAppleseed 2.0 BetaCPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.8117.8120.5smoke54.4118.3120.6OpenBenchmarking.orgWatts, Fewer Is BetterAppleseed 2.0 BetaSystem Power Consumption Monitor4080120160200

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: 400EPYC 4124P @ DDR5-5200smoke2004006008001000SE +/- 6.01, N = 3860.75877.36MAX: 28570.46MAX: 27805.56
MinAvgMaxEPYC 4124P @ DDR5-520040048865141smoke40046295140OpenBenchmarking.orgMegahertz, More Is BetterApache IoTDB 1.2CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.867.680.0smoke16.766.377.2OpenBenchmarking.orgWatts, Fewer Is BetterApache IoTDB 1.2CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 6531 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520042.073.077.9smoke46.475.079.8OpenBenchmarking.orgCelsius, Fewer Is BetterApache IoTDB 1.2CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.8114.0128.9smoke55.5113.2124.3OpenBenchmarking.orgWatts, Fewer Is BetterApache IoTDB 1.2System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 11091 Joules per run.
OpenBenchmarking.orgAverage Latency, Fewer Is BetterApache IoTDB 1.2Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 400EPYC 4124P @ DDR5-5200smoke150300450600750Min: 850.99 / Avg: 860.75 / Max: 871.71

OpenBenchmarking.orgpoint/sec, More Is BetterApache IoTDB 1.2Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 400EPYC 4124P @ DDR5-5200smoke7M14M21M28M35MSE +/- 143283.84, N = 33472448934038308
OpenBenchmarking.orgpoint/sec, More Is BetterApache IoTDB 1.2Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 400EPYC 4124P @ DDR5-5200smoke6M12M18M24M30MMin: 34559756.72 / Avg: 34724489.45 / Max: 35009927.54

OpenBenchmarking.orgAverage Latency, Fewer Is BetterApache IoTDB 1.2Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 100EPYC 4124P @ DDR5-5200smoke50100150200250SE +/- 0.96, N = 3216.40224.63MAX: 24148.64MAX: 24308.93
MinAvgMaxEPYC 4124P @ DDR5-520040048715141smoke40047405140OpenBenchmarking.orgMegahertz, More Is BetterApache IoTDB 1.2CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520018.866.577.7smoke17.664.674.5OpenBenchmarking.orgWatts, Fewer Is BetterApache IoTDB 1.2CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 6160 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520041.373.078.1smoke46.074.579.9OpenBenchmarking.orgCelsius, Fewer Is BetterApache IoTDB 1.2CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520055.5112.6122.7smoke57.8112.2121.6OpenBenchmarking.orgWatts, Fewer Is BetterApache IoTDB 1.2System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 10506 Joules per run.
OpenBenchmarking.orgAverage Latency, Fewer Is BetterApache IoTDB 1.2Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 100EPYC 4124P @ DDR5-5200smoke4080120160200Min: 214.84 / Avg: 216.4 / Max: 218.15

OpenBenchmarking.orgpoint/sec, More Is BetterApache IoTDB 1.2Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 100EPYC 4124P @ DDR5-5200smoke8M16M24M32M40MSE +/- 161259.81, N = 33605218234807635
OpenBenchmarking.orgpoint/sec, More Is BetterApache IoTDB 1.2Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 100EPYC 4124P @ DDR5-5200smoke6M12M18M24M30MMin: 35783866.87 / Avg: 36052181.89 / Max: 36341321.55

TensorFlow

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 512 - Model: AlexNetEPYC 4124P @ DDR5-5200smoke306090120150SE +/- 0.05, N = 3123.63123.92
OpenBenchmarking.orgimages/sec Per Watt, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 512 - Model: AlexNetEPYC 4124P @ DDR5-5200smoke0.49320.98641.47961.97282.4662.1922.153
MinAvgMaxEPYC 4124P @ DDR5-5200493249625141smoke493549805141OpenBenchmarking.orgMegahertz, More Is BetterTensorFlow 2.16.1CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520026.556.463.8smoke16.357.662.4OpenBenchmarking.orgWatts, Fewer Is BetterTensorFlow 2.16.1CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 4643 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520051.954.758.3smoke41.559.462.4OpenBenchmarking.orgCelsius, Fewer Is BetterTensorFlow 2.16.1CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.195.0103.8smoke54.597.0105.8OpenBenchmarking.orgWatts, Fewer Is BetterTensorFlow 2.16.1System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 7853 Joules per run.
OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 512 - Model: AlexNetEPYC 4124P @ DDR5-5200smoke20406080100Min: 123.53 / Avg: 123.63 / Max: 123.7

Primesieve

OpenBenchmarking.orgSeconds, Fewer Is BetterPrimesieve 12.1Length: 1e13EPYC 4124P @ DDR5-520070140210280350SE +/- 0.18, N = 3300.411. (CXX) g++ options: -O3
MinAvgMaxEPYC 4124P @ DDR5-5200492949424969OpenBenchmarking.orgMegahertz, More Is BetterPrimesieve 12.1CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.482.585.5OpenBenchmarking.orgWatts, Fewer Is BetterPrimesieve 12.1CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 4398 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520043.480.881.3OpenBenchmarking.orgCelsius, Fewer Is BetterPrimesieve 12.1CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520055.8128.4130.2OpenBenchmarking.orgWatts, Fewer Is BetterPrimesieve 12.1System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 6935 Joules per run.

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: BM2EPYC 4124P @ DDR5-5200smoke3691215SE +/- 0.00, N = 312.9412.941. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm
OpenBenchmarking.orgBillion Interactions/s Per Watt, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM2EPYC 4124P @ DDR5-5200smoke0.05020.10040.15060.20080.2510.2230.216
MinAvgMaxEPYC 4124P @ DDR5-520040049204947smoke494049414941OpenBenchmarking.orgMegahertz, More Is BetterminiBUDE 20210901CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.758.159.3smoke21.959.860.8OpenBenchmarking.orgWatts, Fewer Is BetterminiBUDE 20210901CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 4147 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520039.155.456.1smoke53.461.261.6OpenBenchmarking.orgCelsius, Fewer Is BetterminiBUDE 20210901CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520053.995.596.3smoke54.397.698.5OpenBenchmarking.orgWatts, Fewer Is BetterminiBUDE 20210901System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 6872 Joules per run.
OpenBenchmarking.orgBillion Interactions/s, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM2EPYC 4124P @ DDR5-5200smoke48121620Min: 12.94 / Avg: 12.94 / Max: 12.941. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm

OpenBenchmarking.orgGFInst/s, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM2EPYC 4124P @ DDR5-5200smoke70140210280350SE +/- 0.04, N = 3323.42323.421. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm
OpenBenchmarking.orgGFInst/s, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM2EPYC 4124P @ DDR5-5200smoke60120180240300Min: 323.36 / Avg: 323.42 / Max: 323.51. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -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: 1 - Input: Bosphorus 4KEPYC 4124P @ DDR5-5200smoke0.3420.6841.0261.3681.71SE +/- 0.00, N = 31.521.521. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-HEVC 1.5.0Tuning: 1 - Input: Bosphorus 4KEPYC 4124P @ DDR5-5200smoke0.00450.0090.01350.0180.02250.0190.020
MinAvgMaxEPYC 4124P @ DDR5-520040049015114smoke40048815140OpenBenchmarking.orgMegahertz, More Is BetterSVT-HEVC 1.5.0CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520015.978.781.8smoke16.977.981.6OpenBenchmarking.orgWatts, Fewer Is BetterSVT-HEVC 1.5.0CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 5480 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520045.680.881.6smoke45.480.781.6OpenBenchmarking.orgCelsius, Fewer Is BetterSVT-HEVC 1.5.0CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520055.4125.0126.6smoke55.6124.2125.9OpenBenchmarking.orgWatts, Fewer Is BetterSVT-HEVC 1.5.0System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 8752 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 1 - Input: Bosphorus 4KEPYC 4124P @ DDR5-5200smoke246810Min: 1.52 / Avg: 1.52 / Max: 1.521. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -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 WindshieldEPYC 4124P @ DDR5-5200smoke80160240320400SE +/- 0.92, N = 3390.30387.18
MinAvgMaxEPYC 4124P @ DDR5-5200494151295145smoke494051185141OpenBenchmarking.orgMegahertz, More Is BetterOpenRadioss 2023.09.15CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.062.065.4smoke16.865.167.5OpenBenchmarking.orgWatts, Fewer Is BetterOpenRadioss 2023.09.15CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 4364 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520039.663.869.3smoke45.170.574.1OpenBenchmarking.orgCelsius, Fewer Is BetterOpenRadioss 2023.09.15CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.3102.6106.2smoke54.9107.6109.8OpenBenchmarking.orgWatts, Fewer Is BetterOpenRadioss 2023.09.15System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 7248 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2023.09.15Model: Bird Strike on WindshieldEPYC 4124P @ DDR5-5200smoke70140210280350Min: 388.83 / Avg: 390.3 / Max: 391.98

PETSc

PETSc, the Portable, Extensible Toolkit for Scientific Computation, is for the scalable (parallel) solution of scientific applications modeled by partial differential equations. This test profile runs the PETSc "make streams" benchmark and records the throughput rate when all available cores are utilized for the MPI Streams build. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterPETSc 3.19Test: StreamsEPYC 4124P @ DDR5-5200smoke3K6K9K12K15KSE +/- 123.57, N = 315733.6515935.171. (CC) gcc options: -fPIC -O3 -O2 -lpthread -ludev -lpciaccess -lm
OpenBenchmarking.orgMB/s Per Watt, More Is BetterPETSc 3.19Test: StreamsEPYC 4124P @ DDR5-5200smoke50100150200250217.55229.41
MinAvgMaxEPYC 4124P @ DDR5-520040049815140smoke483449645139OpenBenchmarking.orgMegahertz, More Is BetterPETSc 3.19CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.372.376.6smoke16.869.573.3OpenBenchmarking.orgWatts, Fewer Is BetterPETSc 3.19CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 4942 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520036.476.278.1smoke43.379.482.0OpenBenchmarking.orgCelsius, Fewer Is BetterPETSc 3.19CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520053.5115.7119.6smoke53.9114.7117.4OpenBenchmarking.orgWatts, Fewer Is BetterPETSc 3.19System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 7948 Joules per run.
OpenBenchmarking.orgMB/s, More Is BetterPETSc 3.19Test: StreamsEPYC 4124P @ DDR5-5200smoke3K6K9K12K15KMin: 15488.47 / Avg: 15733.65 / Max: 15883.121. (CC) gcc options: -fPIC -O3 -O2 -lpthread -ludev -lpciaccess -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: 500 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 400EPYC 4124P @ DDR5-5200smoke120240360480600SE +/- 9.34, N = 5531.88550.43MAX: 28595.84MAX: 29023.3
MinAvgMaxEPYC 4124P @ DDR5-520040049005141smoke40046705140OpenBenchmarking.orgMegahertz, More Is BetterApache IoTDB 1.2CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520019.261.581.3smoke16.856.776.9OpenBenchmarking.orgWatts, Fewer Is BetterApache IoTDB 1.2CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 2841 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520042.171.279.0smoke46.070.979.6OpenBenchmarking.orgCelsius, Fewer Is BetterApache IoTDB 1.2CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520055.8107.1127.9smoke54.399.8121.5OpenBenchmarking.orgWatts, Fewer Is BetterApache IoTDB 1.2System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 4970 Joules per run.
OpenBenchmarking.orgAverage Latency, Fewer Is BetterApache IoTDB 1.2Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 400EPYC 4124P @ DDR5-5200smoke100200300400500Min: 499.73 / Avg: 531.88 / Max: 555.3

OpenBenchmarking.orgpoint/sec, More Is BetterApache IoTDB 1.2Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 400EPYC 4124P @ DDR5-5200smoke10M20M30M40M50MSE +/- 492377.86, N = 54535542943731998
OpenBenchmarking.orgpoint/sec, More Is BetterApache IoTDB 1.2Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 400EPYC 4124P @ DDR5-5200smoke8M16M24M32M40MMin: 44200769.65 / Avg: 45355429.19 / Max: 47129081.06

TensorFlow

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 64 - Model: ResNet-50EPYC 4124P @ DDR5-5200smoke510152025SE +/- 0.01, N = 319.1119.12
OpenBenchmarking.orgimages/sec Per Watt, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 64 - Model: ResNet-50EPYC 4124P @ DDR5-5200smoke0.07110.14220.21330.28440.35550.3150.316
MinAvgMaxEPYC 4124P @ DDR5-520040048935141smoke492649384941OpenBenchmarking.orgMegahertz, More Is BetterTensorFlow 2.16.1CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520015.860.763.5smoke16.660.563.2OpenBenchmarking.orgWatts, Fewer Is BetterTensorFlow 2.16.1CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 4008 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520042.361.163.0smoke42.561.563.3OpenBenchmarking.orgCelsius, Fewer Is BetterTensorFlow 2.16.1CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.1103.1109.4smoke54.2102.7109.2OpenBenchmarking.orgWatts, Fewer Is BetterTensorFlow 2.16.1System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 6841 Joules per run.
OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 64 - Model: ResNet-50EPYC 4124P @ DDR5-5200smoke510152025Min: 19.1 / Avg: 19.11 / Max: 19.12

ASTC Encoder

OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 4.7Preset: Very ThoroughEPYC 4124P @ DDR5-5200smoke0.15780.31560.47340.63120.789SE +/- 0.0007, N = 30.70140.70011. (CXX) g++ options: -O3 -flto -pthread
OpenBenchmarking.orgMT/s Per Watt, More Is BetterASTC Encoder 4.7Preset: Very ThoroughEPYC 4124P @ DDR5-5200smoke0.0020.0040.0060.0080.010.0090.009
MinAvgMaxEPYC 4124P @ DDR5-5200494249795141smoke40048964990OpenBenchmarking.orgMegahertz, More Is BetterASTC Encoder 4.7CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.777.780.2smoke16.676.279.1OpenBenchmarking.orgWatts, Fewer Is BetterASTC Encoder 4.7CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 4816 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520042.877.778.3smoke45.078.078.6OpenBenchmarking.orgCelsius, Fewer Is BetterASTC Encoder 4.7CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.8121.4123.2smoke55.0119.3121.8OpenBenchmarking.orgWatts, Fewer Is BetterASTC Encoder 4.7System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 7566 Joules per run.
OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 4.7Preset: Very ThoroughEPYC 4124P @ DDR5-5200smoke246810Min: 0.7 / Avg: 0.7 / Max: 0.71. (CXX) g++ options: -O3 -flto -pthread

OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 4.7Preset: ExhaustiveEPYC 4124P @ DDR5-5200smoke0.09660.19320.28980.38640.483SE +/- 0.0002, N = 30.42940.42901. (CXX) g++ options: -O3 -flto -pthread
OpenBenchmarking.orgMT/s Per Watt, More Is BetterASTC Encoder 4.7Preset: ExhaustiveEPYC 4124P @ DDR5-5200smoke0.00140.00280.00420.00560.0070.0060.006
MinAvgMaxEPYC 4124P @ DDR5-5200494149755141smoke40048955141OpenBenchmarking.orgMegahertz, More Is BetterASTC Encoder 4.7CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520022.377.480.1smoke14.775.878.7OpenBenchmarking.orgWatts, Fewer Is BetterASTC Encoder 4.7CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 4672 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520058.177.978.3smoke45.977.878.5OpenBenchmarking.orgCelsius, Fewer Is BetterASTC Encoder 4.7CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520055.1121.2122.8smoke54.4120.2121.7OpenBenchmarking.orgWatts, Fewer Is BetterASTC Encoder 4.7System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 7352 Joules per run.
OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 4.7Preset: ExhaustiveEPYC 4124P @ DDR5-5200smoke12345Min: 0.43 / Avg: 0.43 / Max: 0.431. (CXX) g++ options: -O3 -flto -pthread

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 NanotubeEPYC 4124P @ DDR5-5200smoke70140210280350SE +/- 0.42, N = 3318.67320.791. (CC) gcc options: -shared -fwrapv -O2 -lxc -lblas -lmpi
MinAvgMaxEPYC 4124P @ DDR5-520040049725142smoke40049455139OpenBenchmarking.orgMegahertz, More Is BetterGPAW 23.6CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.462.370.6smoke16.363.073.8OpenBenchmarking.orgWatts, Fewer Is BetterGPAW 23.6CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 3612 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520041.165.572.5smoke46.571.681.4OpenBenchmarking.orgCelsius, Fewer Is BetterGPAW 23.6CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.2106.3118.4smoke54.6110.4122.1OpenBenchmarking.orgWatts, Fewer Is BetterGPAW 23.6System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 6166 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterGPAW 23.6Input: Carbon NanotubeEPYC 4124P @ DDR5-5200smoke60120180240300Min: 317.84 / Avg: 318.67 / Max: 319.21. (CC) gcc options: -shared -fwrapv -O2 -lxc -lblas -lmpi

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 RunEPYC 4124P @ DDR5-5200smoke4080120160200SE +/- 0.26, N = 3168.41167.40MIN: 5.2 / MAX: 10000MIN: 5.23 / MAX: 8571.43
OpenBenchmarking.orgQueries Per Minute, Geo Mean Per Watt, More Is BetterClickHouse 22.12.3.5100M Rows Hits Dataset, Third RunEPYC 4124P @ DDR5-5200smoke0.57921.15841.73762.31682.8962.5592.574
MinAvgMaxEPYC 4124P @ DDR5-520040050395142smoke40048815141OpenBenchmarking.orgMegahertz, More Is BetterClickHouse 22.12.3.5CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.865.880.3smoke17.165.077.5OpenBenchmarking.orgWatts, Fewer Is BetterClickHouse 22.12.3.5CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 3685 Joules per run.2. smoke: Approximate power consumption of 3772 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520037.971.280.8smoke43.175.084.0OpenBenchmarking.orgCelsius, Fewer Is BetterClickHouse 22.12.3.5CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520053.7110.3129.3smoke53.8110.7127.3OpenBenchmarking.orgWatts, Fewer Is BetterClickHouse 22.12.3.5System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 6213 Joules per run.2. smoke: Approximate power consumption of 6422 Joules per run.
OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse 22.12.3.5100M Rows Hits Dataset, Third RunEPYC 4124P @ DDR5-5200smoke306090120150Min: 168.03 / Avg: 168.41 / Max: 168.9

OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse 22.12.3.5100M Rows Hits Dataset, Second RunEPYC 4124P @ DDR5-5200smoke4080120160200SE +/- 0.19, N = 3165.39162.78MIN: 5.27 / MAX: 10000MIN: 5.26 / MAX: 10000
OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse 22.12.3.5100M Rows Hits Dataset, Second RunEPYC 4124P @ DDR5-5200smoke306090120150Min: 165.08 / Avg: 165.39 / Max: 165.73

OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse 22.12.3.5100M Rows Hits Dataset, First Run / Cold CacheEPYC 4124P @ DDR5-5200smoke306090120150SE +/- 1.34, N = 3155.72154.32MIN: 5.21 / MAX: 8571.43MIN: 5.18 / MAX: 10000
OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse 22.12.3.5100M Rows Hits Dataset, First Run / Cold CacheEPYC 4124P @ DDR5-5200smoke306090120150Min: 153.68 / Avg: 155.72 / Max: 158.25

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 MaterialEPYC 4124P @ DDR5-5200smoke70140210280350303.43304.02
MinAvgMaxEPYC 4124P @ DDR5-5200493849735138smoke40049435089OpenBenchmarking.orgMegahertz, More Is BetterAppleseed 2.0 BetaCPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.075.977.7smoke15.876.578.2OpenBenchmarking.orgWatts, Fewer Is BetterAppleseed 2.0 BetaCPU Power Consumption Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520046.477.978.4smoke44.877.678.3OpenBenchmarking.orgCelsius, Fewer Is BetterAppleseed 2.0 BetaCPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.6118.6120.1smoke55.1119.4120.5OpenBenchmarking.orgWatts, Fewer Is BetterAppleseed 2.0 BetaSystem Power Consumption Monitor4080120160200

OpenSSL

OpenBenchmarking.orgverify/s, More Is BetterOpenSSL 3.3Algorithm: RSA4096EPYC 4124P @ DDR5-5200smoke20K40K60K80K100KSE +/- 24.26, N = 396458.796005.81. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
OpenBenchmarking.orgverify/s Per Watt, More Is BetterOpenSSL 3.3Algorithm: RSA4096EPYC 4124P @ DDR5-5200smoke300600900120015001338.421344.69
MinAvgMaxEPYC 4124P @ DDR5-5200476850225116smoke493850215069OpenBenchmarking.orgMegahertz, More Is BetterOpenSSL 3.3CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.772.185.2smoke16.971.485.1OpenBenchmarking.orgWatts, Fewer Is BetterOpenSSL 3.3CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 3964 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520043.376.681.4smoke44.577.682.6OpenBenchmarking.orgCelsius, Fewer Is BetterOpenSSL 3.3CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.3114.6130.1smoke55.0113.9130.3OpenBenchmarking.orgWatts, Fewer Is BetterOpenSSL 3.3System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 6343 Joules per run.
OpenBenchmarking.orgverify/s, More Is BetterOpenSSL 3.3Algorithm: RSA4096EPYC 4124P @ DDR5-5200smoke20K40K60K80K100KMin: 96425.1 / Avg: 96458.67 / Max: 96505.81. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

OpenBenchmarking.orgsign/s, More Is BetterOpenSSL 3.3Algorithm: RSA4096EPYC 4124P @ DDR5-5200smoke8001600240032004000SE +/- 5.33, N = 33738.53705.91. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
OpenBenchmarking.orgsign/s, More Is BetterOpenSSL 3.3Algorithm: RSA4096EPYC 4124P @ DDR5-5200smoke6001200180024003000Min: 3727.9 / Avg: 3738.5 / Max: 3744.71. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

MariaDB

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 11.5Test: oltp_read_write - Threads: 32EPYC 4124P @ DDR5-5200smoke20K40K60K80K100KSE +/- 140.46, N = 385078842251. (CXX) g++ options: -fPIC -pie -fstack-protector -O3 -shared -lrt -lpthread -lz -ldl -lm -lstdc++
OpenBenchmarking.orgQueries Per Second Per Watt, More Is BetterMariaDB 11.5Test: oltp_read_write - Threads: 32EPYC 4124P @ DDR5-5200smoke300600900120015001558.191486.34
MinAvgMaxEPYC 4124P @ DDR5-520040050665147smoke40050385141OpenBenchmarking.orgMegahertz, More Is BetterMariaDB 11.5CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.354.667.4smoke17.356.770.8OpenBenchmarking.orgWatts, Fewer Is BetterMariaDB 11.5CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 2912 Joules per run.2. smoke: Approximate power consumption of 3173 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520039.857.660.9smoke48.164.268.6OpenBenchmarking.orgCelsius, Fewer Is BetterMariaDB 11.5CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.793.4107.7smoke54.596.7112.7OpenBenchmarking.orgWatts, Fewer Is BetterMariaDB 11.5System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 5011 Joules per run.2. smoke: Approximate power consumption of 5417 Joules per run.
OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 11.5Test: oltp_read_write - Threads: 32EPYC 4124P @ DDR5-5200smoke15K30K45K60K75KMin: 84841.25 / Avg: 85077.57 / Max: 85327.271. (CXX) g++ options: -fPIC -pie -fstack-protector -O3 -shared -lrt -lpthread -lz -ldl -lm -lstdc++

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 11.5Test: oltp_write_only - Threads: 64EPYC 4124P @ DDR5-5200smoke30K60K90K120K150KSE +/- 535.09, N = 31426511425401. (CXX) g++ options: -fPIC -pie -fstack-protector -O3 -shared -lrt -lpthread -lz -ldl -lm -lstdc++
OpenBenchmarking.orgQueries Per Second Per Watt, More Is BetterMariaDB 11.5Test: oltp_write_only - Threads: 64EPYC 4124P @ DDR5-5200smoke60012001800240030002607.532614.51
MinAvgMaxEPYC 4124P @ DDR5-520040050395143smoke40050445141OpenBenchmarking.orgMegahertz, More Is BetterMariaDB 11.5CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520018.554.766.5smoke16.954.569.1OpenBenchmarking.orgWatts, Fewer Is BetterMariaDB 11.5CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 2881 Joules per run.2. smoke: Approximate power consumption of 2999 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520044.957.860.4smoke44.963.066.6OpenBenchmarking.orgCelsius, Fewer Is BetterMariaDB 11.5CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520053.793.6107.3smoke54.894.4111.0OpenBenchmarking.orgWatts, Fewer Is BetterMariaDB 11.5System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 4961 Joules per run.2. smoke: Approximate power consumption of 5286 Joules per run.
OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 11.5Test: oltp_write_only - Threads: 64EPYC 4124P @ DDR5-5200smoke20K40K60K80K100KMin: 141935.69 / Avg: 142651.32 / Max: 143698.251. (CXX) g++ options: -fPIC -pie -fstack-protector -O3 -shared -lrt -lpthread -lz -ldl -lm -lstdc++

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 11.5Test: oltp_update_index - Threads: 32EPYC 4124P @ DDR5-5200smoke20K40K60K80K100KSE +/- 61.55, N = 31163131166761. (CXX) g++ options: -fPIC -pie -fstack-protector -O3 -shared -lrt -lpthread -lz -ldl -lm -lstdc++
OpenBenchmarking.orgQueries Per Second Per Watt, More Is BetterMariaDB 11.5Test: oltp_update_index - Threads: 32EPYC 4124P @ DDR5-5200smoke50010001500200025002135.592051.43
MinAvgMaxEPYC 4124P @ DDR5-520040050665164smoke40049495150OpenBenchmarking.orgMegahertz, More Is BetterMariaDB 11.5CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520019.054.567.6smoke17.656.970.3OpenBenchmarking.orgWatts, Fewer Is BetterMariaDB 11.5CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 2905 Joules per run.2. smoke: Approximate power consumption of 3071 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520045.158.761.9smoke44.664.768.5OpenBenchmarking.orgCelsius, Fewer Is BetterMariaDB 11.5CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.193.4108.1smoke55.297.3112.5OpenBenchmarking.orgWatts, Fewer Is BetterMariaDB 11.5System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 5010 Joules per run.2. smoke: Approximate power consumption of 5349 Joules per run.
OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 11.5Test: oltp_update_index - Threads: 32EPYC 4124P @ DDR5-5200smoke20K40K60K80K100KMin: 116220.65 / Avg: 116312.91 / Max: 116429.621. (CXX) g++ options: -fPIC -pie -fstack-protector -O3 -shared -lrt -lpthread -lz -ldl -lm -lstdc++

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 11.5Test: oltp_update_non_index - Threads: 32EPYC 4124P @ DDR5-5200smoke30K60K90K120K150KSE +/- 238.60, N = 31314651329991. (CXX) g++ options: -fPIC -pie -fstack-protector -O3 -shared -lrt -lpthread -lz -ldl -lm -lstdc++
OpenBenchmarking.orgQueries Per Second Per Watt, More Is BetterMariaDB 11.5Test: oltp_update_non_index - Threads: 32EPYC 4124P @ DDR5-5200smoke50010001500200025002351.412400.33
MinAvgMaxEPYC 4124P @ DDR5-520040050335141smoke40050445141OpenBenchmarking.orgMegahertz, More Is BetterMariaDB 11.5CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.955.968.0smoke16.955.470.0OpenBenchmarking.orgWatts, Fewer Is BetterMariaDB 11.5CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 2963 Joules per run.2. smoke: Approximate power consumption of 3158 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520040.858.962.0smoke45.164.468.3OpenBenchmarking.orgCelsius, Fewer Is BetterMariaDB 11.5CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.295.4108.5smoke55.096.5112.2OpenBenchmarking.orgWatts, Fewer Is BetterMariaDB 11.5System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 5090 Joules per run.2. smoke: Approximate power consumption of 5403 Joules per run.
OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 11.5Test: oltp_update_non_index - Threads: 32EPYC 4124P @ DDR5-5200smoke20K40K60K80K100KMin: 131016.16 / Avg: 131464.71 / Max: 131830.041. (CXX) g++ options: -fPIC -pie -fstack-protector -O3 -shared -lrt -lpthread -lz -ldl -lm -lstdc++

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 11.5Test: oltp_update_non_index - Threads: 64EPYC 4124P @ DDR5-5200smoke20K40K60K80K100KSE +/- 188.07, N = 31133481152111. (CXX) g++ options: -fPIC -pie -fstack-protector -O3 -shared -lrt -lpthread -lz -ldl -lm -lstdc++
OpenBenchmarking.orgQueries Per Second Per Watt, More Is BetterMariaDB 11.5Test: oltp_update_non_index - Threads: 64EPYC 4124P @ DDR5-5200smoke4008001200160020002024.682045.21
MinAvgMaxEPYC 4124P @ DDR5-5200411551245145smoke40048775141OpenBenchmarking.orgMegahertz, More Is BetterMariaDB 11.5CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520018.756.067.0smoke17.656.369.5OpenBenchmarking.orgWatts, Fewer Is BetterMariaDB 11.5CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 2892 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520048.058.863.4smoke45.064.167.3OpenBenchmarking.orgCelsius, Fewer Is BetterMariaDB 11.5CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520053.094.9107.7smoke54.398.0111.8OpenBenchmarking.orgWatts, Fewer Is BetterMariaDB 11.5System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 4969 Joules per run.
OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 11.5Test: oltp_update_non_index - Threads: 64EPYC 4124P @ DDR5-5200smoke20K40K60K80K100KMin: 113130.51 / Avg: 113347.62 / Max: 113722.181. (CXX) g++ options: -fPIC -pie -fstack-protector -O3 -shared -lrt -lpthread -lz -ldl -lm -lstdc++

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 11.5Test: oltp_read_write - Threads: 64EPYC 4124P @ DDR5-5200smoke20K40K60K80K100KSE +/- 75.46, N = 390232902081. (CXX) g++ options: -fPIC -pie -fstack-protector -O3 -shared -lrt -lpthread -lz -ldl -lm -lstdc++
OpenBenchmarking.orgQueries Per Second Per Watt, More Is BetterMariaDB 11.5Test: oltp_read_write - Threads: 64EPYC 4124P @ DDR5-5200smoke300600900120015001626.101577.50
MinAvgMaxEPYC 4124P @ DDR5-520040050955141smoke40050305141OpenBenchmarking.orgMegahertz, More Is BetterMariaDB 11.5CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520018.155.568.5smoke16.557.271.0OpenBenchmarking.orgWatts, Fewer Is BetterMariaDB 11.5CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 2941 Joules per run.2. smoke: Approximate power consumption of 3145 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520046.958.561.8smoke44.664.568.8OpenBenchmarking.orgCelsius, Fewer Is BetterMariaDB 11.5CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520053.994.4109.1smoke54.597.6113.6OpenBenchmarking.orgWatts, Fewer Is BetterMariaDB 11.5System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 5035 Joules per run.2. smoke: Approximate power consumption of 5368 Joules per run.
OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 11.5Test: oltp_read_write - Threads: 64EPYC 4124P @ DDR5-5200smoke16K32K48K64K80KMin: 90082.67 / Avg: 90231.52 / Max: 90327.51. (CXX) g++ options: -fPIC -pie -fstack-protector -O3 -shared -lrt -lpthread -lz -ldl -lm -lstdc++

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 11.5Test: oltp_update_index - Threads: 64EPYC 4124P @ DDR5-5200smoke20K40K60K80K100KSE +/- 107.36, N = 31010871002231. (CXX) g++ options: -fPIC -pie -fstack-protector -O3 -shared -lrt -lpthread -lz -ldl -lm -lstdc++
OpenBenchmarking.orgQueries Per Second Per Watt, More Is BetterMariaDB 11.5Test: oltp_update_index - Threads: 64EPYC 4124P @ DDR5-5200smoke4008001200160020001836.491815.99
MinAvgMaxEPYC 4124P @ DDR5-520040050755143smoke40050365143OpenBenchmarking.orgMegahertz, More Is BetterMariaDB 11.5CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520019.155.066.3smoke18.655.269.2OpenBenchmarking.orgWatts, Fewer Is BetterMariaDB 11.5CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 2899 Joules per run.2. smoke: Approximate power consumption of 3035 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520045.157.760.4smoke48.463.667.3OpenBenchmarking.orgCelsius, Fewer Is BetterMariaDB 11.5CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.093.8106.7smoke54.095.3111.3OpenBenchmarking.orgWatts, Fewer Is BetterMariaDB 11.5System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 4970 Joules per run.2. smoke: Approximate power consumption of 5240 Joules per run.
OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 11.5Test: oltp_update_index - Threads: 64EPYC 4124P @ DDR5-5200smoke20K40K60K80K100KMin: 100886.73 / Avg: 101086.98 / Max: 101254.21. (CXX) g++ options: -fPIC -pie -fstack-protector -O3 -shared -lrt -lpthread -lz -ldl -lm -lstdc++

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 11.5Test: oltp_write_only - Threads: 32EPYC 4124P @ DDR5-5200smoke40K80K120K160K200KSE +/- 266.84, N = 31895931902551. (CXX) g++ options: -fPIC -pie -fstack-protector -O3 -shared -lrt -lpthread -lz -ldl -lm -lstdc++
OpenBenchmarking.orgQueries Per Second Per Watt, More Is BetterMariaDB 11.5Test: oltp_write_only - Threads: 32EPYC 4124P @ DDR5-5200smoke70014002100280035003325.003266.31
MinAvgMaxEPYC 4124P @ DDR5-520040050305141smoke40050335141OpenBenchmarking.orgMegahertz, More Is BetterMariaDB 11.5CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.957.068.7smoke19.258.271.3OpenBenchmarking.orgWatts, Fewer Is BetterMariaDB 11.5CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 3041 Joules per run.2. smoke: Approximate power consumption of 3087 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520040.158.961.8smoke48.465.068.6OpenBenchmarking.orgCelsius, Fewer Is BetterMariaDB 11.5CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520053.596.1109.4smoke53.899.7113.8OpenBenchmarking.orgWatts, Fewer Is BetterMariaDB 11.5System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 5157 Joules per run.2. smoke: Approximate power consumption of 5284 Joules per run.
OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 11.5Test: oltp_write_only - Threads: 32EPYC 4124P @ DDR5-5200smoke30K60K90K120K150KMin: 189063.61 / Avg: 189593.18 / Max: 189915.251. (CXX) g++ options: -fPIC -pie -fstack-protector -O3 -shared -lrt -lpthread -lz -ldl -lm -lstdc++

SecureMark

SecureMark is an objective, standardized benchmarking framework for measuring the efficiency of cryptographic processing solutions developed by EEMBC. SecureMark-TLS is benchmarking Transport Layer Security performance with a focus on IoT/edge computing. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgmarks, More Is BetterSecureMark 1.0.4Benchmark: SecureMark-TLSEPYC 4124P @ DDR5-5200smoke90K180K270K360K450KSE +/- 3405.24, N = 34239944250601. (CC) gcc options: -pedantic -O3
OpenBenchmarking.orgmarks Per Watt, More Is BetterSecureMark 1.0.4Benchmark: SecureMark-TLSEPYC 4124P @ DDR5-5200smoke3K6K9K12K15K13060.1511842.71
MinAvgMaxEPYC 4124P @ DDR5-520040051115144smoke495851285141OpenBenchmarking.orgMegahertz, More Is BetterSecureMark 1.0.4CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520018.332.538.0smoke16.535.939.3OpenBenchmarking.orgWatts, Fewer Is BetterSecureMark 1.0.4CPU Power Consumption Monitor11223344551. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1699 Joules per run.2. smoke: Approximate power consumption of 1866 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520045.951.963.9smoke46.364.071.8OpenBenchmarking.orgCelsius, Fewer Is BetterSecureMark 1.0.4CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520053.767.574.6smoke55.073.077.4OpenBenchmarking.orgWatts, Fewer Is BetterSecureMark 1.0.4System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 3557 Joules per run.2. smoke: Approximate power consumption of 3798 Joules per run.
OpenBenchmarking.orgmarks, More Is BetterSecureMark 1.0.4Benchmark: SecureMark-TLSEPYC 4124P @ DDR5-5200smoke70K140K210K280K350KMin: 417191.34 / Avg: 423993.98 / Max: 427678.131. (CC) gcc options: -pedantic -O3

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.1Blend File: Junkshop - Compute: CPU-OnlyEPYC 4124P @ DDR5-5200smoke60120180240300SE +/- 0.62, N = 3282.78284.11
MinAvgMaxEPYC 4124P @ DDR5-5200493750765141smoke493550845113OpenBenchmarking.orgMegahertz, More Is BetterBlender 4.1CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.073.875.8smoke17.173.375.7OpenBenchmarking.orgWatts, Fewer Is BetterBlender 4.1CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 3739 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520046.373.274.9smoke45.572.573.5OpenBenchmarking.orgCelsius, Fewer Is BetterBlender 4.1CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.8118.1119.8smoke54.8116.2119.0OpenBenchmarking.orgWatts, Fewer Is BetterBlender 4.1System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 5982 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.1Blend File: Junkshop - Compute: CPU-OnlyEPYC 4124P @ DDR5-5200smoke50100150200250Min: 281.56 / Avg: 282.78 / Max: 283.57

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 TesterEPYC 4124P @ DDR5-5200smoke60120180240300281.67281.37
MinAvgMaxEPYC 4124P @ DDR5-5200497750025141smoke40049605122OpenBenchmarking.orgMegahertz, More Is BetterAppleseed 2.0 BetaCPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.175.677.0smoke16.975.477.5OpenBenchmarking.orgWatts, Fewer Is BetterAppleseed 2.0 BetaCPU Power Consumption Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520044.976.977.4smoke45.376.777.4OpenBenchmarking.orgCelsius, Fewer Is BetterAppleseed 2.0 BetaCPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520055.7119.0120.1smoke54.7118.5120.0OpenBenchmarking.orgWatts, Fewer Is BetterAppleseed 2.0 BetaSystem Power Consumption Monitor4080120160200

BRL-CAD

OpenBenchmarking.orgVGR Performance Metric, More Is BetterBRL-CAD 7.38.2VGR Performance MetricEPYC 4124P @ DDR5-5200smoke20K40K60K80K100K1156531143161. (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
OpenBenchmarking.orgVGR Performance Metric Per Watt, More Is BetterBRL-CAD 7.38.2VGR Performance MetricEPYC 4124P @ DDR5-5200smoke300600900120015001461.961490.34
MinAvgMaxEPYC 4124P @ DDR5-5200493649625041smoke491049315061OpenBenchmarking.orgMegahertz, More Is BetterBRL-CAD 7.38.2CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.979.182.0smoke17.276.779.4OpenBenchmarking.orgWatts, Fewer Is BetterBRL-CAD 7.38.2CPU Power Consumption Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520039.578.881.0smoke44.883.084.5OpenBenchmarking.orgCelsius, Fewer Is BetterBRL-CAD 7.38.2CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.2122.7126.4smoke55.0122.6124.9OpenBenchmarking.orgWatts, Fewer Is BetterBRL-CAD 7.38.2System Power Consumption Monitor4080120160200

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: 100EPYC 4124P @ DDR5-5200smoke306090120150SE +/- 0.49, N = 3109.52113.35MAX: 24035.02MAX: 24211.32
MinAvgMaxEPYC 4124P @ DDR5-520040048005140smoke40047695140OpenBenchmarking.orgMegahertz, More Is BetterApache IoTDB 1.2CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520018.559.776.6smoke17.359.074.9OpenBenchmarking.orgWatts, Fewer Is BetterApache IoTDB 1.2CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 3124 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520041.369.878.8smoke46.971.579.9OpenBenchmarking.orgCelsius, Fewer Is BetterApache IoTDB 1.2CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.5105.1123.3smoke57.1105.8121.8OpenBenchmarking.orgWatts, Fewer Is BetterApache IoTDB 1.2System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 5534 Joules per run.
OpenBenchmarking.orgAverage Latency, Fewer Is BetterApache IoTDB 1.2Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 100EPYC 4124P @ DDR5-5200smoke20406080100Min: 108.63 / Avg: 109.52 / Max: 110.32

OpenBenchmarking.orgpoint/sec, More Is BetterApache IoTDB 1.2Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 100EPYC 4124P @ DDR5-5200smoke9M18M27M36M45MSE +/- 188707.13, N = 34393400842629139
OpenBenchmarking.orgpoint/sec, More Is BetterApache IoTDB 1.2Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 100EPYC 4124P @ DDR5-5200smoke8M16M24M32M40MMin: 43616074.47 / Avg: 43934008.16 / Max: 44269099.31

OpenBenchmarking.orgAverage Latency, Fewer Is BetterApache IoTDB 1.2Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 400EPYC 4124P @ DDR5-5200smoke90180270360450SE +/- 5.93, N = 3406.06413.84MAX: 27165.87MAX: 27569.26
MinAvgMaxEPYC 4124P @ DDR5-520040049275143smoke494150005140OpenBenchmarking.orgMegahertz, More Is BetterApache IoTDB 1.2CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.559.977.9smoke20.659.275.9OpenBenchmarking.orgWatts, Fewer Is BetterApache IoTDB 1.2CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 3196 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520041.670.179.3smoke47.572.080.5OpenBenchmarking.orgCelsius, Fewer Is BetterApache IoTDB 1.2CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520056.5104.8124.4smoke55.1104.4122.1OpenBenchmarking.orgWatts, Fewer Is BetterApache IoTDB 1.2System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 5590 Joules per run.
OpenBenchmarking.orgAverage Latency, Fewer Is BetterApache IoTDB 1.2Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 400EPYC 4124P @ DDR5-5200smoke70140210280350Min: 394.24 / Avg: 406.06 / Max: 412.75

OpenBenchmarking.orgpoint/sec, More Is BetterApache IoTDB 1.2Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 400EPYC 4124P @ DDR5-5200smoke10M20M30M40M50MSE +/- 415945.47, N = 34511785244005866
OpenBenchmarking.orgpoint/sec, More Is BetterApache IoTDB 1.2Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 400EPYC 4124P @ DDR5-5200smoke8M16M24M32M40MMin: 44531167.47 / Avg: 45117851.67 / Max: 45921960.99

OpenBenchmarking.orgAverage Latency, Fewer Is BetterApache IoTDB 1.2Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 100EPYC 4124P @ DDR5-5200smoke4080120160200SE +/- 0.62, N = 3167.03169.95MAX: 17738.52MAX: 15358.81
MinAvgMaxEPYC 4124P @ DDR5-520040049565143smoke40047645121OpenBenchmarking.orgMegahertz, More Is BetterApache IoTDB 1.2CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.361.079.8smoke15.959.678.4OpenBenchmarking.orgWatts, Fewer Is BetterApache IoTDB 1.2CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 3172 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520042.970.778.6smoke45.371.979.5OpenBenchmarking.orgCelsius, Fewer Is BetterApache IoTDB 1.2CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.4106.0128.3smoke54.1104.7127.5OpenBenchmarking.orgWatts, Fewer Is BetterApache IoTDB 1.2System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 5548 Joules per run.
OpenBenchmarking.orgAverage Latency, Fewer Is BetterApache IoTDB 1.2Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 100EPYC 4124P @ DDR5-5200smoke306090120150Min: 166.26 / Avg: 167.03 / Max: 168.25

OpenBenchmarking.orgpoint/sec, More Is BetterApache IoTDB 1.2Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 100EPYC 4124P @ DDR5-5200smoke10M20M30M40M50MSE +/- 147160.66, N = 34482843544042726
OpenBenchmarking.orgpoint/sec, More Is BetterApache IoTDB 1.2Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 100EPYC 4124P @ DDR5-5200smoke8M16M24M32M40MMin: 44641641.15 / Avg: 44828435.42 / Max: 45118808.96

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-OnlyEPYC 4124P @ DDR5-5200smoke0.0270.0540.0810.1080.135SE +/- 0.00, N = 30.120.12
OpenBenchmarking.orgImages / Sec Per Watt, More Is BetterIntel Open Image Denoise 2.2Run: RTLightmap.hdr.4096x4096 - Device: CPU-OnlyEPYC 4124P @ DDR5-5200smoke0.00050.0010.00150.0020.00250.0020.002
MinAvgMaxEPYC 4124P @ DDR5-5200493949414946smoke493949404941OpenBenchmarking.orgMegahertz, More Is BetterIntel Open Image Denoise 2.2CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.955.857.2smoke18.856.257.5OpenBenchmarking.orgWatts, Fewer Is BetterIntel Open Image Denoise 2.2CPU Power Consumption Monitor16324864801. EPYC 4124P @ DDR5-5200: Approximate power consumption of 2662 Joules per run.2. smoke: Approximate power consumption of 2584 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520042.156.056.5smoke46.157.958.5OpenBenchmarking.orgCelsius, Fewer Is BetterIntel Open Image Denoise 2.2CPU Temperature Monitor1632486480
MinAvgMaxEPYC 4124P @ DDR5-520054.895.096.0smoke54.295.696.6OpenBenchmarking.orgWatts, Fewer Is BetterIntel Open Image Denoise 2.2System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 4561 Joules per run.2. smoke: Approximate power consumption of 4587 Joules per run.
OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 2.2Run: RTLightmap.hdr.4096x4096 - Device: CPU-OnlyEPYC 4124P @ DDR5-5200smoke12345Min: 0.12 / Avg: 0.12 / Max: 0.12

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.1Blend File: Fishy Cat - Compute: CPU-OnlyEPYC 4124P @ DDR5-5200smoke60120180240300SE +/- 0.25, N = 3256.10258.36
MinAvgMaxEPYC 4124P @ DDR5-520040049715085smoke40048745026OpenBenchmarking.orgMegahertz, More Is BetterBlender 4.1CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.279.782.1smoke16.277.480.7OpenBenchmarking.orgWatts, Fewer Is BetterBlender 4.1CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 3668 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520043.676.878.0smoke47.077.679.0OpenBenchmarking.orgCelsius, Fewer Is BetterBlender 4.1CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520055.2124.0126.4smoke54.2121.8125.1OpenBenchmarking.orgWatts, Fewer Is BetterBlender 4.1System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 5746 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.1Blend File: Fishy Cat - Compute: CPU-OnlyEPYC 4124P @ DDR5-5200smoke50100150200250Min: 255.77 / Avg: 256.1 / Max: 256.58

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: Rubber O-Ring Seal InstallationEPYC 4124P @ DDR5-5200smoke60120180240300SE +/- 0.45, N = 3254.88257.78
MinAvgMaxEPYC 4124P @ DDR5-520040051025143smoke40050165136OpenBenchmarking.orgMegahertz, More Is BetterOpenRadioss 2023.09.15CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.067.970.1smoke16.670.172.2OpenBenchmarking.orgWatts, Fewer Is BetterOpenRadioss 2023.09.15CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 3123 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520041.061.362.4smoke45.469.670.5OpenBenchmarking.orgCelsius, Fewer Is BetterOpenRadioss 2023.09.15CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.4109.7111.2smoke55.5113.3115.7OpenBenchmarking.orgWatts, Fewer Is BetterOpenRadioss 2023.09.15System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 5048 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2023.09.15Model: Rubber O-Ring Seal InstallationEPYC 4124P @ DDR5-5200smoke50100150200250Min: 254.01 / Avg: 254.88 / Max: 255.49

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 JMHThroughputEPYC 4124P @ DDR5-52004000M8000M12000M16000M20000M19260371856.73
OpenBenchmarking.orgOps/s Per Watt, More Is BetterJava JMHThroughputEPYC 4124P @ DDR5-520060M120M180M240M300M303261470.43
MinAvgMaxEPYC 4124P @ DDR5-520040050365116OpenBenchmarking.orgMegahertz, More Is BetterJava JMHCPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.163.564.7OpenBenchmarking.orgWatts, Fewer Is BetterJava JMHCPU Power Consumption Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520037.072.273.3OpenBenchmarking.orgCelsius, Fewer Is BetterJava JMHCPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.1103.1104.0OpenBenchmarking.orgWatts, Fewer Is BetterJava JMHSystem Power Consumption Monitor20406080100

PyTorch

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 64 - Model: ResNet-50EPYC 4124P @ DDR5-5200smoke612182430SE +/- 0.23, N = 1223.0423.34MIN: 15.25 / MAX: 23.79MIN: 22.94 / MAX: 23.52
OpenBenchmarking.orgbatches/sec Per Watt, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 64 - Model: ResNet-50EPYC 4124P @ DDR5-5200smoke0.10490.20980.31470.41960.52450.4560.466
MinAvgMaxEPYC 4124P @ DDR5-520040048485141smoke40046584973OpenBenchmarking.orgMegahertz, More Is BetterPyTorch 2.2.1CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.250.654.8smoke16.350.155.0OpenBenchmarking.orgWatts, Fewer Is BetterPyTorch 2.2.1CPU Power Consumption Monitor15304560751. EPYC 4124P @ DDR5-5200: Approximate power consumption of 738 Joules per run.2. smoke: Approximate power consumption of 802 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520038.847.852.9smoke40.849.651.6OpenBenchmarking.orgCelsius, Fewer Is BetterPyTorch 2.2.1CPU Temperature Monitor1530456075
MinAvgMaxEPYC 4124P @ DDR5-520052.989.093.3smoke54.088.093.7OpenBenchmarking.orgWatts, Fewer Is BetterPyTorch 2.2.1System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1298 Joules per run.2. smoke: Approximate power consumption of 1408 Joules per run.
OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 64 - Model: ResNet-50EPYC 4124P @ DDR5-5200smoke510152025Min: 20.52 / Avg: 23.04 / Max: 23.48

SPECFEM3D

OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.1.1Model: Layered HalfspaceEPYC 4124P @ DDR5-5200smoke50100150200250SE +/- 0.46, N = 3237.98241.061. (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
MinAvgMaxEPYC 4124P @ DDR5-520040050235139smoke40048885082OpenBenchmarking.orgMegahertz, More Is BetterSPECFEM3D 4.1.1CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.874.578.4smoke16.671.575.3OpenBenchmarking.orgWatts, Fewer Is BetterSPECFEM3D 4.1.1CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 3379 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520041.972.173.8smoke46.875.777.6OpenBenchmarking.orgCelsius, Fewer Is BetterSPECFEM3D 4.1.1CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.2118.6122.9smoke55.4116.3120.8OpenBenchmarking.orgWatts, Fewer Is BetterSPECFEM3D 4.1.1System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 5418 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.1.1Model: Layered HalfspaceEPYC 4124P @ DDR5-5200smoke4080120160200Min: 237.14 / Avg: 237.98 / Max: 238.71. (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

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: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: StandardEPYC 4124P @ DDR5-5200smoke612182430SE +/- 0.52, N = 1519.4523.901. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
MinAvgMaxEPYC 4124P @ DDR5-520040049905144smoke40047395141OpenBenchmarking.orgMegahertz, More Is BetterONNX Runtime 1.17CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.344.848.0smoke16.339.141.5OpenBenchmarking.orgWatts, Fewer Is BetterONNX Runtime 1.17CPU Power Consumption Monitor14284256701. EPYC 4124P @ DDR5-5200: Approximate power consumption of 522 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520039.855.363.5smoke41.558.059.8OpenBenchmarking.orgCelsius, Fewer Is BetterONNX Runtime 1.17CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520052.983.086.6smoke53.876.879.6OpenBenchmarking.orgWatts, Fewer Is BetterONNX Runtime 1.17System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 974 Joules per run.
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: StandardEPYC 4124P @ DDR5-5200smoke612182430Min: 18.37 / Avg: 19.45 / Max: 23.981. (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: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: StandardEPYC 4124P @ DDR5-5200smoke1224364860SE +/- 1.21, N = 1551.8641.841. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: StandardEPYC 4124P @ DDR5-5200smoke612182430SE +/- 0.52, N = 1519.4523.901. (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: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: StandardEPYC 4124P @ DDR5-5200smoke1020304050Min: 41.7 / Avg: 51.86 / Max: 54.421. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: GPT-2 - Device: CPU - Executor: StandardEPYC 4124P @ DDR5-5200smoke246810SE +/- 0.15644, N = 158.403328.038951. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
MinAvgMaxEPYC 4124P @ DDR5-520040047795144smoke493249495141OpenBenchmarking.orgMegahertz, More Is BetterONNX Runtime 1.17CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520018.145.449.0smoke18.346.649.3OpenBenchmarking.orgWatts, Fewer Is BetterONNX Runtime 1.17CPU Power Consumption Monitor14284256701. EPYC 4124P @ DDR5-5200: Approximate power consumption of 536 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520039.143.346.8smoke41.144.545.1OpenBenchmarking.orgCelsius, Fewer Is BetterONNX Runtime 1.17CPU Temperature Monitor1428425670
MinAvgMaxEPYC 4124P @ DDR5-520053.386.490.7smoke53.787.890.8OpenBenchmarking.orgWatts, Fewer Is BetterONNX Runtime 1.17System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1025 Joules per run.
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: GPT-2 - Device: CPU - Executor: StandardEPYC 4124P @ DDR5-5200smoke3691215Min: 8.05 / Avg: 8.4 / Max: 9.571. (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: StandardEPYC 4124P @ DDR5-5200smoke306090120150SE +/- 2.03, N = 15119.46124.321. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: GPT-2 - Device: CPU - Executor: StandardEPYC 4124P @ DDR5-5200smoke246810SE +/- 0.15644, N = 158.403328.038951. (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: StandardEPYC 4124P @ DDR5-5200smoke20406080100Min: 104.42 / Avg: 119.46 / Max: 124.21. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: bertsquad-12 - Device: CPU - Executor: StandardEPYC 4124P @ DDR5-5200smoke20406080100SE +/- 2.21, N = 1595.9591.751. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
MinAvgMaxEPYC 4124P @ DDR5-520040048054948smoke40045214938OpenBenchmarking.orgMegahertz, More Is BetterONNX Runtime 1.17CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.659.466.0smoke16.958.165.9OpenBenchmarking.orgWatts, Fewer Is BetterONNX Runtime 1.17CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 674 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520039.856.058.0smoke41.857.259.4OpenBenchmarking.orgCelsius, Fewer Is BetterONNX Runtime 1.17CPU Temperature Monitor1632486480
MinAvgMaxEPYC 4124P @ DDR5-520053.598.9104.9smoke54.494.0105.5OpenBenchmarking.orgWatts, Fewer Is BetterONNX Runtime 1.17System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1127 Joules per run.
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: bertsquad-12 - Device: CPU - Executor: StandardEPYC 4124P @ DDR5-5200smoke20406080100Min: 88.2 / Avg: 95.95 / Max: 111.661. (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: bertsquad-12 - Device: CPU - Executor: StandardEPYC 4124P @ DDR5-5200smoke3691215SE +/- 0.23, N = 1510.5010.901. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: bertsquad-12 - Device: CPU - Executor: StandardEPYC 4124P @ DDR5-5200smoke20406080100SE +/- 2.21, N = 1595.9591.751. (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: bertsquad-12 - Device: CPU - Executor: StandardEPYC 4124P @ DDR5-5200smoke3691215Min: 8.96 / Avg: 10.5 / Max: 11.341. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

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 WritingEPYC 4124P @ DDR5-5200smoke300K600K900K1200K1500KSE +/- 10363.63, N = 15147776715248021. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.orgOp/s Per Watt, More Is BetterSpeedb 2.7Test: Read While WritingEPYC 4124P @ DDR5-5200smoke5K10K15K20K25K20181.6322099.54
MinAvgMaxEPYC 4124P @ DDR5-520040049475138smoke40045785036OpenBenchmarking.orgMegahertz, More Is BetterSpeedb 2.7CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.873.278.5smoke16.269.076.2OpenBenchmarking.orgWatts, Fewer Is BetterSpeedb 2.7CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 835 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520043.873.776.1smoke47.374.878.4OpenBenchmarking.orgCelsius, Fewer Is BetterSpeedb 2.7CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.4117.2122.6smoke55.1109.0121.3OpenBenchmarking.orgWatts, Fewer Is BetterSpeedb 2.7System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1336 Joules per run.
OpenBenchmarking.orgOp/s, More Is BetterSpeedb 2.7Test: Read While WritingEPYC 4124P @ DDR5-5200smoke300K600K900K1200K1500KMin: 1418435 / Avg: 1477766.67 / Max: 15485821. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

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: StandardEPYC 4124P @ DDR5-5200smoke1.16572.33143.49714.66285.8285SE +/- 0.09911, N = 155.180985.005521. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
MinAvgMaxEPYC 4124P @ DDR5-520040047515136smoke493349364941OpenBenchmarking.orgMegahertz, More Is BetterONNX Runtime 1.17CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.851.656.0smoke16.151.255.7OpenBenchmarking.orgWatts, Fewer Is BetterONNX Runtime 1.17CPU Power Consumption Monitor16324864801. EPYC 4124P @ DDR5-5200: Approximate power consumption of 585 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520038.447.951.6smoke41.948.850.1OpenBenchmarking.orgCelsius, Fewer Is BetterONNX Runtime 1.17CPU Temperature Monitor1530456075
MinAvgMaxEPYC 4124P @ DDR5-520053.089.793.7smoke53.388.293.9OpenBenchmarking.orgWatts, Fewer Is BetterONNX Runtime 1.17System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1023 Joules per run.
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: ResNet50 v1-12-int8 - Device: CPU - Executor: StandardEPYC 4124P @ DDR5-5200smoke246810Min: 4.99 / Avg: 5.18 / Max: 6.061. (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: StandardEPYC 4124P @ DDR5-5200smoke4080120160200SE +/- 3.30, N = 15193.85199.731. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: ResNet50 v1-12-int8 - Device: CPU - Executor: StandardEPYC 4124P @ DDR5-5200smoke1.16572.33143.49714.66285.8285SE +/- 0.09911, N = 155.180985.005521. (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: StandardEPYC 4124P @ DDR5-5200smoke4080120160200Min: 164.89 / Avg: 193.85 / Max: 200.341. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

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 TimeEPYC 4124P @ DDR5-5200smoke90180270360450432.88422.521. (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
MinAvgMaxEPYC 4124P @ DDR5-520040050195140smoke485750865140OpenBenchmarking.orgMegahertz, More Is BetterOpenFOAM 10CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.154.067.1smoke20.356.367.0OpenBenchmarking.orgWatts, Fewer Is BetterOpenFOAM 10CPU Power Consumption Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520043.353.671.4smoke50.059.777.1OpenBenchmarking.orgCelsius, Fewer Is BetterOpenFOAM 10CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.596.7110.2smoke55.9100.7112.6OpenBenchmarking.orgWatts, Fewer Is BetterOpenFOAM 10System Power Consumption Monitor4080120160200

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 10Input: drivaerFastback, Small Mesh Size - Mesh TimeEPYC 4124P @ DDR5-5200smoke112233445550.9050.441. (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

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: super-resolution-10 - Device: CPU - Executor: ParallelEPYC 4124P @ DDR5-5200smoke510152025SE +/- 0.16, N = 1521.4821.171. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
MinAvgMaxEPYC 4124P @ DDR5-520040049155140smoke40046705140OpenBenchmarking.orgMegahertz, More Is BetterONNX Runtime 1.17CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.652.857.7smoke16.048.757.0OpenBenchmarking.orgWatts, Fewer Is BetterONNX Runtime 1.17CPU Power Consumption Monitor16324864801. EPYC 4124P @ DDR5-5200: Approximate power consumption of 598 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520039.359.462.4smoke42.058.661.1OpenBenchmarking.orgCelsius, Fewer Is BetterONNX Runtime 1.17CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520053.990.895.9smoke53.788.994.4OpenBenchmarking.orgWatts, Fewer Is BetterONNX Runtime 1.17System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1035 Joules per run.
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: super-resolution-10 - Device: CPU - Executor: ParallelEPYC 4124P @ DDR5-5200smoke510152025Min: 21.09 / Avg: 21.48 / Max: 23.311. (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: super-resolution-10 - Device: CPU - Executor: ParallelEPYC 4124P @ DDR5-5200smoke1122334455SE +/- 0.32, N = 1546.5947.241. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: super-resolution-10 - Device: CPU - Executor: ParallelEPYC 4124P @ DDR5-5200smoke510152025SE +/- 0.16, N = 1521.4821.171. (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: super-resolution-10 - Device: CPU - Executor: ParallelEPYC 4124P @ DDR5-5200smoke1020304050Min: 42.9 / Avg: 46.59 / Max: 47.411. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -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.orgms, Fewer Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 500 - Mode: Read Only - Average LatencyEPYC 4124P @ DDR5-5200smoke0.57441.14881.72322.29762.872SE +/- 0.025, N = 62.5532.4771. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
MinAvgMaxEPYC 4124P @ DDR5-520040049085141smoke40047805140OpenBenchmarking.orgMegahertz, More Is BetterPostgreSQL 16CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520014.348.353.4smoke16.648.955.8OpenBenchmarking.orgWatts, Fewer Is BetterPostgreSQL 16CPU Power Consumption Monitor16324864801. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1207 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520039.849.266.8smoke43.654.463.3OpenBenchmarking.orgCelsius, Fewer Is BetterPostgreSQL 16CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.388.6117.4smoke54.491.097.4OpenBenchmarking.orgWatts, Fewer Is BetterPostgreSQL 16System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 2214 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 500 - Mode: Read Only - Average LatencyEPYC 4124P @ DDR5-5200smoke246810Min: 2.45 / Avg: 2.55 / Max: 2.631. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 500 - Mode: Read OnlyEPYC 4124P @ DDR5-5200smoke40K80K120K160K200KSE +/- 1920.28, N = 61959052018901. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 500 - Mode: Read OnlyEPYC 4124P @ DDR5-5200smoke30K60K90K120K150KMin: 189865.89 / Avg: 195904.94 / Max: 203921.281. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

TensorFlow

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 256 - Model: AlexNetEPYC 4124P @ DDR5-5200smoke306090120150SE +/- 0.04, N = 3121.85121.97
OpenBenchmarking.orgimages/sec Per Watt, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 256 - Model: AlexNetEPYC 4124P @ DDR5-5200smoke0.49120.98241.47361.96482.4562.1832.179
MinAvgMaxEPYC 4124P @ DDR5-520040049325140smoke40048805140OpenBenchmarking.orgMegahertz, More Is BetterTensorFlow 2.16.1CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.455.861.7smoke16.556.063.0OpenBenchmarking.orgWatts, Fewer Is BetterTensorFlow 2.16.1CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 2363 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520041.355.859.5smoke43.058.460.4OpenBenchmarking.orgCelsius, Fewer Is BetterTensorFlow 2.16.1CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.395.2103.9smoke54.695.1104.3OpenBenchmarking.orgWatts, Fewer Is BetterTensorFlow 2.16.1System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 4060 Joules per run.
OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 256 - Model: AlexNetEPYC 4124P @ DDR5-5200smoke20406080100Min: 121.76 / Avg: 121.85 / Max: 121.9

MariaDB mariadb-slap

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB mariadb-slap 11.5Clients: 128EPYC 4124P @ DDR5-5200smoke100200300400500SE +/- 0.18, N = 34494471. (CXX) g++ options: -fPIC -pie -fstack-protector -O3 -shared -lrt -lpthread -lz -ldl -lm -lstdc++
OpenBenchmarking.orgQueries Per Second Per Watt, More Is BetterMariaDB mariadb-slap 11.5Clients: 128EPYC 4124P @ DDR5-5200smoke2468107.2937.366
MinAvgMaxEPYC 4124P @ DDR5-520040050625140smoke40050115142OpenBenchmarking.orgMegahertz, More Is BetterMariaDB mariadb-slap 11.5CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520018.761.664.8smoke17.760.766.3OpenBenchmarking.orgWatts, Fewer Is BetterMariaDB mariadb-slap 11.5CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 2606 Joules per run.2. smoke: Approximate power consumption of 2609 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520042.065.266.5smoke44.570.172.8OpenBenchmarking.orgCelsius, Fewer Is BetterMariaDB mariadb-slap 11.5CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.3102.0104.7smoke54.2102.7107.9OpenBenchmarking.orgWatts, Fewer Is BetterMariaDB mariadb-slap 11.5System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 4320 Joules per run.2. smoke: Approximate power consumption of 4519 Joules per run.
OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB mariadb-slap 11.5Clients: 128EPYC 4124P @ DDR5-5200smoke80160240320400Min: 448.63 / Avg: 448.9 / Max: 449.241. (CXX) g++ options: -fPIC -pie -fstack-protector -O3 -shared -lrt -lpthread -lz -ldl -lm -lstdc++

SPECFEM3D

OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.1.1Model: Water-layered HalfspaceEPYC 4124P @ DDR5-5200smoke50100150200250SE +/- 0.51, N = 3214.49216.891. (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
MinAvgMaxEPYC 4124P @ DDR5-5200492350965141smoke495550035134OpenBenchmarking.orgMegahertz, More Is BetterSPECFEM3D 4.1.1CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.273.876.2smoke24.571.573.6OpenBenchmarking.orgWatts, Fewer Is BetterSPECFEM3D 4.1.1CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 2904 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520041.371.972.8smoke61.076.477.1OpenBenchmarking.orgCelsius, Fewer Is BetterSPECFEM3D 4.1.1CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520055.2118.3120.8smoke55.2117.3119.4OpenBenchmarking.orgWatts, Fewer Is BetterSPECFEM3D 4.1.1System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 4692 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.1.1Model: Water-layered HalfspaceEPYC 4124P @ DDR5-5200smoke4080120160200Min: 213.71 / Avg: 214.49 / Max: 215.461. (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

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 BeamEPYC 4124P @ DDR5-5200smoke50100150200250SE +/- 0.17, N = 3210.60214.44
MinAvgMaxEPYC 4124P @ DDR5-520040050795139smoke40049775143OpenBenchmarking.orgMegahertz, More Is BetterOpenRadioss 2023.09.15CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.165.868.7smoke16.767.370.2OpenBenchmarking.orgWatts, Fewer Is BetterOpenRadioss 2023.09.15CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 2501 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520040.069.572.4smoke45.973.675.1OpenBenchmarking.orgCelsius, Fewer Is BetterOpenRadioss 2023.09.15CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.0107.5110.1smoke54.8110.4113.3OpenBenchmarking.orgWatts, Fewer Is BetterOpenRadioss 2023.09.15System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 4084 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2023.09.15Model: Bumper BeamEPYC 4124P @ DDR5-5200smoke4080120160200Min: 210.32 / Avg: 210.6 / Max: 210.9

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.1Blend File: BMW27 - Compute: CPU-OnlyEPYC 4124P @ DDR5-5200smoke50100150200250SE +/- 0.26, N = 3206.18208.34
MinAvgMaxEPYC 4124P @ DDR5-5200494150315140smoke40048584987OpenBenchmarking.orgMegahertz, More Is BetterBlender 4.1CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.478.581.3smoke16.675.678.6OpenBenchmarking.orgWatts, Fewer Is BetterBlender 4.1CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 2957 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520040.675.476.8smoke45.377.478.8OpenBenchmarking.orgCelsius, Fewer Is BetterBlender 4.1CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.1121.9124.0smoke54.8118.4122.0OpenBenchmarking.orgWatts, Fewer Is BetterBlender 4.1System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 4591 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.1Blend File: BMW27 - Compute: CPU-OnlyEPYC 4124P @ DDR5-5200smoke4080120160200Min: 205.89 / Avg: 206.18 / Max: 206.7

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: fcn-resnet101-11 - Device: CPU - Executor: ParallelEPYC 4124P @ DDR5-5200smoke30060090012001500SE +/- 61.98, N = 121175.761595.551. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
MinAvgMaxEPYC 4124P @ DDR5-520040048455047smoke492249434995OpenBenchmarking.orgMegahertz, More Is BetterONNX Runtime 1.17CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.952.258.4smoke14.244.456.9OpenBenchmarking.orgWatts, Fewer Is BetterONNX Runtime 1.17CPU Power Consumption Monitor16324864801. EPYC 4124P @ DDR5-5200: Approximate power consumption of 622 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520040.052.253.6smoke42.052.355.1OpenBenchmarking.orgCelsius, Fewer Is BetterONNX Runtime 1.17CPU Temperature Monitor1530456075
MinAvgMaxEPYC 4124P @ DDR5-520053.389.997.1smoke53.584.095.4OpenBenchmarking.orgWatts, Fewer Is BetterONNX Runtime 1.17System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1064 Joules per run.
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: fcn-resnet101-11 - Device: CPU - Executor: ParallelEPYC 4124P @ DDR5-5200smoke30060090012001500Min: 1033.6 / Avg: 1175.76 / Max: 1742.111. (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: fcn-resnet101-11 - Device: CPU - Executor: ParallelEPYC 4124P @ DDR5-5200smoke0.1960.3920.5880.7840.98SE +/- 0.035957, N = 120.8711560.6267431. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: fcn-resnet101-11 - Device: CPU - Executor: ParallelEPYC 4124P @ DDR5-5200smoke30060090012001500SE +/- 61.98, N = 121175.761595.551. (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: fcn-resnet101-11 - Device: CPU - Executor: ParallelEPYC 4124P @ DDR5-5200smoke246810Min: 0.57 / Avg: 0.87 / Max: 0.971. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: CaffeNet 12-int8 - Device: CPU - Executor: StandardEPYC 4124P @ DDR5-5200smoke0.46750.9351.40251.872.3375SE +/- 0.01867, N = 122.077962.057661. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
MinAvgMaxEPYC 4124P @ DDR5-520040047094941smoke493849394941OpenBenchmarking.orgMegahertz, More Is BetterONNX Runtime 1.17CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.445.848.4smoke16.443.448.3OpenBenchmarking.orgWatts, Fewer Is BetterONNX Runtime 1.17CPU Power Consumption Monitor14284256701. EPYC 4124P @ DDR5-5200: Approximate power consumption of 523 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520039.542.644.8smoke42.844.144.6OpenBenchmarking.orgCelsius, Fewer Is BetterONNX Runtime 1.17CPU Temperature Monitor1224364860
MinAvgMaxEPYC 4124P @ DDR5-520053.885.287.8smoke54.184.287.7OpenBenchmarking.orgWatts, Fewer Is BetterONNX Runtime 1.17System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 980 Joules per run.
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: CaffeNet 12-int8 - Device: CPU - Executor: StandardEPYC 4124P @ DDR5-5200smoke246810Min: 2.05 / Avg: 2.08 / Max: 2.281. (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: CaffeNet 12-int8 - Device: CPU - Executor: StandardEPYC 4124P @ DDR5-5200smoke110220330440550SE +/- 3.97, N = 12481.49485.851. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: CaffeNet 12-int8 - Device: CPU - Executor: StandardEPYC 4124P @ DDR5-5200smoke0.46750.9351.40251.872.3375SE +/- 0.01867, N = 122.077962.057661. (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: CaffeNet 12-int8 - Device: CPU - Executor: StandardEPYC 4124P @ DDR5-5200smoke90180270360450Min: 438.07 / Avg: 481.49 / Max: 487.81. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

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_bareEPYC 4124P @ DDR5-5200smoke0.20570.41140.61710.82281.0285SE +/- 0.001, N = 30.9140.9131. (CXX) g++ options: -O3 -lm
OpenBenchmarking.orgNs Per Day Per Watt, More Is BetterGROMACS 2024Implementation: MPI CPU - Input: water_GMX50_bareEPYC 4124P @ DDR5-5200smoke0.00380.00760.01140.01520.0190.0170.017
MinAvgMaxEPYC 4124P @ DDR5-520040048885140smoke477949485110OpenBenchmarking.orgMegahertz, More Is BetterGROMACS 2024CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.353.762.4smoke17.254.961.2OpenBenchmarking.orgWatts, Fewer Is BetterGROMACS 2024CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1898 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520038.653.969.1smoke44.060.971.1OpenBenchmarking.orgCelsius, Fewer Is BetterGROMACS 2024CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.793.9115.7smoke54.498.0115.3OpenBenchmarking.orgWatts, Fewer Is BetterGROMACS 2024System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 3350 Joules per run.
OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2024Implementation: MPI CPU - Input: water_GMX50_bareEPYC 4124P @ DDR5-5200smoke246810Min: 0.91 / Avg: 0.91 / Max: 0.921. (CXX) g++ options: -O3 -lm

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: IMDBEPYC 4124P @ DDR5-5200306090120150SE +/- 0.01, N = 3152.681. (CXX) g++ options: -O3 -rdynamic -lssl -lcrypto -ldl
MinAvgMaxEPYC 4124P @ DDR5-5200493550515141OpenBenchmarking.orgMegahertz, More Is BetterDuckDB 0.9.1CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520023.661.971.3OpenBenchmarking.orgWatts, Fewer Is BetterDuckDB 0.9.1CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 2310 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520060.473.677.3OpenBenchmarking.orgCelsius, Fewer Is BetterDuckDB 0.9.1CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.5104.5114.0OpenBenchmarking.orgWatts, Fewer Is BetterDuckDB 0.9.1System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 3902 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterDuckDB 0.9.1Benchmark: IMDBEPYC 4124P @ DDR5-5200306090120150Min: 152.66 / Avg: 152.68 / Max: 152.691. (CXX) g++ options: -O3 -rdynamic -lssl -lcrypto -ldl

Benchmark: IMDB

smoke: The test run did not produce a result.

TensorFlow

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 32 - Model: ResNet-50EPYC 4124P @ DDR5-5200smoke510152025SE +/- 0.01, N = 319.0119.00
OpenBenchmarking.orgimages/sec Per Watt, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 32 - Model: ResNet-50EPYC 4124P @ DDR5-5200smoke0.07270.14540.21810.29080.36350.3210.323
MinAvgMaxEPYC 4124P @ DDR5-520040048105140smoke493149394941OpenBenchmarking.orgMegahertz, More Is BetterTensorFlow 2.16.1CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.559.262.0smoke16.658.862.1OpenBenchmarking.orgWatts, Fewer Is BetterTensorFlow 2.16.1CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 2072 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520039.658.260.4smoke40.658.760.9OpenBenchmarking.orgCelsius, Fewer Is BetterTensorFlow 2.16.1CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520053.8100.7103.3smoke53.999.7103.3OpenBenchmarking.orgWatts, Fewer Is BetterTensorFlow 2.16.1System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 3492 Joules per run.
OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 32 - Model: ResNet-50EPYC 4124P @ DDR5-5200smoke510152025Min: 19 / Avg: 19.01 / Max: 19.03

libavif avifenc

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 1.0Encoder Speed: 0EPYC 4124P @ DDR5-5200smoke4080120160200SE +/- 0.07, N = 3187.64187.701. (CXX) g++ options: -O3 -fPIC -lm
MinAvgMaxEPYC 4124P @ DDR5-5200493849985143smoke493749885141OpenBenchmarking.orgMegahertz, More Is Betterlibavif avifenc 1.0CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.369.581.1smoke16.868.378.7OpenBenchmarking.orgWatts, Fewer Is Betterlibavif avifenc 1.0CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 2318 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520039.674.879.1smoke43.577.081.5OpenBenchmarking.orgCelsius, Fewer Is Betterlibavif avifenc 1.0CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520053.9112.2123.8smoke54.5109.3122.4OpenBenchmarking.orgWatts, Fewer Is Betterlibavif avifenc 1.0System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 3777 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 1.0Encoder Speed: 0EPYC 4124P @ DDR5-5200smoke306090120150Min: 187.53 / Avg: 187.64 / Max: 187.761. (CXX) g++ options: -O3 -fPIC -lm

OSPRay Studio

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 3 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPUEPYC 4124P @ DDR5-5200smoke40K80K120K160K200KSE +/- 162.34, N = 3177735178542
MinAvgMaxEPYC 4124P @ DDR5-520040050645141smoke40049485140OpenBenchmarking.orgMegahertz, More Is BetterOSPRay Studio 1.0CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.271.576.6smoke17.169.775.9OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay Studio 1.0CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 2455 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520044.369.772.5smoke45.971.373.9OpenBenchmarking.orgCelsius, Fewer Is BetterOSPRay Studio 1.0CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.2114.6119.4smoke55.2112.0119.0OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay Studio 1.0System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 3895 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 3 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPUEPYC 4124P @ DDR5-5200smoke30K60K90K120K150KMin: 177412 / Avg: 177735 / Max: 177925

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: 400EPYC 4124P @ DDR5-5200smoke80160240320400SE +/- 2.44, N = 3346.65359.52MAX: 27744.45MAX: 28576.41
MinAvgMaxEPYC 4124P @ DDR5-520040048105141smoke40046805140OpenBenchmarking.orgMegahertz, More Is BetterApache IoTDB 1.2CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520018.850.074.6smoke20.252.973.4OpenBenchmarking.orgWatts, Fewer Is BetterApache IoTDB 1.2CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1865 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520041.064.578.0smoke45.168.579.4OpenBenchmarking.orgCelsius, Fewer Is BetterApache IoTDB 1.2CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.293.3120.9smoke59.398.4120.3OpenBenchmarking.orgWatts, Fewer Is BetterApache IoTDB 1.2System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 3485 Joules per run.
OpenBenchmarking.orgAverage Latency, Fewer Is BetterApache IoTDB 1.2Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 400EPYC 4124P @ DDR5-5200smoke60120180240300Min: 341.87 / Avg: 346.65 / Max: 349.89

OpenBenchmarking.orgpoint/sec, More Is BetterApache IoTDB 1.2Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 400EPYC 4124P @ DDR5-5200smoke10M20M30M40M50MSE +/- 134066.50, N = 34522655943591311
OpenBenchmarking.orgpoint/sec, More Is BetterApache IoTDB 1.2Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 400EPYC 4124P @ DDR5-5200smoke8M16M24M32M40MMin: 44990957.47 / Avg: 45226558.76 / Max: 45455221.94

Timed Linux Kernel Compilation

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 6.8Build: defconfigEPYC 4124P @ DDR5-5200smoke4080120160200SE +/- 0.30, N = 3182.46185.18
MinAvgMaxEPYC 4124P @ DDR5-520040050045142smoke494050895140OpenBenchmarking.orgMegahertz, More Is BetterTimed Linux Kernel Compilation 6.8CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520021.671.677.8smoke24.870.677.5OpenBenchmarking.orgWatts, Fewer Is BetterTimed Linux Kernel Compilation 6.8CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 2410 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520040.870.373.3smoke42.870.273.4OpenBenchmarking.orgCelsius, Fewer Is BetterTimed Linux Kernel Compilation 6.8CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520053.0114.0120.8smoke53.2112.8120.6OpenBenchmarking.orgWatts, Fewer Is BetterTimed Linux Kernel Compilation 6.8System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 3837 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 6.8Build: defconfigEPYC 4124P @ DDR5-5200smoke306090120150Min: 182.1 / Avg: 182.46 / Max: 183.04

VVenC

OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.11Video Input: Bosphorus 4K - Video Preset: FastEPYC 4124P @ DDR5-5200smoke0.7451.492.2352.983.725SE +/- 0.004, N = 33.3113.2931. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterVVenC 1.11Video Input: Bosphorus 4K - Video Preset: FastEPYC 4124P @ DDR5-5200smoke0.01040.02080.03120.04160.0520.0450.046
MinAvgMaxEPYC 4124P @ DDR5-520040049595143smoke40048515144OpenBenchmarking.orgMegahertz, More Is BetterVVenC 1.11CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520018.774.380.4smoke17.572.379.3OpenBenchmarking.orgWatts, Fewer Is BetterVVenC 1.11CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 2427 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520044.577.479.0smoke46.678.480.9OpenBenchmarking.orgCelsius, Fewer Is BetterVVenC 1.11CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.4117.7126.3smoke55.0118.1125.9OpenBenchmarking.orgWatts, Fewer Is BetterVVenC 1.11System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 3923 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.11Video Input: Bosphorus 4K - Video Preset: FastEPYC 4124P @ DDR5-5200smoke246810Min: 3.3 / Avg: 3.31 / Max: 3.321. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects

OpenSSL

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.3Algorithm: ChaCha20-Poly1305EPYC 4124P @ DDR5-5200smoke5000M10000M15000M20000M25000MSE +/- 35385699.13, N = 323686058987237168866601. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
OpenBenchmarking.orgbyte/s Per Watt, More Is BetterOpenSSL 3.3Algorithm: ChaCha20-Poly1305EPYC 4124P @ DDR5-5200smoke80M160M240M320M400M388198340.49387624812.29
MinAvgMaxEPYC 4124P @ DDR5-520040049035140smoke493949464992OpenBenchmarking.orgMegahertz, More Is BetterOpenSSL 3.3CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520026.361.078.7smoke27.261.277.2OpenBenchmarking.orgWatts, Fewer Is BetterOpenSSL 3.3CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 2014 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520052.562.378.3smoke58.364.478.9OpenBenchmarking.orgCelsius, Fewer Is BetterOpenSSL 3.3CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.4100.3120.4smoke54.699.8119.1OpenBenchmarking.orgWatts, Fewer Is BetterOpenSSL 3.3System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 3310 Joules per run.
OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.3Algorithm: ChaCha20-Poly1305EPYC 4124P @ DDR5-5200smoke4000M8000M12000M16000M20000MMin: 23616293000 / Avg: 23686058986.67 / Max: 237312363201. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.3Algorithm: ChaCha20EPYC 4124P @ DDR5-5200smoke7000M14000M21000M28000M35000MSE +/- 18396330.78, N = 333291996640332530218301. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
OpenBenchmarking.orgbyte/s Per Watt, More Is BetterOpenSSL 3.3Algorithm: ChaCha20EPYC 4124P @ DDR5-5200smoke120M240M360M480M600M563076183.21567346655.80
MinAvgMaxEPYC 4124P @ DDR5-520040048534991smoke40048124983OpenBenchmarking.orgMegahertz, More Is BetterOpenSSL 3.3CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.659.178.6smoke17.058.677.2OpenBenchmarking.orgWatts, Fewer Is BetterOpenSSL 3.3CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1892 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520043.060.478.4smoke46.462.478.8OpenBenchmarking.orgCelsius, Fewer Is BetterOpenSSL 3.3CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520053.997.5120.8smoke54.498.3119.4OpenBenchmarking.orgWatts, Fewer Is BetterOpenSSL 3.3System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 3153 Joules per run.
OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.3Algorithm: ChaCha20EPYC 4124P @ DDR5-5200smoke6000M12000M18000M24000M30000MMin: 33267235770 / Avg: 33291996640 / Max: 333279450501. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.3Algorithm: AES-256-GCMEPYC 4124P @ DDR5-5200smoke12000M24000M36000M48000M60000MSE +/- 6624573.52, N = 356291769550562942530901. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
OpenBenchmarking.orgbyte/s Per Watt, More Is BetterOpenSSL 3.3Algorithm: AES-256-GCMEPYC 4124P @ DDR5-5200smoke200M400M600M800M1000M810281645.81822375346.44
MinAvgMaxEPYC 4124P @ DDR5-520040049425140smoke40048505140OpenBenchmarking.orgMegahertz, More Is BetterOpenSSL 3.3CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520028.969.578.3smoke17.268.576.9OpenBenchmarking.orgWatts, Fewer Is BetterOpenSSL 3.3CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 2246 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520059.370.378.3smoke45.971.478.9OpenBenchmarking.orgCelsius, Fewer Is BetterOpenSSL 3.3CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.6110.1120.8smoke54.8109.1119.4OpenBenchmarking.orgWatts, Fewer Is BetterOpenSSL 3.3System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 3560 Joules per run.
OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.3Algorithm: AES-256-GCMEPYC 4124P @ DDR5-5200smoke10000M20000M30000M40000M50000MMin: 56282727220 / Avg: 56291769550 / Max: 563046771401. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.3Algorithm: AES-128-GCMEPYC 4124P @ DDR5-5200smoke14000M28000M42000M56000M70000MSE +/- 11806687.23, N = 365974534690659324600301. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
OpenBenchmarking.orgbyte/s Per Watt, More Is BetterOpenSSL 3.3Algorithm: AES-128-GCMEPYC 4124P @ DDR5-5200smoke200M400M600M800M1000M933541528.13921968194.26
MinAvgMaxEPYC 4124P @ DDR5-520040048785140smoke493849605014OpenBenchmarking.orgMegahertz, More Is BetterOpenSSL 3.3CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520020.370.778.6smoke36.571.578.9OpenBenchmarking.orgWatts, Fewer Is BetterOpenSSL 3.3CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 2285 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520055.671.578.9smoke65.573.178.8OpenBenchmarking.orgCelsius, Fewer Is BetterOpenSSL 3.3CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520055.1111.5121.0smoke54.9112.4121.2OpenBenchmarking.orgWatts, Fewer Is BetterOpenSSL 3.3System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 3680 Joules per run.
OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.3Algorithm: AES-128-GCMEPYC 4124P @ DDR5-5200smoke11000M22000M33000M44000M55000MMin: 65954821190 / Avg: 65974534690 / Max: 659956487501. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.3Algorithm: SHA512EPYC 4124P @ DDR5-5200smoke600M1200M1800M2400M3000MSE +/- 3598429.85, N = 3288741615728769651201. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
OpenBenchmarking.orgbyte/s Per Watt, More Is BetterOpenSSL 3.3Algorithm: SHA512EPYC 4124P @ DDR5-5200smoke9M18M27M36M45M40894150.2340963991.37
MinAvgMaxEPYC 4124P @ DDR5-520040049785091smoke494850045056OpenBenchmarking.orgMegahertz, More Is BetterOpenSSL 3.3CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.970.675.8smoke33.170.275.6OpenBenchmarking.orgWatts, Fewer Is BetterOpenSSL 3.3CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 2330 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520041.975.679.0smoke74.877.581.1OpenBenchmarking.orgCelsius, Fewer Is BetterOpenSSL 3.3CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.2112.7118.0smoke53.8112.9118.9OpenBenchmarking.orgWatts, Fewer Is BetterOpenSSL 3.3System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 3718 Joules per run.
OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.3Algorithm: SHA512EPYC 4124P @ DDR5-5200smoke500M1000M1500M2000M2500MMin: 2880220000 / Avg: 2887416156.67 / Max: 28911013501. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.3Algorithm: SHA256EPYC 4124P @ DDR5-5200smoke2000M4000M6000M8000M10000MSE +/- 10799214.46, N = 3892846300789091090901. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
OpenBenchmarking.orgbyte/s Per Watt, More Is BetterOpenSSL 3.3Algorithm: SHA256EPYC 4124P @ DDR5-5200smoke30M60M90M120M150M134806866.29134868101.11
MinAvgMaxEPYC 4124P @ DDR5-520040049395116smoke40048435098OpenBenchmarking.orgMegahertz, More Is BetterOpenSSL 3.3CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.166.277.9smoke16.966.178.1OpenBenchmarking.orgWatts, Fewer Is BetterOpenSSL 3.3CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 2186 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520044.670.083.1smoke45.871.784.4OpenBenchmarking.orgCelsius, Fewer Is BetterOpenSSL 3.3CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520053.6107.6121.7smoke55.1106.9122.1OpenBenchmarking.orgWatts, Fewer Is BetterOpenSSL 3.3System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 3586 Joules per run.
OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.3Algorithm: SHA256EPYC 4124P @ DDR5-5200smoke1500M3000M4500M6000M7500MMin: 8914734760 / Avg: 8928463006.67 / Max: 89497673701. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -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: 500 - Client Number: 100EPYC 4124P @ DDR5-5200smoke20406080100SE +/- 0.35, N = 3103.02107.65MAX: 13961.1MAX: 14077.64
MinAvgMaxEPYC 4124P @ DDR5-520040048725140smoke40046755144OpenBenchmarking.orgMegahertz, More Is BetterApache IoTDB 1.2CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520019.251.275.2smoke20.253.673.5OpenBenchmarking.orgWatts, Fewer Is BetterApache IoTDB 1.2CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1793 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520041.865.277.5smoke46.568.778.9OpenBenchmarking.orgCelsius, Fewer Is BetterApache IoTDB 1.2CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.894.4121.3smoke55.296.7120.7OpenBenchmarking.orgWatts, Fewer Is BetterApache IoTDB 1.2System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 3336 Joules per run.
OpenBenchmarking.orgAverage Latency, Fewer Is BetterApache IoTDB 1.2Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 100EPYC 4124P @ DDR5-5200smoke20406080100Min: 102.34 / Avg: 103.02 / Max: 103.52

OpenBenchmarking.orgpoint/sec, More Is BetterApache IoTDB 1.2Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 100EPYC 4124P @ DDR5-5200smoke10M20M30M40M50MSE +/- 87332.86, N = 34506583743525563
OpenBenchmarking.orgpoint/sec, More Is BetterApache IoTDB 1.2Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 100EPYC 4124P @ DDR5-5200smoke8M16M24M32M40MMin: 44961553.37 / Avg: 45065836.71 / Max: 45239324.26

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_bm64_shortEPYC 4124P @ DDR5-5200smoke4080120160200SE +/- 0.08, N = 3176.22176.621. (F9X) gfortran options: -O3 -march=native -funroll-loops -fopenmp
MinAvgMaxEPYC 4124P @ DDR5-520040049365139smoke40048585140OpenBenchmarking.orgMegahertz, More Is BetterCloverLeaf 1.3CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.748.350.2smoke17.149.551.8OpenBenchmarking.orgWatts, Fewer Is BetterCloverLeaf 1.3CPU Power Consumption Monitor15304560751. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1577 Joules per run.2. smoke: Approximate power consumption of 1585 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520039.450.051.9smoke43.656.457.6OpenBenchmarking.orgCelsius, Fewer Is BetterCloverLeaf 1.3CPU Temperature Monitor1632486480
MinAvgMaxEPYC 4124P @ DDR5-520054.092.095.0smoke54.294.698.3OpenBenchmarking.orgWatts, Fewer Is BetterCloverLeaf 1.3System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 3005 Joules per run.2. smoke: Approximate power consumption of 3028 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterCloverLeaf 1.3Input: clover_bm64_shortEPYC 4124P @ DDR5-5200smoke306090120150Min: 176.07 / Avg: 176.22 / Max: 176.361. (F9X) gfortran options: -O3 -march=native -funroll-loops -fopenmp

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: 800 - Mode: Read Only - Average LatencyEPYC 4124P @ DDR5-5200smoke0.99521.99042.98563.98084.976SE +/- 0.054, N = 44.4094.4231. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
MinAvgMaxEPYC 4124P @ DDR5-520040048475141smoke40049255140OpenBenchmarking.orgMegahertz, More Is BetterPostgreSQL 16CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.147.855.3smoke16.747.158.0OpenBenchmarking.orgWatts, Fewer Is BetterPostgreSQL 16CPU Power Consumption Monitor16324864801. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1206 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520039.649.467.6smoke44.053.458.1OpenBenchmarking.orgCelsius, Fewer Is BetterPostgreSQL 16CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.588.2107.6smoke53.889.4100.9OpenBenchmarking.orgWatts, Fewer Is BetterPostgreSQL 16System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 2248 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 800 - Mode: Read Only - Average LatencyEPYC 4124P @ DDR5-5200smoke246810Min: 4.29 / Avg: 4.41 / Max: 4.551. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 800 - Mode: Read OnlyEPYC 4124P @ DDR5-5200smoke40K80K120K160K200KSE +/- 2208.37, N = 41815321808811. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 800 - Mode: Read OnlyEPYC 4124P @ DDR5-5200smoke30K60K90K120K150KMin: 175719.9 / Avg: 181531.6 / Max: 186324.411. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

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 AtomsEPYC 4124P @ DDR5-5200smoke0.06170.12340.18510.24680.3085SE +/- 0.00019, N = 30.274250.27290
OpenBenchmarking.orgns/day Per Watt, More Is BetterNAMD 3.0b6Input: STMV with 1,066,628 AtomsEPYC 4124P @ DDR5-5200smoke0.00090.00180.00270.00360.00450.0040.004
MinAvgMaxEPYC 4124P @ DDR5-5200492349885139smoke492349625136OpenBenchmarking.orgMegahertz, More Is BetterNAMD 3.0b6CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520027.269.772.8smoke16.869.473.3OpenBenchmarking.orgWatts, Fewer Is BetterNAMD 3.0b6CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 2161 Joules per run.2. smoke: Approximate power consumption of 2152 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520060.871.273.4smoke47.374.877.0OpenBenchmarking.orgCelsius, Fewer Is BetterNAMD 3.0b6CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.9112.5123.6smoke55.3114.7117.7OpenBenchmarking.orgWatts, Fewer Is BetterNAMD 3.0b6System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 3526 Joules per run.2. smoke: Approximate power consumption of 3556 Joules per run.
OpenBenchmarking.orgns/day, More Is BetterNAMD 3.0b6Input: STMV with 1,066,628 AtomsEPYC 4124P @ DDR5-5200smoke12345Min: 0.27 / Avg: 0.27 / Max: 0.27

OSPRay

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 3.1Benchmark: particle_volume/pathtracer/real_timeEPYC 4124P @ DDR5-5200smoke20406080100SE +/- 0.27, N = 3105.66107.48
OpenBenchmarking.orgItems Per Second Per Watt, More Is BetterOSPRay 3.1Benchmark: particle_volume/pathtracer/real_timeEPYC 4124P @ DDR5-5200smoke0.35150.7031.05451.4061.75751.5621.542
MinAvgMaxEPYC 4124P @ DDR5-520040049665139smoke40049015139OpenBenchmarking.orgMegahertz, More Is BetterOSPRay 3.1CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.567.678.9smoke16.669.778.0OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay 3.1CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 2029 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520044.670.975.0smoke44.572.276.0OpenBenchmarking.orgCelsius, Fewer Is BetterOSPRay 3.1CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.1109.4120.0smoke55.0111.6119.6OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay 3.1System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 3281 Joules per run.
OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 3.1Benchmark: particle_volume/pathtracer/real_timeEPYC 4124P @ DDR5-5200smoke20406080100Min: 105.13 / Avg: 105.66 / Max: 105.96

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 DemandEPYC 4124P @ DDR5-5200smoke1224364860SE +/- 0.03, N = 351.0750.961. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OpenBenchmarking.orgFPS Per Watt, More Is BetterFFmpeg 6.1Encoder: libx265 - Scenario: Video On DemandEPYC 4124P @ DDR5-5200smoke0.17980.35960.53940.71920.8990.7790.799
MinAvgMaxEPYC 4124P @ DDR5-5200474150655148smoke40049075141OpenBenchmarking.orgMegahertz, More Is BetterFFmpeg 6.1CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.365.677.5smoke15.963.875.9OpenBenchmarking.orgWatts, Fewer Is BetterFFmpeg 6.1CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1946 Joules per run.2. smoke: Approximate power consumption of 1978 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520042.172.677.8smoke46.374.079.6OpenBenchmarking.orgCelsius, Fewer Is BetterFFmpeg 6.1CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520055.4108.0122.2smoke54.8109.3119.9OpenBenchmarking.orgWatts, Fewer Is BetterFFmpeg 6.1System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 3240 Joules per run.2. smoke: Approximate power consumption of 3389 Joules per run.
OpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.1Encoder: libx265 - Scenario: Video On DemandEPYC 4124P @ DDR5-5200smoke1020304050Min: 51.03 / Avg: 51.07 / Max: 51.131. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

OpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.1Encoder: libx265 - Scenario: PlatformEPYC 4124P @ DDR5-5200smoke1224364860SE +/- 0.02, N = 351.1150.931. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OpenBenchmarking.orgFPS Per Watt, More Is BetterFFmpeg 6.1Encoder: libx265 - Scenario: PlatformEPYC 4124P @ DDR5-5200smoke0.18140.36280.54420.72560.9070.7840.806
MinAvgMaxEPYC 4124P @ DDR5-520040050295141smoke40048835141OpenBenchmarking.orgMegahertz, More Is BetterFFmpeg 6.1CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.865.277.4smoke16.863.275.9OpenBenchmarking.orgWatts, Fewer Is BetterFFmpeg 6.1CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1977 Joules per run.2. smoke: Approximate power consumption of 1895 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520043.572.477.8smoke46.173.979.1OpenBenchmarking.orgCelsius, Fewer Is BetterFFmpeg 6.1CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.6109.0122.4smoke55.0107.2120.2OpenBenchmarking.orgWatts, Fewer Is BetterFFmpeg 6.1System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 3269 Joules per run.2. smoke: Approximate power consumption of 3108 Joules per run.
OpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.1Encoder: libx265 - Scenario: PlatformEPYC 4124P @ DDR5-5200smoke1020304050Min: 51.07 / Avg: 51.11 / Max: 51.131. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

OSPRay Studio

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 2 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPUEPYC 4124P @ DDR5-5200smoke30K60K90K120K150KSE +/- 575.91, N = 3152187153006
MinAvgMaxEPYC 4124P @ DDR5-520040050035141smoke507650915141OpenBenchmarking.orgMegahertz, More Is BetterOSPRay Studio 1.0CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.470.176.1smoke20.870.275.8OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay Studio 1.0CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 2009 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520043.969.472.9smoke50.670.673.3OpenBenchmarking.orgCelsius, Fewer Is BetterOSPRay Studio 1.0CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520055.1112.2118.8smoke54.5112.7118.7OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay Studio 1.0System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 3218 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 2 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPUEPYC 4124P @ DDR5-5200smoke30K60K90K120K150KMin: 151190 / Avg: 152187.33 / Max: 153185

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: WritesEPYC 4124P @ DDR5-5200smoke12K24K36K48K60KSE +/- 158.89, N = 35524955105
OpenBenchmarking.orgOp/s Per Watt, More Is BetterScyllaDB 5.2.9Test: WritesEPYC 4124P @ DDR5-5200smoke2004006008001000917.58904.72
MinAvgMaxEPYC 4124P @ DDR5-520040048995139smoke40048375050OpenBenchmarking.orgMegahertz, More Is BetterScyllaDB 5.2.9CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520015.860.276.0smoke16.560.975.2OpenBenchmarking.orgWatts, Fewer Is BetterScyllaDB 5.2.9CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1766 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520040.368.076.4smoke42.470.077.8OpenBenchmarking.orgCelsius, Fewer Is BetterScyllaDB 5.2.9CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520053.9102.4118.9smoke54.2104.7118.5OpenBenchmarking.orgWatts, Fewer Is BetterScyllaDB 5.2.9System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 3037 Joules per run.
OpenBenchmarking.orgOp/s, More Is BetterScyllaDB 5.2.9Test: WritesEPYC 4124P @ DDR5-5200smoke10K20K30K40K50KMin: 54947 / Avg: 55248.67 / Max: 55486

OSPRay Studio

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 1 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPUEPYC 4124P @ DDR5-5200smoke30K60K90K120K150KSE +/- 101.66, N = 3149914149751
MinAvgMaxEPYC 4124P @ DDR5-5200494050905141smoke40049255141OpenBenchmarking.orgMegahertz, More Is BetterOSPRay Studio 1.0CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.370.876.6smoke16.369.376.0OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay Studio 1.0CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 2007 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520043.470.773.8smoke46.370.673.4OpenBenchmarking.orgCelsius, Fewer Is BetterOSPRay Studio 1.0CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.9113.0119.4smoke54.6113.7119.1OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay Studio 1.0System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 3202 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 1 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPUEPYC 4124P @ DDR5-5200smoke30K60K90K120K150KMin: 149741 / Avg: 149914 / Max: 150093

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: UploadEPYC 4124P @ DDR5-5200smoke612182430SE +/- 0.01, N = 324.4224.341. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OpenBenchmarking.orgFPS Per Watt, More Is BetterFFmpeg 6.1Encoder: libx265 - Scenario: UploadEPYC 4124P @ DDR5-5200smoke0.09610.19220.28830.38440.48050.4160.427
MinAvgMaxEPYC 4124P @ DDR5-5200475450695154smoke493950585141OpenBenchmarking.orgMegahertz, More Is BetterFFmpeg 6.1CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520020.858.777.9smoke17.257.076.4OpenBenchmarking.orgWatts, Fewer Is BetterFFmpeg 6.1CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1644 Joules per run.2. smoke: Approximate power consumption of 1654 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520047.070.978.0smoke45.072.779.8OpenBenchmarking.orgCelsius, Fewer Is BetterFFmpeg 6.1CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.7100.9121.3smoke55.599.9120.0OpenBenchmarking.orgWatts, Fewer Is BetterFFmpeg 6.1System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 2858 Joules per run.2. smoke: Approximate power consumption of 2898 Joules per run.
OpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.1Encoder: libx265 - Scenario: UploadEPYC 4124P @ DDR5-5200smoke612182430Min: 24.39 / Avg: 24.42 / Max: 24.441. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

easyWave

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

OpenBenchmarking.orgSeconds, Fewer Is BettereasyWave r34Input: e2Asean Grid + BengkuluSept2007 Source - Time: 1200EPYC 4124P @ DDR5-5200smoke306090120150SE +/- 0.06, N = 3155.66155.981. (CXX) g++ options: -O3 -fopenmp
MinAvgMaxEPYC 4124P @ DDR5-5200490249605141smoke493849685140OpenBenchmarking.orgMegahertz, More Is BettereasyWave r34CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520023.343.345.8smoke20.044.648.0OpenBenchmarking.orgWatts, Fewer Is BettereasyWave r34CPU Power Consumption Monitor14284256701. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1240 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520045.346.354.6smoke52.055.056.4OpenBenchmarking.orgCelsius, Fewer Is BettereasyWave r34CPU Temperature Monitor1632486480
MinAvgMaxEPYC 4124P @ DDR5-520053.986.392.8smoke54.088.390.3OpenBenchmarking.orgWatts, Fewer Is BettereasyWave r34System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 2503 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BettereasyWave r34Input: e2Asean Grid + BengkuluSept2007 Source - Time: 1200EPYC 4124P @ DDR5-5200smoke306090120150Min: 155.54 / Avg: 155.66 / Max: 155.741. (CXX) g++ options: -O3 -fopenmp

OpenVINO

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Road Segmentation ADAS FP16-INT8 - Device: CPUEPYC 4124P @ DDR5-5200smoke714212835SE +/- 0.23, N = 928.4328.77MIN: 16.13 / MAX: 41.37MIN: 23.62 / MAX: 34.61. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
MinAvgMaxEPYC 4124P @ DDR5-5200477150205141smoke490550065138OpenBenchmarking.orgMegahertz, More Is BetterOpenVINO 2024.0CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.065.276.5smoke16.161.571.8OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2024.0CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 739 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520040.365.469.4smoke42.965.969.8OpenBenchmarking.orgCelsius, Fewer Is BetterOpenVINO 2024.0CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.7106.6120.1smoke53.9102.2114.3OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2024.0System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1208 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Road Segmentation ADAS FP16-INT8 - Device: CPUEPYC 4124P @ DDR5-5200smoke612182430Min: 27.36 / Avg: 28.43 / Max: 29.461. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Road Segmentation ADAS FP16-INT8 - Device: CPUEPYC 4124P @ DDR5-5200smoke306090120150SE +/- 1.16, N = 9140.59138.841. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Road Segmentation ADAS FP16-INT8 - Device: CPUEPYC 4124P @ DDR5-5200smoke306090120150Min: 135.58 / Avg: 140.59 / Max: 146.061. (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: SP.CEPYC 4124P @ DDR5-5200smoke2K4K6K8K10KSE +/- 7.32, N = 39840.139837.141. (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
OpenBenchmarking.orgTotal Mop/s Per Watt, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: SP.CEPYC 4124P @ DDR5-5200smoke50100150200250220.42215.65
MinAvgMaxEPYC 4124P @ DDR5-520040049515140smoke40048145140OpenBenchmarking.orgMegahertz, More Is BetterNAS Parallel Benchmarks 3.4CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.744.646.2smoke16.845.647.5OpenBenchmarking.orgWatts, Fewer Is BetterNAS Parallel Benchmarks 3.4CPU Power Consumption Monitor14284256701. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1205 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520039.044.746.3smoke44.050.851.8OpenBenchmarking.orgCelsius, Fewer Is BetterNAS Parallel Benchmarks 3.4CPU Temperature Monitor1530456075
MinAvgMaxEPYC 4124P @ DDR5-520053.988.290.3smoke54.189.291.9OpenBenchmarking.orgWatts, Fewer Is BetterNAS Parallel Benchmarks 3.4System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 2353 Joules per run.
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: SP.CEPYC 4124P @ DDR5-5200smoke2K4K6K8K10KMin: 9832.43 / Avg: 9840.13 / Max: 9854.761. (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

OSPRay

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 3.1Benchmark: particle_volume/scivis/real_timeEPYC 4124P @ DDR5-5200smoke0.52541.05081.57622.10162.627SE +/- 0.00090, N = 32.331762.33489
OpenBenchmarking.orgItems Per Second Per Watt, More Is BetterOSPRay 3.1Benchmark: particle_volume/scivis/real_timeEPYC 4124P @ DDR5-5200smoke0.00830.01660.02490.03320.04150.0360.037
MinAvgMaxEPYC 4124P @ DDR5-520040050435138smoke40049355137OpenBenchmarking.orgMegahertz, More Is BetterOSPRay 3.1CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.464.673.8smoke14.263.673.4OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay 3.1CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1744 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520045.069.472.6smoke42.469.773.4OpenBenchmarking.orgCelsius, Fewer Is BetterOSPRay 3.1CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.9104.2114.2smoke53.8103.1114.2OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay 3.1System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 2814 Joules per run.
OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 3.1Benchmark: particle_volume/scivis/real_timeEPYC 4124P @ DDR5-5200smoke246810Min: 2.33 / Avg: 2.33 / Max: 2.33

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: Cell Phone Drop TestEPYC 4124P @ DDR5-5200smoke306090120150SE +/- 0.33, N = 3138.72139.09
MinAvgMaxEPYC 4124P @ DDR5-520040050615140smoke40049015129OpenBenchmarking.orgMegahertz, More Is BetterOpenRadioss 2023.09.15CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.564.768.6smoke16.964.969.0OpenBenchmarking.orgWatts, Fewer Is BetterOpenRadioss 2023.09.15CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1704 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520041.865.166.9smoke46.870.372.4OpenBenchmarking.orgCelsius, Fewer Is BetterOpenRadioss 2023.09.15CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520053.7107.6110.8smoke55.1108.3112.9OpenBenchmarking.orgWatts, Fewer Is BetterOpenRadioss 2023.09.15System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 2834 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2023.09.15Model: Cell Phone Drop TestEPYC 4124P @ DDR5-5200smoke306090120150Min: 138.08 / Avg: 138.72 / Max: 139.18

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 Write - Average LatencyEPYC 4124P @ DDR5-5200smoke612182430SE +/- 0.01, N = 325.7826.121. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
MinAvgMaxEPYC 4124P @ DDR5-520040050595141smoke40049415140OpenBenchmarking.orgMegahertz, More Is BetterPostgreSQL 16CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.254.762.0smoke16.753.761.9OpenBenchmarking.orgWatts, Fewer Is BetterPostgreSQL 16CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1332 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520039.154.563.3smoke43.558.361.1OpenBenchmarking.orgCelsius, Fewer Is BetterPostgreSQL 16CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.196.1101.5smoke54.396.3103.8OpenBenchmarking.orgWatts, Fewer Is BetterPostgreSQL 16System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 2370 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 500 - Mode: Read Write - Average LatencyEPYC 4124P @ DDR5-5200smoke612182430Min: 25.76 / Avg: 25.78 / Max: 25.81. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 500 - Mode: Read WriteEPYC 4124P @ DDR5-5200smoke4K8K12K16K20KSE +/- 9.63, N = 319393191391. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 500 - Mode: Read WriteEPYC 4124P @ DDR5-5200smoke3K6K9K12K15KMin: 19379.37 / Avg: 19392.61 / Max: 19411.331. (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 LatencyEPYC 4124P @ DDR5-5200smoke1122334455SE +/- 0.38, N = 350.9750.941. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
MinAvgMaxEPYC 4124P @ DDR5-520040049865141smoke40047585140OpenBenchmarking.orgMegahertz, More Is BetterPostgreSQL 16CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.254.461.9smoke17.056.164.4OpenBenchmarking.orgWatts, Fewer Is BetterPostgreSQL 16CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1342 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520039.654.961.4smoke43.659.866.1OpenBenchmarking.orgCelsius, Fewer Is BetterPostgreSQL 16CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.296.2102.7smoke54.697.6105.6OpenBenchmarking.orgWatts, Fewer Is BetterPostgreSQL 16System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 2373 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 800 - Mode: Read Write - Average LatencyEPYC 4124P @ DDR5-5200smoke1020304050Min: 50.27 / Avg: 50.97 / Max: 51.561. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 800 - Mode: Read WriteEPYC 4124P @ DDR5-5200smoke3K6K9K12K15KSE +/- 116.46, N = 315697157041. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 800 - Mode: Read WriteEPYC 4124P @ DDR5-5200smoke3K6K9K12K15KMin: 15517.31 / Avg: 15696.78 / Max: 15915.11. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

TensorFlow

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 64 - Model: GoogLeNetEPYC 4124P @ DDR5-5200smoke1224364860SE +/- 0.02, N = 352.8452.73
OpenBenchmarking.orgimages/sec Per Watt, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 64 - Model: GoogLeNetEPYC 4124P @ DDR5-5200smoke0.20680.41360.62040.82721.0340.9190.913
MinAvgMaxEPYC 4124P @ DDR5-520040048215138smoke40047655141OpenBenchmarking.orgMegahertz, More Is BetterTensorFlow 2.16.1CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.957.560.4smoke18.757.760.5OpenBenchmarking.orgWatts, Fewer Is BetterTensorFlow 2.16.1CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1418 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520041.656.457.3smoke48.658.058.9OpenBenchmarking.orgCelsius, Fewer Is BetterTensorFlow 2.16.1CPU Temperature Monitor1632486480
MinAvgMaxEPYC 4124P @ DDR5-520053.698.5100.7smoke54.198.5101.1OpenBenchmarking.orgWatts, Fewer Is BetterTensorFlow 2.16.1System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 2398 Joules per run.
OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 64 - Model: GoogLeNetEPYC 4124P @ DDR5-5200smoke1122334455Min: 52.81 / Avg: 52.84 / Max: 52.87

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: MediumEPYC 4124P @ DDR5-5200smoke1.00582.01163.01744.02325.029SE +/- 0.01, N = 34.474.44
OpenBenchmarking.orgFrames Per Second Per Watt, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: MediumEPYC 4124P @ DDR5-5200smoke0.01310.02620.03930.05240.06550.0580.058
MinAvgMaxEPYC 4124P @ DDR5-5200480049645134smoke493349514966OpenBenchmarking.orgMegahertz, More Is Betteruvg266 0.4.1CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.776.580.8smoke31.877.279.7OpenBenchmarking.orgWatts, Fewer Is Betteruvg266 0.4.1CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1887 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520045.078.680.5smoke75.880.981.4OpenBenchmarking.orgCelsius, Fewer Is Betteruvg266 0.4.1CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.9121.8124.7smoke54.7121.0124.5OpenBenchmarking.orgWatts, Fewer Is Betteruvg266 0.4.1System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 3005 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: MediumEPYC 4124P @ DDR5-5200smoke246810Min: 4.46 / Avg: 4.47 / Max: 4.49

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.CEPYC 4124P @ DDR5-5200smoke5K10K15K20K25KSE +/- 13.18, N = 322316.9522215.391. (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
OpenBenchmarking.orgTotal Mop/s Per Watt, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: BT.CEPYC 4124P @ DDR5-5200smoke100200300400500451.27429.63
MinAvgMaxEPYC 4124P @ DDR5-520040049225139smoke493150055140OpenBenchmarking.orgMegahertz, More Is BetterNAS Parallel Benchmarks 3.4CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.149.551.6smoke20.751.753.4OpenBenchmarking.orgWatts, Fewer Is BetterNAS Parallel Benchmarks 3.4CPU Power Consumption Monitor15304560751. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1187 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520041.453.154.1smoke51.561.061.9OpenBenchmarking.orgCelsius, Fewer Is BetterNAS Parallel Benchmarks 3.4CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520053.989.993.0smoke54.793.595.3OpenBenchmarking.orgWatts, Fewer Is BetterNAS Parallel Benchmarks 3.4System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 2157 Joules per run.
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: BT.CEPYC 4124P @ DDR5-5200smoke4K8K12K16K20KMin: 22293.97 / Avg: 22316.95 / Max: 22339.611. (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

Llamafile

Mozilla's Llamafile allows distributing and running large language models (LLMs) as a single file. Llamafile aims to make open-source LLMs more accessible to developers and users. Llamafile supports a variety of models, CPUs and GPUs, and other options. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.6Test: mistral-7b-instruct-v0.2.Q8_0 - Acceleration: CPUEPYC 4124P @ DDR5-5200smoke246810SE +/- 0.01, N = 36.406.36
OpenBenchmarking.orgTokens Per Second Per Watt, More Is BetterLlamafile 0.6Test: mistral-7b-instruct-v0.2.Q8_0 - Acceleration: CPUEPYC 4124P @ DDR5-5200smoke0.02950.0590.08850.1180.14750.1300.131
MinAvgMaxEPYC 4124P @ DDR5-520040048785141smoke40047544941OpenBenchmarking.orgMegahertz, More Is BetterLlamafile 0.6CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.849.352.4smoke16.248.651.8OpenBenchmarking.orgWatts, Fewer Is BetterLlamafile 0.6CPU Power Consumption Monitor15304560751. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1168 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520039.444.855.5smoke42.647.259.4OpenBenchmarking.orgCelsius, Fewer Is BetterLlamafile 0.6CPU Temperature Monitor1632486480
MinAvgMaxEPYC 4124P @ DDR5-520053.691.193.6smoke54.289.894.9OpenBenchmarking.orgWatts, Fewer Is BetterLlamafile 0.6System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 2156 Joules per run.
OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.6Test: mistral-7b-instruct-v0.2.Q8_0 - Acceleration: CPUEPYC 4124P @ DDR5-5200smoke3691215Min: 6.39 / Avg: 6.4 / Max: 6.41

OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.6Test: wizardcoder-python-34b-v1.0.Q6_K - Acceleration: CPUEPYC 4124P @ DDR5-5200smoke0.40950.8191.22851.6382.0475SE +/- 0.00, N = 31.811.82
OpenBenchmarking.orgTokens Per Second Per Watt, More Is BetterLlamafile 0.6Test: wizardcoder-python-34b-v1.0.Q6_K - Acceleration: CPUEPYC 4124P @ DDR5-5200smoke0.00770.01540.02310.03080.03850.0320.034
MinAvgMaxEPYC 4124P @ DDR5-520040048875141smoke40047845141OpenBenchmarking.orgMegahertz, More Is BetterLlamafile 0.6CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.555.979.5smoke16.553.678.3OpenBenchmarking.orgWatts, Fewer Is BetterLlamafile 0.6CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1322 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520039.450.073.8smoke42.051.575.9OpenBenchmarking.orgCelsius, Fewer Is BetterLlamafile 0.6CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520053.798.5121.5smoke54.096.2123.8OpenBenchmarking.orgWatts, Fewer Is BetterLlamafile 0.6System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 2332 Joules per run.
OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.6Test: wizardcoder-python-34b-v1.0.Q6_K - Acceleration: CPUEPYC 4124P @ DDR5-5200smoke246810Min: 1.81 / Avg: 1.81 / Max: 1.81

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.hdr_alb_nrm.3840x2160 - Device: CPU-OnlyEPYC 4124P @ DDR5-5200smoke0.0540.1080.1620.2160.27SE +/- 0.00, N = 30.240.24
OpenBenchmarking.orgImages / Sec Per Watt, More Is BetterIntel Open Image Denoise 2.2Run: RT.hdr_alb_nrm.3840x2160 - Device: CPU-OnlyEPYC 4124P @ DDR5-5200smoke0.00090.00180.00270.00360.00450.0040.004
MinAvgMaxEPYC 4124P @ DDR5-520040048764942smoke493849404941OpenBenchmarking.orgMegahertz, More Is BetterIntel Open Image Denoise 2.2CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.355.657.7smoke19.055.658.0OpenBenchmarking.orgWatts, Fewer Is BetterIntel Open Image Denoise 2.2CPU Power Consumption Monitor16324864801. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1298 Joules per run.2. smoke: Approximate power consumption of 1224 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520044.656.156.8smoke47.458.459.3OpenBenchmarking.orgCelsius, Fewer Is BetterIntel Open Image Denoise 2.2CPU Temperature Monitor1632486480
MinAvgMaxEPYC 4124P @ DDR5-520055.395.196.7smoke55.095.297.4OpenBenchmarking.orgWatts, Fewer Is BetterIntel Open Image Denoise 2.2System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 2282 Joules per run.2. smoke: Approximate power consumption of 2094 Joules per run.
OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 2.2Run: RT.hdr_alb_nrm.3840x2160 - Device: CPU-OnlyEPYC 4124P @ DDR5-5200smoke12345Min: 0.24 / Avg: 0.24 / Max: 0.24

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 2.2Run: RT.ldr_alb_nrm.3840x2160 - Device: CPU-OnlyEPYC 4124P @ DDR5-5200smoke0.0540.1080.1620.2160.27SE +/- 0.00, N = 30.240.24
OpenBenchmarking.orgImages / Sec Per Watt, More Is BetterIntel Open Image Denoise 2.2Run: RT.ldr_alb_nrm.3840x2160 - Device: CPU-OnlyEPYC 4124P @ DDR5-5200smoke0.00090.00180.00270.00360.00450.0040.004
MinAvgMaxEPYC 4124P @ DDR5-520040048105140smoke40047675140OpenBenchmarking.orgMegahertz, More Is BetterIntel Open Image Denoise 2.2CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520015.955.557.6smoke16.254.958.2OpenBenchmarking.orgWatts, Fewer Is BetterIntel Open Image Denoise 2.2CPU Power Consumption Monitor16324864801. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1258 Joules per run.2. smoke: Approximate power consumption of 1373 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520042.556.256.9smoke45.357.959.1OpenBenchmarking.orgCelsius, Fewer Is BetterIntel Open Image Denoise 2.2CPU Temperature Monitor1632486480
MinAvgMaxEPYC 4124P @ DDR5-520054.395.096.8smoke54.595.397.5OpenBenchmarking.orgWatts, Fewer Is BetterIntel Open Image Denoise 2.2System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 2153 Joules per run.2. smoke: Approximate power consumption of 2287 Joules per run.
OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 2.2Run: RT.ldr_alb_nrm.3840x2160 - Device: CPU-OnlyEPYC 4124P @ DDR5-5200smoke12345Min: 0.24 / Avg: 0.24 / Max: 0.24

SPECFEM3D

OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.1.1Model: Homogeneous HalfspaceEPYC 4124P @ DDR5-5200smoke306090120150SE +/- 1.30, N = 3112.87116.671. (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
MinAvgMaxEPYC 4124P @ DDR5-5200494350605101smoke494749795140OpenBenchmarking.orgMegahertz, More Is BetterSPECFEM3D 4.1.1CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.175.880.2smoke22.572.076.3OpenBenchmarking.orgWatts, Fewer Is BetterSPECFEM3D 4.1.1CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1617 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520040.872.674.3smoke58.376.978.0OpenBenchmarking.orgCelsius, Fewer Is BetterSPECFEM3D 4.1.1CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.7120.6124.8smoke55.7117.5122.1OpenBenchmarking.orgWatts, Fewer Is BetterSPECFEM3D 4.1.1System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 2573 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.1.1Model: Homogeneous HalfspaceEPYC 4124P @ DDR5-5200smoke20406080100Min: 111.32 / Avg: 112.87 / Max: 115.441. (F9X) gfortran options: -O2 -fopenmp -std=f2008 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

Timed 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 OptimizedEPYC 4124P @ DDR5-5200smoke50100150200250233.27234.12
MinAvgMaxEPYC 4124P @ DDR5-520040050005141smoke40050075143OpenBenchmarking.orgMegahertz, More Is BetterTimed CPython Compilation 3.10.6CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.946.576.4smoke21.646.375.5OpenBenchmarking.orgWatts, Fewer Is BetterTimed CPython Compilation 3.10.6CPU Power Consumption Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520042.962.975.5smoke46.063.176.6OpenBenchmarking.orgCelsius, Fewer Is BetterTimed CPython Compilation 3.10.6CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520053.785.3119.9smoke54.586.6119.5OpenBenchmarking.orgWatts, Fewer Is BetterTimed CPython Compilation 3.10.6System Power Consumption Monitor4080120160200

MariaDB mariadb-slap

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB mariadb-slap 11.5Clients: 64EPYC 4124P @ DDR5-5200smoke2004006008001000SE +/- 2.10, N = 38788731. (CXX) g++ options: -fPIC -pie -fstack-protector -O3 -shared -lrt -lpthread -lz -ldl -lm -lstdc++
OpenBenchmarking.orgQueries Per Second Per Watt, More Is BetterMariaDB mariadb-slap 11.5Clients: 64EPYC 4124P @ DDR5-5200smoke4812162014.8614.84
MinAvgMaxEPYC 4124P @ DDR5-520040049885144smoke40047625140OpenBenchmarking.orgMegahertz, More Is BetterMariaDB mariadb-slap 11.5CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520020.759.163.4smoke20.958.865.1OpenBenchmarking.orgWatts, Fewer Is BetterMariaDB mariadb-slap 11.5CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1320 Joules per run.2. smoke: Approximate power consumption of 1530 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520051.464.566.0smoke50.069.772.0OpenBenchmarking.orgCelsius, Fewer Is BetterMariaDB mariadb-slap 11.5CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.198.2103.2smoke55.998.7106.5OpenBenchmarking.orgWatts, Fewer Is BetterMariaDB mariadb-slap 11.5System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 2259 Joules per run.2. smoke: Approximate power consumption of 2664 Joules per run.
OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB mariadb-slap 11.5Clients: 64EPYC 4124P @ DDR5-5200smoke150300450600750Min: 874.13 / Avg: 878.23 / Max: 881.061. (CXX) g++ options: -fPIC -pie -fstack-protector -O3 -shared -lrt -lpthread -lz -ldl -lm -lstdc++

ACES DGEMM

This is a multi-threaded DGEMM benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOP/s, More Is BetterACES DGEMM 1.0Sustained Floating-Point RateEPYC 4124P @ DDR5-5200smoke0.48640.97281.45921.94562.432SE +/- 0.006425, N = 32.1617952.1279661. (CC) gcc options: -O3 -march=native -fopenmp
OpenBenchmarking.orgGFLOP/s Per Watt, More Is BetterACES DGEMM 1.0Sustained Floating-Point RateEPYC 4124P @ DDR5-5200smoke0.00990.01980.02970.03960.04950.0440.042
MinAvgMaxEPYC 4124P @ DDR5-5200494151175141smoke40049035141OpenBenchmarking.orgMegahertz, More Is BetterACES DGEMM 1.0CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520020.949.558.3smoke16.250.358.6OpenBenchmarking.orgWatts, Fewer Is BetterACES DGEMM 1.0CPU Power Consumption Monitor16324864801. EPYC 4124P @ DDR5-5200: Approximate power consumption of 973 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520040.846.649.3smoke43.951.753.6OpenBenchmarking.orgCelsius, Fewer Is BetterACES DGEMM 1.0CPU Temperature Monitor1530456075
MinAvgMaxEPYC 4124P @ DDR5-520054.085.796.2smoke54.188.096.0OpenBenchmarking.orgWatts, Fewer Is BetterACES DGEMM 1.0System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1685 Joules per run.
OpenBenchmarking.orgGFLOP/s, More Is BetterACES DGEMM 1.0Sustained Floating-Point RateEPYC 4124P @ DDR5-5200smoke246810Min: 2.15 / Avg: 2.16 / Max: 2.171. (CC) gcc options: -O3 -march=native -fopenmp

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: 128EPYC 4124P @ DDR5-5200smoke7K14K21K28K35KSE +/- 100.60, N = 330433.230471.7
OpenBenchmarking.orgops/s Per Watt, More Is BetterCockroachDB 22.2Workload: KV, 50% Reads - Concurrency: 128EPYC 4124P @ DDR5-5200smoke100200300400500484.83469.17
MinAvgMaxEPYC 4124P @ DDR5-520040050465139smoke40046285138OpenBenchmarking.orgMegahertz, More Is BetterCockroachDB 22.2CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520014.462.868.8smoke20.364.970.4OpenBenchmarking.orgWatts, Fewer Is BetterCockroachDB 22.2CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1276 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520041.860.965.4smoke46.464.769.4OpenBenchmarking.orgCelsius, Fewer Is BetterCockroachDB 22.2CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.5103.7110.1smoke54.6104.6113.5OpenBenchmarking.orgWatts, Fewer Is BetterCockroachDB 22.2System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 2109 Joules per run.
OpenBenchmarking.orgops/s, More Is BetterCockroachDB 22.2Workload: KV, 50% Reads - Concurrency: 128EPYC 4124P @ DDR5-5200smoke5K10K15K20K25KMin: 30329.7 / Avg: 30433.23 / Max: 30634.4

OpenBenchmarking.orgops/s, More Is BetterCockroachDB 22.2Workload: KV, 60% Reads - Concurrency: 128EPYC 4124P @ DDR5-5200smoke7K14K21K28K35KSE +/- 20.64, N = 331458.931514.1
OpenBenchmarking.orgops/s Per Watt, More Is BetterCockroachDB 22.2Workload: KV, 60% Reads - Concurrency: 128EPYC 4124P @ DDR5-5200smoke110220330440550503.05500.04
MinAvgMaxEPYC 4124P @ DDR5-5200493851215139smoke494051085137OpenBenchmarking.orgMegahertz, More Is BetterCockroachDB 22.2CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.162.568.9smoke17.163.070.6OpenBenchmarking.orgWatts, Fewer Is BetterCockroachDB 22.2CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1230 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520042.360.764.9smoke46.564.568.5OpenBenchmarking.orgCelsius, Fewer Is BetterCockroachDB 22.2CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520055.0103.6109.8smoke54.7106.4112.3OpenBenchmarking.orgWatts, Fewer Is BetterCockroachDB 22.2System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 2073 Joules per run.
OpenBenchmarking.orgops/s, More Is BetterCockroachDB 22.2Workload: KV, 60% Reads - Concurrency: 128EPYC 4124P @ DDR5-5200smoke5K10K15K20K25KMin: 31423.1 / Avg: 31458.93 / Max: 31494.6

OpenBenchmarking.orgops/s, More Is BetterCockroachDB 22.2Workload: KV, 95% Reads - Concurrency: 128EPYC 4124P @ DDR5-5200smoke8K16K24K32K40KSE +/- 88.19, N = 338555.539041.2
OpenBenchmarking.orgops/s Per Watt, More Is BetterCockroachDB 22.2Workload: KV, 95% Reads - Concurrency: 128EPYC 4124P @ DDR5-5200smoke130260390520650606.27602.14
MinAvgMaxEPYC 4124P @ DDR5-5200493951205139smoke494051085139OpenBenchmarking.orgMegahertz, More Is BetterCockroachDB 22.2CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.863.670.5smoke16.664.872.4OpenBenchmarking.orgWatts, Fewer Is BetterCockroachDB 22.2CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1187 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520042.060.462.8smoke46.165.367.9OpenBenchmarking.orgCelsius, Fewer Is BetterCockroachDB 22.2CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520055.1104.5111.7smoke54.6108.0113.9OpenBenchmarking.orgWatts, Fewer Is BetterCockroachDB 22.2System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1985 Joules per run.
OpenBenchmarking.orgops/s, More Is BetterCockroachDB 22.2Workload: KV, 95% Reads - Concurrency: 128EPYC 4124P @ DDR5-5200smoke7K14K21K28K35KMin: 38428.5 / Avg: 38555.5 / Max: 38725

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 SolveEPYC 4124P @ DDR5-5200smoke20406080100SE +/- 0.04, N = 3105.30107.101. (CXX) g++ options: -fopenmp -O2 -march=native
MinAvgMaxEPYC 4124P @ DDR5-520040049825091smoke40047394991OpenBenchmarking.orgMegahertz, More Is Betterm-queens 1.2CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520028.871.674.7smoke16.768.471.8OpenBenchmarking.orgWatts, Fewer Is Betterm-queens 1.2CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1361 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520067.173.974.4smoke46.176.978.6OpenBenchmarking.orgCelsius, Fewer Is Betterm-queens 1.2CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.7112.1115.3smoke55.7110.6113.8OpenBenchmarking.orgWatts, Fewer Is Betterm-queens 1.2System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 2129 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is Betterm-queens 1.2Time To SolveEPYC 4124P @ DDR5-5200smoke20406080100Min: 105.25 / Avg: 105.3 / Max: 105.371. (CXX) g++ options: -fopenmp -O2 -march=native

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 BenchmarkEPYC 4124P @ DDR5-5200smoke150300450600750SE +/- 1.58, N = 3710.18711.32
OpenBenchmarking.orgScore Per Watt, More Is BetterNumpy BenchmarkEPYC 4124P @ DDR5-5200smoke51015202520.9621.45
MinAvgMaxEPYC 4124P @ DDR5-5200494051225146smoke493951195141OpenBenchmarking.orgMegahertz, More Is BetterNumpy BenchmarkCPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.833.940.3smoke20.733.235.1OpenBenchmarking.orgWatts, Fewer Is BetterNumpy BenchmarkCPU Power Consumption Monitor11223344551. EPYC 4124P @ DDR5-5200: Approximate power consumption of 678 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520042.055.766.1smoke44.455.458.1OpenBenchmarking.orgCelsius, Fewer Is BetterNumpy BenchmarkCPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.669.776.3smoke54.368.870.6OpenBenchmarking.orgWatts, Fewer Is BetterNumpy BenchmarkSystem Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1395 Joules per run.
OpenBenchmarking.orgScore, More Is BetterNumpy BenchmarkEPYC 4124P @ DDR5-5200smoke130260390520650Min: 708.22 / Avg: 710.18 / Max: 713.31

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 DirectionEPYC 4124P @ DDR5-5200smoke20406080100SE +/- 0.03, N = 3104.22104.041. (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
MinAvgMaxEPYC 4124P @ DDR5-520040049025143smoke493649925139OpenBenchmarking.orgMegahertz, More Is BetterXcompact3d Incompact3d 2021-03-11CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.044.647.0smoke22.646.347.8OpenBenchmarking.orgWatts, Fewer Is BetterXcompact3d Incompact3d 2021-03-11CPU Power Consumption Monitor14284256701. EPYC 4124P @ DDR5-5200: Approximate power consumption of 892 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520038.949.250.8smoke48.355.856.9OpenBenchmarking.orgCelsius, Fewer Is BetterXcompact3d Incompact3d 2021-03-11CPU Temperature Monitor1632486480
MinAvgMaxEPYC 4124P @ DDR5-520053.987.490.9smoke54.389.191.0OpenBenchmarking.orgWatts, Fewer Is BetterXcompact3d Incompact3d 2021-03-11System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1747 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: input.i3d 193 Cells Per DirectionEPYC 4124P @ DDR5-5200smoke20406080100Min: 104.16 / Avg: 104.22 / Max: 104.261. (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

High Performance Conjugate Gradient

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

OpenBenchmarking.orgGFLOP/s, More Is BetterHigh Performance Conjugate Gradient 3.1X Y Z: 104 104 104 - RT: 60EPYC 4124P @ DDR5-5200smoke246810SE +/- 0.00245, N = 36.902826.975171. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -lmpi_cxx -lmpi
OpenBenchmarking.orgGFLOP/s Per Watt, More Is BetterHigh Performance Conjugate Gradient 3.1X Y Z: 104 104 104 - RT: 60EPYC 4124P @ DDR5-5200smoke0.03440.06880.10320.13760.1720.1530.152
MinAvgMaxEPYC 4124P @ DDR5-520040047985131smoke493549535099OpenBenchmarking.orgMegahertz, More Is BetterHigh Performance Conjugate Gradient 3.1CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.845.247.7smoke17.045.848.2OpenBenchmarking.orgWatts, Fewer Is BetterHigh Performance Conjugate Gradient 3.1CPU Power Consumption Monitor14284256701. EPYC 4124P @ DDR5-5200: Approximate power consumption of 844 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520040.544.049.6smoke46.849.353.9OpenBenchmarking.orgCelsius, Fewer Is BetterHigh Performance Conjugate Gradient 3.1CPU Temperature Monitor1530456075
MinAvgMaxEPYC 4124P @ DDR5-520052.987.891.2smoke55.087.592.3OpenBenchmarking.orgWatts, Fewer Is BetterHigh Performance Conjugate Gradient 3.1System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1639 Joules per run.
OpenBenchmarking.orgGFLOP/s, More Is BetterHigh Performance Conjugate Gradient 3.1X Y Z: 104 104 104 - RT: 60EPYC 4124P @ DDR5-5200smoke3691215Min: 6.9 / Avg: 6.9 / Max: 6.911. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -lmpi_cxx -lmpi

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 ObjEPYC 4124P @ DDR5-5200smoke246810SE +/- 0.0121, N = 37.83647.8380MIN: 7.78 / MAX: 7.97MIN: 7.8 / MAX: 7.98
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterEmbree 4.3Binary: Pathtracer ISPC - Model: Asian Dragon ObjEPYC 4124P @ DDR5-5200smoke0.02770.05540.08310.11080.13850.1220.123
MinAvgMaxEPYC 4124P @ DDR5-520040050475141smoke40048715141OpenBenchmarking.orgMegahertz, More Is BetterEmbree 4.3CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.164.368.9smoke16.863.970.4OpenBenchmarking.orgWatts, Fewer Is BetterEmbree 4.3CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1222 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520043.061.263.1smoke45.164.166.6OpenBenchmarking.orgCelsius, Fewer Is BetterEmbree 4.3CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.2106.4111.3smoke54.9106.9113.6OpenBenchmarking.orgWatts, Fewer Is BetterEmbree 4.3System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 2021 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.3Binary: Pathtracer ISPC - Model: Asian Dragon ObjEPYC 4124P @ DDR5-5200smoke3691215Min: 7.82 / Avg: 7.84 / Max: 7.86

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 1080pEPYC 4124P @ DDR5-5200smoke246810SE +/- 0.00, N = 36.116.091. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-HEVC 1.5.0Tuning: 1 - Input: Bosphorus 1080pEPYC 4124P @ DDR5-5200smoke0.0180.0360.0540.0720.090.0800.079
MinAvgMaxEPYC 4124P @ DDR5-520040047804964smoke493249555063OpenBenchmarking.orgMegahertz, More Is BetterSVT-HEVC 1.5.0CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.176.280.8smoke20.577.081.3OpenBenchmarking.orgWatts, Fewer Is BetterSVT-HEVC 1.5.0CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1346 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520045.479.981.4smoke53.379.581.4OpenBenchmarking.orgCelsius, Fewer Is BetterSVT-HEVC 1.5.0CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520055.6122.6125.8smoke55.6122.0126.2OpenBenchmarking.orgWatts, Fewer Is BetterSVT-HEVC 1.5.0System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 2206 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 1 - Input: Bosphorus 1080pEPYC 4124P @ DDR5-5200smoke246810Min: 6.1 / Avg: 6.11 / Max: 6.111. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

OSPRay Studio

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 3 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPUEPYC 4124P @ DDR5-5200smoke20K40K60K80K100KSE +/- 186.30, N = 39088591386
MinAvgMaxEPYC 4124P @ DDR5-5200496351135141smoke507750915141OpenBenchmarking.orgMegahertz, More Is BetterOSPRay Studio 1.0CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520021.267.976.3smoke21.067.575.6OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay Studio 1.0CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1199 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520046.068.472.9smoke51.470.473.0OpenBenchmarking.orgCelsius, Fewer Is BetterOSPRay Studio 1.0CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.3109.4118.6smoke54.8109.3118.7OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay Studio 1.0System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1969 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 3 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPUEPYC 4124P @ DDR5-5200smoke16K32K48K64K80KMin: 90624 / Avg: 90885.33 / Max: 91246

ASTC Encoder

OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 4.7Preset: ThoroughEPYC 4124P @ DDR5-5200smoke1.15212.30423.45634.60845.7605SE +/- 0.0100, N = 35.12065.10501. (CXX) g++ options: -O3 -flto -pthread
OpenBenchmarking.orgMT/s Per Watt, More Is BetterASTC Encoder 4.7Preset: ThoroughEPYC 4124P @ DDR5-5200smoke0.01550.0310.04650.0620.07750.0670.069
MinAvgMaxEPYC 4124P @ DDR5-5200494149935140smoke496249825140OpenBenchmarking.orgMegahertz, More Is BetterASTC Encoder 4.7CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.076.080.9smoke19.573.579.8OpenBenchmarking.orgWatts, Fewer Is BetterASTC Encoder 4.7CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1393 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520042.376.578.1smoke52.576.778.6OpenBenchmarking.orgCelsius, Fewer Is BetterASTC Encoder 4.7CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.9119.8123.8smoke54.7117.5122.3OpenBenchmarking.orgWatts, Fewer Is BetterASTC Encoder 4.7System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 2236 Joules per run.
OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 4.7Preset: ThoroughEPYC 4124P @ DDR5-5200smoke246810Min: 5.1 / Avg: 5.12 / Max: 5.141. (CXX) g++ options: -O3 -flto -pthread

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: CrownEPYC 4124P @ DDR5-5200smoke246810SE +/- 0.0041, N = 37.83837.8014MIN: 7.77 / MAX: 8.03MIN: 7.74 / MAX: 7.98
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterEmbree 4.3Binary: Pathtracer ISPC - Model: CrownEPYC 4124P @ DDR5-5200smoke0.02410.04820.07230.09640.12050.1070.107
MinAvgMaxEPYC 4124P @ DDR5-520040050145134smoke494050755111OpenBenchmarking.orgMegahertz, More Is BetterEmbree 4.3CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.073.277.5smoke17.072.677.0OpenBenchmarking.orgWatts, Fewer Is BetterEmbree 4.3CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1294 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520044.470.171.5smoke45.671.072.8OpenBenchmarking.orgCelsius, Fewer Is BetterEmbree 4.3CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.3119.0121.2smoke55.3115.1121.2OpenBenchmarking.orgWatts, Fewer Is BetterEmbree 4.3System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 2062 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.3Binary: Pathtracer ISPC - Model: CrownEPYC 4124P @ DDR5-5200smoke3691215Min: 7.83 / Avg: 7.84 / Max: 7.85

SPECFEM3D

OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.1.1Model: Tomographic ModelEPYC 4124P @ DDR5-5200smoke20406080100SE +/- 0.34, N = 390.5891.891. (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
MinAvgMaxEPYC 4124P @ DDR5-520040047935098smoke40047145016OpenBenchmarking.orgMegahertz, More Is BetterSPECFEM3D 4.1.1CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.975.179.3smoke16.569.675.8OpenBenchmarking.orgWatts, Fewer Is BetterSPECFEM3D 4.1.1CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1277 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520041.172.273.8smoke47.175.777.9OpenBenchmarking.orgCelsius, Fewer Is BetterSPECFEM3D 4.1.1CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520055.0118.3124.2smoke55.6114.8121.5OpenBenchmarking.orgWatts, Fewer Is BetterSPECFEM3D 4.1.1System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 2051 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.1.1Model: Tomographic ModelEPYC 4124P @ DDR5-5200smoke20406080100Min: 90.18 / Avg: 90.58 / Max: 91.261. (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

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_bmEPYC 4124P @ DDR5-5200smoke20406080100SE +/- 0.21, N = 392.4292.651. (F9X) gfortran options: -O3 -march=native -funroll-loops -fopenmp
MinAvgMaxEPYC 4124P @ DDR5-5200480149525027smoke40044345028OpenBenchmarking.orgMegahertz, More Is BetterCloverLeaf 1.3CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520023.048.450.9smoke16.546.452.0OpenBenchmarking.orgWatts, Fewer Is BetterCloverLeaf 1.3CPU Power Consumption Monitor15304560751. EPYC 4124P @ DDR5-5200: Approximate power consumption of 822 Joules per run.2. smoke: Approximate power consumption of 835 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520042.544.745.3smoke46.650.051.3OpenBenchmarking.orgCelsius, Fewer Is BetterCloverLeaf 1.3CPU Temperature Monitor1530456075
MinAvgMaxEPYC 4124P @ DDR5-520054.790.793.9smoke53.187.795.9OpenBenchmarking.orgWatts, Fewer Is BetterCloverLeaf 1.3System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1571 Joules per run.2. smoke: Approximate power consumption of 1579 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterCloverLeaf 1.3Input: clover_bmEPYC 4124P @ DDR5-5200smoke20406080100Min: 92.18 / Avg: 92.42 / Max: 92.841. (F9X) gfortran options: -O3 -march=native -funroll-loops -fopenmp

OSPRay

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 3.1Benchmark: particle_volume/ao/real_timeEPYC 4124P @ DDR5-5200smoke0.52631.05261.57892.10522.6315SE +/- 0.00263, N = 32.339072.33286
OpenBenchmarking.orgItems Per Second Per Watt, More Is BetterOSPRay 3.1Benchmark: particle_volume/ao/real_timeEPYC 4124P @ DDR5-5200smoke0.00860.01720.02580.03440.0430.0330.038
MinAvgMaxEPYC 4124P @ DDR5-520040048095099smoke40048285110OpenBenchmarking.orgMegahertz, More Is BetterOSPRay 3.1CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.269.973.5smoke15.961.073.3OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay 3.1CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1188 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520044.671.873.0smoke45.568.573.4OpenBenchmarking.orgCelsius, Fewer Is BetterOSPRay 3.1CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520055.3111.5114.3smoke54.9104.5114.1OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay 3.1System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1896 Joules per run.
OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 3.1Benchmark: particle_volume/ao/real_timeEPYC 4124P @ DDR5-5200smoke246810Min: 2.33 / Avg: 2.34 / Max: 2.34

SPECFEM3D

OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.1.1Model: Mount St. HelensEPYC 4124P @ DDR5-5200smoke20406080100SE +/- 0.10, N = 389.4891.041. (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
MinAvgMaxEPYC 4124P @ DDR5-5200493850635134smoke494149845032OpenBenchmarking.orgMegahertz, More Is BetterSPECFEM3D 4.1.1CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.973.879.1smoke17.170.275.8OpenBenchmarking.orgWatts, Fewer Is BetterSPECFEM3D 4.1.1CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1254 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520042.472.174.1smoke47.175.577.6OpenBenchmarking.orgCelsius, Fewer Is BetterSPECFEM3D 4.1.1CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.2118.9123.6smoke55.1113.3121.4OpenBenchmarking.orgWatts, Fewer Is BetterSPECFEM3D 4.1.1System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 2022 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.1.1Model: Mount St. HelensEPYC 4124P @ DDR5-5200smoke20406080100Min: 89.27 / Avg: 89.48 / Max: 89.611. (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

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: MediumEPYC 4124P @ DDR5-5200smoke246810SE +/- 0.01, N = 36.646.581. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: MediumEPYC 4124P @ DDR5-5200smoke0.01980.03960.05940.07920.0990.0860.088
MinAvgMaxEPYC 4124P @ DDR5-520040048675041smoke40047014960OpenBenchmarking.orgMegahertz, More Is BetterKvazaar 2.2CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.877.381.5smoke17.474.980.9OpenBenchmarking.orgWatts, Fewer Is BetterKvazaar 2.2CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1288 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520043.679.981.3smoke45.479.381.6OpenBenchmarking.orgCelsius, Fewer Is BetterKvazaar 2.2CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520056.0121.4126.8smoke54.9117.7125.5OpenBenchmarking.orgWatts, Fewer Is BetterKvazaar 2.2System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 2064 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: MediumEPYC 4124P @ DDR5-5200smoke3691215Min: 6.62 / Avg: 6.64 / Max: 6.651. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

Apache HTTP Server

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

OpenBenchmarking.orgRequests Per Second, More Is BetterApache HTTP Server 2.4.56Concurrent Requests: 1000EPYC 4124P @ DDR5-5200smoke10K20K30K40K50KSE +/- 326.47, N = 348650.3048039.151. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2
OpenBenchmarking.orgRequests Per Second Per Watt, More Is BetterApache HTTP Server 2.4.56Concurrent Requests: 1000EPYC 4124P @ DDR5-5200smoke160320480640800745.23754.25
MinAvgMaxEPYC 4124P @ DDR5-520040050315140smoke494151185141OpenBenchmarking.orgMegahertz, More Is BetterApache HTTP Server 2.4.56CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.265.370.3smoke16.763.770.8OpenBenchmarking.orgWatts, Fewer Is BetterApache HTTP Server 2.4.56CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1132 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520041.861.863.9smoke43.562.665.8OpenBenchmarking.orgCelsius, Fewer Is BetterApache HTTP Server 2.4.56CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.4108.4113.7smoke54.5107.4114.5OpenBenchmarking.orgWatts, Fewer Is BetterApache HTTP Server 2.4.56System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1879 Joules per run.
OpenBenchmarking.orgRequests Per Second, More Is BetterApache HTTP Server 2.4.56Concurrent Requests: 1000EPYC 4124P @ DDR5-5200smoke8K16K24K32K40KMin: 48211.3 / Avg: 48650.3 / Max: 49288.371. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2

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: 1000EPYC 4124P @ DDR5-5200smoke9K18K27K36K45KSE +/- 247.36, N = 341180.8142274.331. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2
OpenBenchmarking.orgRequests Per Second Per Watt, More Is Betternginx 1.23.2Connections: 1000EPYC 4124P @ DDR5-5200smoke130260390520650562.64606.52
MinAvgMaxEPYC 4124P @ DDR5-520040050185138smoke40048435138OpenBenchmarking.orgMegahertz, More Is Betternginx 1.23.2CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.873.279.3smoke16.969.779.3OpenBenchmarking.orgWatts, Fewer Is Betternginx 1.23.2CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1244 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520042.068.270.9smoke44.069.072.0OpenBenchmarking.orgCelsius, Fewer Is Betternginx 1.23.2CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.3120.7124.6smoke54.3116.8125.3OpenBenchmarking.orgWatts, Fewer Is Betternginx 1.23.2System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 2053 Joules per run.
OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.23.2Connections: 1000EPYC 4124P @ DDR5-5200smoke7K14K21K28K35KMin: 40686.26 / Avg: 41180.81 / Max: 41439.371. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2

Apache HTTP Server

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

OpenBenchmarking.orgRequests Per Second, More Is BetterApache HTTP Server 2.4.56Concurrent Requests: 500EPYC 4124P @ DDR5-5200smoke12K24K36K48K60KSE +/- 314.71, N = 353643.8656841.621. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2
OpenBenchmarking.orgRequests Per Second Per Watt, More Is BetterApache HTTP Server 2.4.56Concurrent Requests: 500EPYC 4124P @ DDR5-5200smoke2004006008001000804.04901.87
MinAvgMaxEPYC 4124P @ DDR5-520040049475138smoke493951065139OpenBenchmarking.orgMegahertz, More Is BetterApache HTTP Server 2.4.56CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.566.771.6smoke16.463.072.4OpenBenchmarking.orgWatts, Fewer Is BetterApache HTTP Server 2.4.56CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1134 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520041.863.365.6smoke43.863.767.8OpenBenchmarking.orgCelsius, Fewer Is BetterApache HTTP Server 2.4.56CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.3109.6114.8smoke54.3108.1116.0OpenBenchmarking.orgWatts, Fewer Is BetterApache HTTP Server 2.4.56System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1899 Joules per run.
OpenBenchmarking.orgRequests Per Second, More Is BetterApache HTTP Server 2.4.56Concurrent Requests: 500EPYC 4124P @ DDR5-5200smoke10K20K30K40K50KMin: 53052.28 / Avg: 53643.86 / Max: 54125.811. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2

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: 500EPYC 4124P @ DDR5-5200smoke10K20K30K40K50KSE +/- 166.47, N = 345317.1646111.861. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2
OpenBenchmarking.orgRequests Per Second Per Watt, More Is Betternginx 1.23.2Connections: 500EPYC 4124P @ DDR5-5200smoke140280420560700601.65670.51
MinAvgMaxEPYC 4124P @ DDR5-520040048295137smoke40046175125OpenBenchmarking.orgMegahertz, More Is Betternginx 1.23.2CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.475.380.9smoke15.868.881.0OpenBenchmarking.orgWatts, Fewer Is Betternginx 1.23.2CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1306 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520041.870.072.4smoke43.669.173.1OpenBenchmarking.orgCelsius, Fewer Is Betternginx 1.23.2CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.3120.8126.0smoke54.3118.4126.2OpenBenchmarking.orgWatts, Fewer Is Betternginx 1.23.2System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 2094 Joules per run.
OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.23.2Connections: 500EPYC 4124P @ DDR5-5200smoke8K16K24K32K40KMin: 45021.86 / Avg: 45317.16 / Max: 45597.971. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.23.2Connections: 200EPYC 4124P @ DDR5-5200smoke10K20K30K40K50KSE +/- 66.30, N = 347788.2448555.151. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2
OpenBenchmarking.orgRequests Per Second Per Watt, More Is Betternginx 1.23.2Connections: 200EPYC 4124P @ DDR5-5200smoke140280420560700633.54653.83
MinAvgMaxEPYC 4124P @ DDR5-520040049045113smoke40047835094OpenBenchmarking.orgMegahertz, More Is Betternginx 1.23.2CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520015.975.481.7smoke16.474.381.3OpenBenchmarking.orgWatts, Fewer Is Betternginx 1.23.2CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1282 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520040.671.173.1smoke42.671.774.3OpenBenchmarking.orgCelsius, Fewer Is Betternginx 1.23.2CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520053.8120.9126.1smoke53.9117.1126.3OpenBenchmarking.orgWatts, Fewer Is Betternginx 1.23.2System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 2055 Joules per run.
OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.23.2Connections: 200EPYC 4124P @ DDR5-5200smoke8K16K24K32K40KMin: 47657.57 / Avg: 47788.24 / Max: 47873.121. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2

oneDNN

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.4Harness: Recurrent Neural Network Training - Engine: CPUEPYC 4124P @ DDR5-5200smoke9001800270036004500SE +/- 1.52, N = 34388.644389.74MIN: 4379.53MIN: 4384.341. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
MinAvgMaxEPYC 4124P @ DDR5-520040048454950smoke40046364940OpenBenchmarking.orgMegahertz, More Is BetteroneDNN 3.4CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.460.266.3smoke16.658.766.4OpenBenchmarking.orgWatts, Fewer Is BetteroneDNN 3.4CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 963 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520039.454.959.9smoke41.856.361.8OpenBenchmarking.orgCelsius, Fewer Is BetteroneDNN 3.4CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520053.898.4109.8smoke54.796.4110.5OpenBenchmarking.orgWatts, Fewer Is BetteroneDNN 3.4System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1608 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.4Harness: Recurrent Neural Network Training - Engine: CPUEPYC 4124P @ DDR5-5200smoke8001600240032004000Min: 4385.66 / Avg: 4388.64 / Max: 4390.641. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OSPRay Studio

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 3 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPUEPYC 4124P @ DDR5-5200smoke12002400360048006000SE +/- 0.33, N = 354725497
MinAvgMaxEPYC 4124P @ DDR5-520040049205141smoke40048345141OpenBenchmarking.orgMegahertz, More Is BetterOSPRay Studio 1.0CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.265.875.9smoke16.864.275.3OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay Studio 1.0CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1052 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520044.168.172.4smoke47.068.673.3OpenBenchmarking.orgCelsius, Fewer Is BetterOSPRay Studio 1.0CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.4106.0118.3smoke55.0109.0118.1OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay Studio 1.0System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1696 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 3 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPUEPYC 4124P @ DDR5-5200smoke10002000300040005000Min: 5471 / Avg: 5471.67 / Max: 5472

Timed PHP Compilation

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed PHP Compilation 8.3.4Time To CompileEPYC 4124P @ DDR5-5200smoke20406080100SE +/- 0.04, N = 385.8086.53
MinAvgMaxEPYC 4124P @ DDR5-520040048155141smoke40048365141OpenBenchmarking.orgMegahertz, More Is BetterTimed PHP Compilation 8.3.4CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.556.574.6smoke16.955.874.1OpenBenchmarking.orgWatts, Fewer Is BetterTimed PHP Compilation 8.3.4CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1035 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520041.567.377.0smoke45.068.078.0OpenBenchmarking.orgCelsius, Fewer Is BetterTimed PHP Compilation 8.3.4CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.098.0119.2smoke54.499.7118.6OpenBenchmarking.orgWatts, Fewer Is BetterTimed PHP Compilation 8.3.4System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1796 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed PHP Compilation 8.3.4Time To CompileEPYC 4124P @ DDR5-5200smoke1632486480Min: 85.72 / Avg: 85.8 / Max: 85.87

OSPRay Studio

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 2 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPUEPYC 4124P @ DDR5-5200smoke20K40K60K80K100KSE +/- 134.02, N = 37790778522
MinAvgMaxEPYC 4124P @ DDR5-520040050095142smoke40048105141OpenBenchmarking.orgMegahertz, More Is BetterOSPRay Studio 1.0CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.164.775.6smoke16.464.875.6OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay Studio 1.0CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1035 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520044.968.572.9smoke46.468.872.5OpenBenchmarking.orgCelsius, Fewer Is BetterOSPRay Studio 1.0CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.9108.0118.4smoke54.7109.1118.4OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay Studio 1.0System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1728 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 2 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPUEPYC 4124P @ DDR5-5200smoke14K28K42K56K70KMin: 77769 / Avg: 77907 / Max: 78175

libavif avifenc

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 1.0Encoder Speed: 2EPYC 4124P @ DDR5-5200smoke20406080100SE +/- 0.03, N = 385.3985.591. (CXX) g++ options: -O3 -fPIC -lm
MinAvgMaxEPYC 4124P @ DDR5-520040048185141smoke492849935140OpenBenchmarking.orgMegahertz, More Is Betterlibavif avifenc 1.0CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.466.580.6smoke16.965.278.3OpenBenchmarking.orgWatts, Fewer Is Betterlibavif avifenc 1.0CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1108 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520040.874.278.6smoke44.575.681.3OpenBenchmarking.orgCelsius, Fewer Is Betterlibavif avifenc 1.0CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.2107.9123.4smoke53.9106.1122.1OpenBenchmarking.orgWatts, Fewer Is Betterlibavif avifenc 1.0System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1798 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 1.0Encoder Speed: 2EPYC 4124P @ DDR5-5200smoke1632486480Min: 85.33 / Avg: 85.39 / Max: 85.421. (CXX) g++ options: -O3 -fPIC -lm

OSPRay Studio

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 1 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPUEPYC 4124P @ DDR5-5200smoke17K34K51K68K85KSE +/- 181.95, N = 37637977123
MinAvgMaxEPYC 4124P @ DDR5-520040049055141smoke507750945141OpenBenchmarking.orgMegahertz, More Is BetterOSPRay Studio 1.0CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520013.966.276.9smoke18.166.776.1OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay Studio 1.0CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 992 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520045.068.372.5smoke46.068.973.6OpenBenchmarking.orgCelsius, Fewer Is BetterOSPRay Studio 1.0CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.9109.3119.6smoke54.9108.7119.0OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay Studio 1.0System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1639 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 1 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPUEPYC 4124P @ DDR5-5200smoke13K26K39K52K65KMin: 76153 / Avg: 76379 / Max: 76739

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 2 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPUEPYC 4124P @ DDR5-5200smoke10002000300040005000SE +/- 7.84, N = 346624686
MinAvgMaxEPYC 4124P @ DDR5-5200495951085141smoke40047715144OpenBenchmarking.orgMegahertz, More Is BetterOSPRay Studio 1.0CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520018.667.075.8smoke16.864.675.2OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay Studio 1.0CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1050 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520045.468.171.4smoke45.568.972.4OpenBenchmarking.orgCelsius, Fewer Is BetterOSPRay Studio 1.0CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.8107.8118.3smoke55.0104.7118.2OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay Studio 1.0System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1689 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 2 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPUEPYC 4124P @ DDR5-5200smoke8001600240032004000Min: 4654 / Avg: 4662.33 / Max: 4678

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 DragonEPYC 4124P @ DDR5-5200smoke3691215SE +/- 0.0183, N = 39.29489.2753MIN: 9.21 / MAX: 9.46MIN: 9.23 / MAX: 9.39
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterEmbree 4.3Binary: Pathtracer ISPC - Model: Asian DragonEPYC 4124P @ DDR5-5200smoke0.03170.06340.09510.12680.15850.1410.139
MinAvgMaxEPYC 4124P @ DDR5-520040049075135smoke494251215136OpenBenchmarking.orgMegahertz, More Is BetterEmbree 4.3CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.765.869.8smoke16.866.971.5OpenBenchmarking.orgWatts, Fewer Is BetterEmbree 4.3CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 922 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520043.162.363.6smoke46.065.667.5OpenBenchmarking.orgCelsius, Fewer Is BetterEmbree 4.3CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520055.4109.0112.4smoke54.8109.3115.0OpenBenchmarking.orgWatts, Fewer Is BetterEmbree 4.3System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1562 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.3Binary: Pathtracer ISPC - Model: Asian DragonEPYC 4124P @ DDR5-5200smoke3691215Min: 9.26 / Avg: 9.29 / Max: 9.32

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: sedovbigEPYC 4124P @ DDR5-5200smoke20406080100SE +/- 0.09, N = 380.1179.861. (CXX) g++ options: -fopenmp -lmpi_cxx -lmpi
MinAvgMaxEPYC 4124P @ DDR5-520040050195140smoke40047975137OpenBenchmarking.orgMegahertz, More Is BetterPennant 1.0.1CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.560.464.3smoke16.760.466.6OpenBenchmarking.orgWatts, Fewer Is BetterPennant 1.0.1CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 886 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520039.860.763.1smoke46.864.968.4OpenBenchmarking.orgCelsius, Fewer Is BetterPennant 1.0.1CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.3103.7107.2smoke54.6106.2111.3OpenBenchmarking.orgWatts, Fewer Is BetterPennant 1.0.1System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1556 Joules per run.
OpenBenchmarking.orgHydro Cycle Time - Seconds, Fewer Is BetterPennant 1.0.1Test: sedovbigEPYC 4124P @ DDR5-5200smoke1530456075Min: 79.96 / Avg: 80.11 / Max: 80.271. (CXX) g++ options: -fopenmp -lmpi_cxx -lmpi

OSPRay Studio

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 1 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPUEPYC 4124P @ DDR5-5200smoke10002000300040005000SE +/- 8.25, N = 345844591
MinAvgMaxEPYC 4124P @ DDR5-520040049025141smoke40047555140OpenBenchmarking.orgMegahertz, More Is BetterOSPRay Studio 1.0CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520015.967.076.3smoke16.362.675.9OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay Studio 1.0CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1027 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520043.068.673.1smoke45.068.073.1OpenBenchmarking.orgCelsius, Fewer Is BetterOSPRay Studio 1.0CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.2109.4119.2smoke54.5107.3119.0OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay Studio 1.0System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1677 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 1 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPUEPYC 4124P @ DDR5-5200smoke8001600240032004000Min: 4568 / Avg: 4583.67 / Max: 4596

Llama.cpp

Llama.cpp is a port of Facebook's LLaMA model in C/C++ developed by Georgi Gerganov. Llama.cpp allows the inference of LLaMA and other supported models in C/C++. For CPU inference Llama.cpp supports AVX2/AVX-512, ARM NEON, and other modern ISAs along with features like OpenBLAS usage. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b1808Model: llama-2-13b.Q4_0.ggufEPYC 4124P @ DDR5-5200smoke246810SE +/- 0.02, N = 36.176.651. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -march=native -mtune=native -lopenblas
OpenBenchmarking.orgTokens Per Second Per Watt, More Is BetterLlama.cpp b1808Model: llama-2-13b.Q4_0.ggufEPYC 4124P @ DDR5-5200smoke0.02520.05040.07560.10080.1260.1060.112
MinAvgMaxEPYC 4124P @ DDR5-5200492649435141smoke492949495140OpenBenchmarking.orgMegahertz, More Is BetterLlama.cpp b1808CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520014.458.062.7smoke17.259.665.5OpenBenchmarking.orgWatts, Fewer Is BetterLlama.cpp b1808CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 851 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520040.351.158.4smoke43.055.462.0OpenBenchmarking.orgCelsius, Fewer Is BetterLlama.cpp b1808CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.1102.5107.3smoke54.1103.3110.9OpenBenchmarking.orgWatts, Fewer Is BetterLlama.cpp b1808System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1469 Joules per run.
OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b1808Model: llama-2-13b.Q4_0.ggufEPYC 4124P @ DDR5-5200smoke3691215Min: 6.15 / Avg: 6.17 / Max: 6.21. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -march=native -mtune=native -lopenblas

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 CompileEPYC 4124P @ DDR5-5200smoke20406080100SE +/- 0.07, N = 379.5880.31
MinAvgMaxEPYC 4124P @ DDR5-5200493950365140smoke40044855140OpenBenchmarking.orgMegahertz, More Is BetterTimed FFmpeg Compilation 6.1CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520019.771.276.8smoke17.264.675.9OpenBenchmarking.orgWatts, Fewer Is BetterTimed FFmpeg Compilation 6.1CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1068 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520043.573.678.4smoke43.972.278.3OpenBenchmarking.orgCelsius, Fewer Is BetterTimed FFmpeg Compilation 6.1CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.5114.9120.4smoke55.0106.2120.1OpenBenchmarking.orgWatts, Fewer Is BetterTimed FFmpeg Compilation 6.1System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1724 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed FFmpeg Compilation 6.1Time To CompileEPYC 4124P @ DDR5-5200smoke1530456075Min: 79.44 / Avg: 79.58 / Max: 79.69

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: CPUEPYC 4124P @ DDR5-5200smoke0.19580.39160.58740.78320.979SE +/- 0.01, N = 40.810.87MIN: 0.17 / MAX: 1.12MIN: 0.21 / MAX: 1.15
OpenBenchmarking.orgM samples/sec Per Watt, More Is BetterLuxCoreRender 2.6Scene: Danish Mood - Acceleration: CPUEPYC 4124P @ DDR5-5200smoke0.00290.00580.00870.01160.01450.0120.013
MinAvgMaxEPYC 4124P @ DDR5-520040049525141smoke494050485067OpenBenchmarking.orgMegahertz, More Is BetterLuxCoreRender 2.6CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.869.876.0smoke16.369.576.0OpenBenchmarking.orgWatts, Fewer Is BetterLuxCoreRender 2.6CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 820 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520045.373.076.9smoke44.472.075.8OpenBenchmarking.orgCelsius, Fewer Is BetterLuxCoreRender 2.6CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.6112.5120.0smoke54.8111.8120.3OpenBenchmarking.orgWatts, Fewer Is BetterLuxCoreRender 2.6System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1350 Joules per run.
OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.6Scene: Danish Mood - Acceleration: CPUEPYC 4124P @ DDR5-5200smoke246810Min: 0.8 / Avg: 0.81 / Max: 0.84

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 - Decompression SpeedEPYC 4124P @ DDR5-5200smoke400800120016002000SE +/- 0.57, N = 31810.31785.41. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.orgMB/s Per Watt, More Is BetterZstd Compression 1.5.4Compression Level: 19, Long Mode - Decompression SpeedEPYC 4124P @ DDR5-5200smoke112233445548.2946.11
MinAvgMaxEPYC 4124P @ DDR5-520040049295142smoke40048225140OpenBenchmarking.orgMegahertz, More Is BetterZstd Compression 1.5.4CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.437.549.9smoke17.338.747.4OpenBenchmarking.orgWatts, Fewer Is BetterZstd Compression 1.5.4CPU Power Consumption Monitor14284256701. EPYC 4124P @ DDR5-5200: Approximate power consumption of 562 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520042.056.061.3smoke43.359.870.0OpenBenchmarking.orgCelsius, Fewer Is BetterZstd Compression 1.5.4CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.075.090.2smoke53.977.692.7OpenBenchmarking.orgWatts, Fewer Is BetterZstd Compression 1.5.4System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1150 Joules per run.
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 19, Long Mode - Decompression SpeedEPYC 4124P @ DDR5-5200smoke30060090012001500Min: 1809.2 / Avg: 1810.3 / Max: 1811.11. (CC) gcc options: -O3 -pthread -lz -llzma

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 19, Long Mode - Compression SpeedEPYC 4124P @ DDR5-5200smoke3691215SE +/- 0.04, N = 39.008.901. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 19, Long Mode - Compression SpeedEPYC 4124P @ DDR5-5200smoke3691215Min: 8.92 / Avg: 9 / Max: 9.061. (CC) gcc options: -O3 -pthread -lz -llzma

VVenC

OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.11Video Input: Bosphorus 4K - Video Preset: FasterEPYC 4124P @ DDR5-5200smoke246810SE +/- 0.002, N = 37.7427.6971. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterVVenC 1.11Video Input: Bosphorus 4K - Video Preset: FasterEPYC 4124P @ DDR5-5200smoke0.02410.04820.07230.09640.12050.1030.107
MinAvgMaxEPYC 4124P @ DDR5-520040048975141smoke493349865045OpenBenchmarking.orgMegahertz, More Is BetterVVenC 1.11CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.074.980.4smoke16.572.179.4OpenBenchmarking.orgWatts, Fewer Is BetterVVenC 1.11CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1098 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520043.676.478.4smoke45.676.980.1OpenBenchmarking.orgCelsius, Fewer Is BetterVVenC 1.11CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520055.6119.6127.0smoke55.6117.3126.2OpenBenchmarking.orgWatts, Fewer Is BetterVVenC 1.11System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1753 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.11Video Input: Bosphorus 4K - Video Preset: FasterEPYC 4124P @ DDR5-5200smoke3691215Min: 7.74 / Avg: 7.74 / Max: 7.741. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects

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 SecondEPYC 4124P @ DDR5-5200smoke50K100K150K200K250KSE +/- 165.60, N = 3254797.57251757.051. (CC) gcc options: -O2 -lrt" -lrt
OpenBenchmarking.orgIterations/Sec Per Watt, More Is BetterCoremark 1.0CoreMark Size 666 - Iterations Per SecondEPYC 4124P @ DDR5-5200smoke80016002400320040003694.053770.11
MinAvgMaxEPYC 4124P @ DDR5-520040048685140smoke499350245141OpenBenchmarking.orgMegahertz, More Is BetterCoremark 1.0CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.969.075.0smoke19.966.872.2OpenBenchmarking.orgWatts, Fewer Is BetterCoremark 1.0CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1012 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520037.872.074.0smoke52.175.177.4OpenBenchmarking.orgCelsius, Fewer Is BetterCoremark 1.0CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520053.7108.3114.2smoke53.9108.4112.9OpenBenchmarking.orgWatts, Fewer Is BetterCoremark 1.0System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1625 Joules per run.
OpenBenchmarking.orgIterations/Sec, More Is BetterCoremark 1.0CoreMark Size 666 - Iterations Per SecondEPYC 4124P @ DDR5-5200smoke40K80K120K160K200KMin: 254567.63 / Avg: 254797.57 / Max: 255118.991. (CC) gcc options: -O2 -lrt" -lrt

oneDNN

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.4Harness: Recurrent Neural Network Inference - Engine: CPUEPYC 4124P @ DDR5-5200smoke5001000150020002500SE +/- 0.34, N = 32274.052268.56MIN: 2268.03MIN: 2264.081. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
MinAvgMaxEPYC 4124P @ DDR5-5200493349394940smoke493649445005OpenBenchmarking.orgMegahertz, More Is BetteroneDNN 3.4CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520021.660.266.2smoke18.460.366.8OpenBenchmarking.orgWatts, Fewer Is BetteroneDNN 3.4CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 904 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520045.154.758.0smoke46.457.260.4OpenBenchmarking.orgCelsius, Fewer Is BetteroneDNN 3.4CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.199.3109.7smoke54.499.5108.3OpenBenchmarking.orgWatts, Fewer Is BetteroneDNN 3.4System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1490 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.4Harness: Recurrent Neural Network Inference - Engine: CPUEPYC 4124P @ DDR5-5200smoke400800120016002000Min: 2273.37 / Avg: 2274.05 / Max: 2274.411. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -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: LU.CEPYC 4124P @ DDR5-5200smoke6K12K18K24K30KSE +/- 7.85, N = 326610.4926772.721. (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
OpenBenchmarking.orgTotal Mop/s Per Watt, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: LU.CEPYC 4124P @ DDR5-5200smoke110220330440550516.24501.48
MinAvgMaxEPYC 4124P @ DDR5-520040049785142smoke492150665139OpenBenchmarking.orgMegahertz, More Is BetterNAS Parallel Benchmarks 3.4CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.351.555.1smoke16.953.457.5OpenBenchmarking.orgWatts, Fewer Is BetterNAS Parallel Benchmarks 3.4CPU Power Consumption Monitor16324864801. EPYC 4124P @ DDR5-5200: Approximate power consumption of 756 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520040.153.154.9smoke45.559.761.3OpenBenchmarking.orgCelsius, Fewer Is BetterNAS Parallel Benchmarks 3.4CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.391.395.3smoke55.995.198.7OpenBenchmarking.orgWatts, Fewer Is BetterNAS Parallel Benchmarks 3.4System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1339 Joules per run.
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: LU.CEPYC 4124P @ DDR5-5200smoke5K10K15K20K25KMin: 26595.85 / Avg: 26610.49 / Max: 26622.71. (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

Redis

Redis is an open-source in-memory data structure store, used as a database, cache, and message broker. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 7.0.4Test: SET - Parallel Connections: 500EPYC 4124P @ DDR5-5200smoke900K1800K2700K3600K4500KSE +/- 49590.70, N = 153976817.023982548.251. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
OpenBenchmarking.orgRequests Per Second Per Watt, More Is BetterRedis 7.0.4Test: SET - Parallel Connections: 500EPYC 4124P @ DDR5-5200smoke20K40K60K80K100K108458.65113333.76
MinAvgMaxEPYC 4124P @ DDR5-520040041555147OpenBenchmarking.orgMegahertz, More Is BetterRedis 7.0.4CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520015.936.756.9OpenBenchmarking.orgWatts, Fewer Is BetterRedis 7.0.4CPU Power Consumption Monitor16324864801. EPYC 4124P @ DDR5-5200: Approximate power consumption of 147 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520041.059.672.1OpenBenchmarking.orgCelsius, Fewer Is BetterRedis 7.0.4CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.373.994.7OpenBenchmarking.orgWatts, Fewer Is BetterRedis 7.0.4System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 301 Joules per run.
OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 7.0.4Test: SET - Parallel Connections: 500EPYC 4124P @ DDR5-5200smoke700K1400K2100K2800K3500KMin: 3559036 / Avg: 3976817.02 / Max: 41319641. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

OpenVINO

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Machine Translation EN To DE FP16 - Device: CPUEPYC 4124P @ DDR5-5200smoke20406080100SE +/- 0.99, N = 490.3391.42MIN: 51.71 / MAX: 101.44MIN: 81.93 / MAX: 97.731. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
MinAvgMaxEPYC 4124P @ DDR5-520040047454940smoke40045894940OpenBenchmarking.orgMegahertz, More Is BetterOpenVINO 2024.0CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.262.769.8smoke13.661.269.1OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2024.0CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 721 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520040.356.759.4smoke41.858.260.4OpenBenchmarking.orgCelsius, Fewer Is BetterOpenVINO 2024.0CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.7104.5110.0smoke54.3100.4109.4OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2024.0System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1228 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Machine Translation EN To DE FP16 - Device: CPUEPYC 4124P @ DDR5-5200smoke20406080100Min: 88.14 / Avg: 90.33 / Max: 92.651. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Machine Translation EN To DE FP16 - Device: CPUEPYC 4124P @ DDR5-5200smoke1020304050SE +/- 0.49, N = 444.2743.731. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Machine Translation EN To DE FP16 - Device: CPUEPYC 4124P @ DDR5-5200smoke918273645Min: 43.15 / Avg: 44.27 / Max: 45.351. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

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 - Decompression SpeedEPYC 4124P @ DDR5-5200smoke400800120016002000SE +/- 6.89, N = 31904.71895.01. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.orgMB/s Per Watt, More Is BetterZstd Compression 1.5.4Compression Level: 19 - Decompression SpeedEPYC 4124P @ DDR5-5200smoke102030405043.8044.06
MinAvgMaxEPYC 4124P @ DDR5-520040050255142smoke494951265141OpenBenchmarking.orgMegahertz, More Is BetterZstd Compression 1.5.4CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.243.559.8smoke17.743.058.4OpenBenchmarking.orgWatts, Fewer Is BetterZstd Compression 1.5.4CPU Power Consumption Monitor16324864801. EPYC 4124P @ DDR5-5200: Approximate power consumption of 623 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520042.860.469.3smoke43.962.672.5OpenBenchmarking.orgCelsius, Fewer Is BetterZstd Compression 1.5.4CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520053.582.4103.8smoke54.482.5100.7OpenBenchmarking.orgWatts, Fewer Is BetterZstd Compression 1.5.4System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1181 Joules per run.
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 19 - Decompression SpeedEPYC 4124P @ DDR5-5200smoke30060090012001500Min: 1896 / Avg: 1904.7 / Max: 1918.31. (CC) gcc options: -O3 -pthread -lz -llzma

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 19 - Compression SpeedEPYC 4124P @ DDR5-5200smoke48121620SE +/- 0.18, N = 314.915.01. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 19 - Compression SpeedEPYC 4124P @ DDR5-5200smoke48121620Min: 14.6 / Avg: 14.87 / Max: 15.21. (CC) gcc options: -O3 -pthread -lz -llzma

Chaos Group V-RAY

OpenBenchmarking.orgvsamples, More Is BetterChaos Group V-RAY 6.0Mode: CPUEPYC 4124P @ DDR5-5200smoke2K4K6K8K10KSE +/- 5.33, N = 31123811183
OpenBenchmarking.orgvsamples Per Watt, More Is BetterChaos Group V-RAY 6.0Mode: CPUEPYC 4124P @ DDR5-5200smoke4080120160200172.04180.54
MinAvgMaxEPYC 4124P @ DDR5-520040049845141smoke493950875141OpenBenchmarking.orgMegahertz, More Is BetterChaos Group V-RAY 6.0CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.965.376.2smoke16.661.976.3OpenBenchmarking.orgWatts, Fewer Is BetterChaos Group V-RAY 6.0CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 893 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520044.869.373.1smoke45.567.172.5OpenBenchmarking.orgCelsius, Fewer Is BetterChaos Group V-RAY 6.0CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520055.3107.6119.9smoke54.2106.7119.8OpenBenchmarking.orgWatts, Fewer Is BetterChaos Group V-RAY 6.0System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1506 Joules per run.
OpenBenchmarking.orgvsamples, More Is BetterChaos Group V-RAY 6.0Mode: CPUEPYC 4124P @ DDR5-5200smoke2K4K6K8K10KMin: 11233 / Avg: 11238.33 / Max: 11249

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: 1BEPYC 4124P @ DDR5-52001020304050SE +/- 0.01, N = 343.95
MinAvgMaxEPYC 4124P @ DDR5-5200492249635140OpenBenchmarking.orgMegahertz, More Is BetterY-Cruncher 0.8.3CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.667.781.8OpenBenchmarking.orgWatts, Fewer Is BetterY-Cruncher 0.8.3CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 587 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520043.668.375.0OpenBenchmarking.orgCelsius, Fewer Is BetterY-Cruncher 0.8.3CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.6113.8129.6OpenBenchmarking.orgWatts, Fewer Is BetterY-Cruncher 0.8.3System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 986 Joules per run.

TensorFlow

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 32 - Model: GoogLeNetEPYC 4124P @ DDR5-5200smoke1224364860SE +/- 0.02, N = 352.8352.79
OpenBenchmarking.orgimages/sec Per Watt, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 32 - Model: GoogLeNetEPYC 4124P @ DDR5-5200smoke0.22120.44240.66360.88481.1060.9430.983
MinAvgMaxEPYC 4124P @ DDR5-5200493649555140smoke493649404941OpenBenchmarking.orgMegahertz, More Is BetterTensorFlow 2.16.1CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.056.060.6smoke16.653.760.2OpenBenchmarking.orgWatts, Fewer Is BetterTensorFlow 2.16.1CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 728 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520041.656.157.1smoke42.155.457.5OpenBenchmarking.orgCelsius, Fewer Is BetterTensorFlow 2.16.1CPU Temperature Monitor1632486480
MinAvgMaxEPYC 4124P @ DDR5-520054.596.0101.3smoke53.793.5100.6OpenBenchmarking.orgWatts, Fewer Is BetterTensorFlow 2.16.1System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1248 Joules per run.
OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 32 - Model: GoogLeNetEPYC 4124P @ DDR5-5200smoke1122334455Min: 52.81 / Avg: 52.83 / Max: 52.86

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: TradesoapEPYC 4124P @ DDR5-5200400800120016002000SE +/- 17.17, N = 92065
MinAvgMaxEPYC 4124P @ DDR5-520040048125141OpenBenchmarking.orgMegahertz, More Is BetterDaCapo Benchmark 23.11CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.448.265.3OpenBenchmarking.orgWatts, Fewer Is BetterDaCapo Benchmark 23.11CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 172 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520041.361.968.8OpenBenchmarking.orgCelsius, Fewer Is BetterDaCapo Benchmark 23.11CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520055.087.7109.4OpenBenchmarking.orgWatts, Fewer Is BetterDaCapo Benchmark 23.11System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 312 Joules per run.

Dragonflydb

Dragonfly is an open-source database server that is a "modern Redis replacement" that aims to be the fastest memory store while being compliant with the Redis and Memcached protocols. For benchmarking Dragonfly, Memtier_benchmark is used as a NoSQL Redis/Memcache traffic generation plus benchmarking tool developed by Redis Labs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOps/sec, More Is BetterDragonflydb 1.6.2Clients Per Thread: 10 - Set To Get Ratio: 1:100EPYC 4124P @ DDR5-5200smoke600K1200K1800K2400K3000KSE +/- 14179.49, N = 32629939.842634894.241. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
OpenBenchmarking.orgOps/sec Per Watt, More Is BetterDragonflydb 1.6.2Clients Per Thread: 10 - Set To Get Ratio: 1:100EPYC 4124P @ DDR5-5200smoke9K18K27K36K45K42019.4143420.58
MinAvgMaxEPYC 4124P @ DDR5-520040048765138smoke494150795114OpenBenchmarking.orgMegahertz, More Is BetterDragonflydb 1.6.2CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520023.962.671.1smoke16.560.770.1OpenBenchmarking.orgWatts, Fewer Is BetterDragonflydb 1.6.2CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 793 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520057.566.368.6smoke46.668.171.8OpenBenchmarking.orgCelsius, Fewer Is BetterDragonflydb 1.6.2CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.9102.1112.0smoke54.8101.5112.1OpenBenchmarking.orgWatts, Fewer Is BetterDragonflydb 1.6.2System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1293 Joules per run.
OpenBenchmarking.orgOps/sec, More Is BetterDragonflydb 1.6.2Clients Per Thread: 10 - Set To Get Ratio: 1:100EPYC 4124P @ DDR5-5200smoke500K1000K1500K2000K2500KMin: 2605167.34 / Avg: 2629939.84 / Max: 2654280.851. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

OpenBenchmarking.orgOps/sec, More Is BetterDragonflydb 1.6.2Clients Per Thread: 10 - Set To Get Ratio: 1:10EPYC 4124P @ DDR5-5200smoke600K1200K1800K2400K3000KSE +/- 20699.41, N = 32629619.362598346.061. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
OpenBenchmarking.orgOps/sec Per Watt, More Is BetterDragonflydb 1.6.2Clients Per Thread: 10 - Set To Get Ratio: 1:10EPYC 4124P @ DDR5-5200smoke9K18K27K36K45K41495.5943772.06
MinAvgMaxEPYC 4124P @ DDR5-520040049915139smoke40046915112OpenBenchmarking.orgMegahertz, More Is BetterDragonflydb 1.6.2CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.863.471.6smoke16.359.470.8OpenBenchmarking.orgWatts, Fewer Is BetterDragonflydb 1.6.2CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 803 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520042.065.968.8smoke46.868.372.1OpenBenchmarking.orgCelsius, Fewer Is BetterDragonflydb 1.6.2CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.7104.8112.5smoke54.7102.4112.7OpenBenchmarking.orgWatts, Fewer Is BetterDragonflydb 1.6.2System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1328 Joules per run.
OpenBenchmarking.orgOps/sec, More Is BetterDragonflydb 1.6.2Clients Per Thread: 10 - Set To Get Ratio: 1:10EPYC 4124P @ DDR5-5200smoke500K1000K1500K2000K2500KMin: 2599721.69 / Avg: 2629619.36 / Max: 2669367.261. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

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: 1:10EPYC 4124P @ DDR5-5200smoke200K400K600K800K1000KSE +/- 2338.48, N = 31117437.501112711.411. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
OpenBenchmarking.orgOps/sec Per Watt, More Is BetterMemcached 1.6.19Set To Get Ratio: 1:10EPYC 4124P @ DDR5-5200smoke4K8K12K16K20K17921.3317965.79
MinAvgMaxEPYC 4124P @ DDR5-520040046345140smoke40044365115OpenBenchmarking.orgMegahertz, More Is BetterMemcached 1.6.19CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.662.473.0smoke15.961.972.5OpenBenchmarking.orgWatts, Fewer Is BetterMemcached 1.6.19CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 790 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520040.864.268.6smoke44.468.172.5OpenBenchmarking.orgCelsius, Fewer Is BetterMemcached 1.6.19CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.0102.1112.9smoke54.0100.6113.8OpenBenchmarking.orgWatts, Fewer Is BetterMemcached 1.6.19System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1259 Joules per run.
OpenBenchmarking.orgOps/sec, More Is BetterMemcached 1.6.19Set To Get Ratio: 1:10EPYC 4124P @ DDR5-5200smoke200K400K600K800K1000KMin: 1112764.84 / Avg: 1117437.5 / Max: 1119947.61. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

OpenBenchmarking.orgOps/sec, More Is BetterMemcached 1.6.19Set To Get Ratio: 1:100EPYC 4124P @ DDR5-5200smoke200K400K600K800K1000KSE +/- 1131.60, N = 31068869.521061151.621. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
OpenBenchmarking.orgOps/sec Per Watt, More Is BetterMemcached 1.6.19Set To Get Ratio: 1:100EPYC 4124P @ DDR5-5200smoke4K8K12K16K20K16914.2817180.01
MinAvgMaxEPYC 4124P @ DDR5-520040048585140smoke40047015115OpenBenchmarking.orgMegahertz, More Is BetterMemcached 1.6.19CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.863.272.0smoke17.061.872.3OpenBenchmarking.orgWatts, Fewer Is BetterMemcached 1.6.19CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 758 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520040.064.567.9smoke43.467.572.6OpenBenchmarking.orgCelsius, Fewer Is BetterMemcached 1.6.19CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.0102.8111.7smoke54.6103.4113.6OpenBenchmarking.orgWatts, Fewer Is BetterMemcached 1.6.19System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1234 Joules per run.
OpenBenchmarking.orgOps/sec, More Is BetterMemcached 1.6.19Set To Get Ratio: 1:100EPYC 4124P @ DDR5-5200smoke200K400K600K800K1000KMin: 1067056.41 / Avg: 1068869.52 / Max: 1070949.131. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

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: CPUEPYC 4124P @ DDR5-5200smoke0.49730.99461.49191.98922.4865SE +/- 0.00, N = 32.212.21MIN: 2.13 / MAX: 2.24MIN: 2.13 / MAX: 2.24
OpenBenchmarking.orgM samples/sec Per Watt, More Is BetterLuxCoreRender 2.6Scene: Orange Juice - Acceleration: CPUEPYC 4124P @ DDR5-5200smoke0.0070.0140.0210.0280.0350.0310.031
MinAvgMaxEPYC 4124P @ DDR5-520040048905141smoke500750295141OpenBenchmarking.orgMegahertz, More Is BetterLuxCoreRender 2.6CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520020.972.278.2smoke17.771.578.1OpenBenchmarking.orgWatts, Fewer Is BetterLuxCoreRender 2.6CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 866 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520048.674.676.9smoke45.373.576.6OpenBenchmarking.orgCelsius, Fewer Is BetterLuxCoreRender 2.6CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520055.0116.7121.4smoke55.0113.0121.2OpenBenchmarking.orgWatts, Fewer Is BetterLuxCoreRender 2.6System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1401 Joules per run.
OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.6Scene: Orange Juice - Acceleration: CPUEPYC 4124P @ DDR5-5200smoke246810Min: 2.21 / Avg: 2.21 / Max: 2.22

TensorFlow

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 64 - Model: AlexNetEPYC 4124P @ DDR5-5200smoke306090120150SE +/- 0.04, N = 3113.02112.77
OpenBenchmarking.orgimages/sec Per Watt, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 64 - Model: AlexNetEPYC 4124P @ DDR5-5200smoke0.49860.99721.49581.99442.4932.2162.205
MinAvgMaxEPYC 4124P @ DDR5-520040047085144smoke40045914941OpenBenchmarking.orgMegahertz, More Is BetterTensorFlow 2.16.1CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.451.056.7smoke15.851.255.2OpenBenchmarking.orgWatts, Fewer Is BetterTensorFlow 2.16.1CPU Power Consumption Monitor16324864801. EPYC 4124P @ DDR5-5200: Approximate power consumption of 612 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520043.052.455.4smoke43.353.455.4OpenBenchmarking.orgCelsius, Fewer Is BetterTensorFlow 2.16.1CPU Temperature Monitor1530456075
MinAvgMaxEPYC 4124P @ DDR5-520054.291.797.7smoke55.089.294.2OpenBenchmarking.orgWatts, Fewer Is BetterTensorFlow 2.16.1System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1101 Joules per run.
OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 64 - Model: AlexNetEPYC 4124P @ DDR5-5200smoke20406080100Min: 112.96 / Avg: 113.02 / Max: 113.09

GraphicsMagick

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.43Operation: SharpenEPYC 4124P @ DDR5-5200smoke48121620SE +/- 0.00, N = 316161. (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 Per Watt, More Is BetterGraphicsMagick 1.3.43Operation: SharpenEPYC 4124P @ DDR5-5200smoke0.05490.10980.16470.21960.27450.2440.243
MinAvgMaxEPYC 4124P @ DDR5-520040048705142smoke494151085141OpenBenchmarking.orgMegahertz, More Is BetterGraphicsMagick 1.3.43CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.165.571.2smoke16.765.871.2OpenBenchmarking.orgWatts, Fewer Is BetterGraphicsMagick 1.3.43CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 808 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520039.166.868.9smoke41.667.870.5OpenBenchmarking.orgCelsius, Fewer Is BetterGraphicsMagick 1.3.43CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.1106.0110.8smoke53.9105.7110.8OpenBenchmarking.orgWatts, Fewer Is BetterGraphicsMagick 1.3.43System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1272 Joules per run.
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.43Operation: SharpenEPYC 4124P @ DDR5-5200smoke48121620Min: 16 / Avg: 16 / Max: 161. (CC) gcc options: -fopenmp -O2 -ltiff -ljbig -lsharpyuv -lwebp -lwebpmux -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lxml2 -lzstd -llzma -lbz2 -lz -lm -lpthread -lgomp

OpenVINO

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Face Detection FP16 - Device: CPUEPYC 4124P @ DDR5-5200smoke2004006008001000SE +/- 1.02, N = 31135.611134.75MIN: 1110.52 / MAX: 1148.03MIN: 1112.81 / MAX: 1144.791. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
MinAvgMaxEPYC 4124P @ DDR5-520040048175139smoke493749434978OpenBenchmarking.orgMegahertz, More Is BetterOpenVINO 2024.0CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.262.668.1smoke16.561.268.6OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2024.0CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 709 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520037.858.360.3smoke41.060.063.1OpenBenchmarking.orgCelsius, Fewer Is BetterOpenVINO 2024.0CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520053.8103.5108.0smoke54.0100.6109.3OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2024.0System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1207 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Face Detection FP16 - Device: CPUEPYC 4124P @ DDR5-5200smoke2004006008001000Min: 1134.19 / Avg: 1135.61 / Max: 1137.591. (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: CPUEPYC 4124P @ DDR5-5200smoke0.78981.57962.36943.15923.949SE +/- 0.00, N = 33.513.511. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Face Detection FP16 - Device: CPUEPYC 4124P @ DDR5-5200smoke246810Min: 3.51 / Avg: 3.51 / Max: 3.521. (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: CPUEPYC 4124P @ DDR5-5200smoke0.22730.45460.68190.90921.1365SE +/- 0.00, N = 31.011.00MIN: 0.25 / MAX: 1.3MIN: 0.25 / MAX: 1.29
OpenBenchmarking.orgM samples/sec Per Watt, More Is BetterLuxCoreRender 2.6Scene: LuxCore Benchmark - Acceleration: CPUEPYC 4124P @ DDR5-5200smoke0.00340.00680.01020.01360.0170.0140.015
MinAvgMaxEPYC 4124P @ DDR5-520040048855138smoke497150295143OpenBenchmarking.orgMegahertz, More Is BetterLuxCoreRender 2.6CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520029.072.478.1smoke16.468.278.2OpenBenchmarking.orgWatts, Fewer Is BetterLuxCoreRender 2.6CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 820 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520062.375.978.3smoke45.973.078.3OpenBenchmarking.orgCelsius, Fewer Is BetterLuxCoreRender 2.6CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.9116.0122.3smoke54.9115.6121.9OpenBenchmarking.orgWatts, Fewer Is BetterLuxCoreRender 2.6System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1392 Joules per run.
OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.6Scene: LuxCore Benchmark - Acceleration: CPUEPYC 4124P @ DDR5-5200smoke246810Min: 1 / Avg: 1.01 / Max: 1.01

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 - Decompression SpeedEPYC 4124P @ DDR5-5200smoke5001000150020002500SE +/- 1.61, N = 32219.12234.01. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.orgMB/s Per Watt, More Is BetterZstd Compression 1.5.4Compression Level: 8, Long Mode - Decompression SpeedEPYC 4124P @ DDR5-5200smoke102030405044.7346.13
MinAvgMaxEPYC 4124P @ DDR5-520040050035141smoke506751315141OpenBenchmarking.orgMegahertz, More Is BetterZstd Compression 1.5.4CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520023.949.656.7smoke23.548.455.0OpenBenchmarking.orgWatts, Fewer Is BetterZstd Compression 1.5.4CPU Power Consumption Monitor16324864801. EPYC 4124P @ DDR5-5200: Approximate power consumption of 595 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520056.166.770.3smoke57.367.470.8OpenBenchmarking.orgCelsius, Fewer Is BetterZstd Compression 1.5.4CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.490.2113.5smoke54.896.2115.7OpenBenchmarking.orgWatts, Fewer Is BetterZstd Compression 1.5.4System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1082 Joules per run.
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 8, Long Mode - Decompression SpeedEPYC 4124P @ DDR5-5200smoke400800120016002000Min: 2216.1 / Avg: 2219.13 / Max: 2221.61. (CC) gcc options: -O3 -pthread -lz -llzma

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 8, Long Mode - Compression SpeedEPYC 4124P @ DDR5-5200smoke70140210280350SE +/- 0.48, N = 3323.0322.51. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 8, Long Mode - Compression SpeedEPYC 4124P @ DDR5-5200smoke60120180240300Min: 322.1 / Avg: 323.03 / Max: 323.71. (CC) gcc options: -O3 -pthread -lz -llzma

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 12 - Decompression SpeedEPYC 4124P @ DDR5-5200smoke5001000150020002500SE +/- 1.51, N = 32285.32263.71. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.orgMB/s Per Watt, More Is BetterZstd Compression 1.5.4Compression Level: 12 - Decompression SpeedEPYC 4124P @ DDR5-5200smoke122436486053.0553.57
MinAvgMaxEPYC 4124P @ DDR5-520040048765214smoke40047445141OpenBenchmarking.orgMegahertz, More Is BetterZstd Compression 1.5.4CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.243.151.4smoke16.442.351.0OpenBenchmarking.orgWatts, Fewer Is BetterZstd Compression 1.5.4CPU Power Consumption Monitor15304560751. EPYC 4124P @ DDR5-5200: Approximate power consumption of 531 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520043.459.468.5smoke44.859.165.6OpenBenchmarking.orgCelsius, Fewer Is BetterZstd Compression 1.5.4CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520055.284.3102.1smoke54.185.1103.2OpenBenchmarking.orgWatts, Fewer Is BetterZstd Compression 1.5.4System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1039 Joules per run.
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 12 - Decompression SpeedEPYC 4124P @ DDR5-5200smoke400800120016002000Min: 2282.3 / Avg: 2285.3 / Max: 2287.11. (CC) gcc options: -O3 -pthread -lz -llzma

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 12 - Compression SpeedEPYC 4124P @ DDR5-5200smoke306090120150SE +/- 0.15, N = 3114.3115.31. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 12 - Compression SpeedEPYC 4124P @ DDR5-5200smoke20406080100Min: 114 / Avg: 114.3 / Max: 114.51. (CC) gcc options: -O3 -pthread -lz -llzma

OpenVINO

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Face Detection FP16-INT8 - Device: CPUEPYC 4124P @ DDR5-5200smoke130260390520650SE +/- 0.48, N = 3585.23581.53MIN: 563.46 / MAX: 593.11MIN: 566.88 / MAX: 592.741. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
MinAvgMaxEPYC 4124P @ DDR5-5200493749455027smoke493849414951OpenBenchmarking.orgMegahertz, More Is BetterOpenVINO 2024.0CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.060.867.8smoke22.562.467.3OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2024.0CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 709 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520040.857.961.5smoke50.961.563.0OpenBenchmarking.orgCelsius, Fewer Is BetterOpenVINO 2024.0CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.3100.4106.5smoke54.0101.9106.8OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2024.0System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1172 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Face Detection FP16-INT8 - Device: CPUEPYC 4124P @ DDR5-5200smoke100200300400500Min: 584.64 / Avg: 585.23 / Max: 586.171. (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-INT8 - Device: CPUEPYC 4124P @ DDR5-5200smoke246810SE +/- 0.01, N = 36.816.851. (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-INT8 - Device: CPUEPYC 4124P @ DDR5-5200smoke3691215Min: 6.8 / Avg: 6.81 / Max: 6.821. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

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 - Decompression SpeedEPYC 4124P @ DDR5-5200smoke5001000150020002500SE +/- 9.44, N = 32206.82230.61. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.orgMB/s Per Watt, More Is BetterZstd Compression 1.5.4Compression Level: 8 - Decompression SpeedEPYC 4124P @ DDR5-5200smoke112233445544.5046.62
MinAvgMaxEPYC 4124P @ DDR5-520040049905141smoke493950945141OpenBenchmarking.orgMegahertz, More Is BetterZstd Compression 1.5.4CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520026.449.657.3smoke16.847.956.9OpenBenchmarking.orgWatts, Fewer Is BetterZstd Compression 1.5.4CPU Power Consumption Monitor16324864801. EPYC 4124P @ DDR5-5200: Approximate power consumption of 579 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520054.667.170.3smoke46.166.271.3OpenBenchmarking.orgCelsius, Fewer Is BetterZstd Compression 1.5.4CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.892.7114.7smoke54.691.6115.3OpenBenchmarking.orgWatts, Fewer Is BetterZstd Compression 1.5.4System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1112 Joules per run.
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 8 - Decompression SpeedEPYC 4124P @ DDR5-5200smoke400800120016002000Min: 2194.2 / Avg: 2206.83 / Max: 2225.31. (CC) gcc options: -O3 -pthread -lz -llzma

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 8 - Compression SpeedEPYC 4124P @ DDR5-5200smoke70140210280350SE +/- 0.98, N = 3330.3333.01. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 8 - Compression SpeedEPYC 4124P @ DDR5-5200smoke60120180240300Min: 329.3 / Avg: 330.33 / Max: 332.31. (CC) gcc options: -O3 -pthread -lz -llzma

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: BM1EPYC 4124P @ DDR5-5200smoke3691215SE +/- 0.00, N = 312.9112.911. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm
OpenBenchmarking.orgBillion Interactions/s Per Watt, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM1EPYC 4124P @ DDR5-5200smoke0.05290.10580.15870.21160.26450.2350.229
MinAvgMaxEPYC 4124P @ DDR5-520040045404941smoke494049414941OpenBenchmarking.orgMegahertz, More Is BetterminiBUDE 20210901CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520015.955.158.7smoke18.856.560.7OpenBenchmarking.orgWatts, Fewer Is BetterminiBUDE 20210901CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 624 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520037.453.154.8smoke46.158.861.0OpenBenchmarking.orgCelsius, Fewer Is BetterminiBUDE 20210901CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.793.795.4smoke53.993.898.4OpenBenchmarking.orgWatts, Fewer Is BetterminiBUDE 20210901System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1062 Joules per run.
OpenBenchmarking.orgBillion Interactions/s, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM1EPYC 4124P @ DDR5-5200smoke48121620Min: 12.91 / Avg: 12.91 / Max: 12.921. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm

OpenBenchmarking.orgGFInst/s, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM1EPYC 4124P @ DDR5-5200smoke70140210280350SE +/- 0.06, N = 3322.86322.731. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm
OpenBenchmarking.orgGFInst/s, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM1EPYC 4124P @ DDR5-5200smoke60120180240300Min: 322.75 / Avg: 322.86 / Max: 322.951. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm

DaCapo Benchmark

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

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Apache TomcatEPYC 4124P @ DDR5-52003K6K9K12K15KSE +/- 11.72, N = 312840
MinAvgMaxEPYC 4124P @ DDR5-520040045885140OpenBenchmarking.orgMegahertz, More Is BetterDaCapo Benchmark 23.11CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.031.644.2OpenBenchmarking.orgWatts, Fewer Is BetterDaCapo Benchmark 23.11CPU Power Consumption Monitor12243648601. EPYC 4124P @ DDR5-5200: Approximate power consumption of 253 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520042.449.164.1OpenBenchmarking.orgCelsius, Fewer Is BetterDaCapo Benchmark 23.11CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520053.867.293.0OpenBenchmarking.orgWatts, Fewer Is BetterDaCapo Benchmark 23.11System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 537 Joules per run.

GraphicsMagick

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.43Operation: EnhancedEPYC 4124P @ DDR5-5200smoke612182430SE +/- 0.00, N = 326261. (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 Per Watt, More Is BetterGraphicsMagick 1.3.43Operation: EnhancedEPYC 4124P @ DDR5-5200smoke0.08840.17680.26520.35360.4420.3850.393
MinAvgMaxEPYC 4124P @ DDR5-520040048655141smoke40047535140OpenBenchmarking.orgMegahertz, More Is BetterGraphicsMagick 1.3.43CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.467.572.6smoke16.266.272.3OpenBenchmarking.orgWatts, Fewer Is BetterGraphicsMagick 1.3.43CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 810 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520044.068.269.8smoke45.468.670.9OpenBenchmarking.orgCelsius, Fewer Is BetterGraphicsMagick 1.3.43CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520055.7107.0112.8smoke55.7104.2112.9OpenBenchmarking.orgWatts, Fewer Is BetterGraphicsMagick 1.3.43System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1284 Joules per run.
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.43Operation: EnhancedEPYC 4124P @ DDR5-5200smoke612182430Min: 26 / Avg: 26 / Max: 261. (CC) gcc options: -fopenmp -O2 -ltiff -ljbig -lsharpyuv -lwebp -lwebpmux -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lxml2 -lzstd -llzma -lbz2 -lz -lm -lpthread -lgomp

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: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: ParallelEPYC 4124P @ DDR5-5200smoke612182430SE +/- 0.01, N = 323.7923.961. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
MinAvgMaxEPYC 4124P @ DDR5-520040048295140smoke494051025140OpenBenchmarking.orgMegahertz, More Is BetterONNX Runtime 1.17CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.842.946.4smoke16.340.544.8OpenBenchmarking.orgWatts, Fewer Is BetterONNX Runtime 1.17CPU Power Consumption Monitor14284256701. EPYC 4124P @ DDR5-5200: Approximate power consumption of 472 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520038.954.761.9smoke42.454.957.1OpenBenchmarking.orgCelsius, Fewer Is BetterONNX Runtime 1.17CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520053.880.284.3smoke54.077.783.0OpenBenchmarking.orgWatts, Fewer Is BetterONNX Runtime 1.17System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 909 Joules per run.
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: ParallelEPYC 4124P @ DDR5-5200smoke612182430Min: 23.76 / Avg: 23.79 / Max: 23.81. (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: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: ParallelEPYC 4124P @ DDR5-5200smoke1020304050SE +/- 0.02, N = 342.0441.731. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: ParallelEPYC 4124P @ DDR5-5200smoke612182430SE +/- 0.01, N = 323.7923.961. (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: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: ParallelEPYC 4124P @ DDR5-5200smoke918273645Min: 42.01 / Avg: 42.04 / Max: 42.081. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: GPT-2 - Device: CPU - Executor: ParallelEPYC 4124P @ DDR5-5200smoke3691215SE +/- 0.01011, N = 39.292459.239531. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
MinAvgMaxEPYC 4124P @ DDR5-520040048135141smoke40045224935OpenBenchmarking.orgMegahertz, More Is BetterONNX Runtime 1.17CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.645.148.2smoke16.245.349.1OpenBenchmarking.orgWatts, Fewer Is BetterONNX Runtime 1.17CPU Power Consumption Monitor14284256701. EPYC 4124P @ DDR5-5200: Approximate power consumption of 541 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520038.844.147.3smoke40.646.147.5OpenBenchmarking.orgCelsius, Fewer Is BetterONNX Runtime 1.17CPU Temperature Monitor1428425670
MinAvgMaxEPYC 4124P @ DDR5-520054.286.388.9smoke55.586.590.0OpenBenchmarking.orgWatts, Fewer Is BetterONNX Runtime 1.17System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1035 Joules per run.
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: GPT-2 - Device: CPU - Executor: ParallelEPYC 4124P @ DDR5-5200smoke3691215Min: 9.27 / Avg: 9.29 / Max: 9.311. (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: ParallelEPYC 4124P @ DDR5-5200smoke20406080100SE +/- 0.12, N = 3107.58108.201. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: GPT-2 - Device: CPU - Executor: ParallelEPYC 4124P @ DDR5-5200smoke3691215SE +/- 0.01011, N = 39.292459.239531. (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: ParallelEPYC 4124P @ DDR5-5200smoke20406080100Min: 107.4 / Avg: 107.58 / Max: 107.81. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: yolov4 - Device: CPU - Executor: ParallelEPYC 4124P @ DDR5-5200smoke50100150200250SE +/- 0.78, N = 3202.83206.511. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
MinAvgMaxEPYC 4124P @ DDR5-520040046814971smoke493549384940OpenBenchmarking.orgMegahertz, More Is BetterONNX Runtime 1.17CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520014.847.452.3smoke19.647.151.2OpenBenchmarking.orgWatts, Fewer Is BetterONNX Runtime 1.17CPU Power Consumption Monitor15304560751. EPYC 4124P @ DDR5-5200: Approximate power consumption of 553 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520039.651.954.4smoke45.652.654.3OpenBenchmarking.orgCelsius, Fewer Is BetterONNX Runtime 1.17CPU Temperature Monitor1530456075
MinAvgMaxEPYC 4124P @ DDR5-520053.284.689.2smoke53.485.291.2OpenBenchmarking.orgWatts, Fewer Is BetterONNX Runtime 1.17System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 987 Joules per run.
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: yolov4 - Device: CPU - Executor: ParallelEPYC 4124P @ DDR5-5200smoke4080120160200Min: 201.31 / Avg: 202.83 / Max: 203.841. (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: yolov4 - Device: CPU - Executor: ParallelEPYC 4124P @ DDR5-5200smoke1.10932.21863.32794.43725.5465SE +/- 0.01891, N = 34.930354.842341. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: yolov4 - Device: CPU - Executor: ParallelEPYC 4124P @ DDR5-5200smoke50100150200250SE +/- 0.78, N = 3202.83206.511. (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: yolov4 - Device: CPU - Executor: ParallelEPYC 4124P @ DDR5-5200smoke246810Min: 4.91 / Avg: 4.93 / Max: 4.971. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: bertsquad-12 - Device: CPU - Executor: ParallelEPYC 4124P @ DDR5-5200smoke306090120150SE +/- 1.38, N = 3153.15155.461. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
MinAvgMaxEPYC 4124P @ DDR5-5200492849435140smoke493549394941OpenBenchmarking.orgMegahertz, More Is BetterONNX Runtime 1.17CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.748.353.1smoke16.846.353.4OpenBenchmarking.orgWatts, Fewer Is BetterONNX Runtime 1.17CPU Power Consumption Monitor15304560751. EPYC 4124P @ DDR5-5200: Approximate power consumption of 563 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520039.451.653.8smoke42.954.456.0OpenBenchmarking.orgCelsius, Fewer Is BetterONNX Runtime 1.17CPU Temperature Monitor1632486480
MinAvgMaxEPYC 4124P @ DDR5-520052.485.594.0smoke54.082.991.0OpenBenchmarking.orgWatts, Fewer Is BetterONNX Runtime 1.17System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1025 Joules per run.
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: bertsquad-12 - Device: CPU - Executor: ParallelEPYC 4124P @ DDR5-5200smoke306090120150Min: 150.6 / Avg: 153.15 / Max: 155.351. (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: bertsquad-12 - Device: CPU - Executor: ParallelEPYC 4124P @ DDR5-5200smoke246810SE +/- 0.05918, N = 36.530466.432661. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: bertsquad-12 - Device: CPU - Executor: ParallelEPYC 4124P @ DDR5-5200smoke306090120150SE +/- 1.38, N = 3153.15155.461. (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: bertsquad-12 - Device: CPU - Executor: ParallelEPYC 4124P @ DDR5-5200smoke3691215Min: 6.44 / Avg: 6.53 / Max: 6.641. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: yolov4 - Device: CPU - Executor: StandardEPYC 4124P @ DDR5-5200smoke306090120150SE +/- 0.29, N = 3136.38136.151. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
MinAvgMaxEPYC 4124P @ DDR5-520040048115140smoke493749394940OpenBenchmarking.orgMegahertz, More Is BetterONNX Runtime 1.17CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.456.559.5smoke22.756.059.9OpenBenchmarking.orgWatts, Fewer Is BetterONNX Runtime 1.17CPU Power Consumption Monitor16324864801. EPYC 4124P @ DDR5-5200: Approximate power consumption of 622 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520039.953.554.6smoke49.156.257.4OpenBenchmarking.orgCelsius, Fewer Is BetterONNX Runtime 1.17CPU Temperature Monitor1632486480
MinAvgMaxEPYC 4124P @ DDR5-520053.995.298.7smoke53.895.299.7OpenBenchmarking.orgWatts, Fewer Is BetterONNX Runtime 1.17System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1079 Joules per run.
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: yolov4 - Device: CPU - Executor: StandardEPYC 4124P @ DDR5-5200smoke306090120150Min: 136.06 / Avg: 136.38 / Max: 136.951. (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: yolov4 - Device: CPU - Executor: StandardEPYC 4124P @ DDR5-5200smoke246810SE +/- 0.01542, N = 37.332317.344701. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: yolov4 - Device: CPU - Executor: StandardEPYC 4124P @ DDR5-5200smoke306090120150SE +/- 0.29, N = 3136.38136.151. (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: yolov4 - Device: CPU - Executor: StandardEPYC 4124P @ DDR5-5200smoke3691215Min: 7.3 / Avg: 7.33 / Max: 7.351. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -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: DLSC - Acceleration: CPUEPYC 4124P @ DDR5-5200smoke0.31730.63460.95191.26921.5865SE +/- 0.00, N = 31.411.41MIN: 1.37 / MAX: 1.44MIN: 1.37 / MAX: 1.43
OpenBenchmarking.orgM samples/sec Per Watt, More Is BetterLuxCoreRender 2.6Scene: DLSC - Acceleration: CPUEPYC 4124P @ DDR5-5200smoke0.00450.0090.01350.0180.02250.0190.020
MinAvgMaxEPYC 4124P @ DDR5-520040047255064smoke494349935009OpenBenchmarking.orgMegahertz, More Is BetterLuxCoreRender 2.6CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520014.272.778.2smoke17.070.978.2OpenBenchmarking.orgWatts, Fewer Is BetterLuxCoreRender 2.6CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 824 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520045.175.877.4smoke44.674.377.4OpenBenchmarking.orgCelsius, Fewer Is BetterLuxCoreRender 2.6CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520055.2115.8121.6smoke55.4115.3121.7OpenBenchmarking.orgWatts, Fewer Is BetterLuxCoreRender 2.6System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1313 Joules per run.
OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.6Scene: DLSC - Acceleration: CPUEPYC 4124P @ DDR5-5200smoke246810Min: 1.41 / Avg: 1.41 / Max: 1.41

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: T5 Encoder - Device: CPU - Executor: StandardEPYC 4124P @ DDR5-5200smoke246810SE +/- 0.08113, N = 37.031717.583961. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
MinAvgMaxEPYC 4124P @ DDR5-520040048114944smoke494049414941OpenBenchmarking.orgMegahertz, More Is BetterONNX Runtime 1.17CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.739.242.0smoke16.836.940.6OpenBenchmarking.orgWatts, Fewer Is BetterONNX Runtime 1.17CPU Power Consumption Monitor12243648601. EPYC 4124P @ DDR5-5200: Approximate power consumption of 457 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520039.341.942.4smoke42.843.944.4OpenBenchmarking.orgCelsius, Fewer Is BetterONNX Runtime 1.17CPU Temperature Monitor1224364860
MinAvgMaxEPYC 4124P @ DDR5-520052.779.183.2smoke53.278.781.7OpenBenchmarking.orgWatts, Fewer Is BetterONNX Runtime 1.17System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 923 Joules per run.
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: T5 Encoder - Device: CPU - Executor: StandardEPYC 4124P @ DDR5-5200smoke3691215Min: 6.94 / Avg: 7.03 / Max: 7.191. (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: T5 Encoder - Device: CPU - Executor: StandardEPYC 4124P @ DDR5-5200smoke306090120150SE +/- 1.62, N = 3142.21131.801. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: T5 Encoder - Device: CPU - Executor: StandardEPYC 4124P @ DDR5-5200smoke246810SE +/- 0.08113, N = 37.031717.583961. (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: T5 Encoder - Device: CPU - Executor: StandardEPYC 4124P @ DDR5-5200smoke306090120150Min: 138.97 / Avg: 142.21 / Max: 144.091. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

RawTherapee

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

OpenBenchmarking.orgSeconds, Fewer Is BetterRawTherapeeTotal Benchmark TimeEPYC 4124P @ DDR5-5200smoke1326395265SE +/- 0.08, N = 360.1160.051. RawTherapee, version 5.10, command line.
MinAvgMaxEPYC 4124P @ DDR5-520040049485141smoke40047225142OpenBenchmarking.orgMegahertz, More Is BetterRawTherapeeCPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.351.161.6smoke16.949.461.7OpenBenchmarking.orgWatts, Fewer Is BetterRawTherapeeCPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 596 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520038.865.870.8smoke40.867.272.1OpenBenchmarking.orgCelsius, Fewer Is BetterRawTherapeeCPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520053.291.3104.4smoke53.891.0105.8OpenBenchmarking.orgWatts, Fewer Is BetterRawTherapeeSystem Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1066 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterRawTherapeeTotal Benchmark TimeEPYC 4124P @ DDR5-5200smoke1224364860Min: 59.95 / Avg: 60.11 / Max: 60.211. RawTherapee, version 5.10, command line.

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: ArcFace ResNet-100 - Device: CPU - Executor: ParallelEPYC 4124P @ DDR5-5200smoke20406080100SE +/- 0.05, N = 367.4777.521. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
MinAvgMaxEPYC 4124P @ DDR5-520040048024942smoke40044864941OpenBenchmarking.orgMegahertz, More Is BetterONNX Runtime 1.17CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.547.051.4smoke16.444.049.1OpenBenchmarking.orgWatts, Fewer Is BetterONNX Runtime 1.17CPU Power Consumption Monitor15304560751. EPYC 4124P @ DDR5-5200: Approximate power consumption of 517 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520039.451.454.6smoke41.454.256.5OpenBenchmarking.orgCelsius, Fewer Is BetterONNX Runtime 1.17CPU Temperature Monitor1632486480
MinAvgMaxEPYC 4124P @ DDR5-520054.384.488.1smoke53.783.087.6OpenBenchmarking.orgWatts, Fewer Is BetterONNX Runtime 1.17System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 929 Joules per run.
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: ArcFace ResNet-100 - Device: CPU - Executor: ParallelEPYC 4124P @ DDR5-5200smoke1530456075Min: 67.38 / Avg: 67.47 / Max: 67.541. (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: ArcFace ResNet-100 - Device: CPU - Executor: ParallelEPYC 4124P @ DDR5-5200smoke48121620SE +/- 0.01, N = 314.8212.901. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: ArcFace ResNet-100 - Device: CPU - Executor: ParallelEPYC 4124P @ DDR5-5200smoke20406080100SE +/- 0.05, N = 367.4777.521. (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: ArcFace ResNet-100 - Device: CPU - Executor: ParallelEPYC 4124P @ DDR5-5200smoke48121620Min: 14.81 / Avg: 14.82 / Max: 14.841. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenVINO

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Person Detection FP32 - Device: CPUEPYC 4124P @ DDR5-5200smoke306090120150SE +/- 0.18, N = 3126.50125.81MIN: 102.39 / MAX: 136.9MIN: 63 / MAX: 137.411. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
MinAvgMaxEPYC 4124P @ DDR5-520040045895002smoke493349414979OpenBenchmarking.orgMegahertz, More Is BetterOpenVINO 2024.0CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.253.662.3smoke16.157.562.8OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2024.0CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 679 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520039.953.456.3smoke41.056.258.3OpenBenchmarking.orgCelsius, Fewer Is BetterOpenVINO 2024.0CPU Temperature Monitor1632486480
MinAvgMaxEPYC 4124P @ DDR5-520053.295.5106.0smoke54.099.7106.2OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2024.0System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1210 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Person Detection FP32 - Device: CPUEPYC 4124P @ DDR5-5200smoke20406080100Min: 126.18 / Avg: 126.5 / Max: 126.821. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Person Detection FP32 - Device: CPUEPYC 4124P @ DDR5-5200smoke714212835SE +/- 0.06, N = 331.5931.771. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Person Detection FP32 - Device: CPUEPYC 4124P @ DDR5-5200smoke714212835Min: 31.5 / Avg: 31.59 / Max: 31.691. (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.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: T5 Encoder - Device: CPU - Executor: ParallelEPYC 4124P @ DDR5-5200smoke246810SE +/- 0.00939, N = 37.420797.425291. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
MinAvgMaxEPYC 4124P @ DDR5-5200493649605141smoke40046555140OpenBenchmarking.orgMegahertz, More Is BetterONNX Runtime 1.17CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.340.544.0smoke16.640.945.0OpenBenchmarking.orgWatts, Fewer Is BetterONNX Runtime 1.17CPU Power Consumption Monitor12243648601. EPYC 4124P @ DDR5-5200: Approximate power consumption of 472 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520038.141.942.4smoke40.644.144.9OpenBenchmarking.orgCelsius, Fewer Is BetterONNX Runtime 1.17CPU Temperature Monitor1224364860
MinAvgMaxEPYC 4124P @ DDR5-520053.180.984.6smoke53.780.886.4OpenBenchmarking.orgWatts, Fewer Is BetterONNX Runtime 1.17System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 971 Joules per run.
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: T5 Encoder - Device: CPU - Executor: ParallelEPYC 4124P @ DDR5-5200smoke3691215Min: 7.41 / Avg: 7.42 / Max: 7.441. (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: T5 Encoder - Device: CPU - Executor: ParallelEPYC 4124P @ DDR5-5200smoke306090120150SE +/- 0.17, N = 3134.74134.661. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: T5 Encoder - Device: CPU - Executor: ParallelEPYC 4124P @ DDR5-5200smoke246810SE +/- 0.00939, N = 37.420797.425291. (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: T5 Encoder - Device: CPU - Executor: ParallelEPYC 4124P @ DDR5-5200smoke306090120150Min: 134.4 / Avg: 134.74 / Max: 134.911. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenVINO

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Person Detection FP16 - Device: CPUEPYC 4124P @ DDR5-5200smoke306090120150SE +/- 0.57, N = 3126.06126.47MIN: 63.05 / MAX: 145.09MIN: 103.51 / MAX: 136.751. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
MinAvgMaxEPYC 4124P @ DDR5-520040046905027smoke493249384940OpenBenchmarking.orgMegahertz, More Is BetterOpenVINO 2024.0CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.656.763.3smoke29.457.061.3OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2024.0CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 681 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520040.354.356.4smoke54.657.257.9OpenBenchmarking.orgCelsius, Fewer Is BetterOpenVINO 2024.0CPU Temperature Monitor1632486480
MinAvgMaxEPYC 4124P @ DDR5-520054.198.6106.4smoke54.298.2104.8OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2024.0System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1150 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Person Detection FP16 - Device: CPUEPYC 4124P @ DDR5-5200smoke20406080100Min: 124.99 / Avg: 126.06 / Max: 126.911. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Person Detection FP16 - Device: CPUEPYC 4124P @ DDR5-5200smoke714212835SE +/- 0.14, N = 331.7131.591. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Person Detection FP16 - Device: CPUEPYC 4124P @ DDR5-5200smoke714212835Min: 31.49 / Avg: 31.71 / Max: 31.971. (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: CPUEPYC 4124P @ DDR5-5200smoke246810SE +/- 0.01, N = 38.268.24MIN: 5.5 / MAX: 13.88MIN: 6.6 / MAX: 12.341. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
MinAvgMaxEPYC 4124P @ DDR5-520040048715137smoke513251355137OpenBenchmarking.orgMegahertz, More Is BetterOpenVINO 2024.0CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.271.478.4smoke31.974.079.1OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2024.0CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 833 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520041.164.366.6smoke61.667.669.0OpenBenchmarking.orgCelsius, Fewer Is BetterOpenVINO 2024.0CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.1115.0122.0smoke54.2115.3123.5OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2024.0System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1380 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Noise Suppression Poconet-Like FP16 - Device: CPUEPYC 4124P @ DDR5-5200smoke3691215Min: 8.24 / Avg: 8.26 / Max: 8.271. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Noise Suppression Poconet-Like FP16 - Device: CPUEPYC 4124P @ DDR5-5200smoke100200300400500SE +/- 0.42, N = 3479.34480.271. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Noise Suppression Poconet-Like FP16 - Device: CPUEPYC 4124P @ DDR5-5200smoke90180270360450Min: 478.83 / Avg: 479.34 / Max: 480.181. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

GraphicsMagick

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.43Operation: SwirlEPYC 4124P @ DDR5-5200smoke1632486480SE +/- 0.33, N = 372731. (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 Per Watt, More Is BetterGraphicsMagick 1.3.43Operation: SwirlEPYC 4124P @ DDR5-5200smoke0.2450.490.7350.981.2251.0521.089
MinAvgMaxEPYC 4124P @ DDR5-520040047655112smoke499050165062OpenBenchmarking.orgMegahertz, More Is BetterGraphicsMagick 1.3.43CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.368.473.6smoke24.767.072.9OpenBenchmarking.orgWatts, Fewer Is BetterGraphicsMagick 1.3.43CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 753 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520042.473.675.3smoke64.975.076.4OpenBenchmarking.orgCelsius, Fewer Is BetterGraphicsMagick 1.3.43CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.2109.9115.6smoke54.8109.3115.2OpenBenchmarking.orgWatts, Fewer Is BetterGraphicsMagick 1.3.43System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1246 Joules per run.
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.43Operation: SwirlEPYC 4124P @ DDR5-5200smoke1428425670Min: 72 / Avg: 72.33 / Max: 731. (CC) gcc options: -fopenmp -O2 -ltiff -ljbig -lsharpyuv -lwebp -lwebpmux -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lxml2 -lzstd -llzma -lbz2 -lz -lm -lpthread -lgomp

OpenVINO

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Person Vehicle Bike Detection FP16 - Device: CPUEPYC 4124P @ DDR5-5200smoke3691215SE +/- 0.02, N = 310.1810.15MIN: 5.72 / MAX: 20.75MIN: 7.39 / MAX: 17.141. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
MinAvgMaxEPYC 4124P @ DDR5-5200477249605071smoke493349745070OpenBenchmarking.orgMegahertz, More Is BetterOpenVINO 2024.0CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520022.461.265.7smoke23.461.068.0OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2024.0CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 713 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520050.056.258.6smoke52.058.560.1OpenBenchmarking.orgCelsius, Fewer Is BetterOpenVINO 2024.0CPU Temperature Monitor1632486480
MinAvgMaxEPYC 4124P @ DDR5-520053.8101.8106.5smoke54.2101.4107.1OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2024.0System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1188 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Person Vehicle Bike Detection FP16 - Device: CPUEPYC 4124P @ DDR5-5200smoke3691215Min: 10.14 / Avg: 10.18 / Max: 10.221. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Person Vehicle Bike Detection FP16 - Device: CPUEPYC 4124P @ DDR5-5200smoke90180270360450SE +/- 0.95, N = 3391.89393.131. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Person Vehicle Bike Detection FP16 - Device: CPUEPYC 4124P @ DDR5-5200smoke70140210280350Min: 390.38 / Avg: 391.89 / Max: 393.641. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Road Segmentation ADAS FP16 - Device: CPUEPYC 4124P @ DDR5-5200smoke918273645SE +/- 0.22, N = 337.3037.49MIN: 30.15 / MAX: 46.26MIN: 30.14 / MAX: 46.041. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
MinAvgMaxEPYC 4124P @ DDR5-520040047085105smoke492750125138OpenBenchmarking.orgMegahertz, More Is BetterOpenVINO 2024.0CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.962.269.2smoke16.459.867.6OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2024.0CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 725 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520040.961.464.0smoke43.362.765.6OpenBenchmarking.orgCelsius, Fewer Is BetterOpenVINO 2024.0CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.4104.0112.9smoke54.1100.6112.3OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2024.0System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1213 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Road Segmentation ADAS FP16 - Device: CPUEPYC 4124P @ DDR5-5200smoke816243240Min: 36.97 / Avg: 37.3 / Max: 37.711. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Road Segmentation ADAS FP16 - Device: CPUEPYC 4124P @ DDR5-5200smoke20406080100SE +/- 0.63, N = 3107.08106.551. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Road Segmentation ADAS FP16 - Device: CPUEPYC 4124P @ DDR5-5200smoke20406080100Min: 105.91 / Avg: 107.08 / Max: 108.051. (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 Re-Identification Retail FP16 - Device: CPUEPYC 4124P @ DDR5-5200smoke246810SE +/- 0.01, N = 37.967.99MIN: 4.52 / MAX: 22.42MIN: 4.48 / MAX: 18.691. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
MinAvgMaxEPYC 4124P @ DDR5-5200493549394941smoke493349374940OpenBenchmarking.orgMegahertz, More Is BetterOpenVINO 2024.0CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.962.067.9smoke16.359.567.3OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2024.0CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 723 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520041.158.159.8smoke43.059.162.0OpenBenchmarking.orgCelsius, Fewer Is BetterOpenVINO 2024.0CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.3100.7107.1smoke54.3101.3106.9OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2024.0System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1174 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Person Re-Identification Retail FP16 - Device: CPUEPYC 4124P @ DDR5-5200smoke3691215Min: 7.95 / Avg: 7.96 / Max: 7.971. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Person Re-Identification Retail FP16 - Device: CPUEPYC 4124P @ DDR5-5200smoke110220330440550SE +/- 0.38, N = 3500.05498.311. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Person Re-Identification Retail FP16 - Device: CPUEPYC 4124P @ DDR5-5200smoke90180270360450Min: 499.3 / Avg: 500.05 / Max: 500.531. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

GraphicsMagick

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.43Operation: ResizingEPYC 4124P @ DDR5-5200smoke306090120150SE +/- 0.00, N = 31421431. (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 Per Watt, More Is BetterGraphicsMagick 1.3.43Operation: ResizingEPYC 4124P @ DDR5-5200smoke0.49430.98861.48291.97722.47152.1162.197
MinAvgMaxEPYC 4124P @ DDR5-520040049535141smoke40046465115OpenBenchmarking.orgMegahertz, More Is BetterGraphicsMagick 1.3.43CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.667.172.6smoke16.465.172.2OpenBenchmarking.orgWatts, Fewer Is BetterGraphicsMagick 1.3.43CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 783 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520044.371.272.9smoke44.371.174.3OpenBenchmarking.orgCelsius, Fewer Is BetterGraphicsMagick 1.3.43CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.4109.8114.2smoke54.6108.6114.6OpenBenchmarking.orgWatts, Fewer Is BetterGraphicsMagick 1.3.43System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1245 Joules per run.
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.43Operation: ResizingEPYC 4124P @ DDR5-5200smoke306090120150Min: 142 / Avg: 142 / Max: 1421. (CC) gcc options: -fopenmp -O2 -ltiff -ljbig -lsharpyuv -lwebp -lwebpmux -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lxml2 -lzstd -llzma -lbz2 -lz -lm -lpthread -lgomp

OpenVINO

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Vehicle Detection FP16-INT8 - Device: CPUEPYC 4124P @ DDR5-5200smoke3691215SE +/- 0.01, N = 39.689.66MIN: 5.18 / MAX: 21.13MIN: 5.19 / MAX: 21.251. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
MinAvgMaxEPYC 4124P @ DDR5-520040048105139smoke493449374941OpenBenchmarking.orgMegahertz, More Is BetterOpenVINO 2024.0CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.661.466.6smoke17.161.166.9OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2024.0CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 696 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520040.155.757.1smoke42.857.759.6OpenBenchmarking.orgCelsius, Fewer Is BetterOpenVINO 2024.0CPU Temperature Monitor1632486480
MinAvgMaxEPYC 4124P @ DDR5-520053.5100.5106.7smoke54.3100.0107.4OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2024.0System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1172 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Vehicle Detection FP16-INT8 - Device: CPUEPYC 4124P @ DDR5-5200smoke3691215Min: 9.65 / Avg: 9.68 / Max: 9.71. (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-INT8 - Device: CPUEPYC 4124P @ DDR5-5200smoke90180270360450SE +/- 0.52, N = 3412.37412.861. (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-INT8 - Device: CPUEPYC 4124P @ DDR5-5200smoke70140210280350Min: 411.58 / Avg: 412.37 / Max: 413.341. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

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 Fill SyncEPYC 4124P @ DDR5-5200smoke17K34K51K68K85KSE +/- 389.36, N = 377781756831. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.orgOp/s Per Watt, More Is BetterSpeedb 2.7Test: Random Fill SyncEPYC 4124P @ DDR5-5200smoke4008001200160020002090.731961.30
MinAvgMaxEPYC 4124P @ DDR5-520040048695139smoke493550375139OpenBenchmarking.orgMegahertz, More Is BetterSpeedb 2.7CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520020.037.239.5smoke26.038.640.3OpenBenchmarking.orgWatts, Fewer Is BetterSpeedb 2.7CPU Power Consumption Monitor11223344551. EPYC 4124P @ DDR5-5200: Approximate power consumption of 409 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520040.844.845.6smoke49.850.651.1OpenBenchmarking.orgCelsius, Fewer Is BetterSpeedb 2.7CPU Temperature Monitor1530456075
MinAvgMaxEPYC 4124P @ DDR5-520053.672.975.2smoke67.375.576.6OpenBenchmarking.orgWatts, Fewer Is BetterSpeedb 2.7System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 827 Joules per run.
OpenBenchmarking.orgOp/s, More Is BetterSpeedb 2.7Test: Random Fill SyncEPYC 4124P @ DDR5-5200smoke13K26K39K52K65KMin: 77138 / Avg: 77781.33 / Max: 784831. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

OpenBenchmarking.orgOp/s, More Is BetterSpeedb 2.7Test: Random FillEPYC 4124P @ DDR5-5200smoke160K320K480K640K800KSE +/- 1759.75, N = 37586167624821. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.orgOp/s Per Watt, More Is BetterSpeedb 2.7Test: Random FillEPYC 4124P @ DDR5-5200smoke3K6K9K12K15K14553.7415126.16
MinAvgMaxEPYC 4124P @ DDR5-520040049755140smoke494051005146OpenBenchmarking.orgMegahertz, More Is BetterSpeedb 2.7CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.052.156.5smoke16.850.457.7OpenBenchmarking.orgWatts, Fewer Is BetterSpeedb 2.7CPU Power Consumption Monitor16324864801. EPYC 4124P @ DDR5-5200: Approximate power consumption of 608 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520041.962.167.4smoke46.666.370.5OpenBenchmarking.orgCelsius, Fewer Is BetterSpeedb 2.7CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.491.8101.3smoke54.493.599.0OpenBenchmarking.orgWatts, Fewer Is BetterSpeedb 2.7System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1041 Joules per run.
OpenBenchmarking.orgOp/s, More Is BetterSpeedb 2.7Test: Random FillEPYC 4124P @ DDR5-5200smoke130K260K390K520K650KMin: 755098 / Avg: 758616.33 / Max: 7604541. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

OpenVINO

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Handwritten English Recognition FP16-INT8 - Device: CPUEPYC 4124P @ DDR5-5200smoke510152025SE +/- 0.02, N = 322.2421.05MIN: 14.31 / MAX: 32.88MIN: 13.48 / MAX: 26.461. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
MinAvgMaxEPYC 4124P @ DDR5-520040048775139smoke497051065139OpenBenchmarking.orgMegahertz, More Is BetterOpenVINO 2024.0CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.164.273.8smoke17.068.380.4OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2024.0CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 770 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520040.560.664.1smoke42.366.872.5OpenBenchmarking.orgCelsius, Fewer Is BetterOpenVINO 2024.0CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520053.9105.7117.4smoke53.8108.4125.4OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2024.0System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1268 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Handwritten English Recognition FP16-INT8 - Device: CPUEPYC 4124P @ DDR5-5200smoke510152025Min: 22.21 / Avg: 22.24 / Max: 22.281. (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-INT8 - Device: CPUEPYC 4124P @ DDR5-5200smoke4080120160200SE +/- 0.15, N = 3179.64189.901. (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-INT8 - Device: CPUEPYC 4124P @ DDR5-5200smoke306090120150Min: 179.36 / Avg: 179.64 / Max: 179.871. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Handwritten English Recognition FP16 - Device: CPUEPYC 4124P @ DDR5-5200smoke510152025SE +/- 0.08, N = 321.5122.32MIN: 14.59 / MAX: 33.42MIN: 18.8 / MAX: 28.761. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
MinAvgMaxEPYC 4124P @ DDR5-5200464949475140smoke465849045055OpenBenchmarking.orgMegahertz, More Is BetterOpenVINO 2024.0CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.964.771.2smoke28.364.271.3OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2024.0CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 754 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520040.658.260.4smoke58.060.562.4OpenBenchmarking.orgCelsius, Fewer Is BetterOpenVINO 2024.0CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.4103.6111.7smoke53.8104.5111.5OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2024.0System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1209 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Handwritten English Recognition FP16 - Device: CPUEPYC 4124P @ DDR5-5200smoke510152025Min: 21.37 / Avg: 21.51 / Max: 21.661. (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: CPUEPYC 4124P @ DDR5-5200smoke4080120160200SE +/- 0.70, N = 3185.85179.051. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Handwritten English Recognition FP16 - Device: CPUEPYC 4124P @ DDR5-5200smoke306090120150Min: 184.55 / Avg: 185.85 / Max: 186.961. (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-INT8 - Device: CPUEPYC 4124P @ DDR5-5200smoke0.72681.45362.18042.90723.634SE +/- 0.01, N = 33.233.22MIN: 1.85 / MAX: 13.26MIN: 1.85 / MAX: 8.791. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
MinAvgMaxEPYC 4124P @ DDR5-520040047944941smoke40045224936OpenBenchmarking.orgMegahertz, More Is BetterOpenVINO 2024.0CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.862.267.6smoke16.561.468.0OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2024.0CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 664 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520040.857.559.4smoke42.359.061.4OpenBenchmarking.orgCelsius, Fewer Is BetterOpenVINO 2024.0CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.0102.1107.5smoke54.1101.2107.6OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2024.0System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1055 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Face Detection Retail FP16-INT8 - Device: CPUEPYC 4124P @ DDR5-5200smoke246810Min: 3.21 / Avg: 3.23 / Max: 3.251. (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-INT8 - Device: CPUEPYC 4124P @ DDR5-5200smoke30060090012001500SE +/- 4.76, N = 31232.021233.451. (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-INT8 - Device: CPUEPYC 4124P @ DDR5-5200smoke2004006008001000Min: 1223.79 / Avg: 1232.02 / Max: 1240.281. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

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 RandomEPYC 4124P @ DDR5-5200smoke300K600K900K1200K1500KSE +/- 5732.94, N = 3132368513139671. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.orgOp/s Per Watt, More Is BetterSpeedb 2.7Test: Read Random Write RandomEPYC 4124P @ DDR5-5200smoke4K8K12K16K20K18217.7418908.49
MinAvgMaxEPYC 4124P @ DDR5-520040049185141smoke494150035141OpenBenchmarking.orgMegahertz, More Is BetterSpeedb 2.7CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.872.778.6smoke16.969.576.1OpenBenchmarking.orgWatts, Fewer Is BetterSpeedb 2.7CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 823 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520041.373.175.4smoke46.574.777.9OpenBenchmarking.orgCelsius, Fewer Is BetterSpeedb 2.7CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.7115.6122.6smoke56.1114.7120.6OpenBenchmarking.orgWatts, Fewer Is BetterSpeedb 2.7System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1310 Joules per run.
OpenBenchmarking.orgOp/s, More Is BetterSpeedb 2.7Test: Read Random Write RandomEPYC 4124P @ DDR5-5200smoke200K400K600K800K1000KMin: 1312344 / Avg: 1323685 / Max: 13308171. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

OpenVINO

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Vehicle Detection FP16 - Device: CPUEPYC 4124P @ DDR5-5200smoke48121620SE +/- 0.05, N = 317.4617.38MIN: 8.04 / MAX: 25.29MIN: 8.65 / MAX: 29.931. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
MinAvgMaxEPYC 4124P @ DDR5-520040048024938smoke493349364937OpenBenchmarking.orgMegahertz, More Is BetterOpenVINO 2024.0CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520030.258.463.6smoke23.358.063.4OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2024.0CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 661 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520048.852.454.3smoke48.554.456.0OpenBenchmarking.orgCelsius, Fewer Is BetterOpenVINO 2024.0CPU Temperature Monitor1632486480
MinAvgMaxEPYC 4124P @ DDR5-520052.999.8104.9smoke53.899.5105.0OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2024.0System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1165 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Vehicle Detection FP16 - Device: CPUEPYC 4124P @ DDR5-5200smoke48121620Min: 17.36 / Avg: 17.46 / Max: 17.531. (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: CPUEPYC 4124P @ DDR5-5200smoke50100150200250SE +/- 0.62, N = 3228.81229.761. (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: CPUEPYC 4124P @ DDR5-5200smoke4080120160200Min: 227.89 / Avg: 228.81 / Max: 2301. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

GraphicsMagick

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.43Operation: Noise-GaussianEPYC 4124P @ DDR5-5200smoke1020304050SE +/- 0.00, N = 344441. (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 Per Watt, More Is BetterGraphicsMagick 1.3.43Operation: Noise-GaussianEPYC 4124P @ DDR5-5200smoke0.15410.30820.46230.61640.77050.6580.685
MinAvgMaxEPYC 4124P @ DDR5-520040047375141smoke40045835141OpenBenchmarking.orgMegahertz, More Is BetterGraphicsMagick 1.3.43CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520015.866.873.5smoke16.964.272.4OpenBenchmarking.orgWatts, Fewer Is BetterGraphicsMagick 1.3.43CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 780 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520042.676.278.1smoke44.575.379.1OpenBenchmarking.orgCelsius, Fewer Is BetterGraphicsMagick 1.3.43CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.7109.8123.6smoke54.3103.3120.0OpenBenchmarking.orgWatts, Fewer Is BetterGraphicsMagick 1.3.43System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1281 Joules per run.
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.43Operation: Noise-GaussianEPYC 4124P @ DDR5-5200smoke918273645Min: 44 / Avg: 44 / Max: 441. (CC) gcc options: -fopenmp -O2 -ltiff -ljbig -lsharpyuv -lwebp -lwebpmux -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lxml2 -lzstd -llzma -lbz2 -lz -lm -lpthread -lgomp

OpenVINO

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Weld Porosity Detection FP16 - Device: CPUEPYC 4124P @ DDR5-5200smoke3691215SE +/- 0.01, N = 311.4311.43MIN: 5.89 / MAX: 21.52MIN: 5.82 / MAX: 21.371. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
MinAvgMaxEPYC 4124P @ DDR5-520040048024952smoke493849404941OpenBenchmarking.orgMegahertz, More Is BetterOpenVINO 2024.0CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520015.463.368.3smoke16.263.168.3OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2024.0CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 697 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520039.657.759.4smoke41.359.461.8OpenBenchmarking.orgCelsius, Fewer Is BetterOpenVINO 2024.0CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.1101.6107.1smoke54.4102.8107.9OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2024.0System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1152 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Weld Porosity Detection FP16 - Device: CPUEPYC 4124P @ DDR5-5200smoke3691215Min: 11.42 / Avg: 11.43 / Max: 11.451. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Weld Porosity Detection FP16 - Device: CPUEPYC 4124P @ DDR5-5200smoke80160240320400SE +/- 0.29, N = 3349.32349.201. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Weld Porosity Detection FP16 - Device: CPUEPYC 4124P @ DDR5-5200smoke60120180240300Min: 348.75 / Avg: 349.32 / Max: 349.681. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

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: Update RandomEPYC 4124P @ DDR5-5200smoke90K180K270K360K450KSE +/- 3374.72, N = 34143354091901. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.orgOp/s Per Watt, More Is BetterSpeedb 2.7Test: Update RandomEPYC 4124P @ DDR5-5200smoke150030004500600075006381.376773.83
MinAvgMaxEPYC 4124P @ DDR5-520040049835139smoke40047075141OpenBenchmarking.orgMegahertz, More Is BetterSpeedb 2.7CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520026.564.969.4smoke15.860.468.7OpenBenchmarking.orgWatts, Fewer Is BetterSpeedb 2.7CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 758 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520056.068.371.5smoke47.169.875.1OpenBenchmarking.orgCelsius, Fewer Is BetterSpeedb 2.7CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520067.5107.6112.2smoke54.3105.3114.2OpenBenchmarking.orgWatts, Fewer Is BetterSpeedb 2.7System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1255 Joules per run.
OpenBenchmarking.orgOp/s, More Is BetterSpeedb 2.7Test: Update RandomEPYC 4124P @ DDR5-5200smoke70K140K210K280K350KMin: 410758 / Avg: 414334.67 / Max: 4210801. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

OpenVINO

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Face Detection Retail FP16 - Device: CPUEPYC 4124P @ DDR5-5200smoke1.01932.03863.05794.07725.0965SE +/- 0.01, N = 34.534.50MIN: 2.48 / MAX: 9.87MIN: 2.45 / MAX: 14.111. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
MinAvgMaxEPYC 4124P @ DDR5-520040048024941smoke40045224938OpenBenchmarking.orgMegahertz, More Is BetterOpenVINO 2024.0CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.663.568.8smoke16.764.169.4OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2024.0CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 720 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520040.558.159.6smoke41.860.063.0OpenBenchmarking.orgCelsius, Fewer Is BetterOpenVINO 2024.0CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.5104.2108.4smoke54.2104.3110.5OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2024.0System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1181 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Face Detection Retail FP16 - Device: CPUEPYC 4124P @ DDR5-5200smoke246810Min: 4.51 / Avg: 4.53 / Max: 4.551. (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: CPUEPYC 4124P @ DDR5-5200smoke2004006008001000SE +/- 2.00, N = 3879.05884.841. (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: CPUEPYC 4124P @ DDR5-5200smoke160320480640800Min: 875.05 / Avg: 879.05 / Max: 881.291. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Weld Porosity Detection FP16-INT8 - Device: CPUEPYC 4124P @ DDR5-5200smoke1.30732.61463.92195.22926.5365SE +/- 0.00, N = 35.805.81MIN: 3.05 / MAX: 14.45MIN: 3.07 / MAX: 15.91. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
MinAvgMaxEPYC 4124P @ DDR5-5200492349465140smoke493849394940OpenBenchmarking.orgMegahertz, More Is BetterOpenVINO 2024.0CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520031.762.766.5smoke16.061.166.4OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2024.0CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 690 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520049.056.357.6smoke41.557.960.3OpenBenchmarking.orgCelsius, Fewer Is BetterOpenVINO 2024.0CPU Temperature Monitor1632486480
MinAvgMaxEPYC 4124P @ DDR5-520053.8100.8104.4smoke54.499.8105.2OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2024.0System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1109 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Weld Porosity Detection FP16-INT8 - Device: CPUEPYC 4124P @ DDR5-5200smoke246810Min: 5.8 / Avg: 5.8 / Max: 5.811. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Weld Porosity Detection FP16-INT8 - Device: CPUEPYC 4124P @ DDR5-5200smoke150300450600750SE +/- 0.30, N = 3686.87686.261. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Weld Porosity Detection FP16-INT8 - Device: CPUEPYC 4124P @ DDR5-5200smoke120240360480600Min: 686.35 / Avg: 686.87 / Max: 687.381. (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.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: CaffeNet 12-int8 - Device: CPU - Executor: ParallelEPYC 4124P @ DDR5-5200smoke0.53471.06941.60412.13882.6735SE +/- 0.00829, N = 32.376352.372961. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
MinAvgMaxEPYC 4124P @ DDR5-520040046875031smoke493449444977OpenBenchmarking.orgMegahertz, More Is BetterONNX Runtime 1.17CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.045.248.5smoke17.043.848.9OpenBenchmarking.orgWatts, Fewer Is BetterONNX Runtime 1.17CPU Power Consumption Monitor14284256701. EPYC 4124P @ DDR5-5200: Approximate power consumption of 528 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520039.344.745.5smoke41.646.347.4OpenBenchmarking.orgCelsius, Fewer Is BetterONNX Runtime 1.17CPU Temperature Monitor1428425670
MinAvgMaxEPYC 4124P @ DDR5-520053.484.087.4smoke54.085.088.3OpenBenchmarking.orgWatts, Fewer Is BetterONNX Runtime 1.17System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 981 Joules per run.
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: CaffeNet 12-int8 - Device: CPU - Executor: ParallelEPYC 4124P @ DDR5-5200smoke246810Min: 2.36 / Avg: 2.38 / Max: 2.391. (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: CaffeNet 12-int8 - Device: CPU - Executor: ParallelEPYC 4124P @ DDR5-5200smoke90180270360450SE +/- 1.46, N = 3420.70421.291. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: CaffeNet 12-int8 - Device: CPU - Executor: ParallelEPYC 4124P @ DDR5-5200smoke0.53471.06941.60412.13882.6735SE +/- 0.00829, N = 32.376352.372961. (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: CaffeNet 12-int8 - Device: CPU - Executor: ParallelEPYC 4124P @ DDR5-5200smoke70140210280350Min: 417.98 / Avg: 420.7 / Max: 4231. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

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: MD5EPYC 4124P @ DDR5-5200smoke200K400K600K800K1000KSE +/- 151.74, N = 39860949835001. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -lm -lrt -lz -ldl -lcrypt -lbz2
OpenBenchmarking.orgReal C/S Per Watt, More Is BetterJohn The Ripper 2023.03.14Test: MD5EPYC 4124P @ DDR5-5200smoke3K6K9K12K15K15328.7515459.79
MinAvgMaxEPYC 4124P @ DDR5-520040046695140smoke40046985140OpenBenchmarking.orgMegahertz, More Is BetterJohn The Ripper 2023.03.14CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.864.369.4smoke16.763.670.3OpenBenchmarking.orgWatts, Fewer Is BetterJohn The Ripper 2023.03.14CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 729 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520042.864.466.4smoke44.866.769.3OpenBenchmarking.orgCelsius, Fewer Is BetterJohn The Ripper 2023.03.14CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.6104.5108.2smoke54.6104.1110.0OpenBenchmarking.orgWatts, Fewer Is BetterJohn The Ripper 2023.03.14System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1219 Joules per run.
OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: MD5EPYC 4124P @ DDR5-5200smoke200K400K600K800K1000KMin: 985804 / Avg: 986094.33 / Max: 9863161. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -lm -lrt -lz -ldl -lcrypt -lbz2

GraphicsMagick

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.43Operation: HWB Color SpaceEPYC 4124P @ DDR5-5200smoke4080120160200SE +/- 0.33, N = 31901951. (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 Per Watt, More Is BetterGraphicsMagick 1.3.43Operation: HWB Color SpaceEPYC 4124P @ DDR5-5200smoke0.88311.76622.64933.53244.41553.7973.925
MinAvgMaxEPYC 4124P @ DDR5-520040049795141smoke503051035141OpenBenchmarking.orgMegahertz, More Is BetterGraphicsMagick 1.3.43CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520023.950.053.0smoke22.049.753.8OpenBenchmarking.orgWatts, Fewer Is BetterGraphicsMagick 1.3.43CPU Power Consumption Monitor15304560751. EPYC 4124P @ DDR5-5200: Approximate power consumption of 567 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520056.468.870.1smoke53.969.671.6OpenBenchmarking.orgCelsius, Fewer Is BetterGraphicsMagick 1.3.43CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.289.693.1smoke54.090.294.2OpenBenchmarking.orgWatts, Fewer Is BetterGraphicsMagick 1.3.43System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1045 Joules per run.
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.43Operation: HWB Color SpaceEPYC 4124P @ DDR5-5200smoke4080120160200Min: 189 / Avg: 189.67 / Max: 1901. (CC) gcc options: -fopenmp -O2 -ltiff -ljbig -lsharpyuv -lwebp -lwebpmux -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lxml2 -lzstd -llzma -lbz2 -lz -lm -lpthread -lgomp

OpenVINO

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUEPYC 4124P @ DDR5-5200smoke0.06750.1350.20250.270.3375SE +/- 0.00, N = 30.290.30MIN: 0.16 / MAX: 4.31MIN: 0.16 / MAX: 6.941. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
MinAvgMaxEPYC 4124P @ DDR5-520040047225137smoke493650605137OpenBenchmarking.orgMegahertz, More Is BetterOpenVINO 2024.0CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.358.063.3smoke27.861.065.6OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2024.0CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 696 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520041.054.456.9smoke54.459.460.8OpenBenchmarking.orgCelsius, Fewer Is BetterOpenVINO 2024.0CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520053.696.5101.6smoke53.998.5104.5OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2024.0System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1126 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUEPYC 4124P @ DDR5-5200smoke12345Min: 0.29 / Avg: 0.29 / Max: 0.31. (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-INT8 - Device: CPUEPYC 4124P @ DDR5-5200smoke3K6K9K12K15KSE +/- 57.65, N = 313170.1212876.121. (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-INT8 - Device: CPUEPYC 4124P @ DDR5-5200smoke2K4K6K8K10KMin: 13059.47 / Avg: 13170.12 / Max: 13253.491. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

GraphicsMagick

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.43Operation: RotateEPYC 4124P @ DDR5-5200smoke4080120160200SE +/- 0.00, N = 31581601. (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 Per Watt, More Is BetterGraphicsMagick 1.3.43Operation: RotateEPYC 4124P @ DDR5-5200smoke1.20172.40343.60514.80686.00855.3415.062
MinAvgMaxEPYC 4124P @ DDR5-520040048705141smoke494751215141OpenBenchmarking.orgMegahertz, More Is BetterGraphicsMagick 1.3.43CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.529.633.1smoke16.731.633.5OpenBenchmarking.orgWatts, Fewer Is BetterGraphicsMagick 1.3.43CPU Power Consumption Monitor10203040501. EPYC 4124P @ DDR5-5200: Approximate power consumption of 345 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520040.842.745.5smoke44.147.247.8OpenBenchmarking.orgCelsius, Fewer Is BetterGraphicsMagick 1.3.43CPU Temperature Monitor1428425670
MinAvgMaxEPYC 4124P @ DDR5-520054.766.269.4smoke55.268.169.8OpenBenchmarking.orgWatts, Fewer Is BetterGraphicsMagick 1.3.43System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 772 Joules per run.
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.43Operation: RotateEPYC 4124P @ DDR5-5200smoke306090120150Min: 158 / Avg: 158 / Max: 1581. (CC) gcc options: -fopenmp -O2 -ltiff -ljbig -lsharpyuv -lwebp -lwebpmux -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lxml2 -lzstd -llzma -lbz2 -lz -lm -lpthread -lgomp

RocksDB

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Random FillEPYC 4124P @ DDR5-5200smoke200K400K600K800K1000KSE +/- 2258.54, N = 38629318470991. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.orgOp/s Per Watt, More Is BetterRocksDB 9.0Test: Random FillEPYC 4124P @ DDR5-5200smoke3K6K9K12K15K15295.6514910.37
MinAvgMaxEPYC 4124P @ DDR5-520040049975140smoke40046805139OpenBenchmarking.orgMegahertz, More Is BetterRocksDB 9.0CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520021.756.461.2smoke16.656.862.5OpenBenchmarking.orgWatts, Fewer Is BetterRocksDB 9.0CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 639 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520048.163.767.5smoke45.367.771.4OpenBenchmarking.orgCelsius, Fewer Is BetterRocksDB 9.0CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.395.1105.0smoke55.297.6102.8OpenBenchmarking.orgWatts, Fewer Is BetterRocksDB 9.0System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1078 Joules per run.
OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Random FillEPYC 4124P @ DDR5-5200smoke150K300K450K600K750KMin: 858537 / Avg: 862931 / Max: 8660351. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

OpenVINO

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Age Gender Recognition Retail 0013 FP16 - Device: CPUEPYC 4124P @ DDR5-5200smoke0.090.180.270.360.45SE +/- 0.00, N = 30.40.4MIN: 0.22 / MAX: 4.51MIN: 0.22 / MAX: 4.391. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
MinAvgMaxEPYC 4124P @ DDR5-520040048034940smoke493449364938OpenBenchmarking.orgMegahertz, More Is BetterOpenVINO 2024.0CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.760.465.1smoke25.662.165.6OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2024.0CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 685 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520040.554.856.0smoke52.057.758.8OpenBenchmarking.orgCelsius, Fewer Is BetterOpenVINO 2024.0CPU Temperature Monitor1632486480
MinAvgMaxEPYC 4124P @ DDR5-520054.197.2103.3smoke54.199.9104.5OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2024.0System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1101 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Age Gender Recognition Retail 0013 FP16 - Device: CPUEPYC 4124P @ DDR5-5200smoke12345Min: 0.4 / Avg: 0.4 / Max: 0.41. (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: CPUEPYC 4124P @ DDR5-5200smoke2K4K6K8K10KSE +/- 7.10, N = 39649.239665.381. (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: CPUEPYC 4124P @ DDR5-5200smoke2K4K6K8K10KMin: 9635.8 / Avg: 9649.23 / Max: 9659.961. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

RocksDB

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Random Fill SyncEPYC 4124P @ DDR5-5200smoke11K22K33K44K55KSE +/- 133.22, N = 351267510881. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.orgOp/s Per Watt, More Is BetterRocksDB 9.0Test: Random Fill SyncEPYC 4124P @ DDR5-5200smoke4008001200160020001749.571778.66
MinAvgMaxEPYC 4124P @ DDR5-520040048135137smoke493749384941OpenBenchmarking.orgMegahertz, More Is BetterRocksDB 9.0CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.729.331.0smoke16.528.731.5OpenBenchmarking.orgWatts, Fewer Is BetterRocksDB 9.0CPU Power Consumption Monitor9182736451. EPYC 4124P @ DDR5-5200: Approximate power consumption of 342 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520040.040.742.0smoke45.045.446.6OpenBenchmarking.orgCelsius, Fewer Is BetterRocksDB 9.0CPU Temperature Monitor1428425670
MinAvgMaxEPYC 4124P @ DDR5-520052.964.766.3smoke54.765.567.2OpenBenchmarking.orgWatts, Fewer Is BetterRocksDB 9.0System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 734 Joules per run.
OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Random Fill SyncEPYC 4124P @ DDR5-5200smoke9K18K27K36K45KMin: 51020 / Avg: 51267 / Max: 514771. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

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: ParallelEPYC 4124P @ DDR5-5200smoke1.30562.61123.91685.22246.528SE +/- 0.02222, N = 35.732935.802871. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
MinAvgMaxEPYC 4124P @ DDR5-520040046794975smoke493549394941OpenBenchmarking.orgMegahertz, More Is BetterONNX Runtime 1.17CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520018.750.654.8smoke15.948.354.3OpenBenchmarking.orgWatts, Fewer Is BetterONNX Runtime 1.17CPU Power Consumption Monitor15304560751. EPYC 4124P @ DDR5-5200: Approximate power consumption of 591 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520041.649.950.9smoke42.551.352.8OpenBenchmarking.orgCelsius, Fewer Is BetterONNX Runtime 1.17CPU Temperature Monitor1530456075
MinAvgMaxEPYC 4124P @ DDR5-520054.088.492.4smoke53.988.392.3OpenBenchmarking.orgWatts, Fewer Is BetterONNX Runtime 1.17System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1031 Joules per run.
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: ResNet50 v1-12-int8 - Device: CPU - Executor: ParallelEPYC 4124P @ DDR5-5200smoke246810Min: 5.69 / Avg: 5.73 / Max: 5.771. (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: ParallelEPYC 4124P @ DDR5-5200smoke4080120160200SE +/- 0.68, N = 3174.41172.311. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: ResNet50 v1-12-int8 - Device: CPU - Executor: ParallelEPYC 4124P @ DDR5-5200smoke1.30562.61123.91685.22246.528SE +/- 0.02222, N = 35.732935.802871. (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: ParallelEPYC 4124P @ DDR5-5200smoke306090120150Min: 173.42 / Avg: 174.41 / Max: 175.711. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

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 ReadEPYC 4124P @ DDR5-5200smoke8M16M24M32M40MSE +/- 186103.10, N = 335829300357740941. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.orgOp/s Per Watt, More Is BetterSpeedb 2.7Test: Random ReadEPYC 4124P @ DDR5-5200smoke110K220K330K440K550K504939.24526625.28
MinAvgMaxEPYC 4124P @ DDR5-520040046974982smoke493249374947OpenBenchmarking.orgMegahertz, More Is BetterSpeedb 2.7CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.971.077.8smoke16.867.975.0OpenBenchmarking.orgWatts, Fewer Is BetterSpeedb 2.7CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 804 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520038.677.078.9smoke43.078.381.6OpenBenchmarking.orgCelsius, Fewer Is BetterSpeedb 2.7CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.1112.8119.3smoke53.9109.0119.1OpenBenchmarking.orgWatts, Fewer Is BetterSpeedb 2.7System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1279 Joules per run.
OpenBenchmarking.orgOp/s, More Is BetterSpeedb 2.7Test: Random ReadEPYC 4124P @ DDR5-5200smoke6M12M18M24M30MMin: 35459106 / Avg: 35829300.33 / Max: 360478671. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

RocksDB

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Read Random Write RandomEPYC 4124P @ DDR5-5200smoke300K600K900K1200K1500KSE +/- 11016.21, N = 3121996811824541. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.orgOp/s Per Watt, More Is BetterRocksDB 9.0Test: Read Random Write RandomEPYC 4124P @ DDR5-5200smoke4K8K12K16K20K17001.4417955.79
MinAvgMaxEPYC 4124P @ DDR5-520040048245135smoke40046265107OpenBenchmarking.orgMegahertz, More Is BetterRocksDB 9.0CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.071.877.7smoke17.165.975.9OpenBenchmarking.orgWatts, Fewer Is BetterRocksDB 9.0CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 813 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520042.571.173.6smoke47.172.776.3OpenBenchmarking.orgCelsius, Fewer Is BetterRocksDB 9.0CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.7115.5122.3smoke54.8113.7121.1OpenBenchmarking.orgWatts, Fewer Is BetterRocksDB 9.0System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1308 Joules per run.
OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Read Random Write RandomEPYC 4124P @ DDR5-5200smoke200K400K600K800K1000KMin: 1197939 / Avg: 1219968 / Max: 12313191. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: OverwriteEPYC 4124P @ DDR5-5200smoke200K400K600K800K1000KSE +/- 1336.06, N = 38639968636801. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.orgOp/s Per Watt, More Is BetterRocksDB 9.0Test: OverwriteEPYC 4124P @ DDR5-5200smoke3K6K9K12K15K15472.0915063.87
MinAvgMaxEPYC 4124P @ DDR5-520040049955139smoke501351165137OpenBenchmarking.orgMegahertz, More Is BetterRocksDB 9.0CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.855.860.9smoke22.157.361.3OpenBenchmarking.orgWatts, Fewer Is BetterRocksDB 9.0CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 670 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520042.063.367.6smoke51.668.672.8OpenBenchmarking.orgCelsius, Fewer Is BetterRocksDB 9.0CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.894.8105.0smoke54.597.5103.2OpenBenchmarking.orgWatts, Fewer Is BetterRocksDB 9.0System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1138 Joules per run.
OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: OverwriteEPYC 4124P @ DDR5-5200smoke150K300K450K600K750KMin: 861918 / Avg: 863996.33 / Max: 8664901. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Update RandomEPYC 4124P @ DDR5-5200smoke100K200K300K400K500KSE +/- 2398.03, N = 34789804755861. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.orgOp/s Per Watt, More Is BetterRocksDB 9.0Test: Update RandomEPYC 4124P @ DDR5-5200smoke150030004500600075007055.397164.10
MinAvgMaxEPYC 4124P @ DDR5-5200494151225140smoke494150745124OpenBenchmarking.orgMegahertz, More Is BetterRocksDB 9.0CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520018.167.973.1smoke16.766.472.4OpenBenchmarking.orgWatts, Fewer Is BetterRocksDB 9.0CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 747 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520043.368.872.4smoke45.471.274.9OpenBenchmarking.orgCelsius, Fewer Is BetterRocksDB 9.0CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.4109.0115.8smoke55.0110.6116.0OpenBenchmarking.orgWatts, Fewer Is BetterRocksDB 9.0System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1199 Joules per run.
OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Update RandomEPYC 4124P @ DDR5-5200smoke80K160K240K320K400KMin: 474184 / Avg: 478980 / Max: 4813971. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Read While WritingEPYC 4124P @ DDR5-5200smoke200K400K600K800K1000KSE +/- 3157.59, N = 3113526111073211. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.orgOp/s Per Watt, More Is BetterRocksDB 9.0Test: Read While WritingEPYC 4124P @ DDR5-5200smoke3K6K9K12K15K15883.4315728.59
MinAvgMaxEPYC 4124P @ DDR5-5200493650925134smoke500650525086OpenBenchmarking.orgMegahertz, More Is BetterRocksDB 9.0CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.771.577.2smoke22.870.475.7OpenBenchmarking.orgWatts, Fewer Is BetterRocksDB 9.0CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 786 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520042.371.173.4smoke64.974.275.8OpenBenchmarking.orgCelsius, Fewer Is BetterRocksDB 9.0CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520055.4114.8121.4smoke55.1113.5120.5OpenBenchmarking.orgWatts, Fewer Is BetterRocksDB 9.0System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1339 Joules per run.
OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Read While WritingEPYC 4124P @ DDR5-5200smoke200K400K600K800K1000KMin: 1129674 / Avg: 1135261.33 / Max: 11406041. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

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-SHA512EPYC 4124P @ DDR5-5200smoke13M26M39M52M65MSE +/- 38480.88, N = 360798667607960001. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -lm -lrt -lz -ldl -lcrypt -lbz2
OpenBenchmarking.orgReal C/S Per Watt, More Is BetterJohn The Ripper 2023.03.14Test: HMAC-SHA512EPYC 4124P @ DDR5-5200smoke200K400K600K800K1000K1149393.881103993.46
MinAvgMaxEPYC 4124P @ DDR5-520040048104941smoke493749394940OpenBenchmarking.orgMegahertz, More Is BetterJohn The Ripper 2023.03.14CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520019.152.960.8smoke25.855.163.2OpenBenchmarking.orgWatts, Fewer Is BetterJohn The Ripper 2023.03.14CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 617 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520045.154.158.6smoke55.058.762.0OpenBenchmarking.orgCelsius, Fewer Is BetterJohn The Ripper 2023.03.14CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.590.298.2smoke55.192.7101.7OpenBenchmarking.orgWatts, Fewer Is BetterJohn The Ripper 2023.03.14System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1053 Joules per run.
OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: HMAC-SHA512EPYC 4124P @ DDR5-5200smoke11M22M33M44M55MMin: 60752000 / Avg: 60798666.67 / Max: 608750001. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -lm -lrt -lz -ldl -lcrypt -lbz2

RocksDB

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Random ReadEPYC 4124P @ DDR5-5200smoke7M14M21M28M35MSE +/- 11708.73, N = 334885633348820541. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.orgOp/s Per Watt, More Is BetterRocksDB 9.0Test: Random ReadEPYC 4124P @ DDR5-5200smoke110K220K330K440K550K495710.59515752.40
MinAvgMaxEPYC 4124P @ DDR5-520040048394990smoke493349394943OpenBenchmarking.orgMegahertz, More Is BetterRocksDB 9.0CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.270.477.6smoke16.767.674.6OpenBenchmarking.orgWatts, Fewer Is BetterRocksDB 9.0CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 845 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520038.076.979.0smoke42.878.381.6OpenBenchmarking.orgCelsius, Fewer Is BetterRocksDB 9.0CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520053.7116.1118.9smoke116.8117.3117.9OpenBenchmarking.orgWatts, Fewer Is BetterRocksDB 9.0System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1354 Joules per run.
OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Random ReadEPYC 4124P @ DDR5-5200smoke6M12M18M24M30MMin: 34862960 / Avg: 34885632.67 / Max: 349020431. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

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 CompileEPYC 4124P @ DDR5-5200smoke1326395265SE +/- 0.39, N = 359.4760.111. (CC) gcc options: -m64 -ldl -lgcc_s -lutil -lrt -lpthread -lm -lc -pie -nodefaultlibs
MinAvgMaxEPYC 4124P @ DDR5-520040048285141smoke40046505140OpenBenchmarking.orgMegahertz, More Is BetterTimed Wasmer Compilation 2.3CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.564.975.8smoke15.762.274.9OpenBenchmarking.orgWatts, Fewer Is BetterTimed Wasmer Compilation 2.3CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 758 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520040.371.475.3smoke43.970.776.3OpenBenchmarking.orgCelsius, Fewer Is BetterTimed Wasmer Compilation 2.3CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.2106.0119.4smoke54.0108.8119.1OpenBenchmarking.orgWatts, Fewer Is BetterTimed Wasmer Compilation 2.3System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1237 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Wasmer Compilation 2.3Time To CompileEPYC 4124P @ DDR5-5200smoke1224364860Min: 58.68 / Avg: 59.47 / Max: 59.881. (CC) gcc options: -m64 -ldl -lgcc_s -lutil -lrt -lpthread -lm -lc -pie -nodefaultlibs

NAS Parallel Benchmarks

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

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: IS.DEPYC 4124P @ DDR5-5200smoke30060090012001500SE +/- 5.04, N = 31207.101202.871. (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
OpenBenchmarking.orgTotal Mop/s Per Watt, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: IS.DEPYC 4124P @ DDR5-5200smoke71421283530.0029.58
MinAvgMaxEPYC 4124P @ DDR5-5200493750025146smoke40046585140OpenBenchmarking.orgMegahertz, More Is BetterNAS Parallel Benchmarks 3.4CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520018.740.256.4smoke17.740.758.9OpenBenchmarking.orgWatts, Fewer Is BetterNAS Parallel Benchmarks 3.4CPU Power Consumption Monitor16324864801. EPYC 4124P @ DDR5-5200: Approximate power consumption of 443 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520039.447.861.4smoke45.054.568.6OpenBenchmarking.orgCelsius, Fewer Is BetterNAS Parallel Benchmarks 3.4CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520053.978.2107.4smoke55.080.4111.5OpenBenchmarking.orgWatts, Fewer Is BetterNAS Parallel Benchmarks 3.4System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 860 Joules per run.
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: IS.DEPYC 4124P @ DDR5-5200smoke2004006008001000Min: 1200.85 / Avg: 1207.1 / Max: 1217.081. (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

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.smt2EPYC 4124P @ DDR5-5200smoke1326395265SE +/- 0.22, N = 356.8656.371. (CXX) g++ options: -lpthread -std=c++17 -fvisibility=hidden -mfpmath=sse -msse -msse2 -O3 -fPIC
MinAvgMaxEPYC 4124P @ DDR5-520040048365141smoke40046575141OpenBenchmarking.orgMegahertz, More Is BetterZ3 Theorem Prover 4.12.1CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.731.833.2smoke15.629.030.7OpenBenchmarking.orgWatts, Fewer Is BetterZ3 Theorem Prover 4.12.1CPU Power Consumption Monitor10203040501. EPYC 4124P @ DDR5-5200: Approximate power consumption of 339 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520036.846.350.1smoke39.545.047.8OpenBenchmarking.orgCelsius, Fewer Is BetterZ3 Theorem Prover 4.12.1CPU Temperature Monitor1428425670
MinAvgMaxEPYC 4124P @ DDR5-520054.068.171.1smoke53.464.866.3OpenBenchmarking.orgWatts, Fewer Is BetterZ3 Theorem Prover 4.12.1System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 726 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterZ3 Theorem Prover 4.12.1SMT File: 2.smt2EPYC 4124P @ DDR5-5200smoke1122334455Min: 56.51 / Avg: 56.86 / Max: 57.261. (CXX) g++ options: -lpthread -std=c++17 -fvisibility=hidden -mfpmath=sse -msse -msse2 -O3 -fPIC

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 AtomsEPYC 4124P @ DDR5-5200smoke0.20180.40360.60540.80721.009SE +/- 0.00275, N = 30.896780.88756
OpenBenchmarking.orgns/day Per Watt, More Is BetterNAMD 3.0b6Input: ATPase with 327,506 AtomsEPYC 4124P @ DDR5-5200smoke0.00320.00640.00960.01280.0160.0140.014
MinAvgMaxEPYC 4124P @ DDR5-5200492450035140smoke40045905131OpenBenchmarking.orgMegahertz, More Is BetterNAMD 3.0b6CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.464.970.9smoke17.362.472.1OpenBenchmarking.orgWatts, Fewer Is BetterNAMD 3.0b6CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 714 Joules per run.2. smoke: Approximate power consumption of 749 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520040.468.370.9smoke46.372.075.4OpenBenchmarking.orgCelsius, Fewer Is BetterNAMD 3.0b6CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520053.9108.7113.7smoke54.2109.2116.1OpenBenchmarking.orgWatts, Fewer Is BetterNAMD 3.0b6System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1159 Joules per run.2. smoke: Approximate power consumption of 1202 Joules per run.
OpenBenchmarking.orgns/day, More Is BetterNAMD 3.0b6Input: ATPase with 327,506 AtomsEPYC 4124P @ DDR5-5200smoke246810Min: 0.89 / Avg: 0.9 / Max: 0.9

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: leblancbigEPYC 4124P @ DDR5-5200smoke1224364860SE +/- 0.08, N = 354.7854.661. (CXX) g++ options: -fopenmp -lmpi_cxx -lmpi
MinAvgMaxEPYC 4124P @ DDR5-520040049835144smoke40047045136OpenBenchmarking.orgMegahertz, More Is BetterPennant 1.0.1CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.456.862.1smoke15.958.464.8OpenBenchmarking.orgWatts, Fewer Is BetterPennant 1.0.1CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 606 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520039.054.256.8smoke44.360.963.5OpenBenchmarking.orgCelsius, Fewer Is BetterPennant 1.0.1CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520053.599.2104.8smoke54.2103.3108.8OpenBenchmarking.orgWatts, Fewer Is BetterPennant 1.0.1System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1058 Joules per run.
OpenBenchmarking.orgHydro Cycle Time - Seconds, Fewer Is BetterPennant 1.0.1Test: leblancbigEPYC 4124P @ DDR5-5200smoke1122334455Min: 54.63 / Avg: 54.78 / Max: 54.91. (CXX) g++ options: -fopenmp -lmpi_cxx -lmpi

JPEG-XL libjxl

OpenBenchmarking.orgMP/s, More Is BetterJPEG-XL libjxl 0.10.1Input: PNG - Quality: 90EPYC 4124P @ DDR5-5200smoke510152025SE +/- 0.07, N = 322.2422.211. (CXX) g++ options: -fno-rtti -O3 -fPIE -pie -lm
OpenBenchmarking.orgMP/s Per Watt, More Is BetterJPEG-XL libjxl 0.10.1Input: PNG - Quality: 90EPYC 4124P @ DDR5-5200smoke0.07760.15520.23280.31040.3880.3220.345
MinAvgMaxEPYC 4124P @ DDR5-5200494050325140smoke493549795140OpenBenchmarking.orgMegahertz, More Is BetterJPEG-XL libjxl 0.10.1CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520019.269.175.1smoke16.564.374.1OpenBenchmarking.orgWatts, Fewer Is BetterJPEG-XL libjxl 0.10.1CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 714 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520047.076.078.1smoke46.175.379.6OpenBenchmarking.orgCelsius, Fewer Is BetterJPEG-XL libjxl 0.10.1CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520055.2114.1121.0smoke55.0112.0119.0OpenBenchmarking.orgWatts, Fewer Is BetterJPEG-XL libjxl 0.10.1System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1179 Joules per run.
OpenBenchmarking.orgMP/s, More Is BetterJPEG-XL libjxl 0.10.1Input: PNG - Quality: 90EPYC 4124P @ DDR5-5200smoke510152025Min: 22.15 / Avg: 22.24 / Max: 22.371. (CXX) g++ options: -fno-rtti -O3 -fPIE -pie -lm

OpenBenchmarking.orgMP/s, More Is BetterJPEG-XL libjxl 0.10.1Input: PNG - Quality: 100EPYC 4124P @ DDR5-5200smoke3691215SE +/- 0.002, N = 38.9998.9751. (CXX) g++ options: -fno-rtti -O3 -fPIE -pie -lm
OpenBenchmarking.orgMP/s Per Watt, More Is BetterJPEG-XL libjxl 0.10.1Input: PNG - Quality: 100EPYC 4124P @ DDR5-5200smoke0.03150.0630.09450.1260.15750.1380.140
MinAvgMaxEPYC 4124P @ DDR5-520040048355081smoke496449935064OpenBenchmarking.orgMegahertz, More Is BetterJPEG-XL libjxl 0.10.1CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.065.071.3smoke19.764.170.1OpenBenchmarking.orgWatts, Fewer Is BetterJPEG-XL libjxl 0.10.1CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 693 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520044.475.677.8smoke55.576.078.9OpenBenchmarking.orgCelsius, Fewer Is BetterJPEG-XL libjxl 0.10.1CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.9109.2113.7smoke54.8105.6112.4OpenBenchmarking.orgWatts, Fewer Is BetterJPEG-XL libjxl 0.10.1System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1128 Joules per run.
OpenBenchmarking.orgMP/s, More Is BetterJPEG-XL libjxl 0.10.1Input: PNG - Quality: 100EPYC 4124P @ DDR5-5200smoke3691215Min: 9 / Avg: 9 / Max: 91. (CXX) g++ options: -fno-rtti -O3 -fPIE -pie -lm

OpenBenchmarking.orgMP/s, More Is BetterJPEG-XL libjxl 0.10.1Input: JPEG - Quality: 100EPYC 4124P @ DDR5-5200smoke3691215SE +/- 0.002, N = 38.9598.9511. (CXX) g++ options: -fno-rtti -O3 -fPIE -pie -lm
OpenBenchmarking.orgMP/s Per Watt, More Is BetterJPEG-XL libjxl 0.10.1Input: JPEG - Quality: 100EPYC 4124P @ DDR5-5200smoke0.03220.06440.09660.12880.1610.1360.143
MinAvgMaxEPYC 4124P @ DDR5-5200493949845115smoke40046125140OpenBenchmarking.orgMegahertz, More Is BetterJPEG-XL libjxl 0.10.1CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.965.771.2smoke16.162.870.2OpenBenchmarking.orgWatts, Fewer Is BetterJPEG-XL libjxl 0.10.1CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 657 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520044.076.177.9smoke45.675.778.9OpenBenchmarking.orgCelsius, Fewer Is BetterJPEG-XL libjxl 0.10.1CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.8107.2113.5smoke54.4102.9112.8OpenBenchmarking.orgWatts, Fewer Is BetterJPEG-XL libjxl 0.10.1System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1072 Joules per run.
OpenBenchmarking.orgMP/s, More Is BetterJPEG-XL libjxl 0.10.1Input: JPEG - Quality: 100EPYC 4124P @ DDR5-5200smoke3691215Min: 8.96 / Avg: 8.96 / Max: 8.961. (CXX) g++ options: -fno-rtti -O3 -fPIE -pie -lm

Node.js V8 Web Tooling Benchmark

Running the V8 project's Web-Tooling-Benchmark under Node.js. The Web-Tooling-Benchmark stresses JavaScript-related workloads common to web developers like Babel and TypeScript and Babylon. This test profile can test the system's JavaScript performance with Node.js. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgruns/s, More Is BetterNode.js V8 Web Tooling BenchmarkEPYC 4124P @ DDR5-5200smoke510152025SE +/- 0.21, N = 319.4920.01
OpenBenchmarking.orgruns/s Per Watt, More Is BetterNode.js V8 Web Tooling BenchmarkEPYC 4124P @ DDR5-5200smoke0.12940.25880.38820.51760.6470.5320.575
MinAvgMaxEPYC 4124P @ DDR5-520040049915145smoke514051405141OpenBenchmarking.orgMegahertz, More Is BetterNode.js V8 Web Tooling BenchmarkCPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.836.642.8smoke20.134.838.0OpenBenchmarking.orgWatts, Fewer Is BetterNode.js V8 Web Tooling BenchmarkCPU Power Consumption Monitor12243648601. EPYC 4124P @ DDR5-5200: Approximate power consumption of 403 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520042.956.966.4smoke49.455.257.9OpenBenchmarking.orgCelsius, Fewer Is BetterNode.js V8 Web Tooling BenchmarkCPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.374.281.4smoke54.671.075.5OpenBenchmarking.orgWatts, Fewer Is BetterNode.js V8 Web Tooling BenchmarkSystem Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 791 Joules per run.
OpenBenchmarking.orgruns/s, More Is BetterNode.js V8 Web Tooling BenchmarkEPYC 4124P @ DDR5-5200smoke510152025Min: 19.23 / Avg: 19.49 / Max: 19.91

OSPRay

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 3.1Benchmark: gravity_spheres_volume/dim_512/ao/real_timeEPYC 4124P @ DDR5-5200smoke0.4420.8841.3261.7682.21SE +/- 0.00310, N = 31.958621.96430
OpenBenchmarking.orgItems Per Second Per Watt, More Is BetterOSPRay 3.1Benchmark: gravity_spheres_volume/dim_512/ao/real_timeEPYC 4124P @ DDR5-5200smoke0.0070.0140.0210.0280.0350.0310.031
MinAvgMaxEPYC 4124P @ DDR5-5200493350885141smoke493850915124OpenBenchmarking.orgMegahertz, More Is BetterOSPRay 3.1CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.163.271.6smoke19.263.071.4OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay 3.1CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 653 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520044.668.371.0smoke44.667.471.0OpenBenchmarking.orgCelsius, Fewer Is BetterOSPRay 3.1CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.8102.7113.0smoke54.1101.4113.0OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay 3.1System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1061 Joules per run.
OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 3.1Benchmark: gravity_spheres_volume/dim_512/ao/real_timeEPYC 4124P @ DDR5-5200smoke246810Min: 1.95 / Avg: 1.96 / Max: 1.96

JPEG-XL libjxl

OpenBenchmarking.orgMP/s, More Is BetterJPEG-XL libjxl 0.10.1Input: JPEG - Quality: 90EPYC 4124P @ DDR5-5200smoke510152025SE +/- 0.07, N = 322.7122.921. (CXX) g++ options: -fno-rtti -O3 -fPIE -pie -lm
OpenBenchmarking.orgMP/s Per Watt, More Is BetterJPEG-XL libjxl 0.10.1Input: JPEG - Quality: 90EPYC 4124P @ DDR5-5200smoke0.07540.15080.22620.30160.3770.3310.335
MinAvgMaxEPYC 4124P @ DDR5-520040048565141smoke493549875141OpenBenchmarking.orgMegahertz, More Is BetterJPEG-XL libjxl 0.10.1CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.068.674.8smoke24.468.574.3OpenBenchmarking.orgWatts, Fewer Is BetterJPEG-XL libjxl 0.10.1CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 709 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520044.076.078.5smoke65.378.079.9OpenBenchmarking.orgCelsius, Fewer Is BetterJPEG-XL libjxl 0.10.1CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.9111.7118.5smoke55.4110.9118.6OpenBenchmarking.orgWatts, Fewer Is BetterJPEG-XL libjxl 0.10.1System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1117 Joules per run.
OpenBenchmarking.orgMP/s, More Is BetterJPEG-XL libjxl 0.10.1Input: JPEG - Quality: 90EPYC 4124P @ DDR5-5200smoke510152025Min: 22.63 / Avg: 22.71 / Max: 22.861. (CXX) g++ options: -fno-rtti -O3 -fPIE -pie -lm

VVenC

OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.11Video Input: Bosphorus 1080p - Video Preset: FastEPYC 4124P @ DDR5-5200smoke3691215SE +/- 0.02, N = 311.4311.371. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterVVenC 1.11Video Input: Bosphorus 1080p - Video Preset: FastEPYC 4124P @ DDR5-5200smoke0.03530.07060.10590.14120.17650.1570.157
MinAvgMaxEPYC 4124P @ DDR5-520040048305040smoke495649735067OpenBenchmarking.orgMegahertz, More Is BetterVVenC 1.11CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.372.679.1smoke29.472.377.6OpenBenchmarking.orgWatts, Fewer Is BetterVVenC 1.11CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 750 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520042.376.578.9smoke73.679.780.8OpenBenchmarking.orgCelsius, Fewer Is BetterVVenC 1.11CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.7117.7125.3smoke55.0115.8124.7OpenBenchmarking.orgWatts, Fewer Is BetterVVenC 1.11System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1216 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.11Video Input: Bosphorus 1080p - Video Preset: FastEPYC 4124P @ DDR5-5200smoke3691215Min: 11.38 / Avg: 11.43 / Max: 11.461. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects

OSPRay

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 3.1Benchmark: gravity_spheres_volume/dim_512/scivis/real_timeEPYC 4124P @ DDR5-5200smoke0.43760.87521.31281.75042.188SE +/- 0.00828, N = 31.945041.94320
OpenBenchmarking.orgItems Per Second Per Watt, More Is BetterOSPRay 3.1Benchmark: gravity_spheres_volume/dim_512/scivis/real_timeEPYC 4124P @ DDR5-5200smoke0.00740.01480.02220.02960.0370.0310.033
MinAvgMaxEPYC 4124P @ DDR5-520040049425141smoke40046465141OpenBenchmarking.orgMegahertz, More Is BetterOSPRay 3.1CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.763.071.8smoke16.558.871.5OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay 3.1CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 630 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520046.068.671.1smoke45.667.271.0OpenBenchmarking.orgCelsius, Fewer Is BetterOSPRay 3.1CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.9105.8113.4smoke54.6102.2113.3OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay 3.1System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1058 Joules per run.
OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 3.1Benchmark: gravity_spheres_volume/dim_512/scivis/real_timeEPYC 4124P @ DDR5-5200smoke246810Min: 1.93 / Avg: 1.95 / Max: 1.96

Timed Mesa Compilation

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Mesa Compilation 24.0Time To CompileEPYC 4124P @ DDR5-5200smoke1224364860SE +/- 0.12, N = 351.9752.59
MinAvgMaxEPYC 4124P @ DDR5-520040047315115smoke490350385140OpenBenchmarking.orgMegahertz, More Is BetterTimed Mesa Compilation 24.0CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.766.475.9smoke16.863.175.0OpenBenchmarking.orgWatts, Fewer Is BetterTimed Mesa Compilation 24.0CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 687 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520044.373.478.1smoke45.671.377.9OpenBenchmarking.orgCelsius, Fewer Is BetterTimed Mesa Compilation 24.0CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520055.3112.6119.7smoke55.7108.9119.5OpenBenchmarking.orgWatts, Fewer Is BetterTimed Mesa Compilation 24.0System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1126 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Mesa Compilation 24.0Time To CompileEPYC 4124P @ DDR5-5200smoke1122334455Min: 51.79 / Avg: 51.97 / Max: 52.18

OSPRay

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 3.1Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_timeEPYC 4124P @ DDR5-5200smoke0.52811.05621.58432.11242.6405SE +/- 0.00113, N = 32.347262.34015
OpenBenchmarking.orgItems Per Second Per Watt, More Is BetterOSPRay 3.1Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_timeEPYC 4124P @ DDR5-5200smoke0.00810.01620.02430.03240.04050.0360.035
MinAvgMaxEPYC 4124P @ DDR5-5200494150815141smoke493750745108OpenBenchmarking.orgMegahertz, More Is BetterOSPRay 3.1CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.065.474.2smoke19.965.974.0OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay 3.1CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 654 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520043.869.872.3smoke45.069.372.4OpenBenchmarking.orgCelsius, Fewer Is BetterOSPRay 3.1CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.9108.0116.0smoke54.7107.6115.9OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay 3.1System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1080 Joules per run.
OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 3.1Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_timeEPYC 4124P @ DDR5-5200smoke246810Min: 2.35 / Avg: 2.35 / Max: 2.35

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 4KEPYC 4124P @ DDR5-5200smoke3691215SE +/- 0.04, N = 311.6611.521. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OpenBenchmarking.orgFrames Per Second Per Watt, More Is Betterx265 3.4Video Input: Bosphorus 4KEPYC 4124P @ DDR5-5200smoke0.04250.0850.12750.170.21250.1880.189
MinAvgMaxEPYC 4124P @ DDR5-520040049095141smoke40046395141OpenBenchmarking.orgMegahertz, More Is Betterx265 3.4CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520023.362.270.1smoke16.861.067.3OpenBenchmarking.orgWatts, Fewer Is Betterx265 3.4CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 580 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520058.073.576.3smoke43.972.876.6OpenBenchmarking.orgCelsius, Fewer Is Betterx265 3.4CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520055.1106.2116.3smoke55.1102.2111.1OpenBenchmarking.orgWatts, Fewer Is Betterx265 3.4System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 991 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.4Video Input: Bosphorus 4KEPYC 4124P @ DDR5-5200smoke3691215Min: 11.58 / Avg: 11.66 / Max: 11.71. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

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: LiveEPYC 4124P @ DDR5-5200smoke306090120150SE +/- 0.04, N = 3141.03140.451. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OpenBenchmarking.orgFPS Per Watt, More Is BetterFFmpeg 6.1Encoder: libx265 - Scenario: LiveEPYC 4124P @ DDR5-5200smoke0.59271.18541.77812.37082.96352.6202.634
MinAvgMaxEPYC 4124P @ DDR5-520040049405149smoke494050915141OpenBenchmarking.orgMegahertz, More Is BetterFFmpeg 6.1CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.853.872.9smoke16.653.371.8OpenBenchmarking.orgWatts, Fewer Is BetterFFmpeg 6.1CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 556 Joules per run.2. smoke: Approximate power consumption of 533 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520045.367.773.4smoke46.068.775.8OpenBenchmarking.orgCelsius, Fewer Is BetterFFmpeg 6.1CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.894.1117.2smoke55.789.5117.4OpenBenchmarking.orgWatts, Fewer Is BetterFFmpeg 6.1System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 972 Joules per run.2. smoke: Approximate power consumption of 984 Joules per run.
OpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.1Encoder: libx265 - Scenario: LiveEPYC 4124P @ DDR5-5200smoke306090120150Min: 140.96 / Avg: 141.03 / Max: 141.111. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 4 - Input: Bosphorus 4KEPYC 4124P @ DDR5-5200smoke0.73511.47022.20532.94043.6755SE +/- 0.004, N = 33.2633.2671. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 4 - Input: Bosphorus 4KEPYC 4124P @ DDR5-5200smoke0.01010.02020.03030.04040.05050.0440.045
MinAvgMaxEPYC 4124P @ DDR5-520040048205140smoke495050155141OpenBenchmarking.orgMegahertz, More Is BetterSVT-AV1 2.0CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520023.574.282.8smoke19.073.282.5OpenBenchmarking.orgWatts, Fewer Is BetterSVT-AV1 2.0CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 717 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520059.877.680.5smoke44.175.780.8OpenBenchmarking.orgCelsius, Fewer Is BetterSVT-AV1 2.0CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.7118.9128.2smoke55.0120.0128.5OpenBenchmarking.orgWatts, Fewer Is BetterSVT-AV1 2.0System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1149 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 4 - Input: Bosphorus 4KEPYC 4124P @ DDR5-5200smoke246810Min: 3.26 / Avg: 3.26 / Max: 3.271. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

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 1.7EPYC 4124P @ DDR5-52005K10K15K20K25KSE +/- 2.21, N = 323895.281. (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
OpenBenchmarking.orgk/s Per Watt, More Is BetterAircrack-ng 1.7EPYC 4124P @ DDR5-520080160240320400386.95
MinAvgMaxEPYC 4124P @ DDR5-520040044364943OpenBenchmarking.orgMegahertz, More Is BetterAircrack-ng 1.7CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.061.870.2OpenBenchmarking.orgWatts, Fewer Is BetterAircrack-ng 1.7CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 371 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520043.463.165.5OpenBenchmarking.orgCelsius, Fewer Is BetterAircrack-ng 1.7CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.5100.4109.7OpenBenchmarking.orgWatts, Fewer Is BetterAircrack-ng 1.7System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 602 Joules per run.

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 FastEPYC 4124P @ DDR5-5200smoke3691215SE +/- 0.00, N = 313.1413.11
OpenBenchmarking.orgFrames Per Second Per Watt, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Very FastEPYC 4124P @ DDR5-5200smoke0.04120.08240.12360.16480.2060.1780.183
MinAvgMaxEPYC 4124P @ DDR5-520040048025037smoke493949574977OpenBenchmarking.orgMegahertz, More Is Betteruvg266 0.4.1CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.273.781.0smoke23.871.580.1OpenBenchmarking.orgWatts, Fewer Is Betteruvg266 0.4.1CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 688 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520045.377.179.3smoke65.979.181.3OpenBenchmarking.orgCelsius, Fewer Is Betteruvg266 0.4.1CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520055.2115.6125.7smoke54.8115.9125.8OpenBenchmarking.orgWatts, Fewer Is Betteruvg266 0.4.1System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 1079 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Very FastEPYC 4124P @ DDR5-5200smoke48121620Min: 13.14 / Avg: 13.14 / Max: 13.15

Llama.cpp

Llama.cpp is a port of Facebook's LLaMA model in C/C++ developed by Georgi Gerganov. Llama.cpp allows the inference of LLaMA and other supported models in C/C++. For CPU inference Llama.cpp supports AVX2/AVX-512, ARM NEON, and other modern ISAs along with features like OpenBLAS usage. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b1808Model: llama-2-7b.Q4_0.ggufEPYC 4124P @ DDR5-5200smoke3691215SE +/- 0.01, N = 311.7811.771. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -march=native -mtune=native -lopenblas
OpenBenchmarking.orgTokens Per Second Per Watt, More Is BetterLlama.cpp b1808Model: llama-2-7b.Q4_0.ggufEPYC 4124P @ DDR5-5200smoke0.04840.09680.14520.19360.2420.2060.215
MinAvgMaxEPYC 4124P @ DDR5-5200492649515122smoke40044324938OpenBenchmarking.orgMegahertz, More Is BetterLlama.cpp b1808CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520019.157.162.2smoke17.054.762.6OpenBenchmarking.orgWatts, Fewer Is BetterLlama.cpp b1808CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 514 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520039.950.956.0smoke41.652.957.5OpenBenchmarking.orgCelsius, Fewer Is BetterLlama.cpp b1808CPU Temperature Monitor1632486480
MinAvgMaxEPYC 4124P @ DDR5-520053.399.2105.6smoke53.195.4106.4OpenBenchmarking.orgWatts, Fewer Is BetterLlama.cpp b1808System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 893 Joules per run.
OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b1808Model: llama-2-7b.Q4_0.ggufEPYC 4124P @ DDR5-5200smoke3691215Min: 11.77 / Avg: 11.78 / Max: 11.791. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -march=native -mtune=native -lopenblas

Llamafile

Mozilla's Llamafile allows distributing and running large language models (LLMs) as a single file. Llamafile aims to make open-source LLMs more accessible to developers and users. Llamafile supports a variety of models, CPUs and GPUs, and other options. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.6Test: llava-v1.5-7b-q4 - Acceleration: CPUEPYC 4124P @ DDR5-5200smoke3691215SE +/- 0.01, N = 310.5710.68
OpenBenchmarking.orgTokens Per Second Per Watt, More Is BetterLlamafile 0.6Test: llava-v1.5-7b-q4 - Acceleration: CPUEPYC 4124P @ DDR5-5200smoke0.04010.08020.12030.16040.20050.1610.178
MinAvgMaxEPYC 4124P @ DDR5-520040048935145smoke40045645138OpenBenchmarking.orgMegahertz, More Is BetterLlamafile 0.6CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520021.965.779.6smoke16.560.179.8OpenBenchmarking.orgWatts, Fewer Is BetterLlamafile 0.6CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 592 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520044.865.574.1smoke41.666.576.9OpenBenchmarking.orgCelsius, Fewer Is BetterLlamafile 0.6CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.4108.2122.3smoke53.9101.6123.9OpenBenchmarking.orgWatts, Fewer Is BetterLlamafile 0.6System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 974 Joules per run.
OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.6Test: llava-v1.5-7b-q4 - Acceleration: CPUEPYC 4124P @ DDR5-5200smoke3691215Min: 10.56 / Avg: 10.57 / Max: 10.59

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 - DegriddingEPYC 4124P @ DDR5-5200smoke6001200180024003000SE +/- 16.62, N = 152841.952894.091. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
OpenBenchmarking.orgMillion Grid Points Per Second Per Watt, More Is BetterASKAP 1.0Test: tConvolve OpenMP - DegriddingEPYC 4124P @ DDR5-52002040608010097.77
MinAvgMaxEPYC 4124P @ DDR5-520040043925141OpenBenchmarking.orgMegahertz, More Is BetterASKAP 1.0CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.829.133.8OpenBenchmarking.orgWatts, Fewer Is BetterASKAP 1.0CPU Power Consumption Monitor10203040501. EPYC 4124P @ DDR5-5200: Approximate power consumption of 79 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520039.341.645.8OpenBenchmarking.orgCelsius, Fewer Is BetterASKAP 1.0CPU Temperature Monitor1224364860
MinAvgMaxEPYC 4124P @ DDR5-520053.369.494.8OpenBenchmarking.orgWatts, Fewer Is BetterASKAP 1.0System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 190 Joules per run.
OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 1.0Test: tConvolve OpenMP - DegriddingEPYC 4124P @ DDR5-5200smoke5001000150020002500Min: 2744.91 / Avg: 2841.95 / Max: 2894.091. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 1.0Test: tConvolve OpenMP - GriddingEPYC 4124P @ DDR5-5200smoke400800120016002000SE +/- 19.19, N = 151801.151875.041. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 1.0Test: tConvolve OpenMP - GriddingEPYC 4124P @ DDR5-5200smoke30060090012001500Min: 1653.76 / Avg: 1801.15 / Max: 1901.831. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

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, PyriteEPYC 4124P @ DDR5-52003K6K9K12K15KSE +/- 143.80, N = 3144471. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenBenchmarking.orgkH/s Per Watt, More Is BetterCpuminer-Opt 23.5Algorithm: Quad SHA-256, PyriteEPYC 4124P @ DDR5-520060120180240300260.20
MinAvgMaxEPYC 4124P @ DDR5-520040048815141OpenBenchmarking.orgMegahertz, More Is BetterCpuminer-Opt 23.5CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.455.565.3OpenBenchmarking.orgWatts, Fewer Is BetterCpuminer-Opt 23.5CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 352 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520041.359.463.0OpenBenchmarking.orgCelsius, Fewer Is BetterCpuminer-Opt 23.5CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.190.9102.1OpenBenchmarking.orgWatts, Fewer Is BetterCpuminer-Opt 23.5System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 576 Joules per run.

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 23.5Algorithm: DeepcoinEPYC 4124P @ DDR5-52005001000150020002500SE +/- 1.80, N = 32205.101. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenBenchmarking.orgkH/s Per Watt, More Is BetterCpuminer-Opt 23.5Algorithm: DeepcoinEPYC 4124P @ DDR5-520081624324034.74
MinAvgMaxEPYC 4124P @ DDR5-520040046305116OpenBenchmarking.orgMegahertz, More Is BetterCpuminer-Opt 23.5CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.263.573.1OpenBenchmarking.orgWatts, Fewer Is BetterCpuminer-Opt 23.5CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 423 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520042.569.572.9OpenBenchmarking.orgCelsius, Fewer Is BetterCpuminer-Opt 23.5CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.5104.4113.0OpenBenchmarking.orgWatts, Fewer Is BetterCpuminer-Opt 23.5System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 696 Joules per run.

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 EngineEPYC 4124P @ DDR5-52007001400210028003500SE +/- 22.07, N = 33438
MinAvgMaxEPYC 4124P @ DDR5-520040048735141OpenBenchmarking.orgMegahertz, More Is BetterDaCapo Benchmark 23.11CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520021.546.569.2OpenBenchmarking.orgWatts, Fewer Is BetterDaCapo Benchmark 23.11CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 294 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520051.063.869.5OpenBenchmarking.orgCelsius, Fewer Is BetterDaCapo Benchmark 23.11CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.784.7117.8OpenBenchmarking.orgWatts, Fewer Is BetterDaCapo Benchmark 23.11System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 536 Joules per run.

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, OnecoinEPYC 4124P @ DDR5-52005K10K15K20K25KSE +/- 166.77, N = 3253371. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenBenchmarking.orgkH/s Per Watt, More Is BetterCpuminer-Opt 23.5Algorithm: Triple SHA-256, OnecoinEPYC 4124P @ DDR5-5200100200300400500454.77
MinAvgMaxEPYC 4124P @ DDR5-520040046754966OpenBenchmarking.orgMegahertz, More Is BetterCpuminer-Opt 23.5CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.655.763.3OpenBenchmarking.orgWatts, Fewer Is BetterCpuminer-Opt 23.5CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 297 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520042.857.959.6OpenBenchmarking.orgCelsius, Fewer Is BetterCpuminer-Opt 23.5CPU Temperature Monitor1632486480
MinAvgMaxEPYC 4124P @ DDR5-520054.192.1100.8OpenBenchmarking.orgWatts, Fewer Is BetterCpuminer-Opt 23.5System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 522 Joules per run.

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: 4 - Buffer Length: 256 - Filter Length: 512EPYC 4124P @ DDR5-5200smoke16M32M48M64M80MSE +/- 769421.04, N = 572730800748270001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s Per Watt, More Is BetterLiquid-DSP 1.6Threads: 4 - Buffer Length: 256 - Filter Length: 512EPYC 4124P @ DDR5-5200smoke300K600K900K1200K1500K1274615.611340361.12
MinAvgMaxEPYC 4124P @ DDR5-520040048285146OpenBenchmarking.orgMegahertz, More Is BetterLiquid-DSP 1.6CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520025.757.164.3OpenBenchmarking.orgWatts, Fewer Is BetterLiquid-DSP 1.6CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 354 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520050.557.659.5OpenBenchmarking.orgCelsius, Fewer Is BetterLiquid-DSP 1.6CPU Temperature Monitor1632486480
MinAvgMaxEPYC 4124P @ DDR5-520054.395.2101.3OpenBenchmarking.orgWatts, Fewer Is BetterLiquid-DSP 1.6System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 590 Joules per run.
OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 4 - Buffer Length: 256 - Filter Length: 512EPYC 4124P @ DDR5-5200smoke13M26M39M52M65MMin: 69715000 / Avg: 72730800 / Max: 739740001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

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 PointEPYC 4124P @ DDR5-52003K6K9K12K15KSE +/- 17.31, N = 314008.641. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -lEGL -ljpeg -lmpfr -lpthread -lrt -lsctp -lz
OpenBenchmarking.orgBogo Ops/s Per Watt, More Is BetterStress-NG 0.16.04Test: Vector Floating PointEPYC 4124P @ DDR5-520050100150200250234.61
MinAvgMaxEPYC 4124P @ DDR5-520040046465140OpenBenchmarking.orgMegahertz, More Is BetterStress-NG 0.16.04CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520015.359.768.5OpenBenchmarking.orgWatts, Fewer Is BetterStress-NG 0.16.04CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 398 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520040.466.970.6OpenBenchmarking.orgCelsius, Fewer Is BetterStress-NG 0.16.04CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.598.5107.5OpenBenchmarking.orgWatts, Fewer Is BetterStress-NG 0.16.04System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 624 Joules per run.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Floating PointEPYC 4124P @ DDR5-52005001000150020002500SE +/- 1.85, N = 32137.331. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -lEGL -ljpeg -lmpfr -lpthread -lrt -lsctp -lz
OpenBenchmarking.orgBogo Ops/s Per Watt, More Is BetterStress-NG 0.16.04Test: Floating PointEPYC 4124P @ DDR5-520081624324035.46
MinAvgMaxEPYC 4124P @ DDR5-5200493950735140OpenBenchmarking.orgMegahertz, More Is BetterStress-NG 0.16.04CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520015.160.369.8OpenBenchmarking.orgWatts, Fewer Is BetterStress-NG 0.16.04CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 342 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520039.869.873.5OpenBenchmarking.orgCelsius, Fewer Is BetterStress-NG 0.16.04CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520053.3100.1110.0OpenBenchmarking.orgWatts, Fewer Is BetterStress-NG 0.16.04System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 601 Joules per run.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Matrix 3D MathEPYC 4124P @ DDR5-5200400800120016002000SE +/- 12.52, N = 31960.751. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -lEGL -ljpeg -lmpfr -lpthread -lrt -lsctp -lz
OpenBenchmarking.orgBogo Ops/s Per Watt, More Is BetterStress-NG 0.16.04Test: Matrix 3D MathEPYC 4124P @ DDR5-5200112233445547.34
MinAvgMaxEPYC 4124P @ DDR5-520040046805078OpenBenchmarking.orgMegahertz, More Is BetterStress-NG 0.16.04CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.941.445.5OpenBenchmarking.orgWatts, Fewer Is BetterStress-NG 0.16.04CPU Power Consumption Monitor12243648601. EPYC 4124P @ DDR5-5200: Approximate power consumption of 235 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520042.645.245.5OpenBenchmarking.orgCelsius, Fewer Is BetterStress-NG 0.16.04CPU Temperature Monitor1224364860
MinAvgMaxEPYC 4124P @ DDR5-520055.083.888.6OpenBenchmarking.orgWatts, Fewer Is BetterStress-NG 0.16.04System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 475 Joules per run.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Vector ShuffleEPYC 4124P @ DDR5-52009001800270036004500SE +/- 1.14, N = 34319.581. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -lEGL -ljpeg -lmpfr -lpthread -lrt -lsctp -lz
OpenBenchmarking.orgBogo Ops/s Per Watt, More Is BetterStress-NG 0.16.04Test: Vector ShuffleEPYC 4124P @ DDR5-5200163248648070.53
MinAvgMaxEPYC 4124P @ DDR5-520040047975090OpenBenchmarking.orgMegahertz, More Is BetterStress-NG 0.16.04CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.761.268.6OpenBenchmarking.orgWatts, Fewer Is BetterStress-NG 0.16.04CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 347 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520041.970.673.3OpenBenchmarking.orgCelsius, Fewer Is BetterStress-NG 0.16.04CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520055.0100.2108.4OpenBenchmarking.orgWatts, Fewer Is BetterStress-NG 0.16.04System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 568 Joules per run.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: System V Message PassingEPYC 4124P @ DDR5-52001.5M3M4.5M6M7.5MSE +/- 10136.17, N = 37212479.031. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -lEGL -ljpeg -lmpfr -lpthread -lrt -lsctp -lz
OpenBenchmarking.orgBogo Ops/s Per Watt, More Is BetterStress-NG 0.16.04Test: System V Message PassingEPYC 4124P @ DDR5-520030K60K90K120K150K125393.37
MinAvgMaxEPYC 4124P @ DDR5-520040048765140OpenBenchmarking.orgMegahertz, More Is BetterStress-NG 0.16.04CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520015.957.565.4OpenBenchmarking.orgWatts, Fewer Is BetterStress-NG 0.16.04CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 326 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520048.864.666.8OpenBenchmarking.orgCelsius, Fewer Is BetterStress-NG 0.16.04CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520055.395.7104.5OpenBenchmarking.orgWatts, Fewer Is BetterStress-NG 0.16.04System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 574 Joules per run.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: AVX-512 VNNIEPYC 4124P @ DDR5-5200150K300K450K600K750KSE +/- 94.80, N = 3681157.031. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -lEGL -ljpeg -lmpfr -lpthread -lrt -lsctp -lz
OpenBenchmarking.orgBogo Ops/s Per Watt, More Is BetterStress-NG 0.16.04Test: AVX-512 VNNIEPYC 4124P @ DDR5-52002K4K6K8K10K10518.84
MinAvgMaxEPYC 4124P @ DDR5-5200493449404941OpenBenchmarking.orgMegahertz, More Is BetterStress-NG 0.16.04CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520022.764.872.2OpenBenchmarking.orgWatts, Fewer Is BetterStress-NG 0.16.04CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 367 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520055.365.066.8OpenBenchmarking.orgCelsius, Fewer Is BetterStress-NG 0.16.04CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520055.0104.4112.0OpenBenchmarking.orgWatts, Fewer Is BetterStress-NG 0.16.04System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 592 Joules per run.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Wide Vector MathEPYC 4124P @ DDR5-520040K80K120K160K200KSE +/- 117.98, N = 3209322.741. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -lEGL -ljpeg -lmpfr -lpthread -lrt -lsctp -lz
OpenBenchmarking.orgBogo Ops/s Per Watt, More Is BetterStress-NG 0.16.04Test: Wide Vector MathEPYC 4124P @ DDR5-520060012001800240030002956.18
MinAvgMaxEPYC 4124P @ DDR5-520040045344987OpenBenchmarking.orgMegahertz, More Is BetterStress-NG 0.16.04CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.270.881.7OpenBenchmarking.orgWatts, Fewer Is BetterStress-NG 0.16.04CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 496 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520043.975.178.0OpenBenchmarking.orgCelsius, Fewer Is BetterStress-NG 0.16.04CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.5116.3124.2OpenBenchmarking.orgWatts, Fewer Is BetterStress-NG 0.16.04System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 776 Joules per run.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Fused Multiply-AddEPYC 4124P @ DDR5-52003M6M9M12M15MSE +/- 14786.84, N = 315250467.411. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -lEGL -ljpeg -lmpfr -lpthread -lrt -lsctp -lz
OpenBenchmarking.orgBogo Ops/s Per Watt, More Is BetterStress-NG 0.16.04Test: Fused Multiply-AddEPYC 4124P @ DDR5-520050K100K150K200K250K210299.37
MinAvgMaxEPYC 4124P @ DDR5-520040047595083OpenBenchmarking.orgMegahertz, More Is BetterStress-NG 0.16.04CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520027.572.581.5OpenBenchmarking.orgWatts, Fewer Is BetterStress-NG 0.16.04CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 459 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520063.474.776.6OpenBenchmarking.orgCelsius, Fewer Is BetterStress-NG 0.16.04CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.9115.4123.5OpenBenchmarking.orgWatts, Fewer Is BetterStress-NG 0.16.04System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 769 Joules per run.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: x86_64 RdRandEPYC 4124P @ DDR5-5200400K800K1200K1600K2000KSE +/- 861.47, N = 32048750.681. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -lEGL -ljpeg -lmpfr -lpthread -lrt -lsctp -lz
OpenBenchmarking.orgBogo Ops/s Per Watt, More Is BetterStress-NG 0.16.04Test: x86_64 RdRandEPYC 4124P @ DDR5-520012K24K36K48K60K56563.29
MinAvgMaxEPYC 4124P @ DDR5-520040044965017OpenBenchmarking.orgMegahertz, More Is BetterStress-NG 0.16.04CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.636.240.5OpenBenchmarking.orgWatts, Fewer Is BetterStress-NG 0.16.04CPU Power Consumption Monitor11223344551. EPYC 4124P @ DDR5-5200: Approximate power consumption of 241 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520041.943.344.4OpenBenchmarking.orgCelsius, Fewer Is BetterStress-NG 0.16.04CPU Temperature Monitor1224364860
MinAvgMaxEPYC 4124P @ DDR5-520053.071.575.3OpenBenchmarking.orgWatts, Fewer Is BetterStress-NG 0.16.04System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 477 Joules per run.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: CPU CacheEPYC 4124P @ DDR5-5200700K1400K2100K2800K3500KSE +/- 42031.49, N = 33426267.821. (CXX) g++ options: -lm -laio -lapparmor -latomic -lc -lcrypt -ldl -lEGL -ljpeg -lmpfr -lpthread -lrt -lsctp -lz
OpenBenchmarking.orgBogo Ops/s Per Watt, More Is BetterStress-NG 0.16.04Test: CPU CacheEPYC 4124P @ DDR5-520013K26K39K52K65K61215.51
MinAvgMaxEPYC 4124P @ DDR5-520040048495141OpenBenchmarking.orgMegahertz, More Is BetterStress-NG 0.16.04CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.556.065.2OpenBenchmarking.orgWatts, Fewer Is BetterStress-NG 0.16.04CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 317 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520042.465.068.6OpenBenchmarking.orgCelsius, Fewer Is BetterStress-NG 0.16.04CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.496.8111.4OpenBenchmarking.orgWatts, Fewer Is BetterStress-NG 0.16.04System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 549 Joules per run.

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 SEPYC 4124P @ DDR5-52008K16K24K32K40KSE +/- 28.87, N = 3378101. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenBenchmarking.orgkH/s Per Watt, More Is BetterCpuminer-Opt 23.5Algorithm: Blake-2 SEPYC 4124P @ DDR5-5200120240360480600566.87
MinAvgMaxEPYC 4124P @ DDR5-5200494151245141OpenBenchmarking.orgMegahertz, More Is BetterCpuminer-Opt 23.5CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520020.266.775.1OpenBenchmarking.orgWatts, Fewer Is BetterCpuminer-Opt 23.5CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 378 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520050.667.669.8OpenBenchmarking.orgCelsius, Fewer Is BetterCpuminer-Opt 23.5CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.5103.7114.7OpenBenchmarking.orgWatts, Fewer Is BetterCpuminer-Opt 23.5System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 588 Joules per run.

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 23.5Algorithm: scryptEPYC 4124P @ DDR5-520020406080100SE +/- 0.14, N = 383.291. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenBenchmarking.orgkH/s Per Watt, More Is BetterCpuminer-Opt 23.5Algorithm: scryptEPYC 4124P @ DDR5-52000.25430.50860.76291.01721.27151.13
MinAvgMaxEPYC 4124P @ DDR5-520040047935139OpenBenchmarking.orgMegahertz, More Is BetterCpuminer-Opt 23.5CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.973.783.8OpenBenchmarking.orgWatts, Fewer Is BetterCpuminer-Opt 23.5CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 491 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520043.873.176.1OpenBenchmarking.orgCelsius, Fewer Is BetterCpuminer-Opt 23.5CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.7118.9127.4OpenBenchmarking.orgWatts, Fewer Is BetterCpuminer-Opt 23.5System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 793 Joules per run.

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 23.5Algorithm: SkeincoinEPYC 4124P @ DDR5-52002K4K6K8K10KSE +/- 5.33, N = 39066.901. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenBenchmarking.orgkH/s Per Watt, More Is BetterCpuminer-Opt 23.5Algorithm: SkeincoinEPYC 4124P @ DDR5-5200306090120150151.81
MinAvgMaxEPYC 4124P @ DDR5-520040045625141OpenBenchmarking.orgMegahertz, More Is BetterCpuminer-Opt 23.5CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.959.769.3OpenBenchmarking.orgWatts, Fewer Is BetterCpuminer-Opt 23.5CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 338 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520043.568.171.4OpenBenchmarking.orgCelsius, Fewer Is BetterCpuminer-Opt 23.5CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.3101.0108.4OpenBenchmarking.orgWatts, Fewer Is BetterCpuminer-Opt 23.5System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 572 Joules per run.

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 23.5Algorithm: RingcoinEPYC 4124P @ DDR5-52002004006008001000SE +/- 9.66, N = 3944.971. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenBenchmarking.orgkH/s Per Watt, More Is BetterCpuminer-Opt 23.5Algorithm: RingcoinEPYC 4124P @ DDR5-52004812162014.59
MinAvgMaxEPYC 4124P @ DDR5-5200494150485078OpenBenchmarking.orgMegahertz, More Is BetterCpuminer-Opt 23.5CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.564.873.7OpenBenchmarking.orgWatts, Fewer Is BetterCpuminer-Opt 23.5CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 367 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520042.372.275.1OpenBenchmarking.orgCelsius, Fewer Is BetterCpuminer-Opt 23.5CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520055.2103.8114.5OpenBenchmarking.orgWatts, Fewer Is BetterCpuminer-Opt 23.5System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 588 Joules per run.

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 23.5Algorithm: Myriad-GroestlEPYC 4124P @ DDR5-52006001200180024003000SE +/- 0.25, N = 33016.701. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenBenchmarking.orgkH/s Per Watt, More Is BetterCpuminer-Opt 23.5Algorithm: Myriad-GroestlEPYC 4124P @ DDR5-5200112233445547.47
MinAvgMaxEPYC 4124P @ DDR5-5200494049975040OpenBenchmarking.orgMegahertz, More Is BetterCpuminer-Opt 23.5CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.863.571.7OpenBenchmarking.orgWatts, Fewer Is BetterCpuminer-Opt 23.5CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 360 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520040.674.277.3OpenBenchmarking.orgCelsius, Fewer Is BetterCpuminer-Opt 23.5CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520053.9102.7113.1OpenBenchmarking.orgWatts, Fewer Is BetterCpuminer-Opt 23.5System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 582 Joules per run.

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 23.5Algorithm: MagiEPYC 4124P @ DDR5-52004080120160200SE +/- 1.24, N = 3168.371. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenBenchmarking.orgkH/s Per Watt, More Is BetterCpuminer-Opt 23.5Algorithm: MagiEPYC 4124P @ DDR5-52000.61361.22721.84082.45443.0682.727
MinAvgMaxEPYC 4124P @ DDR5-520040046185116OpenBenchmarking.orgMegahertz, More Is BetterCpuminer-Opt 23.5CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.861.770.6OpenBenchmarking.orgWatts, Fewer Is BetterCpuminer-Opt 23.5CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 412 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520042.670.672.8OpenBenchmarking.orgCelsius, Fewer Is BetterCpuminer-Opt 23.5CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520055.9100.4110.3OpenBenchmarking.orgWatts, Fewer Is BetterCpuminer-Opt 23.5System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 669 Joules per run.

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 23.5Algorithm: GarlicoinEPYC 4124P @ DDR5-52002004006008001000SE +/- 0.39, N = 3851.651. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenBenchmarking.orgkH/s Per Watt, More Is BetterCpuminer-Opt 23.5Algorithm: GarlicoinEPYC 4124P @ DDR5-5200369121512.28
MinAvgMaxEPYC 4124P @ DDR5-5200494050445089OpenBenchmarking.orgMegahertz, More Is BetterCpuminer-Opt 23.5CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.569.479.1OpenBenchmarking.orgWatts, Fewer Is BetterCpuminer-Opt 23.5CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 462 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520041.971.674.5OpenBenchmarking.orgCelsius, Fewer Is BetterCpuminer-Opt 23.5CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520055.1112.2120.4OpenBenchmarking.orgWatts, Fewer Is BetterCpuminer-Opt 23.5System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 748 Joules per run.

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 23.5Algorithm: LBC, LBRY CreditsEPYC 4124P @ DDR5-52009001800270036004500SE +/- 2.03, N = 34228.171. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenBenchmarking.orgkH/s Per Watt, More Is BetterCpuminer-Opt 23.5Algorithm: LBC, LBRY CreditsEPYC 4124P @ DDR5-5200163248648070.15
MinAvgMaxEPYC 4124P @ DDR5-520040048745141OpenBenchmarking.orgMegahertz, More Is BetterCpuminer-Opt 23.5CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.060.368.4OpenBenchmarking.orgWatts, Fewer Is BetterCpuminer-Opt 23.5CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 402 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520041.667.870.5OpenBenchmarking.orgCelsius, Fewer Is BetterCpuminer-Opt 23.5CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.897.3107.3OpenBenchmarking.orgWatts, Fewer Is BetterCpuminer-Opt 23.5System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 649 Joules per run.

ASTC Encoder

OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 4.7Preset: FastEPYC 4124P @ DDR5-5200smoke20406080100SE +/- 0.06, N = 3101.37101.101. (CXX) g++ options: -O3 -flto -pthread
OpenBenchmarking.orgMT/s Per Watt, More Is BetterASTC Encoder 4.7Preset: FastEPYC 4124P @ DDR5-5200smoke0.32240.64480.96721.28961.6121.4331.387
MinAvgMaxEPYC 4124P @ DDR5-520040046655140smoke497949985030OpenBenchmarking.orgMegahertz, More Is BetterASTC Encoder 4.7CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.870.781.6smoke26.172.980.0OpenBenchmarking.orgWatts, Fewer Is BetterASTC Encoder 4.7CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 613 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520042.473.676.9smoke74.477.678.3OpenBenchmarking.orgCelsius, Fewer Is BetterASTC Encoder 4.7CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.3112.2123.7smoke55.2114.7122.5OpenBenchmarking.orgWatts, Fewer Is BetterASTC Encoder 4.7System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 972 Joules per run.
OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 4.7Preset: FastEPYC 4124P @ DDR5-5200smoke20406080100Min: 101.29 / Avg: 101.37 / Max: 101.481. (CXX) g++ options: -O3 -flto -pthread

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 FastEPYC 4124P @ DDR5-5200smoke48121620SE +/- 0.01, N = 313.8513.81
OpenBenchmarking.orgFrames Per Second Per Watt, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Super FastEPYC 4124P @ DDR5-5200smoke0.04610.09220.13830.18440.23050.1910.205
MinAvgMaxEPYC 4124P @ DDR5-520040043975006smoke493849584964OpenBenchmarking.orgMegahertz, More Is Betteruvg266 0.4.1CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.972.681.1smoke16.667.580.3OpenBenchmarking.orgWatts, Fewer Is Betteruvg266 0.4.1CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 581 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520045.077.179.3smoke47.476.481.1OpenBenchmarking.orgCelsius, Fewer Is Betteruvg266 0.4.1CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520055.0113.8125.8smoke54.8116.1125.8OpenBenchmarking.orgWatts, Fewer Is Betteruvg266 0.4.1System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 911 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Super FastEPYC 4124P @ DDR5-5200smoke48121620Min: 13.84 / Avg: 13.85 / Max: 13.86

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: EclipseEPYC 4124P @ DDR5-520015003000450060007500SE +/- 49.54, N = 37109
MinAvgMaxEPYC 4124P @ DDR5-520040048505143OpenBenchmarking.orgMegahertz, More Is BetterDaCapo Benchmark 23.11CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520020.543.161.6OpenBenchmarking.orgWatts, Fewer Is BetterDaCapo Benchmark 23.11CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 244 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520044.959.066.9OpenBenchmarking.orgCelsius, Fewer Is BetterDaCapo Benchmark 23.11CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520053.881.3105.5OpenBenchmarking.orgWatts, Fewer Is BetterDaCapo Benchmark 23.11System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 461 Joules per run.

miniFE

MiniFE Finite Element is an application for unstructured implicit finite element codes. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgCG Mflops, More Is BetterminiFE 2.2Problem Size: SmallEPYC 4124P @ DDR5-5200smoke17003400510068008500SE +/- 2.40, N = 37710.507731.491. (CXX) g++ options: -O3 -fopenmp -lmpi_cxx -lmpi
OpenBenchmarking.orgCG Mflops Per Watt, More Is BetterminiFE 2.2Problem Size: SmallEPYC 4124P @ DDR5-5200smoke306090120150145.97153.53
MinAvgMaxEPYC 4124P @ DDR5-520040046925141smoke40045215140OpenBenchmarking.orgMegahertz, More Is BetterminiFE 2.2CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520023.952.866.9smoke16.950.464.4OpenBenchmarking.orgWatts, Fewer Is BetterminiFE 2.2CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 405 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520043.354.275.4smoke46.059.473.3OpenBenchmarking.orgCelsius, Fewer Is BetterminiFE 2.2CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.595.9123.4smoke54.5100.6122.0OpenBenchmarking.orgWatts, Fewer Is BetterminiFE 2.2System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 735 Joules per run.
OpenBenchmarking.orgCG Mflops, More Is BetterminiFE 2.2Problem Size: SmallEPYC 4124P @ DDR5-5200smoke13002600390052006500Min: 7707.46 / Avg: 7710.5 / Max: 7715.241. (CXX) g++ options: -O3 -fopenmp -lmpi_cxx -lmpi

Java SciMark

This test runs the Java version of SciMark 2, which is a benchmark for scientific and numerical computing developed by programmers at the National Institute of Standards and Technology. This benchmark is made up of Fast Foruier Transform, Jacobi Successive Over-relaxation, Monte Carlo, Sparse Matrix Multiply, and dense LU matrix factorization benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterJava SciMark 2.2Computational Test: CompositeEPYC 4124P @ DDR5-520011002200330044005500SE +/- 10.32, N = 35276.08
OpenBenchmarking.orgMflops Per Watt, More Is BetterJava SciMark 2.2Computational Test: CompositeEPYC 4124P @ DDR5-52004080120160200170.00
MinAvgMaxEPYC 4124P @ DDR5-520040044845141OpenBenchmarking.orgMegahertz, More Is BetterJava SciMark 2.2CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.631.048.5OpenBenchmarking.orgWatts, Fewer Is BetterJava SciMark 2.2CPU Power Consumption Monitor14284256701. EPYC 4124P @ DDR5-5200: Approximate power consumption of 166 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520042.953.270.3OpenBenchmarking.orgCelsius, Fewer Is BetterJava SciMark 2.2CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.266.485.2OpenBenchmarking.orgWatts, Fewer Is BetterJava SciMark 2.2System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 354 Joules per run.

Primesieve

OpenBenchmarking.orgSeconds, Fewer Is BetterPrimesieve 12.1Length: 1e12EPYC 4124P @ DDR5-5200612182430SE +/- 0.01, N = 324.501. (CXX) g++ options: -O3
MinAvgMaxEPYC 4124P @ DDR5-520040043884972OpenBenchmarking.orgMegahertz, More Is BetterPrimesieve 12.1CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.173.185.5OpenBenchmarking.orgWatts, Fewer Is BetterPrimesieve 12.1CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 366 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520042.176.080.9OpenBenchmarking.orgCelsius, Fewer Is BetterPrimesieve 12.1CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.9116.2130.1OpenBenchmarking.orgWatts, Fewer Is BetterPrimesieve 12.1System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 659 Joules per run.

TensorFlow

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 32 - Model: AlexNetEPYC 4124P @ DDR5-5200smoke20406080100SE +/- 0.05, N = 3100.57100.06
OpenBenchmarking.orgimages/sec Per Watt, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 32 - Model: AlexNetEPYC 4124P @ DDR5-5200smoke0.48760.97521.46281.95042.4382.1022.167
MinAvgMaxEPYC 4124P @ DDR5-5200493649505140smoke40043724941OpenBenchmarking.orgMegahertz, More Is BetterTensorFlow 2.16.1CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.047.853.3smoke16.646.253.2OpenBenchmarking.orgWatts, Fewer Is BetterTensorFlow 2.16.1CPU Power Consumption Monitor15304560751. EPYC 4124P @ DDR5-5200: Approximate power consumption of 319 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520042.351.654.9smoke43.151.453.4OpenBenchmarking.orgCelsius, Fewer Is BetterTensorFlow 2.16.1CPU Temperature Monitor1530456075
MinAvgMaxEPYC 4124P @ DDR5-520054.486.994.7smoke54.182.893.0OpenBenchmarking.orgWatts, Fewer Is BetterTensorFlow 2.16.1System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 579 Joules per run.
OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 32 - Model: AlexNetEPYC 4124P @ DDR5-5200smoke20406080100Min: 100.48 / Avg: 100.57 / Max: 100.62

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.BEPYC 4124P @ DDR5-5200smoke2K4K6K8K10KSE +/- 3.80, N = 39885.329844.541. (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
OpenBenchmarking.orgTotal Mop/s Per Watt, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: SP.BEPYC 4124P @ DDR5-5200smoke50100150200250238.05240.39
MinAvgMaxEPYC 4124P @ DDR5-520040045215137smoke493749785137OpenBenchmarking.orgMegahertz, More Is BetterNAS Parallel Benchmarks 3.4CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520015.841.545.9smoke16.241.046.9OpenBenchmarking.orgWatts, Fewer Is BetterNAS Parallel Benchmarks 3.4CPU Power Consumption Monitor14284256701. EPYC 4124P @ DDR5-5200: Approximate power consumption of 277 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520039.643.344.1smoke45.349.350.4OpenBenchmarking.orgCelsius, Fewer Is BetterNAS Parallel Benchmarks 3.4CPU Temperature Monitor1428425670
MinAvgMaxEPYC 4124P @ DDR5-520054.384.189.2smoke54.382.590.7OpenBenchmarking.orgWatts, Fewer Is BetterNAS Parallel Benchmarks 3.4System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 560 Joules per run.
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: SP.BEPYC 4124P @ DDR5-5200smoke2K4K6K8K10KMin: 9878.14 / Avg: 9885.32 / Max: 9891.051. (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

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-ThreadedEPYC 4124P @ DDR5-5200smoke5K10K15K20K25KSE +/- 39.28, N = 322228.022101.21. (CXX) g++ options: -O3 -march=native -fPIE -pie
OpenBenchmarking.orgMFLOPS Per Watt, More Is BetterQuantLib 1.32Configuration: Multi-ThreadedEPYC 4124P @ DDR5-5200smoke80160240320400327.42349.94
MinAvgMaxEPYC 4124P @ DDR5-520040045665048smoke40042804967OpenBenchmarking.orgMegahertz, More Is BetterQuantLib 1.32CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.067.980.7smoke16.663.277.2OpenBenchmarking.orgWatts, Fewer Is BetterQuantLib 1.32CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 520 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520039.077.681.6smoke45.578.684.9OpenBenchmarking.orgCelsius, Fewer Is BetterQuantLib 1.32CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.0110.9124.3smoke54.5102.6122.1OpenBenchmarking.orgWatts, Fewer Is BetterQuantLib 1.32System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 850 Joules per run.
OpenBenchmarking.orgMFLOPS, More Is BetterQuantLib 1.32Configuration: Multi-ThreadedEPYC 4124P @ DDR5-5200smoke4K8K12K16K20KMin: 22176.4 / Avg: 22228 / Max: 22305.11. (CXX) g++ options: -O3 -march=native -fPIE -pie

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 FastEPYC 4124P @ DDR5-5200smoke48121620SE +/- 0.00, N = 316.8216.771. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: Very FastEPYC 4124P @ DDR5-5200smoke0.05690.11380.17070.22760.28450.2320.253
MinAvgMaxEPYC 4124P @ DDR5-520040043394965smoke40042954959OpenBenchmarking.orgMegahertz, More Is BetterKvazaar 2.2CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.172.482.0smoke17.466.380.8OpenBenchmarking.orgWatts, Fewer Is BetterKvazaar 2.2CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 531 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520045.377.980.9smoke47.376.381.5OpenBenchmarking.orgCelsius, Fewer Is BetterKvazaar 2.2CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520055.2116.0127.6OpenBenchmarking.orgWatts, Fewer Is BetterKvazaar 2.2System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 851 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: Very FastEPYC 4124P @ DDR5-5200smoke48121620Min: 16.81 / Avg: 16.82 / Max: 16.821. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -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: Ultra FastEPYC 4124P @ DDR5-5200smoke48121620SE +/- 0.03, N = 316.8616.75
OpenBenchmarking.orgFrames Per Second Per Watt, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Ultra FastEPYC 4124P @ DDR5-5200smoke0.05380.10760.16140.21520.2690.2390.225
MinAvgMaxEPYC 4124P @ DDR5-520040045575035OpenBenchmarking.orgMegahertz, More Is Betteruvg266 0.4.1CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.470.581.2OpenBenchmarking.orgWatts, Fewer Is Betteruvg266 0.4.1CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 517 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520045.576.678.9OpenBenchmarking.orgCelsius, Fewer Is Betteruvg266 0.4.1CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520055.1115.4125.4smoke123.4124.6125.1OpenBenchmarking.orgWatts, Fewer Is Betteruvg266 0.4.1System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 808 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Ultra FastEPYC 4124P @ DDR5-5200smoke48121620Min: 16.81 / Avg: 16.86 / Max: 16.9

Apache Hadoop

This is a benchmark of the Apache Hadoop making use of its built-in name-node throughput benchmark (NNThroughputBenchmark). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOps per sec, More Is BetterApache Hadoop 3.3.6Operation: Create - Threads: 500 - Files: 100000EPYC 4124P @ DDR5-5200smoke12K24K36K48K60KSE +/- 349.79, N = 35428454585
OpenBenchmarking.orgOps per sec Per Watt, More Is BetterApache Hadoop 3.3.6Operation: Create - Threads: 500 - Files: 100000EPYC 4124P @ DDR5-5200smoke50010001500200025002294.942253.14
MinAvgMaxEPYC 4124P @ DDR5-520040037085140smoke40044485145OpenBenchmarking.orgMegahertz, More Is BetterApache Hadoop 3.3.6CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.123.738.8smoke16.524.240.7OpenBenchmarking.orgWatts, Fewer Is BetterApache Hadoop 3.3.6CPU Power Consumption Monitor11223344551. EPYC 4124P @ DDR5-5200: Approximate power consumption of 166 Joules per run.2. smoke: Approximate power consumption of 194 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520039.047.462.9smoke43.852.870.0OpenBenchmarking.orgCelsius, Fewer Is BetterApache Hadoop 3.3.6CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520053.060.280.4smoke54.262.081.9OpenBenchmarking.orgWatts, Fewer Is BetterApache Hadoop 3.3.6System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 441 Joules per run.2. smoke: Approximate power consumption of 496 Joules per run.
OpenBenchmarking.orgOps per sec, More Is BetterApache Hadoop 3.3.6Operation: Create - Threads: 500 - Files: 100000EPYC 4124P @ DDR5-5200smoke9K18K27K36K45KMin: 53648.07 / Avg: 54283.51 / Max: 54854.64

OpenBenchmarking.orgOps per sec, More Is BetterApache Hadoop 3.3.6Operation: Create - Threads: 100 - Files: 100000EPYC 4124P @ DDR5-5200smoke14K28K42K56K70KSE +/- 547.65, N = 36623465062
OpenBenchmarking.orgOps per sec Per Watt, More Is BetterApache Hadoop 3.3.6Operation: Create - Threads: 100 - Files: 100000EPYC 4124P @ DDR5-5200smoke60012001800240030002818.342768.01
MinAvgMaxEPYC 4124P @ DDR5-520040040355142OpenBenchmarking.orgMegahertz, More Is BetterApache Hadoop 3.3.6CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.223.536.7OpenBenchmarking.orgWatts, Fewer Is BetterApache Hadoop 3.3.6CPU Power Consumption Monitor10203040501. EPYC 4124P @ DDR5-5200: Approximate power consumption of 149 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520040.948.264.0OpenBenchmarking.orgCelsius, Fewer Is BetterApache Hadoop 3.3.6CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520053.061.993.8OpenBenchmarking.orgWatts, Fewer Is BetterApache Hadoop 3.3.6System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 413 Joules per run.
OpenBenchmarking.orgOps per sec, More Is BetterApache Hadoop 3.3.6Operation: Create - Threads: 100 - Files: 100000EPYC 4124P @ DDR5-5200smoke11K22K33K44K55KMin: 65146.58 / Avg: 66234.29 / Max: 66889.63

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: jMonkeyEngineEPYC 4124P @ DDR5-520015003000450060007500SE +/- 3.38, N = 36816
MinAvgMaxEPYC 4124P @ DDR5-520040043035119OpenBenchmarking.orgMegahertz, More Is BetterDaCapo Benchmark 23.11CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.822.423.7OpenBenchmarking.orgWatts, Fewer Is BetterDaCapo Benchmark 23.11CPU Power Consumption Monitor8162432401. EPYC 4124P @ DDR5-5200: Approximate power consumption of 104 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520040.943.447.0OpenBenchmarking.orgCelsius, Fewer Is BetterDaCapo Benchmark 23.11CPU Temperature Monitor1428425670
MinAvgMaxEPYC 4124P @ DDR5-520054.658.670.7OpenBenchmarking.orgWatts, Fewer Is BetterDaCapo Benchmark 23.11System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 254 Joules per run.

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: 500MEPYC 4124P @ DDR5-5200510152025SE +/- 0.02, N = 319.80
MinAvgMaxEPYC 4124P @ DDR5-520040046465119OpenBenchmarking.orgMegahertz, More Is BetterY-Cruncher 0.8.3CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520026.863.079.5OpenBenchmarking.orgWatts, Fewer Is BetterY-Cruncher 0.8.3CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 294 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520056.468.375.0OpenBenchmarking.orgCelsius, Fewer Is BetterY-Cruncher 0.8.3CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520055.3105.1125.8OpenBenchmarking.orgWatts, Fewer Is BetterY-Cruncher 0.8.3System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 490 Joules per run.

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 MT - DegriddingEPYC 4124P @ DDR5-5200smoke400800120016002000SE +/- 7.28, N = 31930.031855.441. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
OpenBenchmarking.orgMillion Grid Points Per Second Per Watt, More Is BetterASKAP 1.0Test: tConvolve MT - DegriddingEPYC 4124P @ DDR5-5200smoke112233445550.6248.44
MinAvgMaxEPYC 4124P @ DDR5-520040044685141smoke493549675141OpenBenchmarking.orgMegahertz, More Is BetterASKAP 1.0CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520021.038.149.4smoke19.238.350.0OpenBenchmarking.orgWatts, Fewer Is BetterASKAP 1.0CPU Power Consumption Monitor14284256701. EPYC 4124P @ DDR5-5200: Approximate power consumption of 229 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520040.642.043.9smoke47.448.350.5OpenBenchmarking.orgCelsius, Fewer Is BetterASKAP 1.0CPU Temperature Monitor1428425670
MinAvgMaxEPYC 4124P @ DDR5-520053.078.391.0smoke54.478.391.2OpenBenchmarking.orgWatts, Fewer Is BetterASKAP 1.0System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 496 Joules per run.
OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 1.0Test: tConvolve MT - DegriddingEPYC 4124P @ DDR5-5200smoke30060090012001500Min: 1915.51 / Avg: 1930.03 / Max: 1938.171. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 1.0Test: tConvolve MT - GriddingEPYC 4124P @ DDR5-5200smoke30060090012001500SE +/- 1.72, N = 31327.141311.611. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 1.0Test: tConvolve MT - GriddingEPYC 4124P @ DDR5-5200smoke2004006008001000Min: 1324.66 / Avg: 1327.14 / Max: 1330.451. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

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: TradebeansEPYC 4124P @ DDR5-52007001400210028003500SE +/- 8.26, N = 43050
MinAvgMaxEPYC 4124P @ DDR5-520040043795146OpenBenchmarking.orgMegahertz, More Is BetterDaCapo Benchmark 23.11CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520018.846.760.2OpenBenchmarking.orgWatts, Fewer Is BetterDaCapo Benchmark 23.11CPU Power Consumption Monitor16324864801. EPYC 4124P @ DDR5-5200: Approximate power consumption of 152 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520041.160.870.3OpenBenchmarking.orgCelsius, Fewer Is BetterDaCapo Benchmark 23.11CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.187.9108.6OpenBenchmarking.orgWatts, Fewer Is BetterDaCapo Benchmark 23.11System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 286 Joules per run.

WebP Image Encode

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

OpenBenchmarking.orgMP/s, More Is BetterWebP Image Encode 1.2.4Encode Settings: Quality 100, Lossless, Highest CompressionEPYC 4124P @ DDR5-5200smoke0.17550.3510.52650.7020.8775SE +/- 0.00, N = 30.780.781. (CC) gcc options: -fvisibility=hidden -O2 -lm
OpenBenchmarking.orgMP/s Per Watt, More Is BetterWebP Image Encode 1.2.4Encode Settings: Quality 100, Lossless, Highest CompressionEPYC 4124P @ DDR5-5200smoke0.0050.010.0150.020.0250.0220.020
MinAvgMaxEPYC 4124P @ DDR5-520040046805146smoke495151145142OpenBenchmarking.orgMegahertz, More Is BetterWebP Image Encode 1.2.4CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.835.848.5smoke16.538.850.5OpenBenchmarking.orgWatts, Fewer Is BetterWebP Image Encode 1.2.4CPU Power Consumption Monitor14284256701. EPYC 4124P @ DDR5-5200: Approximate power consumption of 251 Joules per run.2. smoke: Approximate power consumption of 272 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520039.453.562.8smoke43.060.269.1OpenBenchmarking.orgCelsius, Fewer Is BetterWebP Image Encode 1.2.4CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520053.772.386.3smoke53.976.187.5OpenBenchmarking.orgWatts, Fewer Is BetterWebP Image Encode 1.2.4System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 482 Joules per run.2. smoke: Approximate power consumption of 533 Joules per run.
OpenBenchmarking.orgMP/s, More Is BetterWebP Image Encode 1.2.4Encode Settings: Quality 100, Lossless, Highest CompressionEPYC 4124P @ DDR5-5200smoke246810Min: 0.78 / Avg: 0.78 / Max: 0.791. (CC) gcc options: -fvisibility=hidden -O2 -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 PSKEPYC 4124P @ DDR5-5200smoke9K18K27K36K45KSE +/- 49.33, N = 342600424961. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -lm -lrt -lz -ldl -lcrypt -lbz2
OpenBenchmarking.orgReal C/S Per Watt, More Is BetterJohn The Ripper 2023.03.14Test: WPA PSKEPYC 4124P @ DDR5-5200smoke2004006008001000761.55790.98
MinAvgMaxEPYC 4124P @ DDR5-520040046734941OpenBenchmarking.orgMegahertz, More Is BetterJohn The Ripper 2023.03.14CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.555.962.4OpenBenchmarking.orgWatts, Fewer Is BetterJohn The Ripper 2023.03.14CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 317 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520042.858.460.4OpenBenchmarking.orgCelsius, Fewer Is BetterJohn The Ripper 2023.03.14CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520055.192.699.9OpenBenchmarking.orgWatts, Fewer Is BetterJohn The Ripper 2023.03.14System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 525 Joules per run.
OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: WPA PSKEPYC 4124P @ DDR5-5200smoke7K14K21K28K35KMin: 42501 / Avg: 42599.67 / Max: 426491. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -lm -lrt -lz -ldl -lcrypt -lbz2

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: bcryptEPYC 4124P @ DDR5-5200smoke3K6K9K12K15KSE +/- 3.71, N = 311818117811. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -lm -lrt -lz -ldl -lcrypt -lbz2
OpenBenchmarking.orgReal C/S Per Watt, More Is BetterJohn The Ripper 2023.03.14Test: bcryptEPYC 4124P @ DDR5-5200smoke4080120160200197.13200.25
OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: bcryptEPYC 4124P @ DDR5-5200smoke2K4K6K8K10KMin: 11813 / Avg: 11817.67 / Max: 118251. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -lm -lrt -lz -ldl -lcrypt -lbz2

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: BlowfishEPYC 4124P @ DDR5-5200smoke3K6K9K12K15KSE +/- 1.00, N = 311819117571. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -lm -lrt -lz -ldl -lcrypt -lbz2
OpenBenchmarking.orgReal C/S Per Watt, More Is BetterJohn The Ripper 2023.03.14Test: BlowfishEPYC 4124P @ DDR5-5200smoke50100150200250199.85205.19
MinAvgMaxXeon E-2488 @ DDR5-4800429444725200EPYC 4124P @ DDR5-520040047475044smoke498150225140OpenBenchmarking.orgMegahertz, More Is BetterJohn The Ripper 2023.03.14CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxXeon E-2488 @ DDR5-480021.688.7124.8EPYC 4124P @ DDR5-520016.459.167.0smoke16.858.866.0OpenBenchmarking.orgWatts, Fewer Is BetterJohn The Ripper 2023.03.14CPU Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 335 Joules per run.
MinAvgMaxXeon E-2488 @ DDR5-480044.068.193.0EPYC 4124P @ DDR5-520043.072.975.5smoke43.872.177.0OpenBenchmarking.orgCelsius, Fewer Is BetterJohn The Ripper 2023.03.14CPU Temperature Monitor20406080100
MinAvgMaxXeon E-2488 @ DDR5-480054.3133.0241.1EPYC 4124P @ DDR5-520054.897.9107.1smoke54.498.9106.9OpenBenchmarking.orgWatts, Fewer Is BetterJohn The Ripper 2023.03.14System Power Consumption Monitor601201802403001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 555 Joules per run.
OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: BlowfishEPYC 4124P @ DDR5-5200smoke2K4K6K8K10KMin: 11817 / Avg: 11819 / Max: 118201. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -lm -lrt -lz -ldl -lcrypt -lbz2

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: 512EPYC 4124P @ DDR5-5200smoke20M40M60M80M100MSE +/- 125033.33, N = 31069600001065400001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s Per Watt, More Is BetterLiquid-DSP 1.6Threads: 16 - Buffer Length: 256 - Filter Length: 512EPYC 4124P @ DDR5-5200smoke400K800K1200K1600K2000K1500643.041740091.46
MinAvgMaxEPYC 4124P @ DDR5-520040047935115OpenBenchmarking.orgMegahertz, More Is BetterLiquid-DSP 1.6CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520024.071.380.0OpenBenchmarking.orgWatts, Fewer Is BetterLiquid-DSP 1.6CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 428 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520060.072.474.5OpenBenchmarking.orgCelsius, Fewer Is BetterLiquid-DSP 1.6CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520055.1113.2120.8OpenBenchmarking.orgWatts, Fewer Is BetterLiquid-DSP 1.6System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 679 Joules per run.
OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 16 - Buffer Length: 256 - Filter Length: 512EPYC 4124P @ DDR5-5200smoke20M40M60M80M100MMin: 106710000 / Avg: 106960000 / Max: 1070900001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 16 - Buffer Length: 256 - Filter Length: 32EPYC 4124P @ DDR5-5200smoke80M160M240M320M400MSE +/- 104774.89, N = 33717133333703400001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s Per Watt, More Is BetterLiquid-DSP 1.6Threads: 16 - Buffer Length: 256 - Filter Length: 32EPYC 4124P @ DDR5-5200smoke1.2M2.4M3.6M4.8M6M5568052.115690010.14
MinAvgMaxEPYC 4124P @ DDR5-5200494150705086OpenBenchmarking.orgMegahertz, More Is BetterLiquid-DSP 1.6CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.066.874.7OpenBenchmarking.orgWatts, Fewer Is BetterLiquid-DSP 1.6CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 378 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520042.170.773.3OpenBenchmarking.orgCelsius, Fewer Is BetterLiquid-DSP 1.6CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520055.2104.6115.1OpenBenchmarking.orgWatts, Fewer Is BetterLiquid-DSP 1.6System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 593 Joules per run.
OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 16 - Buffer Length: 256 - Filter Length: 32EPYC 4124P @ DDR5-5200smoke60M120M180M240M300MMin: 371520000 / Avg: 371713333.33 / Max: 3718800001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 2 - Buffer Length: 256 - Filter Length: 512EPYC 4124P @ DDR5-5200smoke8M16M24M32M40MSE +/- 196299.37, N = 336999333311790001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s Per Watt, More Is BetterLiquid-DSP 1.6Threads: 2 - Buffer Length: 256 - Filter Length: 512EPYC 4124P @ DDR5-5200smoke200K400K600K800K1000K957750.36923712.75
MinAvgMaxEPYC 4124P @ DDR5-520040046575141OpenBenchmarking.orgMegahertz, More Is BetterLiquid-DSP 1.6CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.238.643.6OpenBenchmarking.orgWatts, Fewer Is BetterLiquid-DSP 1.6CPU Power Consumption Monitor12243648601. EPYC 4124P @ DDR5-5200: Approximate power consumption of 258 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520038.952.154.0OpenBenchmarking.orgCelsius, Fewer Is BetterLiquid-DSP 1.6CPU Temperature Monitor1530456075
MinAvgMaxEPYC 4124P @ DDR5-520053.375.479.4OpenBenchmarking.orgWatts, Fewer Is BetterLiquid-DSP 1.6System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 478 Joules per run.
OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 2 - Buffer Length: 256 - Filter Length: 512EPYC 4124P @ DDR5-5200smoke6M12M18M24M30MMin: 36607000 / Avg: 36999333.33 / Max: 372080001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 8 - Buffer Length: 256 - Filter Length: 512EPYC 4124P @ DDR5-5200smoke20M40M60M80M100MSE +/- 20275.88, N = 31071833331068500001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s Per Watt, More Is BetterLiquid-DSP 1.6Threads: 8 - Buffer Length: 256 - Filter Length: 512EPYC 4124P @ DDR5-5200smoke400K800K1200K1600K2000K1548265.631682223.02
MinAvgMaxEPYC 4124P @ DDR5-520040046035140smoke494150335065OpenBenchmarking.orgMegahertz, More Is BetterLiquid-DSP 1.6CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.469.279.9smoke16.563.579.1OpenBenchmarking.orgWatts, Fewer Is BetterLiquid-DSP 1.6CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 462 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520043.571.174.5smoke44.070.275.0OpenBenchmarking.orgCelsius, Fewer Is BetterLiquid-DSP 1.6CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.8113.2120.7smoke54.2101.3120.0OpenBenchmarking.orgWatts, Fewer Is BetterLiquid-DSP 1.6System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 717 Joules per run.
OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 8 - Buffer Length: 256 - Filter Length: 512EPYC 4124P @ DDR5-5200smoke20M40M60M80M100MMin: 107150000 / Avg: 107183333.33 / Max: 1072200001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 2 - Buffer Length: 256 - Filter Length: 32EPYC 4124P @ DDR5-5200smoke20M40M60M80M100MSE +/- 77674.53, N = 31003200001004300001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s Per Watt, More Is BetterLiquid-DSP 1.6Threads: 2 - Buffer Length: 256 - Filter Length: 32EPYC 4124P @ DDR5-5200smoke600K1200K1800K2400K3000K2958214.082824240.72
MinAvgMaxEPYC 4124P @ DDR5-520040048475140OpenBenchmarking.orgMegahertz, More Is BetterLiquid-DSP 1.6CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520019.033.937.7OpenBenchmarking.orgWatts, Fewer Is BetterLiquid-DSP 1.6CPU Power Consumption Monitor11223344551. EPYC 4124P @ DDR5-5200: Approximate power consumption of 192 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520041.344.346.3OpenBenchmarking.orgCelsius, Fewer Is BetterLiquid-DSP 1.6CPU Temperature Monitor1224364860
MinAvgMaxEPYC 4124P @ DDR5-520053.569.273.0OpenBenchmarking.orgWatts, Fewer Is BetterLiquid-DSP 1.6System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 392 Joules per run.
OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 2 - Buffer Length: 256 - Filter Length: 32EPYC 4124P @ DDR5-5200smoke20M40M60M80M100MMin: 100170000 / Avg: 100320000 / Max: 1004300001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 8 - Buffer Length: 256 - Filter Length: 32EPYC 4124P @ DDR5-5200smoke80M160M240M320M400MSE +/- 127322.86, N = 33715366673705600001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s Per Watt, More Is BetterLiquid-DSP 1.6Threads: 8 - Buffer Length: 256 - Filter Length: 32EPYC 4124P @ DDR5-5200smoke1.2M2.4M3.6M4.8M6M5639359.475651364.95
MinAvgMaxEPYC 4124P @ DDR5-5200493950715131smoke494150595128OpenBenchmarking.orgMegahertz, More Is BetterLiquid-DSP 1.6CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.465.974.7smoke17.265.674.4OpenBenchmarking.orgWatts, Fewer Is BetterLiquid-DSP 1.6CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 395 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520041.169.973.3smoke43.569.073.6OpenBenchmarking.orgCelsius, Fewer Is BetterLiquid-DSP 1.6CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.1105.1115.5smoke53.9106.0115.1OpenBenchmarking.orgWatts, Fewer Is BetterLiquid-DSP 1.6System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 631 Joules per run.
OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 8 - Buffer Length: 256 - Filter Length: 32EPYC 4124P @ DDR5-5200smoke60M120M180M240M300MMin: 371350000 / Avg: 371536666.67 / Max: 3717800001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 4 - Buffer Length: 256 - Filter Length: 32EPYC 4124P @ DDR5-5200smoke40M80M120M160M200MSE +/- 60827.63, N = 32003400002002500001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s Per Watt, More Is BetterLiquid-DSP 1.6Threads: 4 - Buffer Length: 256 - Filter Length: 32EPYC 4124P @ DDR5-5200smoke900K1800K2700K3600K4500K4418557.584373798.71
MinAvgMaxEPYC 4124P @ DDR5-5200494051115136OpenBenchmarking.orgMegahertz, More Is BetterLiquid-DSP 1.6CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.445.351.6OpenBenchmarking.orgWatts, Fewer Is BetterLiquid-DSP 1.6CPU Power Consumption Monitor15304560751. EPYC 4124P @ DDR5-5200: Approximate power consumption of 257 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520040.348.450.0OpenBenchmarking.orgCelsius, Fewer Is BetterLiquid-DSP 1.6CPU Temperature Monitor1428425670
MinAvgMaxEPYC 4124P @ DDR5-520053.983.287.4OpenBenchmarking.orgWatts, Fewer Is BetterLiquid-DSP 1.6System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 472 Joules per run.
OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 4 - Buffer Length: 256 - Filter Length: 32EPYC 4124P @ DDR5-5200smoke30M60M90M120M150MMin: 200230000 / Avg: 200340000 / Max: 2004400001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 1 - Buffer Length: 256 - Filter Length: 512EPYC 4124P @ DDR5-5200smoke4M8M12M16M20MSE +/- 229945.89, N = 318207667185480001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s Per Watt, More Is BetterLiquid-DSP 1.6Threads: 1 - Buffer Length: 256 - Filter Length: 512EPYC 4124P @ DDR5-5200smoke140K280K420K560K700K631217.94664020.87
MinAvgMaxEPYC 4124P @ DDR5-520040042935141smoke493951125141OpenBenchmarking.orgMegahertz, More Is BetterLiquid-DSP 1.6CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.328.834.4smoke16.427.931.8OpenBenchmarking.orgWatts, Fewer Is BetterLiquid-DSP 1.6CPU Power Consumption Monitor10203040501. EPYC 4124P @ DDR5-5200: Approximate power consumption of 163 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520038.944.351.5smoke41.846.447.8OpenBenchmarking.orgCelsius, Fewer Is BetterLiquid-DSP 1.6CPU Temperature Monitor1530456075
MinAvgMaxEPYC 4124P @ DDR5-520053.963.769.7OpenBenchmarking.orgWatts, Fewer Is BetterLiquid-DSP 1.6System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 382 Joules per run.
OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 1 - Buffer Length: 256 - Filter Length: 512EPYC 4124P @ DDR5-5200smoke3M6M9M12M15MMin: 17775000 / Avg: 18207666.67 / Max: 185590001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 1 - Buffer Length: 256 - Filter Length: 32EPYC 4124P @ DDR5-5200smoke11M22M33M44M55MSE +/- 333.33, N = 350277333502930001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s Per Watt, More Is BetterLiquid-DSP 1.6Threads: 1 - Buffer Length: 256 - Filter Length: 32EPYC 4124P @ DDR5-5200smoke400K800K1200K1600K2000K1751609.841692471.52
MinAvgMaxEPYC 4124P @ DDR5-5200494051215141smoke40044635141OpenBenchmarking.orgMegahertz, More Is BetterLiquid-DSP 1.6CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.728.732.2smoke16.829.732.7OpenBenchmarking.orgWatts, Fewer Is BetterLiquid-DSP 1.6CPU Power Consumption Monitor10203040501. EPYC 4124P @ DDR5-5200: Approximate power consumption of 191 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520041.044.046.1smoke44.547.848.5OpenBenchmarking.orgCelsius, Fewer Is BetterLiquid-DSP 1.6CPU Temperature Monitor1428425670
MinAvgMaxEPYC 4124P @ DDR5-520052.663.766.8smoke55.664.467.3OpenBenchmarking.orgWatts, Fewer Is BetterLiquid-DSP 1.6System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 425 Joules per run.
OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 1 - Buffer Length: 256 - Filter Length: 32EPYC 4124P @ DDR5-5200smoke9M18M27M36M45MMin: 50277000 / Avg: 50277333.33 / Max: 502780001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

DaCapo Benchmark

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

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Spring BootEPYC 4124P @ DDR5-52006001200180024003000SE +/- 28.10, N = 42571
MinAvgMaxEPYC 4124P @ DDR5-520040047975151OpenBenchmarking.orgMegahertz, More Is BetterDaCapo Benchmark 23.11CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520015.553.772.7OpenBenchmarking.orgWatts, Fewer Is BetterDaCapo Benchmark 23.11CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 201 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520039.063.871.0OpenBenchmarking.orgCelsius, Fewer Is BetterDaCapo Benchmark 23.11CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520053.593.8115.0OpenBenchmarking.orgWatts, Fewer Is BetterDaCapo Benchmark 23.11System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 352 Joules per run.

PyTorch

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 1 - Model: ResNet-50EPYC 4124P @ DDR5-5200smoke918273645SE +/- 0.16, N = 341.0941.04MIN: 39.2 / MAX: 41.9MIN: 39.69 / MAX: 41.53
OpenBenchmarking.orgbatches/sec Per Watt, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 1 - Model: ResNet-50EPYC 4124P @ DDR5-5200smoke0.20750.4150.62250.831.03750.9030.922
MinAvgMaxEPYC 4124P @ DDR5-520040047255141OpenBenchmarking.orgMegahertz, More Is BetterPyTorch 2.2.1CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.245.552.6OpenBenchmarking.orgWatts, Fewer Is BetterPyTorch 2.2.1CPU Power Consumption Monitor15304560751. EPYC 4124P @ DDR5-5200: Approximate power consumption of 288 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520039.546.150.3OpenBenchmarking.orgCelsius, Fewer Is BetterPyTorch 2.2.1CPU Temperature Monitor1428425670
MinAvgMaxEPYC 4124P @ DDR5-520054.381.890.4OpenBenchmarking.orgWatts, Fewer Is BetterPyTorch 2.2.1System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 518 Joules per run.
OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 1 - Model: ResNet-50EPYC 4124P @ DDR5-5200smoke918273645Min: 40.86 / Avg: 41.09 / Max: 41.4

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: BioJava Biological Data FrameworkEPYC 4124P @ DDR5-520010002000300040005000SE +/- 41.21, N = 44502
MinAvgMaxEPYC 4124P @ DDR5-520040043805141OpenBenchmarking.orgMegahertz, More Is BetterDaCapo Benchmark 23.11CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.631.240.3OpenBenchmarking.orgWatts, Fewer Is BetterDaCapo Benchmark 23.11CPU Power Consumption Monitor11223344551. EPYC 4124P @ DDR5-5200: Approximate power consumption of 101 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520042.058.568.6OpenBenchmarking.orgCelsius, Fewer Is BetterDaCapo Benchmark 23.11CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520053.766.878.7OpenBenchmarking.orgWatts, Fewer Is BetterDaCapo Benchmark 23.11System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 217 Joules per run.

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 FastEPYC 4124P @ DDR5-5200smoke510152025SE +/- 0.01, N = 320.7520.711. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: Super FastEPYC 4124P @ DDR5-5200smoke0.07070.14140.21210.28280.35350.2880.314
MinAvgMaxEPYC 4124P @ DDR5-520040047315140OpenBenchmarking.orgMegahertz, More Is BetterKvazaar 2.2CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.572.082.4OpenBenchmarking.orgWatts, Fewer Is BetterKvazaar 2.2CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 456 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520044.577.681.0OpenBenchmarking.orgCelsius, Fewer Is BetterKvazaar 2.2CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520056.0118.7128.4OpenBenchmarking.orgWatts, Fewer Is BetterKvazaar 2.2System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 752 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: Super FastEPYC 4124P @ DDR5-5200smoke510152025Min: 20.73 / Avg: 20.75 / Max: 20.771. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

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 DirectionEPYC 4124P @ DDR5-5200smoke714212835SE +/- 0.04, N = 328.4128.431. (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
MinAvgMaxEPYC 4124P @ DDR5-5200493750095142OpenBenchmarking.orgMegahertz, More Is BetterXcompact3d Incompact3d 2021-03-11CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520018.943.047.6OpenBenchmarking.orgWatts, Fewer Is BetterXcompact3d Incompact3d 2021-03-11CPU Power Consumption Monitor14284256701. EPYC 4124P @ DDR5-5200: Approximate power consumption of 229 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520040.346.948.1OpenBenchmarking.orgCelsius, Fewer Is BetterXcompact3d Incompact3d 2021-03-11CPU Temperature Monitor1428425670
MinAvgMaxEPYC 4124P @ DDR5-520053.983.789.9OpenBenchmarking.orgWatts, Fewer Is BetterXcompact3d Incompact3d 2021-03-11System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 446 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: input.i3d 129 Cells Per DirectionEPYC 4124P @ DDR5-5200smoke612182430Min: 28.33 / Avg: 28.41 / Max: 28.451. (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

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 EngineEPYC 4124P @ DDR5-52008001600240032004000SE +/- 35.27, N = 43854
MinAvgMaxEPYC 4124P @ DDR5-520040043365140OpenBenchmarking.orgMegahertz, More Is BetterDaCapo Benchmark 23.11CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.855.774.5OpenBenchmarking.orgWatts, Fewer Is BetterDaCapo Benchmark 23.11CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 181 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520040.370.876.8OpenBenchmarking.orgCelsius, Fewer Is BetterDaCapo Benchmark 23.11CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.094.1119.0OpenBenchmarking.orgWatts, Fewer Is BetterDaCapo Benchmark 23.11System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 306 Joules per run.

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: JythonEPYC 4124P @ DDR5-52008001600240032004000SE +/- 12.00, N = 43913
MinAvgMaxEPYC 4124P @ DDR5-520040043815141OpenBenchmarking.orgMegahertz, More Is BetterDaCapo Benchmark 23.11CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.232.942.1OpenBenchmarking.orgWatts, Fewer Is BetterDaCapo Benchmark 23.11CPU Power Consumption Monitor12243648601. EPYC 4124P @ DDR5-5200: Approximate power consumption of 107 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520041.557.265.6OpenBenchmarking.orgCelsius, Fewer Is BetterDaCapo Benchmark 23.11CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520053.267.478.8OpenBenchmarking.orgWatts, Fewer Is BetterDaCapo Benchmark 23.11System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 236 Joules per run.

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: GraphChiEPYC 4124P @ DDR5-52007001400210028003500SE +/- 23.55, N = 43194
MinAvgMaxEPYC 4124P @ DDR5-520040041605141OpenBenchmarking.orgMegahertz, More Is BetterDaCapo Benchmark 23.11CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.237.350.8OpenBenchmarking.orgWatts, Fewer Is BetterDaCapo Benchmark 23.11CPU Power Consumption Monitor14284256701. EPYC 4124P @ DDR5-5200: Approximate power consumption of 140 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520041.162.172.0OpenBenchmarking.orgCelsius, Fewer Is BetterDaCapo Benchmark 23.11CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.076.994.8OpenBenchmarking.orgWatts, Fewer Is BetterDaCapo Benchmark 23.11System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 288 Joules per run.

ASTC Encoder

OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 4.7Preset: MediumEPYC 4124P @ DDR5-5200smoke918273645SE +/- 0.03, N = 339.8639.691. (CXX) g++ options: -O3 -flto -pthread
OpenBenchmarking.orgMT/s Per Watt, More Is BetterASTC Encoder 4.7Preset: MediumEPYC 4124P @ DDR5-5200smoke0.13160.26320.39480.52640.6580.5850.577
MinAvgMaxEPYC 4124P @ DDR5-520040047335141OpenBenchmarking.orgMegahertz, More Is BetterASTC Encoder 4.7CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.868.181.6OpenBenchmarking.orgWatts, Fewer Is BetterASTC Encoder 4.7CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 363 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520043.473.077.0OpenBenchmarking.orgCelsius, Fewer Is BetterASTC Encoder 4.7CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.5108.6123.8OpenBenchmarking.orgWatts, Fewer Is BetterASTC Encoder 4.7System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 615 Joules per run.
OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 4.7Preset: MediumEPYC 4124P @ DDR5-5200smoke816243240Min: 39.8 / Avg: 39.86 / Max: 39.91. (CXX) g++ options: -O3 -flto -pthread

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 IndexEPYC 4124P @ DDR5-52006001200180024003000SE +/- 10.87, N = 32599
MinAvgMaxEPYC 4124P @ DDR5-520040044115141OpenBenchmarking.orgMegahertz, More Is BetterDaCapo Benchmark 23.11CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.629.640.9OpenBenchmarking.orgWatts, Fewer Is BetterDaCapo Benchmark 23.11CPU Power Consumption Monitor11223344551. EPYC 4124P @ DDR5-5200: Approximate power consumption of 118 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520041.849.460.6OpenBenchmarking.orgCelsius, Fewer Is BetterDaCapo Benchmark 23.11CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520053.965.992.0OpenBenchmarking.orgWatts, Fewer Is BetterDaCapo Benchmark 23.11System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 307 Joules per run.

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: CPUEPYC 4124P @ DDR5-5200smoke246810SE +/- 0.01, N = 35.956.01MIN: 5.75 / MAX: 5.99MIN: 5.8 / MAX: 6.03
OpenBenchmarking.orgM samples/sec Per Watt, More Is BetterLuxCoreRender 2.6Scene: Rainbow Colors and Prism - Acceleration: CPUEPYC 4124P @ DDR5-5200smoke0.02180.04360.06540.08720.1090.0930.097
MinAvgMaxEPYC 4124P @ DDR5-520040047205049smoke494049675009OpenBenchmarking.orgMegahertz, More Is BetterLuxCoreRender 2.6CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.964.077.3smoke17.061.777.5OpenBenchmarking.orgWatts, Fewer Is BetterLuxCoreRender 2.6CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 384 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520047.074.478.4smoke46.873.078.4OpenBenchmarking.orgCelsius, Fewer Is BetterLuxCoreRender 2.6CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520055.2109.0119.6OpenBenchmarking.orgWatts, Fewer Is BetterLuxCoreRender 2.6System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 654 Joules per run.
OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.6Scene: Rainbow Colors and Prism - Acceleration: CPUEPYC 4124P @ DDR5-5200smoke246810Min: 5.94 / Avg: 5.95 / Max: 5.97

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 KafkaEPYC 4124P @ DDR5-520011002200330044005500SE +/- 2.33, N = 35097
MinAvgMaxEPYC 4124P @ DDR5-520040042265141OpenBenchmarking.orgMegahertz, More Is BetterDaCapo Benchmark 23.11CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520019.528.236.1OpenBenchmarking.orgWatts, Fewer Is BetterDaCapo Benchmark 23.11CPU Power Consumption Monitor10203040501. EPYC 4124P @ DDR5-5200: Approximate power consumption of 104 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520042.048.258.3OpenBenchmarking.orgCelsius, Fewer Is BetterDaCapo Benchmark 23.11CPU Temperature Monitor1632486480
MinAvgMaxEPYC 4124P @ DDR5-520054.766.680.6OpenBenchmarking.orgWatts, Fewer Is BetterDaCapo Benchmark 23.11System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 244 Joules per run.

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: 1.smt2EPYC 4124P @ DDR5-5200smoke612182430SE +/- 0.03, N = 325.7125.641. (CXX) g++ options: -lpthread -std=c++17 -fvisibility=hidden -mfpmath=sse -msse -msse2 -O3 -fPIC
MinAvgMaxEPYC 4124P @ DDR5-520040048345141OpenBenchmarking.orgMegahertz, More Is BetterZ3 Theorem Prover 4.12.1CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.026.629.3OpenBenchmarking.orgWatts, Fewer Is BetterZ3 Theorem Prover 4.12.1CPU Power Consumption Monitor9182736451. EPYC 4124P @ DDR5-5200: Approximate power consumption of 151 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520039.140.742.4OpenBenchmarking.orgCelsius, Fewer Is BetterZ3 Theorem Prover 4.12.1CPU Temperature Monitor1224364860
MinAvgMaxEPYC 4124P @ DDR5-520052.361.464.3OpenBenchmarking.orgWatts, Fewer Is BetterZ3 Theorem Prover 4.12.1System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 348 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterZ3 Theorem Prover 4.12.1SMT File: 1.smt2EPYC 4124P @ DDR5-5200smoke612182430Min: 25.64 / Avg: 25.71 / Max: 25.751. (CXX) g++ options: -lpthread -std=c++17 -fvisibility=hidden -mfpmath=sse -msse -msse2 -O3 -fPIC

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 8 - Input: Bosphorus 4KEPYC 4124P @ DDR5-5200smoke612182430SE +/- 0.06, N = 324.8724.961. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 8 - Input: Bosphorus 4KEPYC 4124P @ DDR5-5200smoke0.09090.18180.27270.36360.45450.3600.404
MinAvgMaxEPYC 4124P @ DDR5-520040047155136OpenBenchmarking.orgMegahertz, More Is BetterSVT-AV1 2.0CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520026.969.181.2OpenBenchmarking.orgWatts, Fewer Is BetterSVT-AV1 2.0CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 345 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520064.575.377.6OpenBenchmarking.orgCelsius, Fewer Is BetterSVT-AV1 2.0CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520055.2112.6127.2OpenBenchmarking.orgWatts, Fewer Is BetterSVT-AV1 2.0System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 563 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 8 - Input: Bosphorus 4KEPYC 4124P @ DDR5-5200smoke612182430Min: 24.76 / Avg: 24.87 / Max: 24.931. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

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: MediumEPYC 4124P @ DDR5-5200smoke612182430SE +/- 0.03, N = 324.2924.14
OpenBenchmarking.orgFrames Per Second Per Watt, More Is Betteruvg266 0.4.1Video Input: Bosphorus 1080p - Video Preset: MediumEPYC 4124P @ DDR5-5200smoke0.08480.16960.25440.33920.4240.3430.377
MinAvgMaxEPYC 4124P @ DDR5-5200495649705036OpenBenchmarking.orgMegahertz, More Is Betteruvg266 0.4.1CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520034.870.979.0OpenBenchmarking.orgWatts, Fewer Is Betteruvg266 0.4.1CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 307 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520073.378.079.0OpenBenchmarking.orgCelsius, Fewer Is Betteruvg266 0.4.1CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520055.2112.0122.8OpenBenchmarking.orgWatts, Fewer Is Betteruvg266 0.4.1System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 485 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 1080p - Video Preset: MediumEPYC 4124P @ DDR5-5200smoke612182430Min: 24.22 / Avg: 24.29 / Max: 24.33

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 13 - Input: Bosphorus 4KEPYC 4124P @ DDR5-5200smoke1530456075SE +/- 0.56, N = 968.4763.341. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 13 - Input: Bosphorus 4KEPYC 4124P @ DDR5-5200smoke0.29390.58780.88171.17561.46951.2431.306
MinAvgMaxEPYC 4124P @ DDR5-520040044565141OpenBenchmarking.orgMegahertz, More Is BetterSVT-AV1 2.0CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.555.179.6OpenBenchmarking.orgWatts, Fewer Is BetterSVT-AV1 2.0CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 141 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520042.868.674.9OpenBenchmarking.orgCelsius, Fewer Is BetterSVT-AV1 2.0CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.195.4124.9OpenBenchmarking.orgWatts, Fewer Is BetterSVT-AV1 2.0System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 244 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 13 - Input: Bosphorus 4KEPYC 4124P @ DDR5-5200smoke1326395265Min: 63.97 / Avg: 68.47 / Max: 69.341. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

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: FOP Print FormatterEPYC 4124P @ DDR5-5200120240360480600SE +/- 8.96, N = 15558
MinAvgMaxEPYC 4124P @ DDR5-520040045265140OpenBenchmarking.orgMegahertz, More Is BetterDaCapo Benchmark 23.11CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.633.638.5OpenBenchmarking.orgWatts, Fewer Is BetterDaCapo Benchmark 23.11CPU Power Consumption Monitor11223344551. EPYC 4124P @ DDR5-5200: Approximate power consumption of 40 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520040.856.363.0OpenBenchmarking.orgCelsius, Fewer Is BetterDaCapo Benchmark 23.11CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.370.8102.7OpenBenchmarking.orgWatts, Fewer Is BetterDaCapo Benchmark 23.11System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 85 Joules per run.

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Avrora AVR Simulation FrameworkEPYC 4124P @ DDR5-52005001000150020002500SE +/- 4.45, N = 62486
MinAvgMaxEPYC 4124P @ DDR5-520040038925138OpenBenchmarking.orgMegahertz, More Is BetterDaCapo Benchmark 23.11CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.328.835.6OpenBenchmarking.orgWatts, Fewer Is BetterDaCapo Benchmark 23.11CPU Power Consumption Monitor10203040501. EPYC 4124P @ DDR5-5200: Approximate power consumption of 62 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520040.846.149.0OpenBenchmarking.orgCelsius, Fewer Is BetterDaCapo Benchmark 23.11CPU Temperature Monitor1428425670
MinAvgMaxEPYC 4124P @ DDR5-520052.465.080.0OpenBenchmarking.orgWatts, Fewer Is BetterDaCapo Benchmark 23.11System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 141 Joules per run.

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: PMD Source Code AnalyzerEPYC 4124P @ DDR5-5200400800120016002000SE +/- 8.71, N = 61824
MinAvgMaxEPYC 4124P @ DDR5-520040040715140OpenBenchmarking.orgMegahertz, More Is BetterDaCapo Benchmark 23.11CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.747.568.1OpenBenchmarking.orgWatts, Fewer Is BetterDaCapo Benchmark 23.11CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 111 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520041.865.171.3OpenBenchmarking.orgCelsius, Fewer Is BetterDaCapo Benchmark 23.11CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.385.6116.3OpenBenchmarking.orgWatts, Fewer Is BetterDaCapo Benchmark 23.11System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 200 Joules per run.

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Zxing 1D/2D Barcode Image ProcessingEPYC 4124P @ DDR5-5200400800120016002000SE +/- 3.20, N = 62033
MinAvgMaxEPYC 4124P @ DDR5-5200494150145144OpenBenchmarking.orgMegahertz, More Is BetterDaCapo Benchmark 23.11CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520020.950.774.2OpenBenchmarking.orgWatts, Fewer Is BetterDaCapo Benchmark 23.11CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 93 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520047.872.278.0OpenBenchmarking.orgCelsius, Fewer Is BetterDaCapo Benchmark 23.11CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.483.8116.7OpenBenchmarking.orgWatts, Fewer Is BetterDaCapo Benchmark 23.11System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 154 Joules per run.

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 digitEPYC 4124P @ DDR5-5200246810SE +/- 0.016, N = 67.6091. (CC) gcc options: -O2 -pthread
MinAvgMaxEPYC 4124P @ DDR5-520040041954966OpenBenchmarking.orgMegahertz, More Is BetterHelsing 1.0-betaCPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.956.070.9OpenBenchmarking.orgWatts, Fewer Is BetterHelsing 1.0-betaCPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 103 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520042.672.379.8OpenBenchmarking.orgCelsius, Fewer Is BetterHelsing 1.0-betaCPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.2102.2125.0OpenBenchmarking.orgWatts, Fewer Is BetterHelsing 1.0-betaSystem Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 204 Joules per run.

VVenC

OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.11Video Input: Bosphorus 1080p - Video Preset: FasterEPYC 4124P @ DDR5-5200smoke612182430SE +/- 0.02, N = 327.3527.191. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterVVenC 1.11Video Input: Bosphorus 1080p - Video Preset: FasterEPYC 4124P @ DDR5-5200smoke0.10310.20620.30930.41240.51550.4110.458
MinAvgMaxEPYC 4124P @ DDR5-5200494049985064OpenBenchmarking.orgMegahertz, More Is BetterVVenC 1.11CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520023.166.579.2OpenBenchmarking.orgWatts, Fewer Is BetterVVenC 1.11CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 310 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520047.073.377.5OpenBenchmarking.orgCelsius, Fewer Is BetterVVenC 1.11CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520058.6109.7124.6OpenBenchmarking.orgWatts, Fewer Is BetterVVenC 1.11System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 512 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.11Video Input: Bosphorus 1080p - Video Preset: FasterEPYC 4124P @ DDR5-5200smoke612182430Min: 27.32 / Avg: 27.35 / Max: 27.41. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects

oneDNN

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.4Harness: Deconvolution Batch shapes_1d - Engine: CPUEPYC 4124P @ DDR5-5200smoke246810SE +/- 0.00779, N = 37.422727.18995MIN: 6.88MIN: 6.841. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
MinAvgMaxEPYC 4124P @ DDR5-520040047465140OpenBenchmarking.orgMegahertz, More Is BetteroneDNN 3.4CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.750.767.5OpenBenchmarking.orgWatts, Fewer Is BetteroneDNN 3.4CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 254 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520038.558.174.1OpenBenchmarking.orgCelsius, Fewer Is BetteroneDNN 3.4CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520053.890.1106.6OpenBenchmarking.orgWatts, Fewer Is BetteroneDNN 3.4System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 451 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.4Harness: Deconvolution Batch shapes_1d - Engine: CPUEPYC 4124P @ DDR5-5200smoke3691215Min: 7.41 / Avg: 7.42 / Max: 7.441. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

SVT-HEVC

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-HEVC CPU-based multi-threaded video encoder for the HEVC / H.265 video format with a sample 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 4KEPYC 4124P @ DDR5-5200smoke714212835SE +/- 0.03, N = 329.8229.721. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-HEVC 1.5.0Tuning: 7 - Input: Bosphorus 4KEPYC 4124P @ DDR5-5200smoke0.10310.20620.30930.41240.51550.4580.443
MinAvgMaxEPYC 4124P @ DDR5-5200493149925141OpenBenchmarking.orgMegahertz, More Is BetterSVT-HEVC 1.5.0CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.965.181.6OpenBenchmarking.orgWatts, Fewer Is BetterSVT-HEVC 1.5.0CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 282 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520045.673.879.1OpenBenchmarking.orgCelsius, Fewer Is BetterSVT-HEVC 1.5.0CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520055.1104.9126.9OpenBenchmarking.orgWatts, Fewer Is BetterSVT-HEVC 1.5.0System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 455 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 7 - Input: Bosphorus 4KEPYC 4124P @ DDR5-5200smoke714212835Min: 29.79 / Avg: 29.82 / Max: 29.871. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -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: Ultra FastEPYC 4124P @ DDR5-5200smoke714212835SE +/- 0.03, N = 328.7528.701. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: Ultra FastEPYC 4124P @ DDR5-5200smoke0.10670.21340.32010.42680.53350.4270.474
MinAvgMaxEPYC 4124P @ DDR5-520040046114993OpenBenchmarking.orgMegahertz, More Is BetterKvazaar 2.2CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.367.481.6OpenBenchmarking.orgWatts, Fewer Is BetterKvazaar 2.2CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 292 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520045.075.080.3OpenBenchmarking.orgCelsius, Fewer Is BetterKvazaar 2.2CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.3114.4127.4OpenBenchmarking.orgWatts, Fewer Is BetterKvazaar 2.2System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 534 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: Ultra FastEPYC 4124P @ DDR5-5200smoke612182430Min: 28.69 / Avg: 28.75 / Max: 28.811. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 1080p - Video Preset: MediumEPYC 4124P @ DDR5-5200smoke816243240SE +/- 0.03, N = 436.1035.961. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterKvazaar 2.2Video Input: Bosphorus 1080p - Video Preset: MediumEPYC 4124P @ DDR5-5200smoke0.13390.26780.40170.53560.66950.5790.595
MinAvgMaxEPYC 4124P @ DDR5-520040044045129OpenBenchmarking.orgMegahertz, More Is BetterKvazaar 2.2CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.962.479.5OpenBenchmarking.orgWatts, Fewer Is BetterKvazaar 2.2CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 250 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520045.376.180.4OpenBenchmarking.orgCelsius, Fewer Is BetterKvazaar 2.2CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520055.2104.9123.1OpenBenchmarking.orgWatts, Fewer Is BetterKvazaar 2.2System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 394 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 1080p - Video Preset: MediumEPYC 4124P @ DDR5-5200smoke816243240Min: 36.03 / Avg: 36.1 / Max: 36.161. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

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: Single-ThreadedEPYC 4124P @ DDR5-5200smoke9001800270036004500SE +/- 29.23, N = 34281.84230.01. (CXX) g++ options: -O3 -march=native -fPIE -pie
OpenBenchmarking.orgMFLOPS Per Watt, More Is BetterQuantLib 1.32Configuration: Single-ThreadedEPYC 4124P @ DDR5-5200smoke306090120150139.61136.29
MinAvgMaxEPYC 4124P @ DDR5-520040047205141OpenBenchmarking.orgMegahertz, More Is BetterQuantLib 1.32CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.930.739.9OpenBenchmarking.orgWatts, Fewer Is BetterQuantLib 1.32CPU Power Consumption Monitor11223344551. EPYC 4124P @ DDR5-5200: Approximate power consumption of 123 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520039.356.270.6OpenBenchmarking.orgCelsius, Fewer Is BetterQuantLib 1.32CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.668.076.7OpenBenchmarking.orgWatts, Fewer Is BetterQuantLib 1.32System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 272 Joules per run.
OpenBenchmarking.orgMFLOPS, More Is BetterQuantLib 1.32Configuration: Single-ThreadedEPYC 4124P @ DDR5-5200smoke7001400210028003500Min: 4224.6 / Avg: 4281.83 / Max: 4320.81. (CXX) g++ options: -O3 -march=native -fPIE -pie

NAS Parallel Benchmarks

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

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: CG.CEPYC 4124P @ DDR5-5200smoke16003200480064008000SE +/- 21.45, N = 37548.437555.241. (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
OpenBenchmarking.orgTotal Mop/s Per Watt, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: CG.CEPYC 4124P @ DDR5-5200smoke306090120150137.16127.53
MinAvgMaxEPYC 4124P @ DDR5-520040044935140OpenBenchmarking.orgMegahertz, More Is BetterNAS Parallel Benchmarks 3.4CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.055.066.3OpenBenchmarking.orgWatts, Fewer Is BetterNAS Parallel Benchmarks 3.4CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 275 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520038.550.552.8OpenBenchmarking.orgCelsius, Fewer Is BetterNAS Parallel Benchmarks 3.4CPU Temperature Monitor1530456075
MinAvgMaxEPYC 4124P @ DDR5-520054.495.9109.7OpenBenchmarking.orgWatts, Fewer Is BetterNAS Parallel Benchmarks 3.4System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 479 Joules per run.
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: CG.CEPYC 4124P @ DDR5-5200smoke13002600390052006500Min: 7511.11 / Avg: 7548.43 / Max: 7585.411. (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

oneDNN

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.4Harness: IP Shapes 1D - Engine: CPUEPYC 4124P @ DDR5-5200smoke0.85891.71782.57673.43564.2945SE +/- 0.00057, N = 43.817533.81404MIN: 3.74MIN: 3.751. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
MinAvgMaxEPYC 4124P @ DDR5-520040046154940OpenBenchmarking.orgMegahertz, More Is BetteroneDNN 3.4CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520030.151.062.3OpenBenchmarking.orgWatts, Fewer Is BetteroneDNN 3.4CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 178 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520047.650.852.9OpenBenchmarking.orgCelsius, Fewer Is BetteroneDNN 3.4CPU Temperature Monitor1530456075
MinAvgMaxEPYC 4124P @ DDR5-520053.587.898.3OpenBenchmarking.orgWatts, Fewer Is BetteroneDNN 3.4System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 307 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.4Harness: IP Shapes 1D - Engine: CPUEPYC 4124P @ DDR5-5200smoke246810Min: 3.82 / Avg: 3.82 / Max: 3.821. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -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: Batik SVG ToolkitEPYC 4124P @ DDR5-52002004006008001000SE +/- 5.72, N = 81002
MinAvgMaxEPYC 4124P @ DDR5-520040034195141OpenBenchmarking.orgMegahertz, More Is BetterDaCapo Benchmark 23.11CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.830.140.6OpenBenchmarking.orgWatts, Fewer Is BetterDaCapo Benchmark 23.11CPU Power Consumption Monitor11223344551. EPYC 4124P @ DDR5-5200: Approximate power consumption of 53 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520039.954.159.9OpenBenchmarking.orgCelsius, Fewer Is BetterDaCapo Benchmark 23.11CPU Temperature Monitor1632486480
MinAvgMaxEPYC 4124P @ DDR5-520053.565.587.7OpenBenchmarking.orgWatts, Fewer Is BetterDaCapo Benchmark 23.11System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 115 Joules per run.

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 RatingEPYC 4124P @ DDR5-5200smoke10K20K30K40K50KSE +/- 61.13, N = 345189451741. (CXX) g++ options: -lpthread -ldl -O2 -fPIC
OpenBenchmarking.orgMIPS Per Watt, More Is Better7-Zip Compression 22.01Test: Decompression RatingEPYC 4124P @ DDR5-5200smoke2004006008001000819.85851.06
MinAvgMaxEPYC 4124P @ DDR5-520040043505135OpenBenchmarking.orgMegahertz, More Is Better7-Zip Compression 22.01CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.155.172.1OpenBenchmarking.orgWatts, Fewer Is Better7-Zip Compression 22.01CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 239 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520043.469.875.6OpenBenchmarking.orgCelsius, Fewer Is Better7-Zip Compression 22.01CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520053.895.3113.3OpenBenchmarking.orgWatts, Fewer Is Better7-Zip Compression 22.01System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 413 Joules per run.
OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 22.01Test: Decompression RatingEPYC 4124P @ DDR5-5200smoke8K16K24K32K40KMin: 45070 / Avg: 45189.33 / Max: 452721. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 22.01Test: Compression RatingEPYC 4124P @ DDR5-5200smoke12K24K36K48K60KSE +/- 61.73, N = 356155562451. (CXX) g++ options: -lpthread -ldl -O2 -fPIC
OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 22.01Test: Compression RatingEPYC 4124P @ DDR5-5200smoke10K20K30K40K50KMin: 56036 / Avg: 56155 / Max: 562431. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

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 4KEPYC 4124P @ DDR5-5200smoke816243240SE +/- 0.42, N = 335.8534.921. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-VP9 0.3Tuning: Visual Quality Optimized - Input: Bosphorus 4KEPYC 4124P @ DDR5-5200smoke0.13410.26820.40230.53640.67050.5920.596
MinAvgMaxEPYC 4124P @ DDR5-520040046785141OpenBenchmarking.orgMegahertz, More Is BetterSVT-VP9 0.3CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.160.680.6OpenBenchmarking.orgWatts, Fewer Is BetterSVT-VP9 0.3CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 242 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520044.571.978.0OpenBenchmarking.orgCelsius, Fewer Is BetterSVT-VP9 0.3CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520055.0105.4127.4OpenBenchmarking.orgWatts, Fewer Is BetterSVT-VP9 0.3System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 457 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: Visual Quality Optimized - Input: Bosphorus 4KEPYC 4124P @ DDR5-5200smoke816243240Min: 35.02 / Avg: 35.85 / Max: 36.321. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: VMAF Optimized - Input: Bosphorus 4KEPYC 4124P @ DDR5-5200smoke1020304050SE +/- 0.04, N = 445.9645.701. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-VP9 0.3Tuning: VMAF Optimized - Input: Bosphorus 4KEPYC 4124P @ DDR5-5200smoke0.17210.34420.51630.68840.86050.7650.740
MinAvgMaxEPYC 4124P @ DDR5-5200501350935140OpenBenchmarking.orgMegahertz, More Is BetterSVT-VP9 0.3CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520019.560.177.4OpenBenchmarking.orgWatts, Fewer Is BetterSVT-VP9 0.3CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 180 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520042.967.875.8OpenBenchmarking.orgCelsius, Fewer Is BetterSVT-VP9 0.3CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.8100.5122.8OpenBenchmarking.orgWatts, Fewer Is BetterSVT-VP9 0.3System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 302 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: VMAF Optimized - Input: Bosphorus 4KEPYC 4124P @ DDR5-5200smoke918273645Min: 45.89 / Avg: 45.96 / Max: 46.081. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

srsRAN Project

OpenBenchmarking.orgMbps, More Is BettersrsRAN Project 23.10.1-20240325Test: PUSCH Processor Benchmark, Throughput ThreadEPYC 4124P @ DDR5-5200smoke4080120160200SE +/- 0.00, N = 4183.4183.4MIN: 105.9MIN: 105.91. (CXX) g++ options: -O3 -march=native -mavx2 -mavx -msse4.1 -mfma -mavx512f -mavx512cd -mavx512bw -mavx512dq -fno-trapping-math -fno-math-errno -ldl
OpenBenchmarking.orgMbps Per Watt, More Is BettersrsRAN Project 23.10.1-20240325Test: PUSCH Processor Benchmark, Throughput ThreadEPYC 4124P @ DDR5-5200smoke2468106.5297.477
MinAvgMaxEPYC 4124P @ DDR5-520040047415141OpenBenchmarking.orgMegahertz, More Is BettersrsRAN Project 23.10.1-20240325CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.328.133.7OpenBenchmarking.orgWatts, Fewer Is BettersrsRAN Project 23.10.1-20240325CPU Power Consumption Monitor10203040501. EPYC 4124P @ DDR5-5200: Approximate power consumption of 105 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520042.649.654.4OpenBenchmarking.orgCelsius, Fewer Is BettersrsRAN Project 23.10.1-20240325CPU Temperature Monitor1530456075
MinAvgMaxEPYC 4124P @ DDR5-520054.563.868.7OpenBenchmarking.orgWatts, Fewer Is BettersrsRAN Project 23.10.1-20240325System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 239 Joules per run.
OpenBenchmarking.orgMbps, More Is BettersrsRAN Project 23.10.1-20240325Test: PUSCH Processor Benchmark, Throughput ThreadEPYC 4124P @ DDR5-5200smoke306090120150Min: 183.4 / Avg: 183.4 / Max: 183.41. (CXX) g++ options: -O3 -march=native -mavx2 -mavx -msse4.1 -mfma -mavx512f -mavx512cd -mavx512bw -mavx512dq -fno-trapping-math -fno-math-errno -ldl

QMCPACK

QMCPACK is a modern high-performance open-source Quantum Monte Carlo (QMC) simulation code making use of MPI for this benchmark of the H20 example code. QMCPACK is an open-source production level many-body ab initio Quantum Monte Carlo code for computing the electronic structure of atoms, molecules, and solids. QMCPACK is supported by the U.S. Department of Energy. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTotal Execution Time - Seconds, Fewer Is BetterQMCPACK 3.17.1Input: simple-H2OEPYC 4124P @ DDR5-5200smoke48121620SE +/- 0.06, N = 317.0517.411. (CXX) g++ options: -fopenmp -foffload=disable -finline-limit=1000 -fstrict-aliasing -funroll-all-loops -ffast-math -march=native -O3 -lm -ldl
MinAvgMaxEPYC 4124P @ DDR5-520040047105139OpenBenchmarking.orgMegahertz, More Is BetterQMCPACK 3.17.1CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.553.466.8OpenBenchmarking.orgWatts, Fewer Is BetterQMCPACK 3.17.1CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 214 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520042.659.763.1OpenBenchmarking.orgCelsius, Fewer Is BetterQMCPACK 3.17.1CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.387.7104.5OpenBenchmarking.orgWatts, Fewer Is BetterQMCPACK 3.17.1System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 351 Joules per run.
OpenBenchmarking.orgTotal Execution Time - Seconds, Fewer Is BetterQMCPACK 3.17.1Input: simple-H2OEPYC 4124P @ DDR5-5200smoke48121620Min: 16.97 / Avg: 17.05 / Max: 17.171. (CXX) g++ options: -fopenmp -foffload=disable -finline-limit=1000 -fstrict-aliasing -funroll-all-loops -ffast-math -march=native -O3 -lm -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.orgMpix/sec, More Is BetterASKAP 1.0Test: tConvolve MPI - GriddingEPYC 4124P @ DDR5-5200smoke7001400210028003500SE +/- 26.67, N = 33226.623199.951. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
OpenBenchmarking.orgMpix/sec Per Watt, More Is BetterASKAP 1.0Test: tConvolve MPI - GriddingEPYC 4124P @ DDR5-5200smoke2040608010089.8193.99
MinAvgMaxEPYC 4124P @ DDR5-5200493749424963OpenBenchmarking.orgMegahertz, More Is BetterASKAP 1.0CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.335.943.9OpenBenchmarking.orgWatts, Fewer Is BetterASKAP 1.0CPU Power Consumption Monitor12243648601. EPYC 4124P @ DDR5-5200: Approximate power consumption of 132 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520039.145.652.0OpenBenchmarking.orgCelsius, Fewer Is BetterASKAP 1.0CPU Temperature Monitor1530456075
MinAvgMaxEPYC 4124P @ DDR5-520053.972.384.1OpenBenchmarking.orgWatts, Fewer Is BetterASKAP 1.0System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 265 Joules per run.
OpenBenchmarking.orgMpix/sec, More Is BetterASKAP 1.0Test: tConvolve MPI - GriddingEPYC 4124P @ DDR5-5200smoke6001200180024003000Min: 3199.95 / Avg: 3226.62 / Max: 3279.951. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

OpenBenchmarking.orgMpix/sec, More Is BetterASKAP 1.0Test: tConvolve MPI - DegriddingEPYC 4124P @ DDR5-5200smoke6001200180024003000SE +/- 0.00, N = 32623.962572.511. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
OpenBenchmarking.orgMpix/sec, More Is BetterASKAP 1.0Test: tConvolve MPI - DegriddingEPYC 4124P @ DDR5-5200smoke5001000150020002500Min: 2623.96 / Avg: 2623.96 / Max: 2623.961. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

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 4KEPYC 4124P @ DDR5-5200smoke1122334455SE +/- 0.01, N = 447.0147.091. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-VP9 0.3Tuning: PSNR/SSIM Optimized - Input: Bosphorus 4KEPYC 4124P @ DDR5-5200smoke0.21940.43880.65820.87761.0970.7960.975
MinAvgMaxEPYC 4124P @ DDR5-520040039225131OpenBenchmarking.orgMegahertz, More Is BetterSVT-VP9 0.3CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.059.077.7OpenBenchmarking.orgWatts, Fewer Is BetterSVT-VP9 0.3CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 177 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520044.470.175.9OpenBenchmarking.orgCelsius, Fewer Is BetterSVT-VP9 0.3CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.895.1123.1OpenBenchmarking.orgWatts, Fewer Is BetterSVT-VP9 0.3System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 285 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: PSNR/SSIM Optimized - Input: Bosphorus 4KEPYC 4124P @ DDR5-5200smoke1020304050Min: 47 / Avg: 47.01 / Max: 47.041. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

NAS Parallel Benchmarks

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

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.CEPYC 4124P @ DDR5-5200smoke2004006008001000SE +/- 7.98, N = 5781.24784.171. (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
OpenBenchmarking.orgTotal Mop/s Per Watt, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.CEPYC 4124P @ DDR5-5200smoke4812162015.1918.22
MinAvgMaxEPYC 4124P @ DDR5-520040047135135OpenBenchmarking.orgMegahertz, More Is BetterNAS Parallel Benchmarks 3.4CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.351.466.9OpenBenchmarking.orgWatts, Fewer Is BetterNAS Parallel Benchmarks 3.4CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 134 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520038.958.767.8OpenBenchmarking.orgCelsius, Fewer Is BetterNAS Parallel Benchmarks 3.4CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520053.788.9104.5OpenBenchmarking.orgWatts, Fewer Is BetterNAS Parallel Benchmarks 3.4System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 231 Joules per run.
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.CEPYC 4124P @ DDR5-5200smoke140280420560700Min: 749.37 / Avg: 781.24 / Max: 790.741. (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

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 Xalan XSLTEPYC 4124P @ DDR5-52002004006008001000SE +/- 2.53, N = 8782
MinAvgMaxEPYC 4124P @ DDR5-520040041725135OpenBenchmarking.orgMegahertz, More Is BetterDaCapo Benchmark 23.11CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.342.368.2OpenBenchmarking.orgWatts, Fewer Is BetterDaCapo Benchmark 23.11CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 58 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520040.364.173.3OpenBenchmarking.orgCelsius, Fewer Is BetterDaCapo Benchmark 23.11CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520053.990.9120.2OpenBenchmarking.orgWatts, Fewer Is BetterDaCapo Benchmark 23.11System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 114 Joules per run.

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 4 - Input: Bosphorus 1080pEPYC 4124P @ DDR5-5200smoke3691215SE +/- 0.01, N = 412.1812.211. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 4 - Input: Bosphorus 1080pEPYC 4124P @ DDR5-5200smoke0.05650.1130.16950.2260.28250.2080.251
MinAvgMaxEPYC 4124P @ DDR5-520040042855139OpenBenchmarking.orgMegahertz, More Is BetterSVT-AV1 2.0CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.658.781.6OpenBenchmarking.orgWatts, Fewer Is BetterSVT-AV1 2.0CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 191 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520046.373.279.4OpenBenchmarking.orgCelsius, Fewer Is BetterSVT-AV1 2.0CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.9104.8128.4OpenBenchmarking.orgWatts, Fewer Is BetterSVT-AV1 2.0System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 341 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 4 - Input: Bosphorus 1080pEPYC 4124P @ DDR5-5200smoke48121620Min: 12.15 / Avg: 12.18 / Max: 12.211. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

libavif avifenc

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 1.0Encoder Speed: 6, LosslessEPYC 4124P @ DDR5-5200smoke3691215SE +/- 0.01, N = 413.4513.431. (CXX) g++ options: -O3 -fPIC -lm
MinAvgMaxEPYC 4124P @ DDR5-520040046125140OpenBenchmarking.orgMegahertz, More Is Betterlibavif avifenc 1.0CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520015.855.178.7OpenBenchmarking.orgWatts, Fewer Is Betterlibavif avifenc 1.0CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 165 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520042.070.377.9OpenBenchmarking.orgCelsius, Fewer Is Betterlibavif avifenc 1.0CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520055.493.5120.4OpenBenchmarking.orgWatts, Fewer Is Betterlibavif avifenc 1.0System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 280 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 1.0Encoder Speed: 6, LosslessEPYC 4124P @ DDR5-5200smoke48121620Min: 13.42 / Avg: 13.45 / Max: 13.491. (CXX) g++ options: -O3 -fPIC -lm

Parallel BZIP2 Compression

OpenBenchmarking.orgSeconds, Fewer Is BetterParallel BZIP2 Compression 1.1.13FreeBSD-13.0-RELEASE-amd64-memstick.img CompressionEPYC 4124P @ DDR5-5200smoke3691215SE +/- 0.09, N = 511.1011.201. (CXX) g++ options: -O2 -pthread -lbz2 -lpthread
MinAvgMaxEPYC 4124P @ DDR5-5200494150315141OpenBenchmarking.orgMegahertz, More Is BetterParallel BZIP2 Compression 1.1.13CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.950.771.4OpenBenchmarking.orgWatts, Fewer Is BetterParallel BZIP2 Compression 1.1.13CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 132 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520045.570.878.0OpenBenchmarking.orgCelsius, Fewer Is BetterParallel BZIP2 Compression 1.1.13CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520055.187.3114.1OpenBenchmarking.orgWatts, Fewer Is BetterParallel BZIP2 Compression 1.1.13System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 227 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterParallel BZIP2 Compression 1.1.13FreeBSD-13.0-RELEASE-amd64-memstick.img CompressionEPYC 4124P @ DDR5-5200smoke3691215Min: 10.75 / Avg: 11.1 / Max: 11.261. (CXX) g++ options: -O2 -pthread -lbz2 -lpthread

Dolfyn

Dolfyn is a Computational Fluid Dynamics (CFD) code of modern numerical simulation techniques. The Dolfyn test profile measures the execution time of the bundled computational fluid dynamics demos that are bundled with Dolfyn. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterDolfyn 0.527Computational Fluid DynamicsEPYC 4124P @ DDR5-5200smoke3691215SE +/- 0.01, N = 510.9810.97
MinAvgMaxEPYC 4124P @ DDR5-5200494150965142OpenBenchmarking.orgMegahertz, More Is BetterDolfyn 0.527CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.129.737.7OpenBenchmarking.orgWatts, Fewer Is BetterDolfyn 0.527CPU Power Consumption Monitor11223344551. EPYC 4124P @ DDR5-5200: Approximate power consumption of 71 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520040.652.860.8OpenBenchmarking.orgCelsius, Fewer Is BetterDolfyn 0.527CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.865.073.7OpenBenchmarking.orgWatts, Fewer Is BetterDolfyn 0.527System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 169 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterDolfyn 0.527Computational Fluid DynamicsEPYC 4124P @ DDR5-5200smoke3691215Min: 10.96 / Avg: 10.98 / Max: 11

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 TimesEPYC 4124P @ DDR5-5200smoke120240360480600SE +/- 3.40, N = 4552546
MinAvgMaxEPYC 4124P @ DDR5-520040042795141OpenBenchmarking.orgMegahertz, More Is BetterPyBench 2018-02-16CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520021.028.634.0OpenBenchmarking.orgWatts, Fewer Is BetterPyBench 2018-02-16CPU Power Consumption Monitor10203040501. EPYC 4124P @ DDR5-5200: Approximate power consumption of 71 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520054.358.460.3OpenBenchmarking.orgCelsius, Fewer Is BetterPyBench 2018-02-16CPU Temperature Monitor1632486480
MinAvgMaxEPYC 4124P @ DDR5-520054.363.268.4OpenBenchmarking.orgWatts, Fewer Is BetterPyBench 2018-02-16System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 174 Joules per run.
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyBench 2018-02-16Total For Average Test TimesEPYC 4124P @ DDR5-5200smoke100200300400500Min: 546 / Avg: 551.5 / Max: 560

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 4KEPYC 4124P @ DDR5-5200smoke1428425670SE +/- 0.02, N = 561.0861.141. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-HEVC 1.5.0Tuning: 10 - Input: Bosphorus 4KEPYC 4124P @ DDR5-5200smoke0.26710.53420.80131.06841.33551.0541.187
MinAvgMaxEPYC 4124P @ DDR5-520040043515141OpenBenchmarking.orgMegahertz, More Is BetterSVT-HEVC 1.5.0CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520018.658.080.0OpenBenchmarking.orgWatts, Fewer Is BetterSVT-HEVC 1.5.0CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 151 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520043.469.776.6OpenBenchmarking.orgCelsius, Fewer Is BetterSVT-HEVC 1.5.0CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520055.298.9125.4OpenBenchmarking.orgWatts, Fewer Is BetterSVT-HEVC 1.5.0System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 257 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 10 - Input: Bosphorus 4KEPYC 4124P @ DDR5-5200smoke1224364860Min: 61.03 / Avg: 61.08 / Max: 61.171. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

NAS Parallel Benchmarks

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

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: MG.CEPYC 4124P @ DDR5-5200smoke4K8K12K16K20KSE +/- 13.69, N = 517132.7017172.151. (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
OpenBenchmarking.orgTotal Mop/s Per Watt, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: MG.CEPYC 4124P @ DDR5-5200smoke110220330440550447.42527.83
MinAvgMaxEPYC 4124P @ DDR5-520040042735140OpenBenchmarking.orgMegahertz, More Is BetterNAS Parallel Benchmarks 3.4CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.438.348.7OpenBenchmarking.orgWatts, Fewer Is BetterNAS Parallel Benchmarks 3.4CPU Power Consumption Monitor14284256701. EPYC 4124P @ DDR5-5200: Approximate power consumption of 100 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520038.944.748.3OpenBenchmarking.orgCelsius, Fewer Is BetterNAS Parallel Benchmarks 3.4CPU Temperature Monitor1428425670
MinAvgMaxEPYC 4124P @ DDR5-520053.877.791.0OpenBenchmarking.orgWatts, Fewer Is BetterNAS Parallel Benchmarks 3.4System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 202 Joules per run.
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: MG.CEPYC 4124P @ DDR5-5200smoke3K6K9K12K15KMin: 17089.77 / Avg: 17132.7 / Max: 17164.861. (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

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 1080pEPYC 4124P @ DDR5-5200smoke1326395265SE +/- 0.16, N = 558.6258.351. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OpenBenchmarking.orgFrames Per Second Per Watt, More Is Betterx265 3.4Video Input: Bosphorus 1080pEPYC 4124P @ DDR5-5200smoke0.30310.60620.90931.21241.51551.0881.347
MinAvgMaxEPYC 4124P @ DDR5-520040046725141OpenBenchmarking.orgMegahertz, More Is Betterx265 3.4CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.153.973.8OpenBenchmarking.orgWatts, Fewer Is Betterx265 3.4CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 140 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520043.469.875.4OpenBenchmarking.orgCelsius, Fewer Is Betterx265 3.4CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520055.3100.0119.6OpenBenchmarking.orgWatts, Fewer Is Betterx265 3.4System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 260 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.4Video Input: Bosphorus 1080pEPYC 4124P @ DDR5-5200smoke1224364860Min: 58.17 / Avg: 58.62 / Max: 59.031. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

TensorFlow

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 1 - Model: ResNet-50EPYC 4124P @ DDR5-5200smoke3691215SE +/- 0.01, N = 412.1812.23
OpenBenchmarking.orgimages/sec Per Watt, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 1 - Model: ResNet-50EPYC 4124P @ DDR5-5200smoke0.08030.16060.24090.32120.40150.2930.357
MinAvgMaxEPYC 4124P @ DDR5-520040035735140OpenBenchmarking.orgMegahertz, More Is BetterTensorFlow 2.16.1CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.141.555.7OpenBenchmarking.orgWatts, Fewer Is BetterTensorFlow 2.16.1CPU Power Consumption Monitor16324864801. EPYC 4124P @ DDR5-5200: Approximate power consumption of 125 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520039.347.150.9OpenBenchmarking.orgCelsius, Fewer Is BetterTensorFlow 2.16.1CPU Temperature Monitor1428425670
MinAvgMaxEPYC 4124P @ DDR5-520053.280.996.6OpenBenchmarking.orgWatts, Fewer Is BetterTensorFlow 2.16.1System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 263 Joules per run.
OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 1 - Model: ResNet-50EPYC 4124P @ DDR5-5200smoke48121620Min: 12.16 / Avg: 12.18 / Max: 12.2

WebP Image Encode

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

OpenBenchmarking.orgMP/s, More Is BetterWebP Image Encode 1.2.4Encode Settings: Quality 100, LosslessEPYC 4124P @ DDR5-5200smoke0.45680.91361.37041.82722.284SE +/- 0.01, N = 42.022.031. (CC) gcc options: -fvisibility=hidden -O2 -lm
OpenBenchmarking.orgMP/s Per Watt, More Is BetterWebP Image Encode 1.2.4Encode Settings: Quality 100, LosslessEPYC 4124P @ DDR5-5200smoke0.01890.03780.05670.07560.09450.0750.084
MinAvgMaxEPYC 4124P @ DDR5-520040046735141OpenBenchmarking.orgMegahertz, More Is BetterWebP Image Encode 1.2.4CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.727.133.4OpenBenchmarking.orgWatts, Fewer Is BetterWebP Image Encode 1.2.4CPU Power Consumption Monitor10203040501. EPYC 4124P @ DDR5-5200: Approximate power consumption of 74 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520038.950.559.3OpenBenchmarking.orgCelsius, Fewer Is BetterWebP Image Encode 1.2.4CPU Temperature Monitor1632486480
MinAvgMaxEPYC 4124P @ DDR5-520053.663.471.4OpenBenchmarking.orgWatts, Fewer Is BetterWebP Image Encode 1.2.4System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 174 Joules per run.
OpenBenchmarking.orgMP/s, More Is BetterWebP Image Encode 1.2.4Encode Settings: Quality 100, LosslessEPYC 4124P @ DDR5-5200smoke246810Min: 2.01 / Avg: 2.02 / Max: 2.031. (CC) gcc options: -fvisibility=hidden -O2 -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 1080p - Video Preset: Very FastEPYC 4124P @ DDR5-5200smoke1428425670SE +/- 0.05, N = 561.1961.21
OpenBenchmarking.orgFrames Per Second Per Watt, More Is Betteruvg266 0.4.1Video Input: Bosphorus 1080p - Video Preset: Very FastEPYC 4124P @ DDR5-52000.23240.46480.69720.92961.1621.033
MinAvgMaxEPYC 4124P @ DDR5-520040042795063OpenBenchmarking.orgMegahertz, More Is Betteruvg266 0.4.1CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520022.859.380.7OpenBenchmarking.orgWatts, Fewer Is Betteruvg266 0.4.1CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 154 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520058.874.378.5OpenBenchmarking.orgCelsius, Fewer Is Betteruvg266 0.4.1CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520055.398.0124.5OpenBenchmarking.orgWatts, Fewer Is Betteruvg266 0.4.1System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 255 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 1080p - Video Preset: Very FastEPYC 4124P @ DDR5-5200smoke1224364860Min: 61.07 / Avg: 61.19 / Max: 61.38

easyWave

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

OpenBenchmarking.orgSeconds, Fewer Is BettereasyWave r34Input: e2Asean Grid + BengkuluSept2007 Source - Time: 240EPYC 4124P @ DDR5-5200smoke246810SE +/- 0.019, N = 67.5567.5201. (CXX) g++ options: -O3 -fopenmp
MinAvgMaxEPYC 4124P @ DDR5-5200493650165140OpenBenchmarking.orgMegahertz, More Is BettereasyWave r34CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520025.235.946.2OpenBenchmarking.orgWatts, Fewer Is BettereasyWave r34CPU Power Consumption Monitor12243648601. EPYC 4124P @ DDR5-5200: Approximate power consumption of 72 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520045.447.850.0OpenBenchmarking.orgCelsius, Fewer Is BettereasyWave r34CPU Temperature Monitor1428425670
MinAvgMaxEPYC 4124P @ DDR5-520052.672.191.7OpenBenchmarking.orgWatts, Fewer Is BettereasyWave r34System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 144 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BettereasyWave r34Input: e2Asean Grid + BengkuluSept2007 Source - Time: 240EPYC 4124P @ DDR5-5200smoke3691215Min: 7.53 / Avg: 7.56 / Max: 7.651. (CXX) g++ options: -O3 -fopenmp

libavif avifenc

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 1.0Encoder Speed: 6EPYC 4124P @ DDR5-5200smoke3691215SE +/- 0.010, N = 59.4719.5071. (CXX) g++ options: -O3 -fPIC -lm
MinAvgMaxEPYC 4124P @ DDR5-520040046125142OpenBenchmarking.orgMegahertz, More Is Betterlibavif avifenc 1.0CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.053.980.1OpenBenchmarking.orgWatts, Fewer Is Betterlibavif avifenc 1.0CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 129 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520039.870.378.3OpenBenchmarking.orgCelsius, Fewer Is Betterlibavif avifenc 1.0CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520053.798.2122.9OpenBenchmarking.orgWatts, Fewer Is Betterlibavif avifenc 1.0System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 216 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 1.0Encoder Speed: 6EPYC 4124P @ DDR5-5200smoke3691215Min: 9.43 / Avg: 9.47 / Max: 9.491. (CXX) g++ options: -O3 -fPIC -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 1080p - Video Preset: Super FastEPYC 4124P @ DDR5-5200smoke1428425670SE +/- 0.04, N = 563.9663.90
OpenBenchmarking.orgFrames Per Second Per Watt, More Is Betteruvg266 0.4.1Video Input: Bosphorus 1080p - Video Preset: Super FastEPYC 4124P @ DDR5-52000.25020.50040.75061.00081.2511.112
MinAvgMaxEPYC 4124P @ DDR5-520040037375066OpenBenchmarking.orgMegahertz, More Is Betteruvg266 0.4.1CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.157.580.6OpenBenchmarking.orgWatts, Fewer Is Betteruvg266 0.4.1CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 127 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520043.972.078.5OpenBenchmarking.orgCelsius, Fewer Is Betteruvg266 0.4.1CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520055.7100.8124.7OpenBenchmarking.orgWatts, Fewer Is Betteruvg266 0.4.1System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 222 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 1080p - Video Preset: Super FastEPYC 4124P @ DDR5-5200smoke1326395265Min: 63.85 / Avg: 63.96 / Max: 64.07

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 12 - Input: Bosphorus 4KEPYC 4124P @ DDR5-5200smoke1530456075SE +/- 0.06, N = 568.8468.991. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 12 - Input: Bosphorus 4KEPYC 4124P @ DDR5-5200smoke0.36340.72681.09021.45361.8171.2561.615
MinAvgMaxEPYC 4124P @ DDR5-520040042695140OpenBenchmarking.orgMegahertz, More Is BetterSVT-AV1 2.0CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520020.754.879.3OpenBenchmarking.orgWatts, Fewer Is BetterSVT-AV1 2.0CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 132 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520049.968.175.1OpenBenchmarking.orgCelsius, Fewer Is BetterSVT-AV1 2.0CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.4104.5125.0OpenBenchmarking.orgWatts, Fewer Is BetterSVT-AV1 2.0System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 272 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 12 - Input: Bosphorus 4KEPYC 4124P @ DDR5-5200smoke1326395265Min: 68.67 / Avg: 68.84 / Max: 69.021. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

oneDNN

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.4Harness: IP Shapes 3D - Engine: CPUEPYC 4124P @ DDR5-5200smoke1.13452.2693.40354.5385.6725SE +/- 0.00492, N = 55.033675.04226MIN: 4.94MIN: 4.941. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
MinAvgMaxEPYC 4124P @ DDR5-520040039795124OpenBenchmarking.orgMegahertz, More Is BetteroneDNN 3.4CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.351.069.3OpenBenchmarking.orgWatts, Fewer Is BetteroneDNN 3.4CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 133 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520039.559.267.4OpenBenchmarking.orgCelsius, Fewer Is BetteroneDNN 3.4CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520053.889.9130.1OpenBenchmarking.orgWatts, Fewer Is BetteroneDNN 3.4System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 216 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.4Harness: IP Shapes 3D - Engine: CPUEPYC 4124P @ DDR5-5200smoke246810Min: 5.02 / Avg: 5.03 / Max: 5.051. (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 FastEPYC 4124P @ DDR5-5200smoke20406080100SE +/- 0.05, N = 675.9775.841. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterKvazaar 2.2Video Input: Bosphorus 1080p - Video Preset: Very FastEPYC 4124P @ DDR5-52000.31550.6310.94651.2621.57751.402
MinAvgMaxEPYC 4124P @ DDR5-520040045795011OpenBenchmarking.orgMegahertz, More Is BetterKvazaar 2.2CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.154.271.7OpenBenchmarking.orgWatts, Fewer Is BetterKvazaar 2.2CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 108 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520045.573.578.3OpenBenchmarking.orgCelsius, Fewer Is BetterKvazaar 2.2CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.987.2123.7OpenBenchmarking.orgWatts, Fewer Is BetterKvazaar 2.2System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 160 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 1080p - Video Preset: Very FastEPYC 4124P @ DDR5-5200smoke1530456075Min: 75.84 / Avg: 75.97 / Max: 76.131. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

TensorFlow

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 1 - Model: AlexNetEPYC 4124P @ DDR5-5200smoke48121620SE +/- 0.01, N = 514.5614.60
OpenBenchmarking.orgimages/sec Per Watt, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 1 - Model: AlexNetEPYC 4124P @ DDR5-52000.10040.20080.30120.40160.5020.446
MinAvgMaxEPYC 4124P @ DDR5-520040045635140OpenBenchmarking.orgMegahertz, More Is BetterTensorFlow 2.16.1CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.132.642.6OpenBenchmarking.orgWatts, Fewer Is BetterTensorFlow 2.16.1CPU Power Consumption Monitor12243648601. EPYC 4124P @ DDR5-5200: Approximate power consumption of 72 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520039.447.053.0OpenBenchmarking.orgCelsius, Fewer Is BetterTensorFlow 2.16.1CPU Temperature Monitor1530456075
MinAvgMaxEPYC 4124P @ DDR5-520054.472.187.8OpenBenchmarking.orgWatts, Fewer Is BetterTensorFlow 2.16.1System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 159 Joules per run.
OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 1 - Model: AlexNetEPYC 4124P @ DDR5-5200smoke48121620Min: 14.54 / Avg: 14.56 / Max: 14.6

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 FastEPYC 4124P @ DDR5-5200smoke20406080100SE +/- 0.06, N = 677.3576.66
OpenBenchmarking.orgFrames Per Second Per Watt, More Is Betteruvg266 0.4.1Video Input: Bosphorus 1080p - Video Preset: Ultra FastEPYC 4124P @ DDR5-52000.3060.6120.9181.2241.531.36
MinAvgMaxEPYC 4124P @ DDR5-520040046455050OpenBenchmarking.orgMegahertz, More Is Betteruvg266 0.4.1CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.456.980.4OpenBenchmarking.orgWatts, Fewer Is Betteruvg266 0.4.1CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 133 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520042.872.278.1OpenBenchmarking.orgCelsius, Fewer Is Betteruvg266 0.4.1CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.897.9124.3OpenBenchmarking.orgWatts, Fewer Is Betteruvg266 0.4.1System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 228 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 1080p - Video Preset: Ultra FastEPYC 4124P @ DDR5-5200smoke1530456075Min: 77.22 / Avg: 77.35 / Max: 77.63

RNNoise

OpenBenchmarking.orgSeconds, Fewer Is BetterRNNoise 0.2Input: 26 Minute Long Talking SampleEPYC 4124P @ DDR5-5200smoke246810SE +/- 0.016, N = 67.5257.5661. (CC) gcc options: -O2 -pedantic -fvisibility=hidden
MinAvgMaxEPYC 4124P @ DDR5-520040039995143OpenBenchmarking.orgMegahertz, More Is BetterRNNoise 0.2CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.426.633.3OpenBenchmarking.orgWatts, Fewer Is BetterRNNoise 0.2CPU Power Consumption Monitor10203040501. EPYC 4124P @ DDR5-5200: Approximate power consumption of 58 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520038.943.745.4OpenBenchmarking.orgCelsius, Fewer Is BetterRNNoise 0.2CPU Temperature Monitor1224364860
MinAvgMaxEPYC 4124P @ DDR5-520054.162.668.9OpenBenchmarking.orgWatts, Fewer Is BetterRNNoise 0.2System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 146 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterRNNoise 0.2Input: 26 Minute Long Talking SampleEPYC 4124P @ DDR5-5200smoke3691215Min: 7.49 / Avg: 7.52 / Max: 7.591. (CC) gcc options: -O2 -pedantic -fvisibility=hidden

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 8 - Input: Bosphorus 1080pEPYC 4124P @ DDR5-5200smoke20406080100SE +/- 0.05, N = 686.4786.321. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 8 - Input: Bosphorus 1080pEPYC 4124P @ DDR5-52000.36250.7251.08751.451.81251.611
MinAvgMaxEPYC 4124P @ DDR5-5200493849935139OpenBenchmarking.orgMegahertz, More Is BetterSVT-AV1 2.0CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520022.453.780.1OpenBenchmarking.orgWatts, Fewer Is BetterSVT-AV1 2.0CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 107 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520055.471.277.0OpenBenchmarking.orgCelsius, Fewer Is BetterSVT-AV1 2.0CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.995.5125.1OpenBenchmarking.orgWatts, Fewer Is BetterSVT-AV1 2.0System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 207 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 8 - Input: Bosphorus 1080pEPYC 4124P @ DDR5-5200smoke1632486480Min: 86.35 / Avg: 86.47 / Max: 86.641. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Google Draco

OpenBenchmarking.orgms, Fewer Is BetterGoogle Draco 1.5.6Model: Church FacadeEPYC 4124P @ DDR5-5200smoke12002400360048006000SE +/- 12.94, N = 6570856931. (CXX) g++ options: -O3
MinAvgMaxEPYC 4124P @ DDR5-520040039665144OpenBenchmarking.orgMegahertz, More Is BetterGoogle Draco 1.5.6CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.724.429.3OpenBenchmarking.orgWatts, Fewer Is BetterGoogle Draco 1.5.6CPU Power Consumption Monitor9182736451. EPYC 4124P @ DDR5-5200: Approximate power consumption of 53 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520045.548.353.0OpenBenchmarking.orgCelsius, Fewer Is BetterGoogle Draco 1.5.6CPU Temperature Monitor1530456075
MinAvgMaxEPYC 4124P @ DDR5-520052.960.670.5OpenBenchmarking.orgWatts, Fewer Is BetterGoogle Draco 1.5.6System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 131 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterGoogle Draco 1.5.6Model: Church FacadeEPYC 4124P @ DDR5-5200smoke10002000300040005000Min: 5657 / Avg: 5708.33 / Max: 57381. (CXX) g++ options: -O3

oneDNN

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.4Harness: Convolution Batch Shapes Auto - Engine: CPUEPYC 4124P @ DDR5-5200smoke3691215SE +/- 0.00783, N = 79.055469.03289MIN: 8.91MIN: 8.911. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
MinAvgMaxEPYC 4124P @ DDR5-520040038044942OpenBenchmarking.orgMegahertz, More Is BetteroneDNN 3.4CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520026.738.753.4OpenBenchmarking.orgWatts, Fewer Is BetteroneDNN 3.4CPU Power Consumption Monitor15304560751. EPYC 4124P @ DDR5-5200: Approximate power consumption of 66 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520042.043.945.1OpenBenchmarking.orgCelsius, Fewer Is BetteroneDNN 3.4CPU Temperature Monitor1224364860
MinAvgMaxEPYC 4124P @ DDR5-520052.979.9100.5OpenBenchmarking.orgWatts, Fewer Is BetteroneDNN 3.4System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 137 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.4Harness: Convolution Batch Shapes Auto - Engine: CPUEPYC 4124P @ DDR5-5200smoke3691215Min: 9.04 / Avg: 9.06 / Max: 9.091. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

SVT-HEVC

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-HEVC CPU-based multi-threaded video encoder for the HEVC / H.265 video format with a sample 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 1080pEPYC 4124P @ DDR5-5200smoke20406080100SE +/- 0.07, N = 693.0192.281. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-HEVC 1.5.0Tuning: 7 - Input: Bosphorus 1080pEPYC 4124P @ DDR5-52000.38410.76821.15231.53641.92051.707
MinAvgMaxEPYC 4124P @ DDR5-520040038225020OpenBenchmarking.orgMegahertz, More Is BetterSVT-HEVC 1.5.0CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520035.454.581.6OpenBenchmarking.orgWatts, Fewer Is BetterSVT-HEVC 1.5.0CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 109 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520067.674.579.0OpenBenchmarking.orgCelsius, Fewer Is BetterSVT-HEVC 1.5.0CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520055.1104.7127.0OpenBenchmarking.orgWatts, Fewer Is BetterSVT-HEVC 1.5.0System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 209 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 7 - Input: Bosphorus 1080pEPYC 4124P @ DDR5-5200smoke20406080100Min: 92.75 / Avg: 93.01 / Max: 93.231. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

Algebraic Multi-Grid Benchmark

AMG is a parallel algebraic multigrid solver for linear systems arising from problems on unstructured grids. The driver provided with AMG builds linear systems for various 3-dimensional problems. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFigure Of Merit, More Is BetterAlgebraic Multi-Grid Benchmark 1.2EPYC 4124P @ DDR5-5200smoke80M160M240M320M400MSE +/- 168306.70, N = 63528494173529630001. (CC) gcc options: -lparcsr_ls -lparcsr_mv -lseq_mv -lIJ_mv -lkrylov -lHYPRE_utilities -lm -fopenmp -lmpi
OpenBenchmarking.orgFigure Of Merit Per Watt, More Is BetterAlgebraic Multi-Grid Benchmark 1.2EPYC 4124P @ DDR5-52002M4M6M8M10M8630818.00
MinAvgMaxEPYC 4124P @ DDR5-520040046625140OpenBenchmarking.orgMegahertz, More Is BetterAlgebraic Multi-Grid Benchmark 1.2CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.340.956.2OpenBenchmarking.orgWatts, Fewer Is BetterAlgebraic Multi-Grid Benchmark 1.2CPU Power Consumption Monitor16324864801. EPYC 4124P @ DDR5-5200: Approximate power consumption of 82 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520040.850.256.4OpenBenchmarking.orgCelsius, Fewer Is BetterAlgebraic Multi-Grid Benchmark 1.2CPU Temperature Monitor1632486480
MinAvgMaxEPYC 4124P @ DDR5-520054.182.6104.6OpenBenchmarking.orgWatts, Fewer Is BetterAlgebraic Multi-Grid Benchmark 1.2System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 165 Joules per run.
OpenBenchmarking.orgFigure Of Merit, More Is BetterAlgebraic Multi-Grid Benchmark 1.2EPYC 4124P @ DDR5-5200smoke60M120M180M240M300MMin: 352146300 / Avg: 352849416.67 / Max: 3532379001. (CC) gcc options: -lparcsr_ls -lparcsr_mv -lseq_mv -lIJ_mv -lkrylov -lHYPRE_utilities -lm -fopenmp -lmpi

srsRAN Project

OpenBenchmarking.orgMbps, More Is BettersrsRAN Project 23.10.1-20240325Test: PDSCH Processor Benchmark, Throughput TotalEPYC 4124P @ DDR5-5200smoke9001800270036004500SE +/- 3.81, N = 74054.64061.91. (CXX) g++ options: -O3 -march=native -mavx2 -mavx -msse4.1 -mfma -mavx512f -mavx512cd -mavx512bw -mavx512dq -fno-trapping-math -fno-math-errno -ldl
OpenBenchmarking.orgMbps Per Watt, More Is BettersrsRAN Project 23.10.1-20240325Test: PDSCH Processor Benchmark, Throughput TotalEPYC 4124P @ DDR5-52002040608010082.41
MinAvgMaxEPYC 4124P @ DDR5-520040037885122OpenBenchmarking.orgMegahertz, More Is BettersrsRAN Project 23.10.1-20240325CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520020.149.271.6OpenBenchmarking.orgWatts, Fewer Is BettersrsRAN Project 23.10.1-20240325CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 77 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520050.968.274.5OpenBenchmarking.orgCelsius, Fewer Is BettersrsRAN Project 23.10.1-20240325CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.292.3118.3OpenBenchmarking.orgWatts, Fewer Is BettersrsRAN Project 23.10.1-20240325System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 158 Joules per run.
OpenBenchmarking.orgMbps, More Is BettersrsRAN Project 23.10.1-20240325Test: PDSCH Processor Benchmark, Throughput TotalEPYC 4124P @ DDR5-5200smoke7001400210028003500Min: 4040.2 / Avg: 4054.57 / Max: 4068.51. (CXX) g++ options: -O3 -march=native -mavx2 -mavx -msse4.1 -mfma -mavx512f -mavx512cd -mavx512bw -mavx512dq -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 8.4.0EPYC 4124P @ DDR5-5200smoke1.33072.66143.99215.32286.6535SE +/- 0.012, N = 75.8805.914
MinAvgMaxEPYC 4124P @ DDR5-520040039075141OpenBenchmarking.orgMegahertz, More Is BetterGNU Octave Benchmark 8.4.0CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.525.531.6OpenBenchmarking.orgWatts, Fewer Is BetterGNU Octave Benchmark 8.4.0CPU Power Consumption Monitor9182736451. EPYC 4124P @ DDR5-5200: Approximate power consumption of 40 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520040.047.455.0OpenBenchmarking.orgCelsius, Fewer Is BetterGNU Octave Benchmark 8.4.0CPU Temperature Monitor1530456075
MinAvgMaxEPYC 4124P @ DDR5-520053.864.273.9OpenBenchmarking.orgWatts, Fewer Is BetterGNU Octave Benchmark 8.4.0System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 101 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterGNU Octave Benchmark 8.4.0EPYC 4124P @ DDR5-5200smoke246810Min: 5.85 / Avg: 5.88 / Max: 5.94

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: DefaultEPYC 4124P @ DDR5-5200smoke61218243023.2023.44
MinAvgMaxEPYC 4124P @ DDR5-5200494150625141smoke493950455140OpenBenchmarking.orgMegahertz, More Is BetterTimed CPython Compilation 3.10.6CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520021.347.175.8smoke14.846.874.7OpenBenchmarking.orgWatts, Fewer Is BetterTimed CPython Compilation 3.10.6CPU Power Consumption Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520044.561.075.1smoke45.061.076.3OpenBenchmarking.orgCelsius, Fewer Is BetterTimed CPython Compilation 3.10.6CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.685.7120.3smoke55.284.2119.7OpenBenchmarking.orgWatts, Fewer Is BetterTimed CPython Compilation 3.10.6System Power Consumption Monitor4080120160200

libavif avifenc

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 1.0Encoder Speed: 10, LosslessEPYC 4124P @ DDR5-5200smoke1.28572.57143.85715.14286.4285SE +/- 0.006, N = 75.7105.7141. (CXX) g++ options: -O3 -fPIC -lm
MinAvgMaxEPYC 4124P @ DDR5-520040038895140OpenBenchmarking.orgMegahertz, More Is Betterlibavif avifenc 1.0CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.540.563.4OpenBenchmarking.orgWatts, Fewer Is Betterlibavif avifenc 1.0CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 69 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520041.966.677.3OpenBenchmarking.orgCelsius, Fewer Is Betterlibavif avifenc 1.0CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520055.474.3120.2OpenBenchmarking.orgWatts, Fewer Is Betterlibavif avifenc 1.0System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 127 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 1.0Encoder Speed: 10, LosslessEPYC 4124P @ DDR5-5200smoke246810Min: 5.68 / Avg: 5.71 / Max: 5.721. (CXX) g++ options: -O3 -fPIC -lm

Google Draco

OpenBenchmarking.orgms, Fewer Is BetterGoogle Draco 1.5.6Model: LionEPYC 4124P @ DDR5-5200smoke9001800270036004500SE +/- 5.86, N = 7425342401. (CXX) g++ options: -O3
MinAvgMaxEPYC 4124P @ DDR5-520040041515141OpenBenchmarking.orgMegahertz, More Is BetterGoogle Draco 1.5.6CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520018.923.628.0OpenBenchmarking.orgWatts, Fewer Is BetterGoogle Draco 1.5.6CPU Power Consumption Monitor9182736451. EPYC 4124P @ DDR5-5200: Approximate power consumption of 37 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520042.544.547.3OpenBenchmarking.orgCelsius, Fewer Is BetterGoogle Draco 1.5.6CPU Temperature Monitor1428425670
MinAvgMaxEPYC 4124P @ DDR5-520054.259.563.6OpenBenchmarking.orgWatts, Fewer Is BetterGoogle Draco 1.5.6System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 102 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterGoogle Draco 1.5.6Model: LionEPYC 4124P @ DDR5-5200smoke7001400210028003500Min: 4229 / Avg: 4253.14 / Max: 42761. (CXX) g++ options: -O3

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 FastEPYC 4124P @ DDR5-5200smoke20406080100SE +/- 0.12, N = 692.9192.781. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterKvazaar 2.2Video Input: Bosphorus 1080p - Video Preset: Super FastEPYC 4124P @ DDR5-52000.3870.7741.1611.5481.9351.72
MinAvgMaxEPYC 4124P @ DDR5-520040038174971OpenBenchmarking.orgMegahertz, More Is BetterKvazaar 2.2CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.554.081.6OpenBenchmarking.orgWatts, Fewer Is BetterKvazaar 2.2CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 108 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520043.070.078.5OpenBenchmarking.orgCelsius, Fewer Is BetterKvazaar 2.2CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.9107.4125.5OpenBenchmarking.orgWatts, Fewer Is BetterKvazaar 2.2System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 215 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 1080p - Video Preset: Super FastEPYC 4124P @ DDR5-5200smoke20406080100Min: 92.62 / Avg: 92.91 / Max: 93.331. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

srsRAN Project

OpenBenchmarking.orgMbps, More Is BettersrsRAN Project 23.10.1-20240325Test: PUSCH Processor Benchmark, Throughput TotalEPYC 4124P @ DDR5-5200smoke2004006008001000SE +/- 2.54, N = 6881.5852.8MIN: 613.1 / MAX: 888.5MIN: 584.81. (CXX) g++ options: -O3 -march=native -mavx2 -mavx -msse4.1 -mfma -mavx512f -mavx512cd -mavx512bw -mavx512dq -fno-trapping-math -fno-math-errno -ldl
OpenBenchmarking.orgMbps Per Watt, More Is BettersrsRAN Project 23.10.1-20240325Test: PUSCH Processor Benchmark, Throughput TotalEPYC 4124P @ DDR5-520051015202518.35
MinAvgMaxEPYC 4124P @ DDR5-520040037605110OpenBenchmarking.orgMegahertz, More Is BettersrsRAN Project 23.10.1-20240325CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.348.068.8OpenBenchmarking.orgWatts, Fewer Is BettersrsRAN Project 23.10.1-20240325CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 88 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520042.566.975.5OpenBenchmarking.orgCelsius, Fewer Is BettersrsRAN Project 23.10.1-20240325CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520055.487.3122.1OpenBenchmarking.orgWatts, Fewer Is BettersrsRAN Project 23.10.1-20240325System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 175 Joules per run.
OpenBenchmarking.orgMbps, More Is BettersrsRAN Project 23.10.1-20240325Test: PUSCH Processor Benchmark, Throughput TotalEPYC 4124P @ DDR5-5200smoke150300450600750Min: 874 / Avg: 881.53 / Max: 888.51. (CXX) g++ options: -O3 -march=native -mavx2 -mavx -msse4.1 -mfma -mavx512f -mavx512cd -mavx512bw -mavx512dq -fno-trapping-math -fno-math-errno -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: Ultra FastEPYC 4124P @ DDR5-5200smoke306090120150SE +/- 0.09, N = 8126.17126.241. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterKvazaar 2.2Video Input: Bosphorus 1080p - Video Preset: Ultra FastEPYC 4124P @ DDR5-52000.57131.14261.71392.28522.85652.539
MinAvgMaxEPYC 4124P @ DDR5-520040038565137OpenBenchmarking.orgMegahertz, More Is BetterKvazaar 2.2CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.449.776.7OpenBenchmarking.orgWatts, Fewer Is BetterKvazaar 2.2CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 75 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520043.571.178.0OpenBenchmarking.orgCelsius, Fewer Is BetterKvazaar 2.2CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520055.392.1124.4OpenBenchmarking.orgWatts, Fewer Is BetterKvazaar 2.2System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 138 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 1080p - Video Preset: Ultra FastEPYC 4124P @ DDR5-5200smoke20406080100Min: 125.7 / Avg: 126.17 / Max: 126.561. (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: Visual Quality Optimized - Input: Bosphorus 1080pEPYC 4124P @ DDR5-5200smoke306090120150SE +/- 0.47, N = 7127.23123.931. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-VP9 0.3Tuning: Visual Quality Optimized - Input: Bosphorus 1080pEPYC 4124P @ DDR5-52000.61941.23881.85822.47763.0972.753
MinAvgMaxEPYC 4124P @ DDR5-520040033275082OpenBenchmarking.orgMegahertz, More Is BetterSVT-VP9 0.3CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.846.265.7OpenBenchmarking.orgWatts, Fewer Is BetterSVT-VP9 0.3CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 73 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520045.667.374.8OpenBenchmarking.orgCelsius, Fewer Is BetterSVT-VP9 0.3CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.489.5122.5OpenBenchmarking.orgWatts, Fewer Is BetterSVT-VP9 0.3System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 128 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: Visual Quality Optimized - Input: Bosphorus 1080pEPYC 4124P @ DDR5-5200smoke20406080100Min: 124.42 / Avg: 127.23 / Max: 127.961. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

TensorFlow

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 1 - Model: GoogLeNetEPYC 4124P @ DDR5-5200smoke918273645SE +/- 0.04, N = 739.3839.04
OpenBenchmarking.orgimages/sec Per Watt, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 1 - Model: GoogLeNetEPYC 4124P @ DDR5-52000.2770.5540.8311.1081.3851.231
MinAvgMaxEPYC 4124P @ DDR5-520040030635141OpenBenchmarking.orgMegahertz, More Is BetterTensorFlow 2.16.1CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.832.042.3OpenBenchmarking.orgWatts, Fewer Is BetterTensorFlow 2.16.1CPU Power Consumption Monitor12243648601. EPYC 4124P @ DDR5-5200: Approximate power consumption of 55 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520039.148.554.5OpenBenchmarking.orgCelsius, Fewer Is BetterTensorFlow 2.16.1CPU Temperature Monitor1530456075
MinAvgMaxEPYC 4124P @ DDR5-520053.872.497.9OpenBenchmarking.orgWatts, Fewer Is BetterTensorFlow 2.16.1System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 114 Joules per run.
OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 1 - Model: GoogLeNetEPYC 4124P @ DDR5-5200smoke816243240Min: 39.23 / Avg: 39.38 / Max: 39.58

WebP Image Encode

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

OpenBenchmarking.orgMP/s, More Is BetterWebP Image Encode 1.2.4Encode Settings: Quality 100, Highest CompressionEPYC 4124P @ DDR5-5200smoke1.13852.2773.41554.5545.6925SE +/- 0.01, N = 75.055.061. (CC) gcc options: -fvisibility=hidden -O2 -lm
OpenBenchmarking.orgMP/s Per Watt, More Is BetterWebP Image Encode 1.2.4Encode Settings: Quality 100, Highest CompressionEPYC 4124P @ DDR5-52000.0450.090.1350.180.2250.2
MinAvgMaxEPYC 4124P @ DDR5-520040033625141OpenBenchmarking.orgMegahertz, More Is BetterWebP Image Encode 1.2.4CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.525.229.5OpenBenchmarking.orgWatts, Fewer Is BetterWebP Image Encode 1.2.4CPU Power Consumption Monitor9182736451. EPYC 4124P @ DDR5-5200: Approximate power consumption of 40 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520038.952.661.8OpenBenchmarking.orgCelsius, Fewer Is BetterWebP Image Encode 1.2.4CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520053.563.273.4OpenBenchmarking.orgWatts, Fewer Is BetterWebP Image Encode 1.2.4System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 90 Joules per run.
OpenBenchmarking.orgMP/s, More Is BetterWebP Image Encode 1.2.4Encode Settings: Quality 100, Highest CompressionEPYC 4124P @ DDR5-5200smoke246810Min: 5.01 / Avg: 5.05 / Max: 5.071. (CC) gcc options: -fvisibility=hidden -O2 -lm

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 ProteinEPYC 4124P @ DDR5-5200smoke1.03912.07823.11734.15645.1955SE +/- 0.003, N = 84.6184.5851. (CXX) g++ options: -O3 -lm -ldl
OpenBenchmarking.orgns/day Per Watt, More Is BetterLAMMPS Molecular Dynamics Simulator 23Jun2022Model: Rhodopsin ProteinEPYC 4124P @ DDR5-52000.02540.05080.07620.10160.1270.113
MinAvgMaxEPYC 4124P @ DDR5-520040033715134OpenBenchmarking.orgMegahertz, More Is BetterLAMMPS Molecular Dynamics Simulator 23Jun2022CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.240.854.8OpenBenchmarking.orgWatts, Fewer Is BetterLAMMPS Molecular Dynamics Simulator 23Jun2022CPU Power Consumption Monitor15304560751. EPYC 4124P @ DDR5-5200: Approximate power consumption of 56 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520040.460.767.9OpenBenchmarking.orgCelsius, Fewer Is BetterLAMMPS Molecular Dynamics Simulator 23Jun2022CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.578.1113.8OpenBenchmarking.orgWatts, Fewer Is BetterLAMMPS Molecular Dynamics Simulator 23Jun2022System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 107 Joules per run.
OpenBenchmarking.orgns/day, More Is BetterLAMMPS Molecular Dynamics Simulator 23Jun2022Model: Rhodopsin ProteinEPYC 4124P @ DDR5-5200smoke246810Min: 4.61 / Avg: 4.62 / Max: 4.631. (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: VMAF Optimized - Input: Bosphorus 1080pEPYC 4124P @ DDR5-5200smoke306090120150SE +/- 0.15, N = 8154.14154.061. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-VP9 0.3Tuning: VMAF Optimized - Input: Bosphorus 1080pEPYC 4124P @ DDR5-52000.8241.6482.4723.2964.123.662
MinAvgMaxEPYC 4124P @ DDR5-520040039825134OpenBenchmarking.orgMegahertz, More Is BetterSVT-VP9 0.3CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520014.542.162.9OpenBenchmarking.orgWatts, Fewer Is BetterSVT-VP9 0.3CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 68 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520045.064.972.5OpenBenchmarking.orgCelsius, Fewer Is BetterSVT-VP9 0.3CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.688.9120.9OpenBenchmarking.orgWatts, Fewer Is BetterSVT-VP9 0.3System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 144 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: VMAF Optimized - Input: Bosphorus 1080pEPYC 4124P @ DDR5-5200smoke306090120150Min: 153.29 / Avg: 154.14 / Max: 154.651. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080pEPYC 4124P @ DDR5-5200smoke306090120150SE +/- 0.23, N = 8155.85155.981. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-VP9 0.3Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080pEPYC 4124P @ DDR5-52000.80661.61322.41983.22644.0333.585
MinAvgMaxEPYC 4124P @ DDR5-520040025285106OpenBenchmarking.orgMegahertz, More Is BetterSVT-VP9 0.3CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.643.563.7OpenBenchmarking.orgWatts, Fewer Is BetterSVT-VP9 0.3CPU Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 60 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520043.965.672.9OpenBenchmarking.orgCelsius, Fewer Is BetterSVT-VP9 0.3CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520055.384.4122.1OpenBenchmarking.orgWatts, Fewer Is BetterSVT-VP9 0.3System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 116 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080pEPYC 4124P @ DDR5-5200smoke306090120150Min: 155.03 / Avg: 155.85 / Max: 157.141. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

LULESH

LULESH is the Livermore Unstructured Lagrangian Explicit Shock Hydrodynamics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgz/s, More Is BetterLULESH 2.0.3EPYC 4124P @ DDR5-5200smoke400800120016002000SE +/- 3.30, N = 81832.991846.401. (CXX) g++ options: -O3 -fopenmp -lm -lmpi_cxx -lmpi
OpenBenchmarking.orgz/s Per Watt, More Is BetterLULESH 2.0.3EPYC 4124P @ DDR5-52002040608010078.48
MinAvgMaxEPYC 4124P @ DDR5-520040046545141OpenBenchmarking.orgMegahertz, More Is BetterLULESH 2.0.3CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520015.923.427.9OpenBenchmarking.orgWatts, Fewer Is BetterLULESH 2.0.3CPU Power Consumption Monitor9182736451. EPYC 4124P @ DDR5-5200: Approximate power consumption of 38 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520038.943.045.5OpenBenchmarking.orgCelsius, Fewer Is BetterLULESH 2.0.3CPU Temperature Monitor1224364860
MinAvgMaxEPYC 4124P @ DDR5-520053.860.868.3OpenBenchmarking.orgWatts, Fewer Is BetterLULESH 2.0.3System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 99 Joules per run.
OpenBenchmarking.orgz/s, More Is BetterLULESH 2.0.3EPYC 4124P @ DDR5-5200smoke30060090012001500Min: 1822.31 / Avg: 1832.99 / Max: 1851.561. (CXX) g++ options: -O3 -fopenmp -lm -lmpi_cxx -lmpi

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 1080pEPYC 4124P @ DDR5-5200smoke4080120160200SE +/- 0.16, N = 9192.92192.001. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-HEVC 1.5.0Tuning: 10 - Input: Bosphorus 1080pEPYC 4124P @ DDR5-52001.06072.12143.18214.24285.30354.714
MinAvgMaxEPYC 4124P @ DDR5-520040027085062OpenBenchmarking.orgMegahertz, More Is BetterSVT-HEVC 1.5.0CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.340.957.4OpenBenchmarking.orgWatts, Fewer Is BetterSVT-HEVC 1.5.0CPU Power Consumption Monitor16324864801. EPYC 4124P @ DDR5-5200: Approximate power consumption of 55 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520045.567.873.9OpenBenchmarking.orgCelsius, Fewer Is BetterSVT-HEVC 1.5.0CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520056.376.9124.5OpenBenchmarking.orgWatts, Fewer Is BetterSVT-HEVC 1.5.0System Power Consumption Monitor40801201602001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 103 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 10 - Input: Bosphorus 1080pEPYC 4124P @ DDR5-5200smoke4080120160200Min: 192.06 / Avg: 192.92 / Max: 193.741. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

oneDNN

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.4Harness: Deconvolution Batch shapes_3d - Engine: CPUEPYC 4124P @ DDR5-5200smoke246810SE +/- 0.00081, N = 97.512867.51345MIN: 7.5MIN: 7.51. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
MinAvgMaxEPYC 4124P @ DDR5-520040031244944OpenBenchmarking.orgMegahertz, More Is BetteroneDNN 3.4CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520020.835.140.6OpenBenchmarking.orgWatts, Fewer Is BetteroneDNN 3.4CPU Power Consumption Monitor11223344551. EPYC 4124P @ DDR5-5200: Approximate power consumption of 39 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520045.348.251.5OpenBenchmarking.orgCelsius, Fewer Is BetteroneDNN 3.4CPU Temperature Monitor1530456075
MinAvgMaxEPYC 4124P @ DDR5-520052.876.799.1OpenBenchmarking.orgWatts, Fewer Is BetteroneDNN 3.4System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 94 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.4Harness: Deconvolution Batch shapes_3d - Engine: CPUEPYC 4124P @ DDR5-5200smoke3691215Min: 7.51 / Avg: 7.51 / Max: 7.521. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

srsRAN Project

OpenBenchmarking.orgMbps, More Is BettersrsRAN Project 23.10.1-20240325Test: PDSCH Processor Benchmark, Throughput ThreadEPYC 4124P @ DDR5-5200smoke2004006008001000SE +/- 5.88, N = 91023.81039.41. (CXX) g++ options: -O3 -march=native -mavx2 -mavx -msse4.1 -mfma -mavx512f -mavx512cd -mavx512bw -mavx512dq -fno-trapping-math -fno-math-errno -ldl
OpenBenchmarking.orgMbps Per Watt, More Is BettersrsRAN Project 23.10.1-20240325Test: PDSCH Processor Benchmark, Throughput ThreadEPYC 4124P @ DDR5-5200102030405043.54
MinAvgMaxEPYC 4124P @ DDR5-520040037935140OpenBenchmarking.orgMegahertz, More Is BettersrsRAN Project 23.10.1-20240325CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520020.323.529.4OpenBenchmarking.orgWatts, Fewer Is BettersrsRAN Project 23.10.1-20240325CPU Power Consumption Monitor9182736451. EPYC 4124P @ DDR5-5200: Approximate power consumption of 29 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520045.051.660.6OpenBenchmarking.orgCelsius, Fewer Is BettersrsRAN Project 23.10.1-20240325CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520053.260.573.3OpenBenchmarking.orgWatts, Fewer Is BettersrsRAN Project 23.10.1-20240325System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 74 Joules per run.
OpenBenchmarking.orgMbps, More Is BettersrsRAN Project 23.10.1-20240325Test: PDSCH Processor Benchmark, Throughput ThreadEPYC 4124P @ DDR5-5200smoke2004006008001000Min: 994.5 / Avg: 1023.76 / Max: 1043.31. (CXX) g++ options: -O3 -march=native -mavx2 -mavx -msse4.1 -mfma -mavx512f -mavx512cd -mavx512bw -mavx512dq -fno-trapping-math -fno-math-errno -ldl

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 13 - Input: Bosphorus 1080pEPYC 4124P @ DDR5-5200smoke80160240320400SE +/- 4.04, N = 15384.17319.291. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 13 - Input: Bosphorus 1080pEPYC 4124P @ DDR5-5200369121512.35
MinAvgMaxEPYC 4124P @ DDR5-520040040725141OpenBenchmarking.orgMegahertz, More Is BetterSVT-AV1 2.0CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520015.631.136.7OpenBenchmarking.orgWatts, Fewer Is BetterSVT-AV1 2.0CPU Power Consumption Monitor10203040501. EPYC 4124P @ DDR5-5200: Approximate power consumption of 31 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520042.660.665.6OpenBenchmarking.orgCelsius, Fewer Is BetterSVT-AV1 2.0CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.261.399.5OpenBenchmarking.orgWatts, Fewer Is BetterSVT-AV1 2.0System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 61 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 13 - Input: Bosphorus 1080pEPYC 4124P @ DDR5-5200smoke70140210280350Min: 328.28 / Avg: 384.17 / Max: 391.941. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

WebP Image Encode

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

OpenBenchmarking.orgMP/s, More Is BetterWebP Image Encode 1.2.4Encode Settings: Quality 100EPYC 4124P @ DDR5-5200smoke48121620SE +/- 0.05, N = 1515.7315.791. (CC) gcc options: -fvisibility=hidden -O2 -lm
OpenBenchmarking.orgMP/s Per Watt, More Is BetterWebP Image Encode 1.2.4Encode Settings: Quality 100EPYC 4124P @ DDR5-52000.1670.3340.5010.6680.8350.742
MinAvgMaxEPYC 4124P @ DDR5-520040031115141OpenBenchmarking.orgMegahertz, More Is BetterWebP Image Encode 1.2.4CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.121.224.0OpenBenchmarking.orgWatts, Fewer Is BetterWebP Image Encode 1.2.4CPU Power Consumption Monitor8162432401. EPYC 4124P @ DDR5-5200: Approximate power consumption of 24 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520039.946.252.5OpenBenchmarking.orgCelsius, Fewer Is BetterWebP Image Encode 1.2.4CPU Temperature Monitor1530456075
MinAvgMaxEPYC 4124P @ DDR5-520052.858.172.1OpenBenchmarking.orgWatts, Fewer Is BetterWebP Image Encode 1.2.4System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 66 Joules per run.
OpenBenchmarking.orgMP/s, More Is BetterWebP Image Encode 1.2.4Encode Settings: Quality 100EPYC 4124P @ DDR5-5200smoke48121620Min: 15.08 / Avg: 15.73 / Max: 15.821. (CC) gcc options: -fvisibility=hidden -O2 -lm

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 12 - Input: Bosphorus 1080pEPYC 4124P @ DDR5-5200smoke70140210280350SE +/- 0.40, N = 11313.43314.711. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 12 - Input: Bosphorus 1080pEPYC 4124P @ DDR5-520036912159.095
MinAvgMaxEPYC 4124P @ DDR5-520040019134941OpenBenchmarking.orgMegahertz, More Is BetterSVT-AV1 2.0CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.434.536.6OpenBenchmarking.orgWatts, Fewer Is BetterSVT-AV1 2.0CPU Power Consumption Monitor10203040501. EPYC 4124P @ DDR5-5200: Approximate power consumption of 38 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520044.463.867.8OpenBenchmarking.orgCelsius, Fewer Is BetterSVT-AV1 2.0CPU Temperature Monitor20406080100
MinAvgMaxEPYC 4124P @ DDR5-520054.956.662.6OpenBenchmarking.orgWatts, Fewer Is BetterSVT-AV1 2.0System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 62 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 12 - Input: Bosphorus 1080pEPYC 4124P @ DDR5-5200smoke60120180240300Min: 310.2 / Avg: 313.43 / Max: 314.41. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

WebP Image Encode

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

OpenBenchmarking.orgMP/s, More Is BetterWebP Image Encode 1.2.4Encode Settings: DefaultEPYC 4124P @ DDR5-5200smoke612182430SE +/- 0.02, N = 1525.5825.641. (CC) gcc options: -fvisibility=hidden -O2 -lm
OpenBenchmarking.orgMP/s Per Watt, More Is BetterWebP Image Encode 1.2.4Encode Settings: DefaultEPYC 4124P @ DDR5-52000.29450.5890.88351.1781.47251.309
MinAvgMaxEPYC 4124P @ DDR5-520040025265141OpenBenchmarking.orgMegahertz, More Is BetterWebP Image Encode 1.2.4CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520016.819.522.5OpenBenchmarking.orgWatts, Fewer Is BetterWebP Image Encode 1.2.4CPU Power Consumption Monitor6121824301. EPYC 4124P @ DDR5-5200: Approximate power consumption of 17 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520043.947.055.5OpenBenchmarking.orgCelsius, Fewer Is BetterWebP Image Encode 1.2.4CPU Temperature Monitor1530456075
MinAvgMaxEPYC 4124P @ DDR5-520052.857.467.1OpenBenchmarking.orgWatts, Fewer Is BetterWebP Image Encode 1.2.4System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 46 Joules per run.
OpenBenchmarking.orgMP/s, More Is BetterWebP Image Encode 1.2.4Encode Settings: DefaultEPYC 4124P @ DDR5-5200smoke612182430Min: 25.32 / Avg: 25.58 / Max: 25.641. (CC) gcc options: -fvisibility=hidden -O2 -lm

HeFFTe - Highly Efficient FFT for Exascale

HeFFTe is the Highly Efficient FFT for Exascale software developed as part of the Exascale Computing Project. This test profile uses HeFFTe's built-in speed benchmarks under a variety of configuration options and currently catering to CPU/processor testing. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOP/s, More Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.4Test: r2c - Backend: FFTW - Precision: double - X Y Z: 128EPYC 4124P @ DDR5-5200smoke48121620SE +/- 0.18, N = 1517.2516.791. (CXX) g++ options: -O3
OpenBenchmarking.orgGFLOP/s Per Watt, More Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.4Test: r2c - Backend: FFTW - Precision: double - X Y Z: 128EPYC 4124P @ DDR5-52000.21060.42120.63180.84241.0530.936
MinAvgMaxEPYC 4124P @ DDR5-520040030494942OpenBenchmarking.orgMegahertz, More Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.4CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520017.418.419.8OpenBenchmarking.orgWatts, Fewer Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.4CPU Power Consumption Monitor6121824301. EPYC 4124P @ DDR5-5200: Approximate power consumption of 15 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520036.937.438.3OpenBenchmarking.orgCelsius, Fewer Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.4CPU Temperature Monitor1122334455
MinAvgMaxEPYC 4124P @ DDR5-520052.955.662.6OpenBenchmarking.orgWatts, Fewer Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.4System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 48 Joules per run.
OpenBenchmarking.orgGFLOP/s, More Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.4Test: r2c - Backend: FFTW - Precision: double - X Y Z: 128EPYC 4124P @ DDR5-5200smoke48121620Min: 16.39 / Avg: 17.25 / Max: 18.131. (CXX) g++ options: -O3

OpenBenchmarking.orgGFLOP/s, More Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.4Test: r2c - Backend: FFTW - Precision: float - X Y Z: 128EPYC 4124P @ DDR5-5200smoke1020304050SE +/- 1.04, N = 1544.0935.981. (CXX) g++ options: -O3
OpenBenchmarking.orgGFLOP/s Per Watt, More Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.4Test: r2c - Backend: FFTW - Precision: float - X Y Z: 128EPYC 4124P @ DDR5-52000.55491.10981.66472.21962.77452.466
MinAvgMaxEPYC 4124P @ DDR5-520040032894942OpenBenchmarking.orgMegahertz, More Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.4CPU Peak Freq (Highest CPU Core Frequency) Monitor13002600390052006500
MinAvgMaxEPYC 4124P @ DDR5-520015.717.918.9OpenBenchmarking.orgWatts, Fewer Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.4CPU Power Consumption Monitor6121824301. EPYC 4124P @ DDR5-5200: Approximate power consumption of 13 Joules per run.
MinAvgMaxEPYC 4124P @ DDR5-520037.538.439.0OpenBenchmarking.orgCelsius, Fewer Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.4CPU Temperature Monitor1122334455
MinAvgMaxEPYC 4124P @ DDR5-520054.556.260.4OpenBenchmarking.orgWatts, Fewer Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.4System Power Consumption Monitor204060801001. EPYC 4124P @ DDR5-5200: Approximate power consumption of 41 Joules per run.
OpenBenchmarking.orgGFLOP/s, More Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.4Test: r2c - Backend: FFTW - Precision: float - X Y Z: 128EPYC 4124P @ DDR5-5200smoke918273645Min: 35.97 / Avg: 44.09 / Max: 48.131. (CXX) g++ options: -O3

Meta Performance Per Watts

OpenBenchmarking.orgPerformance Per Watts, More Is BetterMeta Performance Per WattsPerformance Per WattsEPYC 4124P @ DDR5-5200300600900120015001587.79

System Power Consumption Monitor

OpenBenchmarking.orgWattsSystem Power Consumption MonitorPhoronix Test Suite System MonitoringEPYC 4124P @ DDR5-5200306090120150Min: 52.3 / Avg: 99.43 / Max: 139.4

CPU Temperature Monitor

OpenBenchmarking.orgCelsiusCPU Temperature MonitorPhoronix Test Suite System MonitoringEPYC 4124P @ DDR5-52001632486480Min: 34 / Avg: 61.91 / Max: 83.13

CPU Power Consumption Monitor

OpenBenchmarking.orgWattsCPU Power Consumption MonitorPhoronix Test Suite System MonitoringEPYC 4124P @ DDR5-520020406080100Min: 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 MonitoringEPYC 4124P @ DDR5-52009001800270036004500Min: 400 / Avg: 4694.07 / Max: 5214

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.

Test: Genetic Algorithm Using Jenetics + Futures

EPYC 4124P @ DDR5-5200: The test run did not produce a result. E: sh: 1: exec: ./renaissance: not found

Test: Finagle HTTP Requests

EPYC 4124P @ DDR5-5200: The test run did not produce a result. E: sh: 1: exec: ./renaissance: not found

Java SciMark

This test runs the Java version of SciMark 2, which is a benchmark for scientific and numerical computing developed by programmers at the National Institute of Standards and Technology. This benchmark is made up of Fast Foruier Transform, Jacobi Successive Over-relaxation, Monte Carlo, Sparse Matrix Multiply, and dense LU matrix factorization benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterJava SciMark 2.2Computational Test: Dense LU Matrix FactorizationEPYC 4124P @ DDR5-52004K8K12K16K20KSE +/- 30.99, N = 317467.36

OpenBenchmarking.orgMflops, More Is BetterJava SciMark 2.2Computational Test: Monte CarloEPYC 4124P @ DDR5-52005001000150020002500SE +/- 0.87, N = 32487.91

OpenBenchmarking.orgMflops, More Is BetterJava SciMark 2.2Computational Test: Jacobi Successive Over-RelaxationEPYC 4124P @ DDR5-52005001000150020002500SE +/- 0.28, N = 32281.43

OpenBenchmarking.orgMflops, More Is BetterJava SciMark 2.2Computational Test: Fast Fourier TransformEPYC 4124P @ DDR5-520080160240320400SE +/- 2.13, N = 3353.84

466 Results Shown

TensorFlow
Xmrig
Timed Linux Kernel Compilation
OpenFOAM:
  drivaerFastback, Medium Mesh Size - Execution Time
  drivaerFastback, Medium Mesh Size - Mesh Time
Blender
LAMMPS Molecular Dynamics Simulator
OpenRadioss
TensorFlow
Timed Node.js Compilation
Timed LLVM Compilation:
  Unix Makefiles
  Ninja
Helsing
TensorFlow
Stockfish
OpenRadioss
Timed Gem5 Compilation
OpenVKL
Blender
Timed Godot Game Engine Compilation
Llama.cpp
TensorFlow
Blender
Appleseed
Apache IoTDB:
  800 - 100 - 800 - 400:
    Average Latency
    point/sec
  800 - 100 - 800 - 100:
    Average Latency
    point/sec
TensorFlow
Primesieve
miniBUDE:
  OpenMP - BM2:
    Billion Interactions/s
    GFInst/s
SVT-HEVC
OpenRadioss
PETSc
Apache IoTDB:
  500 - 100 - 800 - 400:
    Average Latency
    point/sec
TensorFlow
ASTC Encoder:
  Very Thorough
  Exhaustive
GPAW
ClickHouse:
  100M Rows Hits Dataset, Third Run
  100M Rows Hits Dataset, Second Run
  100M Rows Hits Dataset, First Run / Cold Cache
Appleseed
OpenSSL:
  RSA4096:
    verify/s
    sign/s
MariaDB:
  oltp_read_write - 32
  oltp_write_only - 64
  oltp_update_index - 32
  oltp_update_non_index - 32
  oltp_update_non_index - 64
  oltp_read_write - 64
  oltp_update_index - 64
  oltp_write_only - 32
SecureMark
Blender
Appleseed
BRL-CAD
Apache IoTDB:
  800 - 100 - 500 - 100:
    Average Latency
    point/sec
  800 - 100 - 500 - 400:
    Average Latency
    point/sec
  500 - 100 - 800 - 100:
    Average Latency
    point/sec
Intel Open Image Denoise
Blender
OpenRadioss
Java JMH
PyTorch
SPECFEM3D
ONNX Runtime:
  Faster R-CNN R-50-FPN-int8 - CPU - Standard:
    Inference Time Cost (ms)
    Inferences Per Second
  GPT-2 - CPU - Standard:
    Inference Time Cost (ms)
    Inferences Per Second
  bertsquad-12 - CPU - Standard:
    Inference Time Cost (ms)
    Inferences Per Second
Speedb
ONNX Runtime:
  ResNet50 v1-12-int8 - CPU - Standard:
    Inference Time Cost (ms)
    Inferences Per Second
OpenFOAM:
  drivaerFastback, Small Mesh Size - Execution Time
  drivaerFastback, Small Mesh Size - Mesh Time
ONNX Runtime:
  super-resolution-10 - CPU - Parallel:
    Inference Time Cost (ms)
    Inferences Per Second
PostgreSQL:
  100 - 500 - Read Only - Average Latency
  100 - 500 - Read Only
TensorFlow
MariaDB mariadb-slap
SPECFEM3D
OpenRadioss
Blender
ONNX Runtime:
  fcn-resnet101-11 - CPU - Parallel:
    Inference Time Cost (ms)
    Inferences Per Second
  CaffeNet 12-int8 - CPU - Standard:
    Inference Time Cost (ms)
    Inferences Per Second
GROMACS
DuckDB
TensorFlow
libavif avifenc
OSPRay Studio
Apache IoTDB:
  500 - 100 - 500 - 400:
    Average Latency
    point/sec
Timed Linux Kernel Compilation
VVenC
OpenSSL:
  ChaCha20-Poly1305
  ChaCha20
  AES-256-GCM
  AES-128-GCM
  SHA512
  SHA256
Apache IoTDB:
  500 - 100 - 500 - 100:
    Average Latency
    point/sec
CloverLeaf
PostgreSQL:
  100 - 800 - Read Only - Average Latency
  100 - 800 - Read Only
NAMD
OSPRay
FFmpeg:
  libx265 - Video On Demand
  libx265 - Platform
OSPRay Studio
ScyllaDB
OSPRay Studio
FFmpeg
easyWave
OpenVINO:
  Road Segmentation ADAS FP16-INT8 - CPU:
    ms
    FPS
NAS Parallel Benchmarks
OSPRay
OpenRadioss
PostgreSQL:
  100 - 500 - Read Write - Average Latency
  100 - 500 - Read Write
  100 - 800 - Read Write - Average Latency
  100 - 800 - Read Write
TensorFlow
uvg266
NAS Parallel Benchmarks
Llamafile:
  mistral-7b-instruct-v0.2.Q8_0 - CPU
  wizardcoder-python-34b-v1.0.Q6_K - CPU
Intel Open Image Denoise:
  RT.hdr_alb_nrm.3840x2160 - CPU-Only
  RT.ldr_alb_nrm.3840x2160 - CPU-Only
SPECFEM3D
Timed CPython Compilation
MariaDB mariadb-slap
ACES DGEMM
CockroachDB:
  KV, 50% Reads - 128
  KV, 60% Reads - 128
  KV, 95% Reads - 128
m-queens
Numpy Benchmark
Xcompact3d Incompact3d
High Performance Conjugate Gradient
Embree
SVT-HEVC
OSPRay Studio
ASTC Encoder
Embree
SPECFEM3D
CloverLeaf
OSPRay
SPECFEM3D
Kvazaar
Apache HTTP Server
nginx
Apache HTTP Server
nginx:
  500
  200
oneDNN
OSPRay Studio
Timed PHP Compilation
OSPRay Studio
libavif avifenc
OSPRay Studio:
  1 - 1080p - 16 - Path Tracer - CPU
  2 - 1080p - 1 - Path Tracer - CPU
Embree
Pennant
OSPRay Studio
Llama.cpp
Timed FFmpeg Compilation
LuxCoreRender
Zstd Compression:
  19, Long Mode - Decompression Speed
  19, Long Mode - Compression Speed
VVenC
Coremark
oneDNN
NAS Parallel Benchmarks
Redis
OpenVINO:
  Machine Translation EN To DE FP16 - CPU:
    ms
    FPS
Zstd Compression:
  19 - Decompression Speed
  19 - Compression Speed
Chaos Group V-RAY
Y-Cruncher
TensorFlow
DaCapo Benchmark
Dragonflydb:
  10 - 1:100
  10 - 1:10
Memcached:
  1:10
  1:100
LuxCoreRender
TensorFlow
GraphicsMagick
OpenVINO:
  Face Detection FP16 - CPU:
    ms
    FPS
LuxCoreRender
Zstd Compression:
  8, Long Mode - Decompression Speed
  8, Long Mode - Compression Speed
  12 - Decompression Speed
  12 - Compression Speed
OpenVINO:
  Face Detection FP16-INT8 - CPU:
    ms
    FPS
Zstd Compression:
  8 - Decompression Speed
  8 - Compression Speed
miniBUDE:
  OpenMP - BM1:
    Billion Interactions/s
    GFInst/s
DaCapo Benchmark
GraphicsMagick
ONNX Runtime:
  Faster R-CNN R-50-FPN-int8 - CPU - Parallel:
    Inference Time Cost (ms)
    Inferences Per Second
  GPT-2 - CPU - Parallel:
    Inference Time Cost (ms)
    Inferences Per Second
  yolov4 - CPU - Parallel:
    Inference Time Cost (ms)
    Inferences Per Second
  bertsquad-12 - CPU - Parallel:
    Inference Time Cost (ms)
    Inferences Per Second
  yolov4 - CPU - Standard:
    Inference Time Cost (ms)
    Inferences Per Second
LuxCoreRender
ONNX Runtime:
  T5 Encoder - CPU - Standard:
    Inference Time Cost (ms)
    Inferences Per Second
RawTherapee
ONNX Runtime:
  ArcFace ResNet-100 - CPU - Parallel:
    Inference Time Cost (ms)
    Inferences Per Second
OpenVINO:
  Person Detection FP32 - CPU:
    ms
    FPS
ONNX Runtime:
  T5 Encoder - CPU - Parallel:
    Inference Time Cost (ms)
    Inferences Per Second
OpenVINO:
  Person Detection FP16 - CPU:
    ms
    FPS
  Noise Suppression Poconet-Like FP16 - CPU:
    ms
    FPS
GraphicsMagick
OpenVINO:
  Person Vehicle Bike Detection FP16 - CPU:
    ms
    FPS
  Road Segmentation ADAS FP16 - CPU:
    ms
    FPS
  Person Re-Identification Retail FP16 - CPU:
    ms
    FPS
GraphicsMagick
OpenVINO:
  Vehicle Detection FP16-INT8 - CPU:
    ms
    FPS
Speedb:
  Rand Fill Sync
  Rand Fill
OpenVINO:
  Handwritten English Recognition FP16-INT8 - CPU:
    ms
    FPS
  Handwritten English Recognition FP16 - CPU:
    ms
    FPS
  Face Detection Retail FP16-INT8 - CPU:
    ms
    FPS
Speedb
OpenVINO:
  Vehicle Detection FP16 - CPU:
    ms
    FPS
GraphicsMagick
OpenVINO:
  Weld Porosity Detection FP16 - CPU:
    ms
    FPS
Speedb
OpenVINO:
  Face Detection Retail FP16 - CPU:
    ms
    FPS
  Weld Porosity Detection FP16-INT8 - CPU:
    ms
    FPS
ONNX Runtime:
  CaffeNet 12-int8 - CPU - Parallel:
    Inference Time Cost (ms)
    Inferences Per Second
John The Ripper
GraphicsMagick
OpenVINO:
  Age Gender Recognition Retail 0013 FP16-INT8 - CPU:
    ms
    FPS
GraphicsMagick
RocksDB
OpenVINO:
  Age Gender Recognition Retail 0013 FP16 - CPU:
    ms
    FPS
RocksDB
ONNX Runtime:
  ResNet50 v1-12-int8 - CPU - Parallel:
    Inference Time Cost (ms)
    Inferences Per Second
Speedb
RocksDB:
  Read Rand Write Rand
  Overwrite
  Update Rand
  Read While Writing
John The Ripper
RocksDB
Timed Wasmer Compilation
NAS Parallel Benchmarks
Z3 Theorem Prover
NAMD
Pennant
JPEG-XL libjxl:
  PNG - 90
  PNG - 100
  JPEG - 100
Node.js V8 Web Tooling Benchmark
OSPRay
JPEG-XL libjxl
VVenC
OSPRay
Timed Mesa Compilation
OSPRay
x265
FFmpeg
SVT-AV1
Aircrack-ng
uvg266
Llama.cpp
Llamafile
ASKAP:
  tConvolve OpenMP - Degridding
  tConvolve OpenMP - Gridding
Cpuminer-Opt:
  Quad SHA-256, Pyrite
  Deepcoin
DaCapo Benchmark
Cpuminer-Opt
Liquid-DSP
Stress-NG:
  Vector Floating Point
  Floating Point
  Matrix 3D Math
  Vector Shuffle
  System V Message Passing
  AVX-512 VNNI
  Wide Vector Math
  Fused Multiply-Add
  x86_64 RdRand
  CPU Cache
Cpuminer-Opt:
  Blake-2 S
  scrypt
  Skeincoin
  Ringcoin
  Myriad-Groestl
  Magi
  Garlicoin
  LBC, LBRY Credits
ASTC Encoder
uvg266
DaCapo Benchmark
miniFE
Java SciMark
Primesieve
TensorFlow
NAS Parallel Benchmarks
QuantLib
Kvazaar
uvg266
Apache Hadoop:
  Create - 500 - 100000
  Create - 100 - 100000
DaCapo Benchmark
Y-Cruncher
ASKAP:
  tConvolve MT - Degridding
  tConvolve MT - Gridding
DaCapo Benchmark
WebP Image Encode
John The Ripper:
  WPA PSK
  bcrypt
  Blowfish
Liquid-DSP:
  16 - 256 - 512
  16 - 256 - 32
  2 - 256 - 512
  8 - 256 - 512
  2 - 256 - 32
  8 - 256 - 32
  4 - 256 - 32
  1 - 256 - 512
  1 - 256 - 32
DaCapo Benchmark
PyTorch
DaCapo Benchmark
Kvazaar
Xcompact3d Incompact3d
DaCapo Benchmark:
  Apache Lucene Search Engine
  Jython
  GraphChi
ASTC Encoder
DaCapo Benchmark
LuxCoreRender
DaCapo Benchmark
Z3 Theorem Prover
SVT-AV1
uvg266
SVT-AV1
DaCapo Benchmark:
  FOP Print Formatter
  Avrora AVR Simulation Framework
  PMD Source Code Analyzer
  Zxing 1D/2D Barcode Image Processing
Helsing
VVenC
oneDNN
SVT-HEVC
Kvazaar:
  Bosphorus 4K - Ultra Fast
  Bosphorus 1080p - Medium
QuantLib
NAS Parallel Benchmarks
oneDNN
DaCapo Benchmark
7-Zip Compression:
  Decompression Rating
  Compression Rating
SVT-VP9:
  Visual Quality Optimized - Bosphorus 4K
  VMAF Optimized - Bosphorus 4K
srsRAN Project
QMCPACK
ASKAP:
  tConvolve MPI - Gridding
  tConvolve MPI - Degridding
SVT-VP9
NAS Parallel Benchmarks
DaCapo Benchmark
SVT-AV1
libavif avifenc
Parallel BZIP2 Compression
Dolfyn
PyBench
SVT-HEVC
NAS Parallel Benchmarks
x265
TensorFlow
WebP Image Encode
uvg266
easyWave
libavif avifenc
uvg266
SVT-AV1
oneDNN
Kvazaar
TensorFlow
uvg266
RNNoise
SVT-AV1
Google Draco
oneDNN
SVT-HEVC
Algebraic Multi-Grid Benchmark
srsRAN Project
GNU Octave Benchmark
Timed CPython Compilation
libavif avifenc
Google Draco
Kvazaar
srsRAN Project
Kvazaar
SVT-VP9
TensorFlow
WebP Image Encode
LAMMPS Molecular Dynamics Simulator
SVT-VP9:
  VMAF Optimized - Bosphorus 1080p
  PSNR/SSIM Optimized - Bosphorus 1080p
LULESH
SVT-HEVC
oneDNN
srsRAN Project
SVT-AV1
WebP Image Encode
SVT-AV1
WebP Image Encode
HeFFTe - Highly Efficient FFT for Exascale:
  r2c - FFTW - double - 128
  r2c - FFTW - float - 128
Meta Performance Per Watts:
  Performance Per Watts
  Phoronix Test Suite System Monitoring
  Phoronix Test Suite System Monitoring
  Phoronix Test Suite System Monitoring
  Phoronix Test Suite System Monitoring
Java SciMark:
  Dense LU Matrix Factorization
  Monte Carlo
  Jacobi Successive Over-Relaxation
  Fast Fourier Transform

EPYC 4124P @ DDR5-5200

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --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
Processor Notes: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xa601203
Java Notes: OpenJDK Runtime Environment (build 21.0.2+13-Ubuntu-2)
Python Notes: Python 3.12.2
Security Notes: 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

Testing initiated at 20 May 2024 00:32 by user phoronix.

smoke

Processor: AMD EPYC 4124P 4-Core @ 5.17GHz (4 Cores / 8 Threads), Motherboard: Supermicro AS-3015A-I H13SAE-MF v1.00 (1.1 BIOS), Chipset: AMD Device 14d8, Memory: 2 x 32GB DRAM-5200MT/s, Disk: 3201GB Micron_7450_MTFDKCC3T2TFS + 960GB SAMSUNG MZ1L2960HCJR-00A07, Graphics: ASPEED, Audio: AMD Rembrandt Radeon HD Audio, Monitor: VE228, Network: 2 x Intel I210

OS: Ubuntu 24.04, Kernel: 6.8.0-11-generic (x86_64), Desktop: GNOME Shell 45.3, Display Server: X Server 1.21.1.11, Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1080

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --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
Processor Notes: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xa601203
Java Notes: OpenJDK Runtime Environment (build 21.0.2+13-Ubuntu-2)
Python Notes: Python 3.12.2
Security Notes: 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

Testing initiated at 23 May 2024 01:29 by user phoronix.