Ryzen 9 7900X3D Ryzen 9 7950X3D Linux Benchmarks

AMD Ryzen 9 7900X  / Ryzen 9 7900X3D / Ryzen 9 7950X / Ryzen 9 7950X3D Linux benchmarks by Michael Larabel for a future article.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2303061-NE-X3DZEN41555
Jump To Table - Results

View

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

Limit displaying results to tests within:

BLAS (Basic Linear Algebra Sub-Routine) Tests 2 Tests
C/C++ Compiler Tests 2 Tests
CPU Massive 4 Tests
Creator Workloads 3 Tests
Fortran Tests 2 Tests
HPC - High Performance Computing 13 Tests
Machine Learning 5 Tests
Molecular Dynamics 6 Tests
MPI Benchmarks 5 Tests
Multi-Core 7 Tests
NVIDIA GPU Compute 3 Tests
Intel oneAPI 3 Tests
OpenMPI Tests 8 Tests
Python Tests 3 Tests
Scientific Computing 7 Tests
Server CPU Tests 2 Tests

Statistics

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

Graph Settings

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

Additional Graphs

Show Perf Per Core/Thread Calculation Graphs Where Applicable
Show Perf Per Clock Calculation Graphs Where Applicable

Multi-Way Comparison

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

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
Ryzen 9 7900X
March 04 2023
  5 Hours, 10 Minutes
Ryzen 9 7900X3D
March 05 2023
  6 Hours, 17 Minutes
Ryzen 9 7950X
March 05 2023
  4 Hours, 38 Minutes
Ryzen 9 7950X3D
March 04 2023
  4 Hours, 41 Minutes
Invert Hiding All Results Option
  5 Hours, 12 Minutes

Only show results where is faster than
Only show results matching title/arguments (delimit multiple options with a comma):
Do not show results matching title/arguments (delimit multiple options with a comma):


Ryzen 9 7900X3D Ryzen 9 7950X3D Linux BenchmarksOpenBenchmarking.orgPhoronix Test SuiteAMD Ryzen 9 7900X 12-Core @ 4.70GHz (12 Cores / 24 Threads)AMD Ryzen 9 7900X3D 12-Core @ 4.40GHz (12 Cores / 24 Threads)AMD Ryzen 9 7950X 16-Core @ 4.50GHz (16 Cores / 32 Threads)AMD Ryzen 9 7950X3D 16-Core @ 4.20GHz (16 Cores / 32 Threads)ASUS ROG CROSSHAIR X670E HERO (9922 BIOS)AMD Device 14d832GBWestern Digital WD_BLACK SN850X 1000GB + 2000GBAMD Radeon RX 7900 XTX 24GB (2304/1249MHz)AMD Device ab30ASUS MG28UIntel I225-V + Intel Wi-Fi 6 AX210/AX211/AX411Ubuntu 23.046.2.2-060202-generic (x86_64)GNOME Shell 43.2X Server 1.21.1.6 + Wayland4.6 Mesa 23.1.0-devel (git-efcb639 2023-02-13 lunar-oibaf-ppa) (LLVM 15.0.7 DRM 3.49)GCC 12.2.0ext43840x2160ProcessorsMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerOpenGLCompilerFile-SystemScreen ResolutionRyzen 9 7900X3D Ryzen 9 7950X3D Linux 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-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-12-AKimc9/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-AKimc9/gcc-12-12.2.0/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: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa601203- Python 3.11.1- itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Ryzen 9 7900XRyzen 9 7900X3DRyzen 9 7950XRyzen 9 7950X3DResult OverviewPhoronix Test Suite100%124%147%171%194%oneDNNCloverLeafPennantOpenVINOEmbreeONNX RuntimeASKAPOpenFOAMGPAWGROMACSNCNNZstd CompressionXcompact3d Incompact3dClickHouseLULESHLeelaChessZero

Ryzen 9 7900XRyzen 9 7900X3DRyzen 9 7950XRyzen 9 7950X3DPer Watt Result OverviewPhoronix Test Suite100%124%149%173%LeelaChessZeroEmbreeClickHouseGROMACSASKAPLULESHP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.M

Ryzen 9 7900X3D Ryzen 9 7950X3D Linux Benchmarksaskap: tConvolve OpenMP - Degriddingcloverleaf: Lagrangian-Eulerian Hydrodynamicsopenvino: Vehicle Detection FP16 - CPUpennant: leblancbigpennant: sedovbigopenfoam: drivaerFastback, Small Mesh Size - Execution Timeopenvino: Vehicle Detection FP16 - CPUaskap: tConvolve OpenMP - Griddingembree: Pathtracer - Asian Dragonembree: Pathtracer - Asian Dragon Objembree: Pathtracer ISPC - Asian Dragon Objembree: Pathtracer ISPC - Asian Dragoncompress-zstd: 8 - Compression Speedaskap: Hogbom Clean OpenMPcompress-zstd: 8, Long Mode - Compression Speedcompress-zstd: 12 - Compression Speedgpaw: Carbon Nanotubegromacs: MPI CPU - water_GMX50_barencnn: CPU - resnet18ncnn: CPU - alexnetincompact3d: input.i3d 129 Cells Per Directionclickhouse: 100M Rows Hits Dataset, Third Runonnx: GPT-2 - CPU - Standardincompact3d: input.i3d 193 Cells Per Directionopenfoam: drivaerFastback, Medium Mesh Size - Execution Timeclickhouse: 100M Rows Hits Dataset, Second Runaskap: tConvolve MT - Griddingonnx: GPT-2 - CPU - Parallelopenfoam: drivaerFastback, Medium Mesh Size - Mesh Timeclickhouse: 100M Rows Hits Dataset, First Run / Cold Cacheaskap: tConvolve MPI - Griddingaskap: tConvolve MT - Degriddingcompress-zstd: 19 - Compression Speedlulesh: lczero: BLASonednn: Convolution Batch Shapes Auto - bf16bf16bf16 - CPUcompress-zstd: 19, Long Mode - Compression Speedonnx: ResNet50 v1-12-int8 - CPU - Standardonnx: ResNet50 v1-12-int8 - CPU - Standardonnx: GPT-2 - CPU - Parallelonnx: GPT-2 - CPU - Standardonnx: fcn-resnet101-11 - CPU - Standardonnx: fcn-resnet101-11 - CPU - StandardRyzen 9 7900XRyzen 9 7900X3DRyzen 9 7950XRyzen 9 7950X3D5756.7749.63666.3525.1461236.88098171.618469.005024.8926.507923.815826.494130.8877857.4440.183808.5248.8150.8682.2707.774.9814.6115010290.14172.80968.21861272161.5558285.412002.69146.338199.34498258.6411693.22755.4923.48484.566118791.8129113.02.33461430.9596.831775.79435571.2861.750539923.2531.18797.6019.1914331.14960139.58657.526074.0026.493723.933327.031431.46021032.5546.455934.9305.2142.7022.2866.594.2312.6076226300.71196.76260.70284531936.9236302.362099.92158.381191.81722270.9712035.22906.7125.18980.496018911.3742113.62.45139409.7256.310145.08318398.9312.611596156.8247.00784.2524.3587734.84577161.6749210.196099.2233.632429.815331.778337.2215837.4448.459845.7253.6138.0142.6077.464.8614.6268368276.94169.50266.21399432126.1028275.452173.95146.497190.93673250.5011211.22833.4923.38479.877619152.1083112.52.06309485.2416.822615.89782448.7642.2283611369.629.181003.4816.8608227.03524125.985427.976780.7934.703531.009234.164239.71441053.7548.2501004.2292.4126.8992.6956.604.2812.5392537321.76185.38458.77319241863.9535316.842293.31164.532178.10769279.87124952995.1925.28987.939119451.0864015.02.06799486.6126.074385.39416282.6443.53941OpenBenchmarking.org

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 - DegriddingRyzen 9 7900XRyzen 9 7900X3DRyzen 9 7950XRyzen 9 7950X3D2K4K6K8K10KSE +/- 107.63, N = 6SE +/- 124.67, N = 7SE +/- 35.18, N = 4SE +/- 97.44, N = 75756.779923.256156.8211369.601. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

CloverLeaf

CloverLeaf is a Lagrangian-Eulerian hydrodynamics benchmark. This test profile currently makes use of CloverLeaf's OpenMP version and benchmarked with the clover_bm.in input file (Problem 5). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterCloverLeafLagrangian-Eulerian HydrodynamicsRyzen 9 7900XRyzen 9 7900X3DRyzen 9 7950XRyzen 9 7950X3D1122334455SE +/- 0.50, N = 3SE +/- 0.21, N = 3SE +/- 0.12, N = 3SE +/- 0.10, N = 349.6331.1847.0029.181. (F9X) gfortran options: -O3 -march=native -funroll-loops -fopenmp

OpenVINO

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

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Vehicle Detection FP16 - Device: CPURyzen 9 7900XRyzen 9 7900X3DRyzen 9 7950XRyzen 9 7950X3D2004006008001000SE +/- 9.18, N = 3SE +/- 2.24, N = 3SE +/- 3.17, N = 3SE +/- 3.11, N = 3666.35797.60784.251003.481. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

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: leblancbigRyzen 9 7900XRyzen 9 7900X3DRyzen 9 7950XRyzen 9 7950X3D612182430SE +/- 0.01, N = 3SE +/- 0.06, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 325.1519.1924.3616.861. (CXX) g++ options: -fopenmp -lmpi_cxx -lmpi

OpenBenchmarking.orgHydro Cycle Time - Seconds, Fewer Is BetterPennant 1.0.1Test: sedovbigRyzen 9 7900XRyzen 9 7900X3DRyzen 9 7950XRyzen 9 7950X3D816243240SE +/- 0.14, N = 3SE +/- 0.10, N = 3SE +/- 0.02, N = 3SE +/- 0.11, N = 336.8831.1534.8527.041. (CXX) g++ options: -fopenmp -lmpi_cxx -lmpi

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 TimeRyzen 9 7900XRyzen 9 7900X3DRyzen 9 7950XRyzen 9 7950X3D4080120160200171.62139.59161.67125.991. (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

OpenVINO

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

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Vehicle Detection FP16 - Device: CPURyzen 9 7900XRyzen 9 7900X3DRyzen 9 7950XRyzen 9 7950X3D3691215SE +/- 0.12, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 39.007.5210.197.97MIN: 4.65 / MAX: 19.47MIN: 4.14 / MAX: 14.84MIN: 4.41 / MAX: 24.5MIN: 4.7 / MAX: 18.61. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared

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 - GriddingRyzen 9 7900XRyzen 9 7900X3DRyzen 9 7950XRyzen 9 7950X3D15003000450060007500SE +/- 34.63, N = 6SE +/- 54.56, N = 7SE +/- 46.08, N = 6SE +/- 61.20, N = 75024.896074.006099.226780.791. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

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 4.0Binary: Pathtracer - Model: Asian DragonRyzen 9 7900XRyzen 9 7900X3DRyzen 9 7950XRyzen 9 7950X3D816243240SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.05, N = 326.5126.4933.6334.70MIN: 26.37 / MAX: 26.79MIN: 26.31 / MAX: 26.92MIN: 33.39 / MAX: 34.01MIN: 34.46 / MAX: 35.13

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.0Binary: Pathtracer - Model: Asian Dragon ObjRyzen 9 7900XRyzen 9 7900X3DRyzen 9 7950XRyzen 9 7950X3D714212835SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 323.8223.9329.8231.01MIN: 23.68 / MAX: 24.06MIN: 23.78 / MAX: 24.29MIN: 29.53 / MAX: 30.29MIN: 30.82 / MAX: 31.62

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.0Binary: Pathtracer ISPC - Model: Asian Dragon ObjRyzen 9 7900XRyzen 9 7900X3DRyzen 9 7950XRyzen 9 7950X3D816243240SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.07, N = 326.4927.0331.7834.16MIN: 26.24 / MAX: 27.06MIN: 26.82 / MAX: 27.58MIN: 31.44 / MAX: 32.76MIN: 33.76 / MAX: 35.23

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.0Binary: Pathtracer ISPC - Model: Asian DragonRyzen 9 7900XRyzen 9 7900X3DRyzen 9 7950XRyzen 9 7950X3D918273645SE +/- 0.01, N = 3SE +/- 0.08, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 430.8931.4637.2239.71MIN: 30.69 / MAX: 31.38MIN: 31.14 / MAX: 32.1MIN: 36.85 / MAX: 38.38MIN: 39.34 / MAX: 40.55

Zstd Compression

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

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 8 - Compression SpeedRyzen 9 7900XRyzen 9 7900X3DRyzen 9 7950XRyzen 9 7950X3D2004006008001000SE +/- 1.87, N = 3SE +/- 8.26, N = 3SE +/- 3.61, N = 3SE +/- 9.05, N = 15857.41032.5837.41053.71. (CC) gcc options: -O3 -pthread -lz -llzma -llz4

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.orgIterations Per Second, More Is BetterASKAP 1.0Test: Hogbom Clean OpenMPRyzen 9 7900XRyzen 9 7900X3DRyzen 9 7950XRyzen 9 7950X3D120240360480600SE +/- 2.17, N = 5SE +/- 0.94, N = 5SE +/- 1.79, N = 5SE +/- 0.74, N = 5440.18546.46448.46548.251. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

Zstd Compression

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

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 8, Long Mode - Compression SpeedRyzen 9 7900XRyzen 9 7900X3DRyzen 9 7950XRyzen 9 7950X3D2004006008001000SE +/- 0.92, N = 3SE +/- 0.84, N = 3SE +/- 0.72, N = 3SE +/- 1.52, N = 3808.5934.9845.71004.21. (CC) gcc options: -O3 -pthread -lz -llzma -llz4

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 12 - Compression SpeedRyzen 9 7900XRyzen 9 7900X3DRyzen 9 7950XRyzen 9 7950X3D70140210280350SE +/- 0.55, N = 3SE +/- 1.83, N = 3SE +/- 1.42, N = 3SE +/- 1.20, N = 3248.8305.2253.6292.41. (CC) gcc options: -O3 -pthread -lz -llzma -llz4

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 22.1Input: Carbon NanotubeRyzen 9 7900XRyzen 9 7900X3DRyzen 9 7950XRyzen 9 7950X3D306090120150SE +/- 0.21, N = 3SE +/- 0.36, N = 3SE +/- 0.12, N = 3SE +/- 0.16, N = 3150.87142.70138.01126.901. (CC) gcc options: -shared -fwrapv -O2 -lxc -lblas -lmpi

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 2023Implementation: MPI CPU - Input: water_GMX50_bareRyzen 9 7900XRyzen 9 7900X3DRyzen 9 7950XRyzen 9 7950X3D0.60641.21281.81922.42563.032SE +/- 0.004, N = 3SE +/- 0.001, N = 3SE +/- 0.004, N = 3SE +/- 0.002, N = 32.2702.2862.6072.6951. (CXX) g++ options: -O3

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: resnet18Ryzen 9 7900XRyzen 9 7900X3DRyzen 9 7950XRyzen 9 7950X3D246810SE +/- 0.25, N = 3SE +/- 0.03, N = 15SE +/- 0.10, N = 7SE +/- 0.01, N = 37.776.597.466.60MIN: 7.02 / MAX: 14.55MIN: 6.31 / MAX: 13.27MIN: 7.15 / MAX: 14.27MIN: 6.42 / MAX: 12.761. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: alexnetRyzen 9 7900XRyzen 9 7900X3DRyzen 9 7950XRyzen 9 7950X3D1.12052.2413.36154.4825.6025SE +/- 0.06, N = 3SE +/- 0.05, N = 15SE +/- 0.08, N = 7SE +/- 0.03, N = 34.984.234.864.28MIN: 4.73 / MAX: 10.59MIN: 3.91 / MAX: 27.96MIN: 4.63 / MAX: 9.89MIN: 4.13 / MAX: 10.291. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

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 DirectionRyzen 9 7900XRyzen 9 7900X3DRyzen 9 7950XRyzen 9 7950X3D48121620SE +/- 0.05, N = 4SE +/- 0.15, N = 4SE +/- 0.04, N = 4SE +/- 0.02, N = 414.6112.6114.6312.541. (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

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 RunRyzen 9 7900XRyzen 9 7900X3DRyzen 9 7950XRyzen 9 7950X3D70140210280350SE +/- 3.74, N = 3SE +/- 2.37, N = 4SE +/- 0.25, N = 3SE +/- 3.76, N = 3290.14300.71276.94321.76MIN: 16.06 / MAX: 12000MIN: 14.79 / MAX: 10000MIN: 15.4 / MAX: 10000MIN: 15.82 / MAX: 10000

ONNX Runtime

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

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.14Model: GPT-2 - Device: CPU - Executor: StandardRyzen 9 7900XRyzen 9 7900X3DRyzen 9 7950XRyzen 9 7950X3D4080120160200SE +/- 1.80, N = 15SE +/- 1.67, N = 8SE +/- 0.39, N = 3SE +/- 2.46, N = 3172.81196.76169.50185.381. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -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 193 Cells Per DirectionRyzen 9 7900XRyzen 9 7900X3DRyzen 9 7950XRyzen 9 7950X3D1530456075SE +/- 0.82, N = 3SE +/- 0.86, N = 3SE +/- 0.31, N = 3SE +/- 0.66, N = 468.2260.7066.2158.771. (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

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 TimeRyzen 9 7900XRyzen 9 7900X3DRyzen 9 7950XRyzen 9 7950X3D50010001500200025002161.561936.922126.101863.951. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfoamToVTK -ldynamicMesh -llagrangian -lgenericPatchFields -lfileFormats -lOpenFOAM -ldl -lm

ClickHouse

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

OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse 22.12.3.5100M Rows Hits Dataset, Second RunRyzen 9 7900XRyzen 9 7900X3DRyzen 9 7950XRyzen 9 7950X3D70140210280350SE +/- 0.26, N = 3SE +/- 2.35, N = 4SE +/- 3.10, N = 3SE +/- 2.16, N = 3285.41302.36275.45316.84MIN: 16.08 / MAX: 12000MIN: 14.76 / MAX: 10000MIN: 16.28 / MAX: 12000MIN: 16.12 / MAX: 10000

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 - GriddingRyzen 9 7900XRyzen 9 7900X3DRyzen 9 7950XRyzen 9 7950X3D5001000150020002500SE +/- 11.79, N = 3SE +/- 14.39, N = 3SE +/- 8.23, N = 3SE +/- 8.06, N = 32002.692099.922173.952293.311. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

ONNX Runtime

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

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.14Model: GPT-2 - Device: CPU - Executor: ParallelRyzen 9 7900XRyzen 9 7900X3DRyzen 9 7950XRyzen 9 7950X3D4080120160200SE +/- 1.56, N = 3SE +/- 0.51, N = 3SE +/- 0.20, N = 3SE +/- 0.66, N = 3146.34158.38146.50164.531. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -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, Medium Mesh Size - Mesh TimeRyzen 9 7900XRyzen 9 7900X3DRyzen 9 7950XRyzen 9 7950X3D4080120160200199.34191.82190.94178.111. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfoamToVTK -ldynamicMesh -llagrangian -lgenericPatchFields -lfileFormats -lOpenFOAM -ldl -lm

ClickHouse

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

OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse 22.12.3.5100M Rows Hits Dataset, First Run / Cold CacheRyzen 9 7900XRyzen 9 7900X3DRyzen 9 7950XRyzen 9 7950X3D60120180240300SE +/- 1.44, N = 3SE +/- 3.08, N = 4SE +/- 0.81, N = 3SE +/- 1.59, N = 3258.64270.97250.50279.87MIN: 15.82 / MAX: 10000MIN: 14.66 / MAX: 10000MIN: 12.61 / MAX: 10000MIN: 13.15 / MAX: 7500

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 - GriddingRyzen 9 7900XRyzen 9 7900X3DRyzen 9 7950XRyzen 9 7950X3D3K6K9K12K15KSE +/- 116.93, N = 3SE +/- 59.95, N = 14SE +/- 111.37, N = 6SE +/- 0.00, N = 311693.212035.211211.212495.01. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 1.0Test: tConvolve MT - DegriddingRyzen 9 7900XRyzen 9 7900X3DRyzen 9 7950XRyzen 9 7950X3D6001200180024003000SE +/- 39.07, N = 3SE +/- 33.60, N = 3SE +/- 6.59, N = 3SE +/- 7.84, N = 32755.492906.712833.492995.191. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

Zstd Compression

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

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 19 - Compression SpeedRyzen 9 7900XRyzen 9 7900X3DRyzen 9 7950XRyzen 9 7950X3D612182430SE +/- 0.03, N = 3SE +/- 0.34, N = 15SE +/- 0.09, N = 3SE +/- 0.37, N = 1523.425.123.325.21. (CC) gcc options: -O3 -pthread -lz -llzma -llz4

LULESH

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

OpenBenchmarking.orgz/s, More Is BetterLULESH 2.0.3Ryzen 9 7900XRyzen 9 7900X3DRyzen 9 7950XRyzen 9 7950X3D2K4K6K8K10KSE +/- 18.50, N = 6SE +/- 33.05, N = 7SE +/- 22.43, N = 6SE +/- 15.81, N = 78484.578980.508479.888987.941. (CXX) g++ options: -O3 -fopenmp -lm -lmpi_cxx -lmpi

LeelaChessZero

LeelaChessZero (lc0 / lczero) is a chess engine automated vian neural networks. This test profile can be used for OpenCL, CUDA + cuDNN, and BLAS (CPU-based) benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.28Backend: BLASRyzen 9 7900XRyzen 9 7900X3DRyzen 9 7950XRyzen 9 7950X3D400800120016002000SE +/- 14.80, N = 3SE +/- 7.77, N = 3SE +/- 14.71, N = 3SE +/- 13.05, N = 318791891191519451. (CXX) g++ options: -flto -pthread

CPU Power Consumption Monitor

OpenBenchmarking.orgWattsCPU Power Consumption MonitorPhoronix Test Suite System MonitoringRyzen 9 7900XRyzen 9 7900X3DRyzen 9 7950XRyzen 9 7950X3D4080120160200Min: 10.57 / Avg: 122.28 / Max: 219.21Min: 8.08 / Avg: 76.47 / Max: 121.69Min: 11.12 / Avg: 138.7 / Max: 234.54Min: 10.27 / Avg: 85.51 / Max: 144.29

oneDNN

MinAvgMaxRyzen 9 7900X20.4110.6183.5Ryzen 9 7900X3D8.169.2106.7Ryzen 9 7950X17.8122.2217.5Ryzen 9 7950X3D19.079.6124.2OpenBenchmarking.orgWatts, Fewer Is BetteroneDNN 3.0CPU Power Consumption Monitor60120180240300

CPU Temperature Monitor

OpenBenchmarking.orgCelsiusCPU Temperature MonitorPhoronix Test Suite System MonitoringRyzen 9 7900XRyzen 9 7900X3DRyzen 9 7950XRyzen 9 7950X3D20406080100Min: 37 / Avg: 69.18 / Max: 91.63Min: 35 / Avg: 63.05 / Max: 89.5Min: 34.38 / Avg: 73.94 / Max: 97.38Min: 36.5 / Avg: 61.51 / Max: 90.63

oneDNN

MinAvgMaxRyzen 9 7900X39.871.682.0Ryzen 9 7900X3D37.553.458.4Ryzen 9 7950X38.376.489.9Ryzen 9 7950X3D39.554.559.4OpenBenchmarking.orgCelsius, Fewer Is BetteroneDNN 3.0CPU Temperature Monitor20406080100

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPURyzen 9 7900XRyzen 9 7900X3DRyzen 9 7950XRyzen 9 7950X3D0.47440.94881.42321.89762.372SE +/- 0.00247, N = 7SE +/- 0.00151, N = 7SE +/- 0.37855, N = 15SE +/- 0.00908, N = 71.812911.374212.108311.08640MIN: 1.74MIN: 1.35MIN: 1.63MIN: 1.011. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

Zstd Compression

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

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 19, Long Mode - Compression SpeedRyzen 9 7900XRyzen 9 7900X3DRyzen 9 7950XRyzen 9 7950X3D48121620SE +/- 0.12, N = 15SE +/- 0.28, N = 12SE +/- 0.03, N = 3SE +/- 0.03, N = 313.013.612.515.01. (CC) gcc options: -O3 -pthread -lz -llzma -llz4

ONNX Runtime

MinAvgMaxRyzen 9 7900X42.465.971.0Ryzen 9 7900X3D37.352.755.8Ryzen 9 7950X42.571.478.4Ryzen 9 7950X3D40.055.858.1OpenBenchmarking.orgCelsius, Fewer Is BetterONNX Runtime 1.14CPU Temperature Monitor20406080100

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.14Model: ResNet50 v1-12-int8 - Device: CPU - Executor: StandardRyzen 9 7900XRyzen 9 7900X3DRyzen 9 7950XRyzen 9 7950X3D0.55161.10321.65482.20642.758SE +/- 0.05616, N = 12SE +/- 0.04473, N = 15SE +/- 0.02087, N = 15SE +/- 0.04809, N = 152.334612.451392.063092.067991. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.14Model: ResNet50 v1-12-int8 - Device: CPU - Executor: StandardRyzen 9 7900XRyzen 9 7900X3DRyzen 9 7950XRyzen 9 7950X3D110220330440550SE +/- 10.29, N = 12SE +/- 7.36, N = 15SE +/- 4.65, N = 15SE +/- 9.53, N = 15430.96409.73485.24486.611. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.14Model: fcn-resnet101-11 - Device: CPU - Executor: StandardRyzen 9 7900XRyzen 9 7900X3DRyzen 9 7950XRyzen 9 7950X3D120240360480600SE +/- 3.02, N = 3SE +/- 24.90, N = 15SE +/- 1.13, N = 3SE +/- 4.02, N = 3571.29398.93448.76282.641. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.14Model: fcn-resnet101-11 - Device: CPU - Executor: StandardRyzen 9 7900XRyzen 9 7900X3DRyzen 9 7950XRyzen 9 7950X3D0.79641.59282.38923.18563.982SE +/- 0.00921, N = 3SE +/- 0.12063, N = 15SE +/- 0.00558, N = 3SE +/- 0.04984, N = 31.750532.611592.228363.539411. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt