AMD Ryzen 5800X, 5800X3D, 5950X Linux Benchmarks

AMD EPYC 7702 64-Core testing with a Supermicro Super Server H12SSL-NT v1.02 (2.4 BIOS) and Tesla P40 24GB on Debian 12 via the Phoronix Test Suite.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2408161-NE-2204253NE56
Jump To Table - Results

View

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

Limit displaying results to tests within:

AV1 4 Tests
BLAS (Basic Linear Algebra Sub-Routine) Tests 2 Tests
C++ Boost Tests 5 Tests
Web Browsers 1 Tests
Chess Test Suite 4 Tests
Timed Code Compilation 7 Tests
C/C++ Compiler Tests 18 Tests
Compression Tests 2 Tests
CPU Massive 27 Tests
Creator Workloads 34 Tests
Cryptography 3 Tests
Database Test Suite 4 Tests
Encoding 10 Tests
Finance 2 Tests
Fortran Tests 2 Tests
Game Development 5 Tests
HPC - High Performance Computing 19 Tests
Imaging 7 Tests
Java 2 Tests
Common Kernel Benchmarks 3 Tests
Linear Algebra 2 Tests
Machine Learning 8 Tests
Molecular Dynamics 5 Tests
MPI Benchmarks 5 Tests
Multi-Core 39 Tests
NVIDIA GPU Compute 7 Tests
Intel oneAPI 4 Tests
OpenCL 2 Tests
OpenMPI Tests 9 Tests
Productivity 2 Tests
Programmer / Developer System Benchmarks 12 Tests
Python 2 Tests
Raytracing 4 Tests
Renderers 9 Tests
Scientific Computing 8 Tests
Software Defined Radio 3 Tests
Server 6 Tests
Server CPU Tests 25 Tests
Single-Threaded 5 Tests
Texture Compression 3 Tests
Video Encoding 9 Tests
Common Workstation Benchmarks 3 Tests

Statistics

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

Graph Settings

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

Additional Graphs

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

Multi-Way Comparison

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

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
Ryzen 7 5800X
April 20 2022
  21 Hours, 54 Minutes
Ryzen 7 5800X3D
April 22 2022
  18 Hours, 52 Minutes
Ryzen 9 5950X
April 24 2022
  17 Hours, 12 Minutes
Epyc 7702
August 08
  1 Hour, 40 Minutes
Epyc 7702-retest
August 09
  2 Hours, 37 Minutes
Invert Hiding All Results Option
  12 Hours, 27 Minutes

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


AMD Ryzen 5800X, 5800X3D, 5950X Linux BenchmarksProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerOpenGLVulkanCompilerFile-SystemScreen ResolutionDisplay DriverRyzen 7 5800XRyzen 7 5800X3DRyzen 9 5950XEpyc 7702Epyc 7702-retestAMD Ryzen 7 5800X 8-Core @ 3.80GHz (8 Cores / 16 Threads)ASRock X570 Pro4 (P4.30 BIOS)AMD Starship/Matisse16GB1000GB Sabrent Rocket 4.0 1TBAMD Radeon RX 6800 XT 16GB (2575/1000MHz)AMD Navi 21 HDMI AudioASUS MG28UIntel I211Ubuntu 22.045.17.4-051704-generic (x86_64)GNOME Shell 42.0X Server + Wayland4.6 Mesa 22.2.0-devel (git-092ac67 2022-04-21 jammy-oibaf-ppa) (LLVM 14.0.0 DRM 3.44)1.3.211GCC 11.2.0ext43840x2160AMD Ryzen 7 5800X3D 8-Core @ 3.40GHz (8 Cores / 16 Threads)AMD Ryzen 9 5950X 16-Core @ 3.40GHz (16 Cores / 32 Threads)ASUS ROG CROSSHAIR VIII HERO (WI-FI) (4006 BIOS)32GBAMD Radeon RX 6800 16GB (2475/1000MHz)Realtek RTL8125 2.5GbE + Intel I211 + Intel Wi-Fi 6 AX200AMD EPYC 7702 64-Core @ 2.00GHz (64 Cores / 128 Threads)Supermicro Super Server H12SSL-NT v1.02 (2.4 BIOS)8 x 64GB DDR4-3200MT/s Samsung M393A8G40AB2-CWE4 x 2000GB Samsung SSD 980 PRO 2TB + 2 x 3841GB VO003840KXAVQ + 6 x 4001GB CT4000P3SSD8Tesla P40 24GB2 x Broadcom BCM57416 NetXtreme-E Dual-Media 10G RDMADebian 126.8.8-2-pve (x86_64)NVIDIAGCC 12.2.0zfs1024x768OpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseCompiler Details- Ryzen 7 5800X, Ryzen 7 5800X3D, Ryzen 9 5950X: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-gBFGDP/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-gBFGDP/gcc-11-11.2.0/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-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v Processor Details- Ryzen 7 5800X: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa201016- Ryzen 7 5800X3D: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa201205- Ryzen 9 5950X: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa201016- Epyc 7702: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0x8301055- Epyc 7702-retest: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0x8301055Java Details- Ryzen 7 5800X, Ryzen 7 5800X3D, Ryzen 9 5950X: OpenJDK Runtime Environment (build 11.0.14.1+1-Ubuntu-0ubuntu1)Python Details- Ryzen 7 5800X: Python 3.10.4- Ryzen 7 5800X3D: Python 3.10.4- Ryzen 9 5950X: Python 3.10.4- Epyc 7702: Python 3.11.2- Epyc 7702-retest: Python 3.11.2Security Details- Ryzen 7 5800X: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: 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 + srbds: Not affected + tsx_async_abort: Not affected - Ryzen 7 5800X3D: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: 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 + srbds: Not affected + tsx_async_abort: Not affected - Ryzen 9 5950X: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: 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 + srbds: Not affected + tsx_async_abort: Not affected - Epyc 7702: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Vulnerable + spec_rstack_overflow: Vulnerable + spec_store_bypass: Vulnerable + spectre_v1: Vulnerable: __user pointer sanitization and usercopy barriers only; no swapgs barriers + spectre_v2: Vulnerable; IBPB: disabled; STIBP: disabled; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected - Epyc 7702-retest: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Vulnerable + spec_rstack_overflow: Vulnerable + spec_store_bypass: Vulnerable + spectre_v1: Vulnerable: __user pointer sanitization and usercopy barriers only; no swapgs barriers + spectre_v2: Vulnerable; IBPB: disabled; STIBP: disabled; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Ryzen 7 5800XRyzen 7 5800X3DRyzen 9 5950XEpyc 7702Epyc 7702-retestResult OverviewPhoronix Test Suite100%163%225%288%350%TensorFlow LiteNAMDOSPrayNumpy BenchmarkKTX-Software toktx

AMD Ryzen 5800X, 5800X3D, 5950X Linux Benchmarksaskap: tConvolve OpenMP - Griddingblender: Classroom - CPU-Onlyblender: Pabellon Barcelona - CPU-Onlyblender: BMW27 - CPU-Onlyblender: Fishy Cat - CPU-Onlyopencv: DNN - Deep Neural Networkblender: Barbershop - CPU-Onlytoktx: UASTC 4 + Zstd Compression 19onednn: IP Shapes 3D - u8s8f32 - CPUospray: particle_volume/scivis/real_timeospray: gravity_spheres_volume/dim_512/pathtracer/real_timeospray: gravity_spheres_volume/dim_512/ao/real_timeaskap: tConvolve OpenMP - Degriddingtensorflow-lite: Inception V4appleseed: Disney Materialtensorflow-lite: Inception ResNet V2askap: Hogbom Clean OpenMPcompress-zstd: 8 - Compression Speedtensorflow-lite: Mobilenet Quantmnn: mobilenetV3tensorflow-lite: SqueezeNettensorflow-lite: Mobilenet Floatopenfoam: Motorbike 30Mtoktx: Zstd Compression 19ncnn: CPU - shufflenet-v2ncnn: CPU-v2-v2 - mobilenet-v2ncnn: CPU-v3-v3 - mobilenet-v3mt-dgemm: Sustained Floating-Point Ratenpb: EP.Dncnn: CPU - mnasnetappleseed: Emilyospray-studio: 2 - 1080p - 32 - Path Tracerospray-studio: 1 - 1080p - 32 - Path Tracerjava-jmh: Throughputmnn: MobileNetV2_224askap: tConvolve MPI - Griddingnpb: EP.Cn-queens: Elapsed Timetoybrot: TBBm-queens: Time To Solveopenssl: RSA4096toybrot: OpenMPopenssl: RSA4096rodinia: OpenMP Streamclustertoybrot: C++ Threadsgraphics-magick: Sharpennumpy: toybrot: C++ Tasksgraphics-magick: Enhancedopenssl: SHA256ospray-studio: 1 - 1080p - 1 - Path Tracerospray-studio: 2 - 1080p - 1 - Path Tracerospray-studio: 3 - 1080p - 1 - Path Tracerospray-studio: 2 - 1080p - 16 - Path Tracerospray-studio: 1 - 1080p - 16 - Path Tracerospray-studio: 3 - 1080p - 16 - Path Tracerstargate: 44100 - 1024lczero: BLASstockfish: Total Timetoktx: UASTC 3rocksdb: Rand Readastcenc: Exhaustivestargate: 44100 - 512ncnn: CPU - googlenetstargate: 480000 - 1024indigobench: CPU - Supercarospray-studio: 3 - 1080p - 32 - Path Tracerx265: Bosphorus 4Kstargate: 480000 - 512graphics-magick: Swirlembree: Pathtracer ISPC - Crownindigobench: CPU - Bedroomncnn: CPU - efficientnet-b0embree: Pathtracer - Crownrodinia: OpenMP LavaMDx264: H.264 Video Encodinglczero: Eigenncnn: CPU - blazefacerocksdb: Read While Writingsvt-hevc: 1 - Bosphorus 1080ppovray: Trace Timemnn: mobilenet-v1-1.0toktx: Zstd Compression 9embree: Pathtracer ISPC - Asian Dragonphpbench: PHP Benchmark Suiteonednn: Deconvolution Batch shapes_1d - u8s8f32 - CPUgraphics-magick: Resizingncnn: CPU - mobilenetembree: Pathtracer - Asian Dragononednn: Convolution Batch Shapes Auto - u8s8f32 - CPUliquid-dsp: 16 - 256 - 57avifenc: 6appleseed: Material Testerbuild-mplayer: Time To Compileonnx: super-resolution-10 - CPU - Standardrodinia: OpenMP CFD Solvermnn: squeezenetv1.1graphics-magick: Noise-Gaussianonednn: Deconvolution Batch shapes_3d - f32 - CPUdav1d: Chimera 1080pcoremark: CoreMark Size 666 - Iterations Per Secondsvt-hevc: 7 - Bosphorus 1080pbuild-llvm: Ninjaonednn: Deconvolution Batch shapes_3d - u8s8f32 - CPUonednn: IP Shapes 1D - u8s8f32 - CPUsvt-av1: Preset 8 - Bosphorus 4Kospray: particle_volume/pathtracer/real_timeaskap: tConvolve MPI - Degriddingsvt-av1: Preset 4 - Bosphorus 4Kbuild-llvm: Unix Makefilesavifenc: 0build-godot: Time To Compileonednn: Convolution Batch Shapes Auto - f32 - CPUrodinia: OpenMP Leukocyteavifenc: 6, Losslesscompress-zstd: 19 - Compression Speedsvt-vp9: Visual Quality Optimized - Bosphorus 1080pncnn: CPU - resnet18pybench: Total For Average Test Timesavifenc: 2java-gradle-perf: Reactorsvt-av1: Preset 10 - Bosphorus 4Kdav1d: Chimera 1080p 10-bitastcenc: Thoroughrocksdb: Read Rand Write Randaom-av1: Speed 8 Realtime - Bosphorus 1080pncnn: CPU - yolov4-tinybuild-mesa: Time To Compiletoktx: UASTC 3 + Zstd Compression 19build-imagemagick: Time To Compileonednn: Recurrent Neural Network Inference - u8s8f32 - CPUsvt-av1: Preset 8 - Bosphorus 1080ponednn: Recurrent Neural Network Inference - f32 - CPUonednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPUcompress-zstd: 3 - Compression Speedncnn: CPU - vgg16onednn: IP Shapes 1D - f32 - CPUbuild-wasmer: Time To Compileincompact3d: input.i3d 129 Cells Per Directionrays1bench: Large Sceneonednn: IP Shapes 3D - f32 - CPUgegl: Cropsvt-hevc: 10 - Bosphorus 1080procksdb: Update Randocrmypdf: Processing 60 Page PDF Documentsvt-av1: Preset 10 - Bosphorus 1080psvt-av1: Preset 4 - Bosphorus 1080pbuild-php: Time To Compilecompress-zstd: 8, Long Mode - Compression Speeddraco: Church Facadenpb: BT.Cgromacs: MPI CPU - water_GMX50_barechia-vdf: Square Assembly Optimizedsvt-vp9: VMAF Optimized - Bosphorus 1080pmnn: SqueezeNetV1.0mnn: resnet-v2-50svt-vp9: PSNR/SSIM Optimized - Bosphorus 1080pcompress-zstd: 19, Long Mode - Compression Speedredis: GETaom-av1: Speed 6 Two-Pass - Bosphorus 1080px265: Bosphorus 1080paom-av1: Speed 6 Realtime - Bosphorus 4Kdav1d: Summer Nature 4Kavifenc: 10, Losslesslulesh: onnx: GPT-2 - CPU - Standardnpb: FT.Cncnn: CPU - alexnetaskap: tConvolve MT - Degriddingaskap: tConvolve MT - Griddingopencv: Features 2Dmnn: inception-v3npb: CG.Cluaradio: Five Back to Back FIR Filterssvt-av1: Preset 12 - Bosphorus 4Kdraco: Liongimp: unsharp-maskgimp: resizesvt-av1: Preset 12 - Bosphorus 1080pastcenc: Mediumgegl: Tile Glassopencv: Object Detectiongraphics-magick: HWB Color Spacegegl: Cartoonngspice: C2670amg: compress-zstd: 3, Long Mode - Compression Speedgegl: Antialiasgimp: auto-levelsgpaw: Carbon Nanotubeselenium: PSPDFKit WASM - Google Chromeaom-av1: Speed 6 Two-Pass - Bosphorus 4Kdarktable: Masskrug - CPU-onlydarktable: Server Room - CPU-onlyonednn: Recurrent Neural Network Training - f32 - CPUngspice: C7552vpxenc: Speed 5 - Bosphorus 4Konednn: Recurrent Neural Network Training - bf16bf16bf16 - CPUwebp: Quality 100, Losslessinfluxdb: 64 - 10000 - 2,5000,1 - 10000onednn: Recurrent Neural Network Training - u8s8f32 - CPUdarktable: Boat - CPU-onlyaom-av1: Speed 6 Realtime - Bosphorus 1080pinfluxdb: 4 - 10000 - 2,5000,1 - 10000compress-zstd: 8 - Decompression Speedvpxenc: Speed 5 - Bosphorus 1080pgegl: Wavelet Bluronnx: yolov4 - CPU - Standardchia-vdf: Square Plain C++gegl: Rotate 90 Degreesdarktable: Server Rack - CPU-onlysecuremark: SecureMark-TLSwebp: Quality 100, Lossless, Highest Compressionluaradio: Complex Phaseluaradio: Hilbert Transformfinancebench: Repo OpenMPradiance: SMP Parallelselenium: WASM collisionDetection - Google Chromequantlib: synthmark: VoiceMark_100gegl: Color Enhancesrsran: 4G PHY_DL_Test 100 PRB SISO 64-QAMliquid-dsp: 8 - 256 - 57compress-zstd: 8, Long Mode - Decompression Speedrawtherapee: Total Benchmark Timedav1d: Summer Nature 1080pselenium: Kraken - Google Chromewebp: Defaultredis: SETsrsran: 4G PHY_DL_Test 100 PRB SISO 256-QAMwebp: Quality 100webp: Quality 100, Highest Compressionsrsran: 5G PHY_DL_NR Test 52 PRB SISO 64-QAMluaradio: FM Deemphasis Filtersrsran: 5G PHY_DL_NR Test 52 PRB SISO 64-QAMsrsran: 4G PHY_DL_Test 100 PRB MIMO 256-QAMsrsran: 4G PHY_DL_Test 100 PRB MIMO 64-QAMsrsran: OFDM_Testsrsran: 4G PHY_DL_Test 100 PRB SISO 64-QAMliquid-dsp: 1 - 256 - 57compress-zstd: 19, Long Mode - Decompression Speedsrsran: 4G PHY_DL_Test 100 PRB SISO 256-QAMcompress-lz4: 3 - Compression Speedsrsran: 4G PHY_DL_Test 100 PRB MIMO 256-QAMsrsran: 4G PHY_DL_Test 100 PRB MIMO 64-QAMliquid-dsp: 4 - 256 - 57selenium: WASM imageConvolute - Google Chromeradiance: Serialselenium: Speedometer - Google Chromecompress-zstd: 3, Long Mode - Decompression Speedcompress-lz4: 9 - Compression Speedliquid-dsp: 2 - 256 - 57selenium: Jetstream 2 - Google Chromegegl: Reflectsqlite-speedtest: Timed Time - Size 1,000compress-zstd: 19 - Decompression Speedcompress-lz4: 1 - Compression Speedfinancebench: Bonds OpenMPvpxenc: Speed 0 - Bosphorus 1080pcompress-lz4: 9 - Decompression Speedvpxenc: Speed 0 - Bosphorus 4Kcompress-lz4: 3 - Decompression Speedselenium: StyleBench - Google Chromegimp: rotatecompress-lz4: 1 - Decompression Speedgraphics-magick: Rotateonnx: ArcFace ResNet-100 - CPU - Standardonnx: fcn-resnet101-11 - CPU - Standardonnx: bertsquad-12 - CPU - Standardnatron: Spaceshipncnn: CPU - regnety_400mncnn: CPU - squeezenet_ssdncnn: CPU - resnet50gegl: Scaletensorflow-lite: NASNet Mobileonednn: Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPUonednn: Matrix Multiply Batch Shapes Transformer - f32 - CPUonednn: Deconvolution Batch shapes_1d - f32 - CPUaom-av1: Speed 10 Realtime - Bosphorus 1080paom-av1: Speed 9 Realtime - Bosphorus 1080paom-av1: Speed 10 Realtime - Bosphorus 4Kaom-av1: Speed 9 Realtime - Bosphorus 4Kaom-av1: Speed 8 Realtime - Bosphorus 4Knamd: ATPase Simulation - 327,506 Atomsrodinia: OpenMP HotSpot3DRyzen 7 5800XRyzen 7 5800X3DRyzen 9 5950XEpyc 7702Epyc 7702-retest1696.39353.35431.50132.03173.3266551379.08281.5931.6620414.74902.732621.790903363.312346757201.3843512117847220.589623.91245521.018162834109099177.0714.5152.022.362.015.152186965.941.97311.759759969459531915581729946.6331.7024447.38968.5413.1203526758.128170460.4354752609.815.26635156123588.6935060234145293483172808285833394561644956533593.8856459573140131410.0236250259856.87103.8001789.643.8358774.88911250215.233.76238264112.80772.3553.2413.8729183.727121.449101.0523313009.7738.2971.5752.11513.88309276801.72877116210.7315.196718.77546436000009.365176.50829930.525422317.4692.5172855.46412718.64434185.157749145.23580.5932.420911.2145033.597256.1944302.342.758600.180148.419101.14820.245691.48911.82635.3151.3012.6775769.900152.35565.666521.799.43392004512135.0718.3443.13514.12424.0041831.79122.1241835.641838.683891.956.222.9197472.88036.986757979.4810.32286.305281.3459078316.383267.4589.09746.401961.0515419009.970.975233900178.214.12216.687185.8929.44154420.2530.2670.0113.58209.585.4184611.9202679514083.7811.471483.49856.8188148122.8386704.121942.698.571395513.58812.171460.8273.693921.2844591893272.972102.848225209933985.827.25611.795324.622278311.225.3334.5102800.5584.01523.602807.7413.0831757043.32812.704.83610.891644844.74749.641.8543.33239721290034.7940.21732606427.589810.9128.927436.230469138.099252.633587.0949.51740.399516.95742800005020.049.794998.34479.81.1132905516.00560.21.7425.357165.2471.280.8560.3511.4173166667185.9750013334190.3193.970.80182.3171.229602000021.40433.9932434887.568.46150230000212.66124.19242.2994145.512299.3940833.91276118.2613316.18.9613264.857.711.65213559.610331260567343.35.1915.8819.705.3011357370.8061402.587437.53719176.16171.6161.2756.0442.551.8200165.8136657.59365.49444.57136.26177.1255321387.02290.8500.60310814.40282.639501.745328711.62429047205.8014342197410533.3451511.71293151.07716882111308681.1013.2962.102.151.914.838431938.172.02316.879939974349636615094033350.861.8078558.43943.7613.5353640260.117164163.3366832514.88.26136298119599.6536263227139519780572826285833564586045306536253.74939512493183677610.3826057567159.04983.6730157.293.7173144.92611304116.143.63925162213.21032.3523.0114.4107191.152118.7911601.0623647319.5239.4731.6712.27414.59888924421.7875611107.5316.225511.86896256866679.707183.22685229.900672417.0002.5862765.61850774.13417397.204975145.80535.0772.508751.2453933.388247.2076453.222.714552.645153.43698.41013.598794.83712.29841.1161.6110.0078072.635156.86867.744692.239.82312014096155.8714.4238.73713.14921.1831397.68120.4281400.611401.653942.043.212.9405370.12227.809932777.227.803596.516298.4259232816.912275.0758.84044.4631187.8419418839.721.227223967204.104.22816.408209.4133.13595604.3832.9171.7413.46256.315.6355573.9640819314014.629.621601.94929.9728019423.3277861.401850.0108.453351713.76912.628528.8413.815122.4184794189676.339102.7252337981331008.828.78812.156295.485282211.524.8774.3912721.4077.09824.312734.3714.1691709606.92735.694.87810.601565473.94519.741.3245.51642420290036.8220.20430656429.322763.7121.628746.895182146.304267.333425.6907.12942.723489.75523566674804.748.9811051.70504.61.1612857092.31533.31.8195.621157.5449.677.1534.9489.8165513333177.7732593334009.5185.667.80174.7165.928616000022.11450.7152364732.466.12145303333206.33724.13943.5184036.612002.3141821.02474017.9013029.18.9413023.058.711.84313467.0102919141009873.25.1612.4017.955.5371404720.8260851.065717.67542211.35203.0474.7272.0555.381.8558670.1442698.60203.53250.3277.04101.1719243780.07159.1540.50453125.15914.809933.201783233.981337080119.6238631203653213.5231301.469722.12.31694571.762457.198.1014.7114.164.313.789.5100681833.423.84194.27234503424982429174162897.2263.2766615.251812.547.0771906731.652311721.4193414765.815.65019197225608.9719414421256685775471543156218352507824848295486.747661697561373726.47010751619233.29646.48177112.846.5305018.5696459026.656.342804107422.09414.0565.1823.8444111.499203.176791.79396801616.1423.3892.6522.13222.91479435661.08720181212.2724.690519.235510133000006.053114.73928219.11811.0193.9034273.63571502.74642198.783312223.21378.2161.634430.81184150.555333.2776505.904.097397.937102.25767.92717.299964.3838.38351.5219.4414.4874150.372217.10793.271489.356.95202829796110.5720.3030.79910.52417.2541941.58167.2181921.671918.245301.258.323.9374254.38534.2316945102.419.545098.296369.3177548712.969348.64211.43936.0781233.3537124111.911.245183800225.585.20320.635231.6336.43362059.0026.6585.9211.07212.234.6165221.514511684.8011.391355.5787.3819452026.8007099.311666.5114.557406315.68814.032526.7723.325424.24842308100881.674114.399209997300907.730.25113.018302.380305412.285.0274.8012966.0279.31322.352971.5413.1561850267.02960.054.52610.111528176.34845.239.1346.28021666737.1480.21632029127.615807.2129.027120.867188139.616253.133624.5959.69240.917512.65826466675066.947.2461022.54492.81.1042765545.48558.61.7325.413163.6469.380.4555.6512.9171806667184.5765930004156.4193.570.08182.2173.129806000021.26435.6972454903.468.02149576250210.38024.84543.4304096.412138.7241209.83593718.3313218.88.7913267.557.911.83813608.710283.39.6214.9124.536.7971013461.8009761.4785604.68415159.36147.9556.8956.1744.261.1063666.51245.32188.218465.3753791426985499653733.075401.351992.4324.215.8123.417220.1301754570.7673899.51125.4538.4950.85404.4786.15845.35378.216495.4333291650178.01849885613254149.276617.951439.327.753162.930707325.095.8293.493572391173.693566220.375106914.6461875890.76113OpenBenchmarking.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 - GriddingRyzen 7 5800X3DRyzen 9 5950XRyzen 7 5800X14002800420056007000SE +/- 36.34, N = 7SE +/- 9.15, N = 3SE +/- 28.25, N = 126657.592698.601696.391. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

Blender

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

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.0Blend File: Classroom - Compute: CPU-OnlyEpyc 7702-retestRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D80160240320400SE +/- 0.27, N = 3SE +/- 0.24, N = 3SE +/- 0.22, N = 3SE +/- 0.27, N = 399.51203.53353.35365.49

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.0Blend File: Pabellon Barcelona - Compute: CPU-OnlyEpyc 7702-retestRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D100200300400500SE +/- 0.21, N = 3SE +/- 0.18, N = 3SE +/- 0.52, N = 3SE +/- 0.36, N = 3125.45250.32431.50444.57

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.0Blend File: BMW27 - Compute: CPU-OnlyEpyc 7702-retestRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D306090120150SE +/- 0.08, N = 3SE +/- 0.14, N = 3SE +/- 0.12, N = 3SE +/- 0.12, N = 338.4977.04132.03136.26

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.0Blend File: Fishy Cat - Compute: CPU-OnlyEpyc 7702-retestRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D4080120160200SE +/- 0.02, N = 3SE +/- 0.11, N = 3SE +/- 0.03, N = 3SE +/- 0.29, N = 350.85101.17173.32177.12

OpenCV

This is a benchmark of the OpenCV (Computer Vision) library's built-in performance tests. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenCV 4.5.4Test: DNN - Deep Neural NetworkRyzen 7 5800X3DRyzen 7 5800XRyzen 9 5950X4K8K12K16K20KSE +/- 18.50, N = 7SE +/- 60.94, N = 15SE +/- 198.04, N = 355326655192431. (CXX) g++ options: -fPIC -fsigned-char -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -msse -msse2 -msse3 -fvisibility=hidden -O3 -shared

Blender

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

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.0Blend File: Barbershop - Compute: CPU-OnlyEpyc 7702-retestRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D30060090012001500SE +/- 0.38, N = 3SE +/- 0.12, N = 3SE +/- 0.30, N = 3SE +/- 1.63, N = 3404.47780.071379.081387.02

KTX-Software toktx

This is a benchmark of The Khronos Group's KTX-Software library and tools. KTX-Software provides "toktx" for converting/creating in the KTX container format for image textures. This benchmark times how long it takes to convert to KTX 2.0 format with various settings using a reference PNG sample input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterKTX-Software toktx 4.0Settings: UASTC 4 + Zstd Compression 19Epyc 7702-retestRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D60120180240300SE +/- 0.08, N = 3SE +/- 0.23, N = 3SE +/- 0.16, N = 3SE +/- 0.20, N = 386.16159.15281.59290.85

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPURyzen 9 5950XRyzen 7 5800X3DRyzen 7 5800X0.3740.7481.1221.4961.87SE +/- 0.004708, N = 3SE +/- 0.000684, N = 5SE +/- 0.000985, N = 30.5045310.6031081.662040MIN: 0.46MIN: 0.58MIN: 1.611. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl

OSPray

OpenBenchmarking.orgItems Per Second, More Is BetterOSPray 2.9Benchmark: particle_volume/scivis/real_timeEpyc 7702-retestEpyc 7702Ryzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D1020304050SE +/- 0.03, N = 3SE +/- 0.12, N = 3SE +/- 0.07, N = 3SE +/- 0.05, N = 3SE +/- 0.01, N = 345.3545.3225.1614.7514.40

OpenBenchmarking.orgItems Per Second, More Is BetterOSPray 2.9Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_timeEpyc 7702Epyc 7702-retestRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D246810SE +/- 0.01643, N = 3SE +/- 0.00542, N = 3SE +/- 0.00069, N = 3SE +/- 0.00144, N = 3SE +/- 0.00560, N = 38.218468.216494.809932.732622.63950

OpenBenchmarking.orgItems Per Second, More Is BetterOSPray 2.9Benchmark: gravity_spheres_volume/dim_512/ao/real_timeEpyc 7702-retestEpyc 7702Ryzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D1.22252.4453.66754.896.1125SE +/- 0.03894, N = 3SE +/- 0.03577, N = 3SE +/- 0.00702, N = 3SE +/- 0.00312, N = 3SE +/- 0.00319, N = 35.433325.375373.201781.790901.74532

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 7 5800X3DRyzen 7 5800XRyzen 9 5950X2K4K6K8K10KSE +/- 57.84, N = 7SE +/- 4.73, N = 12SE +/- 13.04, N = 38711.603363.313233.981. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

TensorFlow Lite

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

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception V4Epyc 7702Epyc 7702-retestRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D500K1000K1500K2000K2500KSE +/- 4312.53, N = 3SE +/- 3635.72, N = 3SE +/- 470.57, N = 3SE +/- 1440.02, N = 3SE +/- 1467.88, N = 3914269916501133708023467572429047

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 7702-retestRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D5010015020025078.02119.62201.38205.80

TensorFlow Lite

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

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception ResNet V2Epyc 7702Epyc 7702-retestRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D500K1000K1500K2000K2500KSE +/- 5739.64, N = 3SE +/- 5600.71, N = 3SE +/- 558.13, N = 3SE +/- 1053.82, N = 3SE +/- 3045.63, N = 3854996856132120365321178472197410

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 7 5800X3DRyzen 7 5800XRyzen 9 5950X120240360480600SE +/- 1.41, N = 4SE +/- 0.16, N = 3SE +/- 0.15, N = 3533.35220.59213.521. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

Zstd Compression

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

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 8 - Compression SpeedRyzen 7 5800X3DRyzen 9 5950XRyzen 7 5800X30060090012001500SE +/- 2.41, N = 3SE +/- 10.27, N = 3SE +/- 6.91, N = 151511.71301.4623.91. (CC) gcc options: -O3 -pthread -lz -llzma

TensorFlow Lite

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

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet QuantEpyc 7702Epyc 7702-retestRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D30K60K90K120K150KSE +/- 568.85, N = 4SE +/- 411.52, N = 3SE +/- 58.26, N = 3SE +/- 71.37, N = 3SE +/- 42.23, N = 353733.054149.269722.1124552.0129315.0

Mobile Neural Network

MNN is the Mobile Neural Network as a highly efficient, lightweight deep learning framework developed by Alibaba. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: mobilenetV3Ryzen 7 5800XRyzen 7 5800X3DRyzen 9 5950X0.52111.04221.56332.08442.6055SE +/- 0.006, N = 3SE +/- 0.001, N = 3SE +/- 0.002, N = 31.0181.0772.316MIN: 0.99 / MAX: 1.96MIN: 1.06 / MAX: 1.59MIN: 1.86 / MAX: 3.11. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

TensorFlow Lite

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

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: SqueezeNetEpyc 7702Epyc 7702-retestRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D40K80K120K160K200KSE +/- 239.31, N = 3SE +/- 372.35, N = 3SE +/- 82.30, N = 3SE +/- 131.90, N = 3SE +/- 105.31, N = 375401.376617.994571.7162834.0168821.0

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet FloatEpyc 7702-retestEpyc 7702Ryzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D20K40K60K80K100KSE +/- 556.33, N = 3SE +/- 232.59, N = 3SE +/- 27.44, N = 3SE +/- 58.07, N = 3SE +/- 105.70, N = 351439.351992.462457.1109099.0113086.0

OpenFOAM

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

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 8Input: Motorbike 30MRyzen 7 5800X3DRyzen 9 5950XRyzen 7 5800X4080120160200SE +/- 0.24, N = 3SE +/- 0.18, N = 3SE +/- 0.17, N = 381.1098.10177.07-lfiniteVolume -lmeshTools1. (CXX) g++ options: -std=c++11 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -ldynamicMesh -lgenericPatchFields -lOpenFOAM -ldl -lm

KTX-Software toktx

This is a benchmark of The Khronos Group's KTX-Software library and tools. KTX-Software provides "toktx" for converting/creating in the KTX container format for image textures. This benchmark times how long it takes to convert to KTX 2.0 format with various settings using a reference PNG sample input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterKTX-Software toktx 4.0Settings: Zstd Compression 19Ryzen 7 5800X3DRyzen 7 5800XRyzen 9 5950XEpyc 7702-retest714212835SE +/- 0.01, N = 4SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.06, N = 313.3014.5214.7127.75

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 20210720Target: CPU - Model: shufflenet-v2Ryzen 7 5800XRyzen 7 5800X3DRyzen 9 5950X0.9361.8722.8083.7444.68SE +/- 0.02, N = 7SE +/- 0.00, N = 3SE +/- 0.03, N = 32.022.104.16MIN: 1.97 / MAX: 9.79MIN: 2.07 / MAX: 3.23MIN: 4.04 / MAX: 5.531. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU-v2-v2 - Model: mobilenet-v2Ryzen 7 5800X3DRyzen 7 5800XRyzen 9 5950X0.96981.93962.90943.87924.849SE +/- 0.01, N = 3SE +/- 0.01, N = 15SE +/- 0.01, N = 32.152.364.31MIN: 2.08 / MAX: 2.93MIN: 2.24 / MAX: 19.98MIN: 4.18 / MAX: 4.561. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU-v3-v3 - Model: mobilenet-v3Ryzen 7 5800X3DRyzen 7 5800XRyzen 9 5950X0.85051.7012.55153.4024.2525SE +/- 0.00, N = 3SE +/- 0.00, N = 15SE +/- 0.01, N = 31.912.013.78MIN: 1.87 / MAX: 2.37MIN: 1.96 / MAX: 2.89MIN: 3.71 / MAX: 4.061. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

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 RateRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D3691215SE +/- 0.071660, N = 3SE +/- 0.054523, N = 3SE +/- 0.026965, N = 39.5100685.1521864.8384311. (CC) gcc options: -O3 -march=native -fopenmp

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.DRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D400800120016002000SE +/- 7.91, N = 3SE +/- 3.38, N = 3SE +/- 4.55, N = 31833.42965.94938.171. (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 4.1.2

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 20210720Target: CPU - Model: mnasnetRyzen 7 5800XRyzen 7 5800X3DRyzen 9 5950X0.8641.7282.5923.4564.32SE +/- 0.01, N = 15SE +/- 0.01, N = 3SE +/- 0.01, N = 31.972.023.84MIN: 1.89 / MAX: 3.67MIN: 1.97 / MAX: 2.58MIN: 3.78 / MAX: 4.031. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Appleseed

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

OpenBenchmarking.orgSeconds, Fewer Is BetterAppleseed 2.0 BetaScene: EmilyEpyc 7702-retestRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D70140210280350162.93194.27311.76316.88

OSPray Studio

Intel OSPray Studio is an open-source, interactive visualization and ray-tracing software package. OSPray Studio makes use of Intel OSPray, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPray builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOSPray Studio 0.10Camera: 2 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path TracerRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D20K40K60K80K100KSE +/- 66.91, N = 3SE +/- 261.55, N = 3SE +/- 59.40, N = 35034296945974341. (CXX) g++ options: -O3 -ldl

OpenBenchmarking.orgms, Fewer Is BetterOSPray Studio 0.10Camera: 1 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path TracerRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D20K40K60K80K100KSE +/- 60.40, N = 3SE +/- 240.81, N = 3SE +/- 140.94, N = 34982495319963661. (CXX) g++ options: -O3 -ldl

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 JMHThroughputRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D6000M12000M18000M24000M30000M29174162897.2315581729946.6315094033350.86

Mobile Neural Network

MNN is the Mobile Neural Network as a highly efficient, lightweight deep learning framework developed by Alibaba. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: MobileNetV2_224Ryzen 7 5800XRyzen 7 5800X3DRyzen 9 5950X0.73711.47422.21132.94843.6855SE +/- 0.019, N = 3SE +/- 0.018, N = 3SE +/- 0.033, N = 31.7021.8073.276MIN: 1.66 / MAX: 3.58MIN: 1.77 / MAX: 2.82MIN: 3.19 / MAX: 4.491. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -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 - GriddingRyzen 7 5800X3DRyzen 9 5950XRyzen 7 5800X2K4K6K8K10KSE +/- 94.05, N = 3SE +/- 27.68, N = 3SE +/- 0.00, N = 38558.436615.254447.381. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

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.CRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D400800120016002000SE +/- 19.23, N = 5SE +/- 3.58, N = 3SE +/- 3.12, N = 51812.54968.54943.761. (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 4.1.2

N-Queens

This is a test of the OpenMP version of a test that solves the N-queens problem. The board problem size is 18. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterN-Queens 1.0Elapsed TimeRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D3691215SE +/- 0.002, N = 3SE +/- 0.001, N = 3SE +/- 0.006, N = 47.07713.12013.5351. (CC) gcc options: -static -fopenmp -O3 -march=native

toyBrot Fractal Generator

ToyBrot is a Mandelbrot fractal generator supporting C++ threads/tasks, OpenMP, Intel Threaded Building Blocks (TBB), and other targets. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BettertoyBrot Fractal Generator 2020-11-18Implementation: TBBRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D8K16K24K32K40KSE +/- 10.73, N = 3SE +/- 238.41, N = 3SE +/- 198.08, N = 31906735267364021. (CXX) g++ options: -O3 -lpthread

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 SolveRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D1326395265SE +/- 0.08, N = 3SE +/- 0.03, N = 3SE +/- 0.06, N = 331.6558.1360.121. (CXX) g++ options: -fopenmp -O2 -march=native

OpenSSL

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

OpenBenchmarking.orgverify/s, More Is BetterOpenSSL 3.0Algorithm: RSA4096Ryzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D70K140K210K280K350KSE +/- 60.52, N = 3SE +/- 26.60, N = 3SE +/- 16.89, N = 3311721.4170460.4164163.31. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

toyBrot Fractal Generator

ToyBrot is a Mandelbrot fractal generator supporting C++ threads/tasks, OpenMP, Intel Threaded Building Blocks (TBB), and other targets. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BettertoyBrot Fractal Generator 2020-11-18Implementation: OpenMPRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D8K16K24K32K40KSE +/- 19.13, N = 3SE +/- 16.70, N = 3SE +/- 30.56, N = 31934135475366831. (CXX) g++ options: -O3 -lpthread

OpenSSL

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

OpenBenchmarking.orgsign/s, More Is BetterOpenSSL 3.0Algorithm: RSA4096Ryzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D10002000300040005000SE +/- 4.42, N = 3SE +/- 2.57, N = 3SE +/- 2.35, N = 34765.82609.82514.81. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

Rodinia

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

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP StreamclusterRyzen 7 5800X3DRyzen 7 5800XRyzen 9 5950X48121620SE +/- 0.007, N = 6SE +/- 0.008, N = 3SE +/- 0.183, N = 38.26115.26615.6501. (CXX) g++ options: -O2 -lOpenCL

toyBrot Fractal Generator

ToyBrot is a Mandelbrot fractal generator supporting C++ threads/tasks, OpenMP, Intel Threaded Building Blocks (TBB), and other targets. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BettertoyBrot Fractal Generator 2020-11-18Implementation: C++ ThreadsRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D8K16K24K32K40KSE +/- 18.35, N = 3SE +/- 6.57, N = 3SE +/- 26.74, N = 31919735156362981. (CXX) g++ options: -O3 -lpthread

GraphicsMagick

This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample 6000x4000 pixel JPEG image. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: SharpenRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D50100150200250SE +/- 0.67, N = 3SE +/- 0.00, N = 3SE +/- 0.33, N = 32251231191. (CC) gcc options: -fopenmp -O2 -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lxml2 -lz -lm -lpthread

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 BenchmarkRyzen 9 5950XRyzen 7 5800X3DRyzen 7 5800XEpyc 7702-retestEpyc 7702130260390520650SE +/- 7.26, N = 4SE +/- 1.69, N = 3SE +/- 1.23, N = 3SE +/- 0.58, N = 3SE +/- 0.66, N = 3608.97599.65588.69325.09324.21

toyBrot Fractal Generator

ToyBrot is a Mandelbrot fractal generator supporting C++ threads/tasks, OpenMP, Intel Threaded Building Blocks (TBB), and other targets. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BettertoyBrot Fractal Generator 2020-11-18Implementation: C++ TasksRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D8K16K24K32K40KSE +/- 62.10, N = 3SE +/- 20.67, N = 3SE +/- 40.86, N = 31941435060362631. (CXX) g++ options: -O3 -lpthread

GraphicsMagick

This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample 6000x4000 pixel JPEG image. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: EnhancedRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D90180270360450SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 34212342271. (CC) gcc options: -fopenmp -O2 -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lxml2 -lz -lm -lpthread

OpenSSL

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

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.0Algorithm: SHA256Ryzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D5000M10000M15000M20000M25000MSE +/- 93370409.11, N = 3SE +/- 14281170.04, N = 3SE +/- 23531355.03, N = 32566857754714529348317139519780571. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

OSPray Studio

Intel OSPray Studio is an open-source, interactive visualization and ray-tracing software package. OSPray Studio makes use of Intel OSPray, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPray builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOSPray Studio 0.10Camera: 1 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path TracerRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D6001200180024003000SE +/- 1.20, N = 3SE +/- 2.73, N = 3SE +/- 4.91, N = 31543280828261. (CXX) g++ options: -O3 -ldl

OpenBenchmarking.orgms, Fewer Is BetterOSPray Studio 0.10Camera: 2 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path TracerRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D6001200180024003000SE +/- 0.88, N = 3SE +/- 2.08, N = 3SE +/- 7.22, N = 31562285828581. (CXX) g++ options: -O3 -ldl

OpenBenchmarking.orgms, Fewer Is BetterOSPray Studio 0.10Camera: 3 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path TracerRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D7001400210028003500SE +/- 3.53, N = 3SE +/- 9.54, N = 3SE +/- 2.89, N = 31835333933561. (CXX) g++ options: -O3 -ldl

OpenBenchmarking.orgms, Fewer Is BetterOSPray Studio 0.10Camera: 2 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path TracerRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D10K20K30K40K50KSE +/- 17.19, N = 3SE +/- 43.11, N = 3SE +/- 83.05, N = 32507845616458601. (CXX) g++ options: -O3 -ldl

OpenBenchmarking.orgms, Fewer Is BetterOSPray Studio 0.10Camera: 1 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path TracerRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D10K20K30K40K50KSE +/- 1.76, N = 3SE +/- 25.96, N = 3SE +/- 107.70, N = 32484844956453061. (CXX) g++ options: -O3 -ldl

OpenBenchmarking.orgms, Fewer Is BetterOSPray Studio 0.10Camera: 3 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path TracerRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D11K22K33K44K55KSE +/- 9.24, N = 3SE +/- 67.13, N = 3SE +/- 46.46, N = 32954853359536251. (CXX) g++ options: -O3 -ldl

Stargate Digital Audio Workstation

Stargate is an open-source, cross-platform digital audio workstation (DAW) software package with "a unique and carefully curated experience" with scalability from old systems up through modern multi-core systems. Stargate is GPLv3 licensed and makes use of Qt5 (PyQt5) for its user-interface. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRender Ratio, More Is BetterStargate Digital Audio Workstation 21.10.9Sample Rate: 44100 - Buffer Size: 1024Ryzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D246810SE +/- 0.011671, N = 3SE +/- 0.003900, N = 3SE +/- 0.010070, N = 36.7476613.8856453.7493951. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions

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 7 5800X3DRyzen 7 5800XRyzen 9 5950X30060090012001500SE +/- 13.68, N = 3SE +/- 6.84, N = 3SE +/- 8.54, N = 912499576971. (CXX) g++ options: -flto -pthread

Stockfish

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

OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 13Total TimeRyzen 9 5950XRyzen 7 5800X3DRyzen 7 5800X12M24M36M48M60MSE +/- 385704.04, N = 15SE +/- 207082.21, N = 3SE +/- 289117.59, N = 35613737231836776314013141. (CXX) g++ options: -lgcov -m64 -lpthread -fno-exceptions -std=c++17 -fprofile-use -fno-peel-loops -fno-tracer -pedantic -O3 -msse -msse3 -mpopcnt -mavx2 -msse4.1 -mssse3 -msse2 -mbmi2 -flto -flto=jobserver

KTX-Software toktx

This is a benchmark of The Khronos Group's KTX-Software library and tools. KTX-Software provides "toktx" for converting/creating in the KTX container format for image textures. This benchmark times how long it takes to convert to KTX 2.0 format with various settings using a reference PNG sample input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterKTX-Software toktx 4.0Settings: UASTC 3Epyc 7702Epyc 7702-retestRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D3691215SE +/- 0.029, N = 3SE +/- 0.024, N = 3SE +/- 0.006, N = 3SE +/- 0.006, N = 3SE +/- 0.007, N = 55.8125.8296.47010.02310.382

Facebook RocksDB

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

OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 7.0.1Test: Random ReadRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D20M40M60M80M100MSE +/- 241421.01, N = 3SE +/- 82279.34, N = 3SE +/- 68132.96, N = 310751619262502598605756711. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

ASTC Encoder

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

OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 3.2Preset: ExhaustiveRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D1326395265SE +/- 0.07, N = 3SE +/- 0.07, N = 3SE +/- 0.07, N = 333.3056.8759.051. (CXX) g++ options: -O3 -flto -pthread

Stargate Digital Audio Workstation

Stargate is an open-source, cross-platform digital audio workstation (DAW) software package with "a unique and carefully curated experience" with scalability from old systems up through modern multi-core systems. Stargate is GPLv3 licensed and makes use of Qt5 (PyQt5) for its user-interface. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRender Ratio, More Is BetterStargate Digital Audio Workstation 21.10.9Sample Rate: 44100 - Buffer Size: 512Ryzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D246810SE +/- 0.034193, N = 3SE +/- 0.004546, N = 3SE +/- 0.001790, N = 36.4817713.8001783.6730151. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions

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 20210720Target: CPU - Model: googlenetRyzen 7 5800X3DRyzen 7 5800XRyzen 9 5950X3691215SE +/- 0.02, N = 3SE +/- 0.06, N = 15SE +/- 0.06, N = 37.299.6412.84MIN: 7.14 / MAX: 8.43MIN: 9.08 / MAX: 12.9MIN: 12.39 / MAX: 20.271. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Stargate Digital Audio Workstation

Stargate is an open-source, cross-platform digital audio workstation (DAW) software package with "a unique and carefully curated experience" with scalability from old systems up through modern multi-core systems. Stargate is GPLv3 licensed and makes use of Qt5 (PyQt5) for its user-interface. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRender Ratio, More Is BetterStargate Digital Audio Workstation 21.10.9Sample Rate: 480000 - Buffer Size: 1024Ryzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D246810SE +/- 0.047545, N = 3SE +/- 0.003806, N = 3SE +/- 0.001493, N = 36.5305013.8358773.7173141. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions

IndigoBench

This is a test of Indigo Renderer's IndigoBench benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.4Acceleration: CPU - Scene: SupercarRyzen 9 5950XRyzen 7 5800X3DRyzen 7 5800X246810SE +/- 0.019, N = 3SE +/- 0.005, N = 3SE +/- 0.001, N = 38.5694.9264.889

OSPray Studio

Intel OSPray Studio is an open-source, interactive visualization and ray-tracing software package. OSPray Studio makes use of Intel OSPray, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPray builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOSPray Studio 0.10Camera: 3 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path TracerRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D20K40K60K80K100KSE +/- 85.03, N = 3SE +/- 75.76, N = 3SE +/- 163.91, N = 3645901125021130411. (CXX) g++ options: -O3 -ldl

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 4KRyzen 9 5950XRyzen 7 5800X3DRyzen 7 5800X612182430SE +/- 0.11, N = 3SE +/- 0.07, N = 3SE +/- 0.17, N = 526.6516.1415.231. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

Stargate Digital Audio Workstation

Stargate is an open-source, cross-platform digital audio workstation (DAW) software package with "a unique and carefully curated experience" with scalability from old systems up through modern multi-core systems. Stargate is GPLv3 licensed and makes use of Qt5 (PyQt5) for its user-interface. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRender Ratio, More Is BetterStargate Digital Audio Workstation 21.10.9Sample Rate: 480000 - Buffer Size: 512Ryzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D246810SE +/- 0.028020, N = 3SE +/- 0.004837, N = 3SE +/- 0.011062, N = 36.3428043.7623823.6392511. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions

GraphicsMagick

This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample 6000x4000 pixel JPEG image. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: SwirlRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D2004006008001000SE +/- 5.78, N = 3SE +/- 1.20, N = 3SE +/- 0.88, N = 310746416221. (CC) gcc options: -fopenmp -O2 -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lxml2 -lz -lm -lpthread

Embree

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

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer ISPC - Model: CrownRyzen 9 5950XRyzen 7 5800X3DRyzen 7 5800X510152025SE +/- 0.05, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 322.0913.2112.81MIN: 21.83 / MAX: 22.58MIN: 13.1 / MAX: 13.36MIN: 12.7 / MAX: 13.05

IndigoBench

This is a test of Indigo Renderer's IndigoBench benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.4Acceleration: CPU - Scene: BedroomRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D0.91261.82522.73783.65044.563SE +/- 0.007, N = 3SE +/- 0.003, N = 3SE +/- 0.004, N = 34.0562.3552.352

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 20210720Target: CPU - Model: efficientnet-b0Ryzen 7 5800X3DRyzen 7 5800XRyzen 9 5950X1.16552.3313.49654.6625.8275SE +/- 0.01, N = 3SE +/- 0.03, N = 15SE +/- 0.01, N = 33.013.245.18MIN: 2.95 / MAX: 3.71MIN: 3.11 / MAX: 20.85MIN: 5.12 / MAX: 5.51. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Embree

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

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer - Model: CrownRyzen 9 5950XRyzen 7 5800X3DRyzen 7 5800X612182430SE +/- 0.08, N = 3SE +/- 0.08, N = 3SE +/- 0.08, N = 323.8414.4113.87MIN: 23.5 / MAX: 24.49MIN: 14.18 / MAX: 14.65MIN: 13.62 / MAX: 14.22

Rodinia

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

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP LavaMDRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D4080120160200SE +/- 0.21, N = 3SE +/- 0.45, N = 3SE +/- 0.31, N = 3111.50183.73191.151. (CXX) g++ options: -O2 -lOpenCL

x264

This is a simple test of the x264 encoder run on the CPU (OpenCL support disabled) with a sample video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betterx264 2019-12-17H.264 Video EncodingRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D4080120160200SE +/- 2.07, N = 14SE +/- 1.10, N = 7SE +/- 0.95, N = 7203.17121.44118.791. (CC) gcc options: -ldl -m64 -lm -lpthread -O3 -ffast-math -std=gnu99 -fPIC -fomit-frame-pointer -fno-tree-vectorize

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: EigenRyzen 7 5800X3DRyzen 7 5800XRyzen 9 5950X2004006008001000SE +/- 7.88, N = 3SE +/- 13.08, N = 3SE +/- 8.13, N = 911609106791. (CXX) g++ options: -flto -pthread

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 20210720Target: CPU - Model: blazefaceRyzen 7 5800XRyzen 7 5800X3DRyzen 9 5950X0.40280.80561.20841.61122.014SE +/- 0.01, N = 15SE +/- 0.00, N = 3SE +/- 0.01, N = 31.051.061.79MIN: 1.01 / MAX: 2.28MIN: 1.04 / MAX: 1.4MIN: 1.76 / MAX: 1.971. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Facebook RocksDB

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

OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 7.0.1Test: Read While WritingRyzen 9 5950XRyzen 7 5800X3DRyzen 7 5800X800K1600K2400K3200K4000KSE +/- 18864.84, N = 3SE +/- 25911.37, N = 5SE +/- 13078.28, N = 33968016236473123313001. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

SVT-HEVC

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

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 1 - Input: Bosphorus 1080pRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D48121620SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 316.149.779.521. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

POV-Ray

This is a test of POV-Ray, the Persistence of Vision Raytracer. POV-Ray is used to create 3D graphics using ray-tracing. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPOV-Ray 3.7.0.7Trace TimeRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D918273645SE +/- 0.06, N = 3SE +/- 0.15, N = 3SE +/- 0.23, N = 323.3938.3039.471. (CXX) g++ options: -pipe -O3 -ffast-math -march=native -R/usr/lib -lXpm -lSM -lICE -lX11 -ltiff -ljpeg -lpng -lz -lrt -lm -lboost_thread -lboost_system

Mobile Neural Network

MNN is the Mobile Neural Network as a highly efficient, lightweight deep learning framework developed by Alibaba. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: mobilenet-v1-1.0Ryzen 7 5800XRyzen 7 5800X3DRyzen 9 5950X0.59671.19341.79012.38682.9835SE +/- 0.010, N = 3SE +/- 0.013, N = 3SE +/- 0.035, N = 31.5751.6712.652MIN: 1.54 / MAX: 2.72MIN: 1.62 / MAX: 2.72MIN: 2.51 / MAX: 4.221. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

KTX-Software toktx

This is a benchmark of The Khronos Group's KTX-Software library and tools. KTX-Software provides "toktx" for converting/creating in the KTX container format for image textures. This benchmark times how long it takes to convert to KTX 2.0 format with various settings using a reference PNG sample input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterKTX-Software toktx 4.0Settings: Zstd Compression 9Ryzen 7 5800XRyzen 9 5950XRyzen 7 5800X3DEpyc 7702Epyc 7702-retest0.78591.57182.35773.14363.9295SE +/- 0.003, N = 3SE +/- 0.004, N = 3SE +/- 0.001, N = 10SE +/- 0.022, N = 3SE +/- 0.051, N = 152.1152.1322.2743.4173.493

Embree

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

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer ISPC - Model: Asian DragonRyzen 9 5950XRyzen 7 5800X3DRyzen 7 5800X510152025SE +/- 0.08, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 322.9114.6013.88MIN: 22.7 / MAX: 23.31MIN: 14.5 / MAX: 14.81MIN: 13.8 / MAX: 14.05

PHPBench

PHPBench is a benchmark suite for PHP. It performs a large number of simple tests in order to bench various aspects of the PHP interpreter. PHPBench can be used to compare hardware, operating systems, PHP versions, PHP accelerators and caches, compiler options, etc. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterPHPBench 0.8.1PHP Benchmark SuiteRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3DEpyc 7702-retest200K400K600K800K1000KSE +/- 10608.77, N = 4SE +/- 5151.80, N = 3SE +/- 3999.60, N = 3SE +/- 3067.32, N = 3943566927680892442572391

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPURyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D0.40220.80441.20661.60882.011SE +/- 0.00569, N = 3SE +/- 0.00199, N = 3SE +/- 0.00284, N = 31.087201.728771.78756MIN: 0.97MIN: 1.7MIN: 1.751. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl

GraphicsMagick

This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample 6000x4000 pixel JPEG image. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: ResizingRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D400800120016002000SE +/- 1.00, N = 3SE +/- 0.58, N = 3SE +/- 1.33, N = 31812116211101. (CC) gcc options: -fopenmp -O2 -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lxml2 -lz -lm -lpthread

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 20210720Target: CPU - Model: mobilenetRyzen 7 5800X3DRyzen 7 5800XRyzen 9 5950X3691215SE +/- 0.02, N = 3SE +/- 0.07, N = 15SE +/- 0.05, N = 37.5310.7312.27MIN: 7.37 / MAX: 8.81MIN: 10.29 / MAX: 27.85MIN: 11.77 / MAX: 12.791. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Embree

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

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer - Model: Asian DragonRyzen 9 5950XRyzen 7 5800X3DRyzen 7 5800X612182430SE +/- 0.18, N = 3SE +/- 0.06, N = 3SE +/- 0.06, N = 324.6916.2315.20MIN: 24.3 / MAX: 25.5MIN: 16.05 / MAX: 16.56MIN: 15.03 / MAX: 15.46

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPURyzen 7 5800X3DRyzen 7 5800XRyzen 9 5950X510152025SE +/- 0.18, N = 15SE +/- 0.08, N = 3SE +/- 0.05, N = 311.8718.7819.24MIN: 11.35MIN: 16.9MIN: 18.791. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl

Liquid-DSP

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

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 16 - Buffer Length: 256 - Filter Length: 57Ryzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D200M400M600M800M1000MSE +/- 2511971.34, N = 3SE +/- 940283.65, N = 3SE +/- 651314.91, N = 310133000006436000006256866671. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

libavif avifenc

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

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 6Ryzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D3691215SE +/- 0.006, N = 3SE +/- 0.026, N = 3SE +/- 0.011, N = 56.0539.3659.7071. (CXX) g++ options: -O3 -fPIC -lm

Appleseed

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

OpenBenchmarking.orgSeconds, Fewer Is BetterAppleseed 2.0 BetaScene: Material TesterRyzen 9 5950XEpyc 7702-retestRyzen 7 5800XRyzen 7 5800X3D4080120160200114.74173.69176.51183.23

Timed MPlayer Compilation

This test times how long it takes to build the MPlayer open-source media player program. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MPlayer Compilation 1.5Time To CompileRyzen 9 5950XRyzen 7 5800X3DRyzen 7 5800X714212835SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 319.1229.9030.53

ONNX Runtime

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

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: super-resolution-10 - Device: CPU - Executor: StandardRyzen 7 5800X3DRyzen 7 5800X14002800420056007000SE +/- 48.99, N = 12SE +/- 28.44, N = 3672442231. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

Rodinia

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

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP CFD SolverRyzen 9 5950XRyzen 7 5800X3DRyzen 7 5800X48121620SE +/- 0.05, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 311.0217.0017.471. (CXX) g++ options: -O2 -lOpenCL

Mobile Neural Network

MNN is the Mobile Neural Network as a highly efficient, lightweight deep learning framework developed by Alibaba. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: squeezenetv1.1Ryzen 7 5800XRyzen 7 5800X3DRyzen 9 5950X0.87821.75642.63463.51284.391SE +/- 0.008, N = 3SE +/- 0.012, N = 3SE +/- 0.005, N = 32.5172.5863.903MIN: 2.47 / MAX: 3.98MIN: 2.54 / MAX: 3.66MIN: 3.83 / MAX: 11.531. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

GraphicsMagick

This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample 6000x4000 pixel JPEG image. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: Noise-GaussianRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D90180270360450SE +/- 1.45, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 34272852761. (CC) gcc options: -fopenmp -O2 -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lxml2 -lz -lm -lpthread

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPURyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D1.26422.52843.79265.05686.321SE +/- 0.00158, N = 3SE +/- 0.01720, N = 3SE +/- 0.00363, N = 93.635715.464125.61850MIN: 3.43MIN: 5.3MIN: 5.461. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl

dav1d

Dav1d is an open-source, speedy AV1 video decoder. This test profile times how long it takes to decode sample AV1 video content. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is Betterdav1d 1.0Video Input: Chimera 1080pRyzen 7 5800X3DRyzen 7 5800XRyzen 9 5950X170340510680850SE +/- 0.94, N = 4SE +/- 1.74, N = 3SE +/- 6.61, N = 3774.13718.64502.741. (CC) gcc options: -pthread -lm

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 SecondRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D140K280K420K560K700KSE +/- 578.10, N = 3SE +/- 1098.96, N = 3SE +/- 1111.17, N = 3642198.78434185.16417397.201. (CC) gcc options: -O2 -lrt" -lrt

SVT-HEVC

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

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 7 - Input: Bosphorus 1080pRyzen 9 5950XRyzen 7 5800X3DRyzen 7 5800X50100150200250SE +/- 0.24, N = 3SE +/- 0.11, N = 8SE +/- 0.17, N = 3223.21145.80145.231. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

Timed LLVM Compilation

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 13.0Build System: NinjaRyzen 9 5950XRyzen 7 5800X3DRyzen 7 5800X130260390520650SE +/- 0.24, N = 3SE +/- 0.05, N = 3SE +/- 0.12, N = 3378.22535.08580.59

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPURyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D0.56451.1291.69352.2582.8225SE +/- 0.00635, N = 3SE +/- 0.00802, N = 3SE +/- 0.00784, N = 91.634432.420912.50875MIN: 1.5MIN: 2.36MIN: 2.41. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPURyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D0.28020.56040.84061.12081.401SE +/- 0.009458, N = 3SE +/- 0.000342, N = 3SE +/- 0.002415, N = 40.8118411.2145001.245390MIN: 0.73MIN: 1.18MIN: 1.221. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl

SVT-AV1

This is a benchmark of the SVT-AV1 open-source video encoder/decoder. SVT-AV1 was originally developed by Intel as part of their Open Visual Cloud / Scalable Video Technology (SVT). Development of SVT-AV1 has since moved to the Alliance for Open Media as part of upstream AV1 development. SVT-AV1 is a CPU-based multi-threaded video encoder for the AV1 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.9Encoder Mode: Preset 8 - Input: Bosphorus 4KRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D1122334455SE +/- 0.31, N = 3SE +/- 0.08, N = 3SE +/- 0.03, N = 350.5633.6033.391. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie

OSPray

OpenBenchmarking.orgItems Per Second, More Is BetterOSPray 2.9Benchmark: particle_volume/pathtracer/real_timeRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3DEpyc 7702-retestEpyc 770270140210280350SE +/- 0.01, N = 3SE +/- 0.13, N = 3SE +/- 0.08, N = 3SE +/- 0.22, N = 3SE +/- 0.10, N = 3333.28256.19247.21220.38220.13

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 - DegriddingRyzen 9 5950XRyzen 7 5800X3DRyzen 7 5800X14002800420056007000SE +/- 27.00, N = 3SE +/- 53.33, N = 3SE +/- 40.73, N = 36505.906453.224302.341. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

SVT-AV1

This is a benchmark of the SVT-AV1 open-source video encoder/decoder. SVT-AV1 was originally developed by Intel as part of their Open Visual Cloud / Scalable Video Technology (SVT). Development of SVT-AV1 has since moved to the Alliance for Open Media as part of upstream AV1 development. SVT-AV1 is a CPU-based multi-threaded video encoder for the AV1 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.9Encoder Mode: Preset 4 - Input: Bosphorus 4KRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D0.92181.84362.76543.68724.609SE +/- 0.009, N = 3SE +/- 0.004, N = 3SE +/- 0.004, N = 34.0972.7582.7141. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie

Timed LLVM Compilation

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 13.0Build System: Unix MakefilesRyzen 9 5950XRyzen 7 5800X3DRyzen 7 5800X130260390520650SE +/- 1.74, N = 3SE +/- 0.92, N = 3SE +/- 2.89, N = 3397.94552.65600.18

libavif avifenc

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

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 0Ryzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D306090120150SE +/- 0.25, N = 3SE +/- 0.07, N = 3SE +/- 0.26, N = 3102.26148.42153.441. (CXX) g++ options: -O3 -fPIC -lm

Timed Godot Game Engine Compilation

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Godot Game Engine Compilation 3.2.3Time To CompileRyzen 9 5950XRyzen 7 5800X3DRyzen 7 5800X20406080100SE +/- 0.34, N = 3SE +/- 0.03, N = 3SE +/- 0.09, N = 367.9398.41101.15

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPURyzen 7 5800X3DRyzen 9 5950XRyzen 7 5800X510152025SE +/- 0.01, N = 7SE +/- 0.01, N = 3SE +/- 0.00, N = 313.6017.3020.25MIN: 13.12MIN: 16.94MIN: 19.651. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl

Rodinia

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

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP LeukocyteRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D20406080100SE +/- 0.78, N = 3SE +/- 0.76, N = 3SE +/- 0.75, N = 364.3891.4994.841. (CXX) g++ options: -O2 -lOpenCL

libavif avifenc

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

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 6, LosslessRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D3691215SE +/- 0.011, N = 3SE +/- 0.026, N = 3SE +/- 0.028, N = 48.38311.82612.2981. (CXX) g++ options: -O3 -fPIC -lm

Zstd Compression

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

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19 - Compression SpeedRyzen 9 5950XRyzen 7 5800X3DRyzen 7 5800X1224364860SE +/- 0.00, N = 3SE +/- 0.07, N = 3SE +/- 0.12, N = 351.541.135.31. (CC) gcc options: -O3 -pthread -lz -llzma

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 1080pRyzen 9 5950XRyzen 7 5800X3DRyzen 7 5800X50100150200250SE +/- 0.54, N = 3SE +/- 0.17, N = 8SE +/- 0.49, N = 3219.44161.61151.301. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

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 20210720Target: CPU - Model: resnet18Ryzen 7 5800X3DRyzen 7 5800XRyzen 9 5950X48121620SE +/- 0.06, N = 3SE +/- 0.03, N = 15SE +/- 0.08, N = 310.0012.6714.48MIN: 9.77 / MAX: 10.83MIN: 12.41 / MAX: 14.98MIN: 14.27 / MAX: 15.081. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

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 TimesRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3DEpyc 7702-retest2004006008001000SE +/- 5.93, N = 3SE +/- 6.66, N = 3SE +/- 4.58, N = 3SE +/- 1.20, N = 37417577801069

libavif avifenc

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

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 2Ryzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D1632486480SE +/- 0.09, N = 3SE +/- 0.13, N = 3SE +/- 0.05, N = 350.3769.9072.641. (CXX) g++ options: -O3 -fPIC -lm

Java Gradle Build

This test runs Java software project builds using the Gradle build system. It is intended to give developers an idea as to the build performance for development activities and build servers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterJava Gradle BuildGradle Build: ReactorRyzen 7 5800XRyzen 7 5800X3DRyzen 9 5950X50100150200250SE +/- 1.51, N = 12SE +/- 1.06, N = 3SE +/- 2.45, N = 4152.36156.87217.11

SVT-AV1

This is a benchmark of the SVT-AV1 open-source video encoder/decoder. SVT-AV1 was originally developed by Intel as part of their Open Visual Cloud / Scalable Video Technology (SVT). Development of SVT-AV1 has since moved to the Alliance for Open Media as part of upstream AV1 development. SVT-AV1 is a CPU-based multi-threaded video encoder for the AV1 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.9Encoder Mode: Preset 10 - Input: Bosphorus 4KRyzen 9 5950XRyzen 7 5800X3DRyzen 7 5800X20406080100SE +/- 0.32, N = 3SE +/- 0.17, N = 5SE +/- 0.36, N = 393.2767.7465.671. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie

dav1d

Dav1d is an open-source, speedy AV1 video decoder. This test profile times how long it takes to decode sample AV1 video content. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is Betterdav1d 1.0Video Input: Chimera 1080p 10-bitRyzen 7 5800X3DRyzen 7 5800XRyzen 9 5950X150300450600750SE +/- 1.32, N = 4SE +/- 3.57, N = 3SE +/- 1.19, N = 3692.23521.79489.351. (CC) gcc options: -pthread -lm

ASTC Encoder

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

OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 3.2Preset: ThoroughRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D3691215SE +/- 0.0377, N = 3SE +/- 0.0211, N = 3SE +/- 0.0069, N = 56.95209.43399.82311. (CXX) g++ options: -O3 -flto -pthread

Facebook RocksDB

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

OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 7.0.1Test: Read Random Write RandomRyzen 9 5950XRyzen 7 5800X3DRyzen 7 5800X600K1200K1800K2400K3000KSE +/- 8502.59, N = 3SE +/- 2640.85, N = 3SE +/- 8863.72, N = 32829796201409620045121. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

AOM AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.3Encoder Mode: Speed 8 Realtime - Input: Bosphorus 1080pRyzen 7 5800X3DRyzen 7 5800XRyzen 9 5950X306090120150SE +/- 1.86, N = 15SE +/- 0.55, N = 3SE +/- 1.35, N = 15155.87135.07110.571. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

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 20210720Target: CPU - Model: yolov4-tinyRyzen 7 5800X3DRyzen 7 5800XRyzen 9 5950X510152025SE +/- 0.13, N = 3SE +/- 0.19, N = 15SE +/- 0.09, N = 314.4218.3420.30MIN: 14.15 / MAX: 21.88MIN: 17.36 / MAX: 61.71MIN: 19.91 / MAX: 20.911. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Timed Mesa Compilation

This test profile times how long it takes to compile Mesa with Meson/Ninja. For minimizing build dependencies and avoid versioning conflicts, test this is just the core Mesa build without LLVM or the extra Gallium3D/Mesa drivers enabled. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Mesa Compilation 21.0Time To CompileRyzen 9 5950XRyzen 7 5800X3DRyzen 7 5800X1020304050SE +/- 0.09, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 330.8038.7443.14

KTX-Software toktx

This is a benchmark of The Khronos Group's KTX-Software library and tools. KTX-Software provides "toktx" for converting/creating in the KTX container format for image textures. This benchmark times how long it takes to convert to KTX 2.0 format with various settings using a reference PNG sample input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterKTX-Software toktx 4.0Settings: UASTC 3 + Zstd Compression 19Ryzen 9 5950XRyzen 7 5800X3DRyzen 7 5800XEpyc 7702-retest48121620SE +/- 0.01, N = 3SE +/- 0.01, N = 4SE +/- 0.01, N = 3SE +/- 0.08, N = 310.5213.1514.1214.65

Timed ImageMagick Compilation

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed ImageMagick Compilation 6.9.0Time To CompileRyzen 9 5950XRyzen 7 5800X3DRyzen 7 5800X612182430SE +/- 0.08, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 317.2521.1824.00

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPURyzen 7 5800X3DRyzen 7 5800XRyzen 9 5950X400800120016002000SE +/- 4.74, N = 3SE +/- 4.81, N = 3SE +/- 5.64, N = 31397.681831.791941.58MIN: 1381.91MIN: 1818.12MIN: 1920.621. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl

SVT-AV1

This is a benchmark of the SVT-AV1 open-source video encoder/decoder. SVT-AV1 was originally developed by Intel as part of their Open Visual Cloud / Scalable Video Technology (SVT). Development of SVT-AV1 has since moved to the Alliance for Open Media as part of upstream AV1 development. SVT-AV1 is a CPU-based multi-threaded video encoder for the AV1 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.9Encoder Mode: Preset 8 - Input: Bosphorus 1080pRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D4080120160200SE +/- 0.14, N = 3SE +/- 0.19, N = 3SE +/- 0.35, N = 7167.22122.12120.431. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPURyzen 7 5800X3DRyzen 7 5800XRyzen 9 5950X400800120016002000SE +/- 1.44, N = 3SE +/- 4.18, N = 3SE +/- 12.11, N = 31400.611835.641921.67MIN: 1390.67MIN: 1823.57MIN: 1889.481. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPURyzen 7 5800X3DRyzen 7 5800XRyzen 9 5950X400800120016002000SE +/- 1.35, N = 3SE +/- 7.57, N = 3SE +/- 14.82, N = 101401.651838.681918.24MIN: 1391.86MIN: 1816.96MIN: 1837.781. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl

Zstd Compression

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

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 3 - Compression SpeedRyzen 9 5950XRyzen 7 5800X3DRyzen 7 5800X11002200330044005500SE +/- 7.04, N = 3SE +/- 7.54, N = 3SE +/- 14.80, N = 35301.23942.03891.91. (CC) gcc options: -O3 -pthread -lz -llzma

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 20210720Target: CPU - Model: vgg16Ryzen 7 5800X3DRyzen 7 5800XRyzen 9 5950X1326395265SE +/- 0.07, N = 3SE +/- 0.07, N = 15SE +/- 0.07, N = 343.2156.2258.32MIN: 42.71 / MAX: 48.54MIN: 55.28 / MAX: 198.02MIN: 57.33 / MAX: 65.551. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: IP Shapes 1D - Data Type: f32 - Engine: CPURyzen 7 5800XRyzen 7 5800X3DRyzen 9 5950X0.88591.77182.65773.54364.4295SE +/- 0.00621, N = 3SE +/- 0.03084, N = 5SE +/- 0.00689, N = 32.919742.940533.93742MIN: 2.82MIN: 2.82MIN: 3.751. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl

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 2.2Time To CompileRyzen 9 5950XRyzen 7 5800X3DRyzen 7 5800X1632486480SE +/- 0.08, N = 3SE +/- 0.08, N = 3SE +/- 0.27, N = 354.3970.1272.881. (CC) gcc options: -m64 -ldl -lxkbcommon -lgcc_s -lutil -lrt -lpthread -lm -lc -pie -nodefaultlibs

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 7 5800X3DRyzen 9 5950XRyzen 7 5800X918273645SE +/- 0.02, N = 3SE +/- 0.33, N = 3SE +/- 0.15, N = 327.8134.2336.991. (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

rays1bench

This is a test of rays1bench, a simple path-tracer / ray-tracing that supports SSE and AVX instructions, multi-threading, and other features. This test profile is measuring the performance of the "large scene" in rays1bench. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgmrays/s, More Is Betterrays1bench 2020-01-09Large SceneRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D20406080100SE +/- 0.21, N = 3SE +/- 0.04, N = 3SE +/- 0.09, N = 4102.4179.4877.22

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: IP Shapes 3D - Data Type: f32 - Engine: CPURyzen 7 5800X3DRyzen 9 5950XRyzen 7 5800X3691215SE +/- 0.00148, N = 5SE +/- 0.01785, N = 3SE +/- 0.11773, N = 37.803599.5450910.32280MIN: 7.67MIN: 9.43MIN: 9.911. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl

GEGL

GEGL is the Generic Graphics Library and is the library/framework used by GIMP and other applications like GNOME Photos. This test profile times how long it takes to complete various GEGL operations on a static set of sample JPEG images. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: CropRyzen 7 5800XRyzen 7 5800X3DRyzen 9 5950X246810SE +/- 0.075, N = 3SE +/- 0.034, N = 6SE +/- 0.046, N = 36.3056.5168.296

Operation: Crop

Epyc 7702-retest: The test quit with a non-zero exit status. E: ./gegl: 4: gegl: not found

SVT-HEVC

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

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 10 - Input: Bosphorus 1080pRyzen 9 5950XRyzen 7 5800X3DRyzen 7 5800X80160240320400SE +/- 0.83, N = 3SE +/- 0.44, N = 10SE +/- 1.11, N = 3369.31298.42281.341. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

Facebook RocksDB

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

OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 7.0.1Test: Update RandomRyzen 9 5950XRyzen 7 5800X3DRyzen 7 5800X170K340K510K680K850KSE +/- 1540.47, N = 3SE +/- 2259.63, N = 3SE +/- 2665.90, N = 37754875923285907831. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

OCRMyPDF

OCRMyPDF is an optical character recognition (OCR) text layer to scanned PDF files, producing new PDFs with the text now selectable/searchable/copy-paste capable. OCRMyPDF leverages the Tesseract OCR engine and is written in Python. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOCRMyPDF 13.4.0+dfsgProcessing 60 Page PDF DocumentRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D48121620SE +/- 0.14, N = 4SE +/- 0.09, N = 3SE +/- 0.11, N = 312.9716.3816.91

SVT-AV1

This is a benchmark of the SVT-AV1 open-source video encoder/decoder. SVT-AV1 was originally developed by Intel as part of their Open Visual Cloud / Scalable Video Technology (SVT). Development of SVT-AV1 has since moved to the Alliance for Open Media as part of upstream AV1 development. SVT-AV1 is a CPU-based multi-threaded video encoder for the AV1 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.9Encoder Mode: Preset 10 - Input: Bosphorus 1080pRyzen 9 5950XRyzen 7 5800X3DRyzen 7 5800X80160240320400SE +/- 1.45, N = 3SE +/- 0.43, N = 10SE +/- 1.84, N = 3348.64275.08267.461. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.9Encoder Mode: Preset 4 - Input: Bosphorus 1080pRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D3691215SE +/- 0.016, N = 3SE +/- 0.009, N = 3SE +/- 0.013, N = 311.4399.0978.8401. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie

Timed PHP Compilation

This test times how long it takes to build PHP 7. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed PHP Compilation 7.4.2Time To CompileRyzen 9 5950XRyzen 7 5800X3DRyzen 7 5800X1122334455SE +/- 0.08, N = 3SE +/- 0.04, N = 3SE +/- 0.08, N = 336.0844.4646.40

Zstd Compression

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

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 8, Long Mode - Compression SpeedRyzen 9 5950XRyzen 7 5800X3DRyzen 7 5800X30060090012001500SE +/- 12.85, N = 3SE +/- 3.86, N = 3SE +/- 0.83, N = 31233.31187.8961.01. (CC) gcc options: -O3 -pthread -lz -llzma

Google Draco

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

OpenBenchmarking.orgms, Fewer Is BetterGoogle Draco 1.5.0Model: Church FacadeRyzen 7 5800X3DRyzen 7 5800XRyzen 9 5950X12002400360048006000SE +/- 12.22, N = 7SE +/- 11.02, N = 3SE +/- 18.03, N = 34194515453711. (CXX) g++ options: -O3

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.CRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D5K10K15K20K25KSE +/- 34.07, N = 3SE +/- 13.24, N = 3SE +/- 15.73, N = 324111.9119009.9718839.721. (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 4.1.2

GROMACS

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

OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2021.2Implementation: MPI CPU - Input: water_GMX50_bareRyzen 9 5950XRyzen 7 5800X3DRyzen 7 5800X0.28010.56020.84031.12041.4005SE +/- 0.002, N = 3SE +/- 0.005, N = 3SE +/- 0.002, N = 31.2451.2270.9751. (CXX) g++ options: -O3

Chia Blockchain VDF

Chia is a blockchain and smart transaction platform based on proofs of space and time rather than proofs of work with other cryptocurrencies. This test profile is benchmarking the CPU performance for Chia VDF performance using the Chia VDF benchmark. The Chia VDF is for the Chia Verifiable Delay Function (Proof of Time). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIPS, More Is BetterChia Blockchain VDF 1.0.1Test: Square Assembly OptimizedRyzen 7 5800XRyzen 7 5800X3DRyzen 9 5950X50K100K150K200K250KSE +/- 100.00, N = 3SE +/- 648.93, N = 3SE +/- 1464.01, N = 32339002239671838001. (CXX) g++ options: -flto -no-pie -lgmpxx -lgmp -lboost_system -pthread

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 1080pRyzen 9 5950XRyzen 7 5800X3DRyzen 7 5800X50100150200250SE +/- 1.85, N = 12SE +/- 1.20, N = 9SE +/- 1.87, N = 5225.58204.10178.211. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

Mobile Neural Network

MNN is the Mobile Neural Network as a highly efficient, lightweight deep learning framework developed by Alibaba. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: SqueezeNetV1.0Ryzen 7 5800XRyzen 7 5800X3DRyzen 9 5950X1.17072.34143.51214.68285.8535SE +/- 0.023, N = 3SE +/- 0.002, N = 3SE +/- 0.051, N = 34.1224.2285.203MIN: 4 / MAX: 5.48MIN: 4.19 / MAX: 5.51MIN: 5.05 / MAX: 5.91. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: resnet-v2-50Ryzen 7 5800X3DRyzen 7 5800XRyzen 9 5950X510152025SE +/- 0.02, N = 3SE +/- 0.07, N = 3SE +/- 0.05, N = 316.4116.6920.64MIN: 16.25 / MAX: 23.59MIN: 16.39 / MAX: 18.64MIN: 20.28 / MAX: 91.781. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

SVT-VP9

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

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080pRyzen 9 5950XRyzen 7 5800X3DRyzen 7 5800X50100150200250SE +/- 0.42, N = 3SE +/- 0.15, N = 9SE +/- 0.32, N = 3231.63209.41185.891. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

Zstd Compression

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

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19, Long Mode - Compression SpeedRyzen 9 5950XRyzen 7 5800X3DRyzen 7 5800X816243240SE +/- 0.03, N = 3SE +/- 0.06, N = 3SE +/- 0.12, N = 336.433.129.41. (CC) gcc options: -O3 -pthread -lz -llzma

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 6.0.9Test: GETRyzen 7 5800XRyzen 7 5800X3DRyzen 9 5950X900K1800K2700K3600K4500KSE +/- 26925.83, N = 3SE +/- 6782.61, N = 4SE +/- 32200.66, N = 144154420.253595604.383362059.001. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

AOM AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.3Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 1080pRyzen 7 5800X3DRyzen 7 5800XRyzen 9 5950X816243240SE +/- 0.07, N = 3SE +/- 0.06, N = 3SE +/- 0.15, N = 332.9130.2626.651. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

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 1080pRyzen 9 5950XRyzen 7 5800X3DRyzen 7 5800X20406080100SE +/- 0.38, N = 3SE +/- 0.50, N = 6SE +/- 0.58, N = 1585.9271.7470.011. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

AOM AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.3Encoder Mode: Speed 6 Realtime - Input: Bosphorus 4KRyzen 7 5800XRyzen 7 5800X3DRyzen 9 5950X3691215SE +/- 0.04, N = 3SE +/- 0.07, N = 3SE +/- 0.14, N = 1513.5813.4611.071. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

dav1d

Dav1d is an open-source, speedy AV1 video decoder. This test profile times how long it takes to decode sample AV1 video content. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is Betterdav1d 1.0Video Input: Summer Nature 4KRyzen 7 5800X3DRyzen 9 5950XRyzen 7 5800X60120180240300SE +/- 0.16, N = 4SE +/- 1.01, N = 3SE +/- 0.23, N = 3256.31212.23209.581. (CC) gcc options: -pthread -lm

libavif avifenc

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

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 10, LosslessRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D1.26792.53583.80375.07166.3395SE +/- 0.017, N = 3SE +/- 0.017, N = 3SE +/- 0.008, N = 74.6165.4185.6351. (CXX) g++ options: -O3 -fPIC -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 2.0.3Ryzen 7 5800X3DRyzen 9 5950XRyzen 7 5800X12002400360048006000SE +/- 59.46, N = 5SE +/- 22.25, N = 3SE +/- 13.51, N = 35573.965221.514611.921. (CXX) g++ options: -O3 -fopenmp -lm -lmpi_cxx -lmpi

ONNX Runtime

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

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: GPT-2 - Device: CPU - Executor: StandardRyzen 7 5800X3DRyzen 7 5800X2K4K6K8K10KSE +/- 105.46, N = 12SE +/- 100.84, N = 9819367951. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

NAS Parallel Benchmarks

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

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: FT.CRyzen 7 5800XRyzen 7 5800X3DRyzen 9 5950X3K6K9K12K15KSE +/- 54.83, N = 3SE +/- 25.70, N = 3SE +/- 13.07, N = 314083.7814014.6211684.801. (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 4.1.2

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 20210720Target: CPU - Model: alexnetRyzen 7 5800X3DRyzen 9 5950XRyzen 7 5800X3691215SE +/- 0.07, N = 3SE +/- 0.26, N = 3SE +/- 0.01, N = 159.6211.3911.47MIN: 9 / MAX: 11.09MIN: 10.97 / MAX: 12.4MIN: 11.26 / MAX: 12.551. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

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 - DegriddingRyzen 7 5800X3DRyzen 7 5800XRyzen 9 5950X30060090012001500SE +/- 0.53, N = 3SE +/- 1.05, N = 3SE +/- 1.69, N = 31601.941483.491355.501. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 1.0Test: tConvolve MT - GriddingRyzen 7 5800X3DRyzen 7 5800XRyzen 9 5950X2004006008001000SE +/- 3.26, N = 3SE +/- 0.46, N = 3SE +/- 1.35, N = 3929.97856.82787.381. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

OpenCV

This is a benchmark of the OpenCV (Computer Vision) library's built-in performance tests. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenCV 4.5.4Test: Features 2DRyzen 7 5800X3DRyzen 7 5800XRyzen 9 5950X20K40K60K80K100KSE +/- 496.53, N = 3SE +/- 1150.95, N = 3SE +/- 633.61, N = 38019481481945201. (CXX) g++ options: -fPIC -fsigned-char -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -msse -msse2 -msse3 -fvisibility=hidden -O3 -shared

Mobile Neural Network

MNN is the Mobile Neural Network as a highly efficient, lightweight deep learning framework developed by Alibaba. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: inception-v3Ryzen 7 5800XRyzen 7 5800X3DRyzen 9 5950X612182430SE +/- 0.05, N = 3SE +/- 0.07, N = 3SE +/- 0.40, N = 322.8423.3326.80MIN: 22.6 / MAX: 30.23MIN: 23.08 / MAX: 37.4MIN: 25.64 / MAX: 34.731. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -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: CG.CRyzen 7 5800X3DRyzen 9 5950XRyzen 7 5800X2K4K6K8K10KSE +/- 2.58, N = 3SE +/- 7.54, N = 3SE +/- 2.02, N = 37861.407099.316704.121. (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 4.1.2

LuaRadio

LuaRadio is a lightweight software-defined radio (SDR) framework built atop LuaJIT. LuaRadio provides a suite of source, sink, and processing blocks, with a simple API for defining flow graphs, running flow graphs, creating blocks, and creating data types. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterLuaRadio 0.9.1Test: Five Back to Back FIR FiltersRyzen 7 5800XRyzen 7 5800X3DRyzen 9 5950X400800120016002000SE +/- 3.67, N = 3SE +/- 22.52, N = 3SE +/- 2.52, N = 31942.61850.01666.5

SVT-AV1

This is a benchmark of the SVT-AV1 open-source video encoder/decoder. SVT-AV1 was originally developed by Intel as part of their Open Visual Cloud / Scalable Video Technology (SVT). Development of SVT-AV1 has since moved to the Alliance for Open Media as part of upstream AV1 development. SVT-AV1 is a CPU-based multi-threaded video encoder for the AV1 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.9Encoder Mode: Preset 12 - Input: Bosphorus 4KRyzen 9 5950XRyzen 7 5800X3DRyzen 7 5800X306090120150SE +/- 0.65, N = 3SE +/- 0.23, N = 7SE +/- 0.30, N = 3114.56108.4598.571. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie

Google Draco

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

OpenBenchmarking.orgms, Fewer Is BetterGoogle Draco 1.5.0Model: LionRyzen 7 5800X3DRyzen 7 5800XRyzen 9 5950X9001800270036004500SE +/- 2.68, N = 8SE +/- 3.00, N = 3SE +/- 14.50, N = 33517395540631. (CXX) g++ options: -O3

GIMP

GIMP is an open-source image manipulaton program. This test profile will use the system-provided GIMP program otherwise on Windows relys upon a pre-packaged Windows binary from upstream GIMP.org. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.30Test: unsharp-maskRyzen 7 5800XRyzen 7 5800X3DRyzen 9 5950X48121620SE +/- 0.01, N = 3SE +/- 0.02, N = 4SE +/- 0.04, N = 313.5913.7715.69

Test: unsharp-mask

Epyc 7702-retest: The test quit with a non-zero exit status. E: ./gimp: 26: gimp: not found

OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.30Test: resizeRyzen 7 5800XRyzen 7 5800X3DRyzen 9 5950X48121620SE +/- 0.15, N = 4SE +/- 0.13, N = 4SE +/- 0.12, N = 812.1712.6314.03

Test: resize

Epyc 7702-retest: The test quit with a non-zero exit status. E: ./gimp: 26: gimp: not found

SVT-AV1

This is a benchmark of the SVT-AV1 open-source video encoder/decoder. SVT-AV1 was originally developed by Intel as part of their Open Visual Cloud / Scalable Video Technology (SVT). Development of SVT-AV1 has since moved to the Alliance for Open Media as part of upstream AV1 development. SVT-AV1 is a CPU-based multi-threaded video encoder for the AV1 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.9Encoder Mode: Preset 12 - Input: Bosphorus 1080pRyzen 7 5800X3DRyzen 9 5950XRyzen 7 5800X110220330440550SE +/- 1.11, N = 12SE +/- 2.21, N = 3SE +/- 1.82, N = 3528.84526.77460.831. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie

ASTC Encoder

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

OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 3.2Preset: MediumRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D0.85841.71682.57523.43364.292SE +/- 0.0225, N = 3SE +/- 0.0078, N = 3SE +/- 0.0023, N = 83.32543.69393.81511. (CXX) g++ options: -O3 -flto -pthread

GEGL

GEGL is the Generic Graphics Library and is the library/framework used by GIMP and other applications like GNOME Photos. This test profile times how long it takes to complete various GEGL operations on a static set of sample JPEG images. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: Tile GlassRyzen 7 5800XRyzen 7 5800X3DRyzen 9 5950X612182430SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 321.2822.4224.25

Operation: Tile Glass

Epyc 7702-retest: The test quit with a non-zero exit status. E: ./gegl: 4: gegl: not found

OpenCV

This is a benchmark of the OpenCV (Computer Vision) library's built-in performance tests. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenCV 4.5.4Test: Object DetectionRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D10K20K30K40K50KSE +/- 694.11, N = 12SE +/- 366.22, N = 15SE +/- 491.40, N = 154230845918479411. (CXX) g++ options: -fPIC -fsigned-char -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -msse -msse2 -msse3 -fvisibility=hidden -O3 -shared

GraphicsMagick

This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample 6000x4000 pixel JPEG image. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: HWB Color SpaceRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D2004006008001000SE +/- 2.91, N = 3SE +/- 0.33, N = 3SE +/- 4.51, N = 310089328961. (CC) gcc options: -fopenmp -O2 -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lxml2 -lz -lm -lpthread

GEGL

GEGL is the Generic Graphics Library and is the library/framework used by GIMP and other applications like GNOME Photos. This test profile times how long it takes to complete various GEGL operations on a static set of sample JPEG images. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: CartoonRyzen 7 5800XRyzen 7 5800X3DRyzen 9 5950X20406080100SE +/- 0.05, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 372.9776.3481.67

Operation: Cartoon

Epyc 7702-retest: The test quit with a non-zero exit status. E: ./gegl: 4: gegl: not found

Ngspice

Ngspice is an open-source SPICE circuit simulator. Ngspice was originally based on the Berkeley SPICE electronic circuit simulator. Ngspice supports basic threading using OpenMP. This test profile is making use of the ISCAS 85 benchmark circuits. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterNgspice 34Circuit: C2670Ryzen 7 5800X3DRyzen 7 5800XRyzen 9 5950X306090120150SE +/- 0.16, N = 3SE +/- 0.23, N = 3SE +/- 0.07, N = 3102.73102.85114.401. (CC) gcc options: -O0 -fopenmp -lm -lstdc++ -lfftw3 -lXaw -lXmu -lXt -lXext -lX11 -lXft -lfontconfig -lXrender -lfreetype -lSM -lICE

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 1.2Ryzen 7 5800X3DRyzen 7 5800XRyzen 9 5950X50M100M150M200M250MSE +/- 88227.74, N = 3SE +/- 309195.65, N = 3SE +/- 51710.48, N = 32337981332252099332099973001. (CC) gcc options: -lparcsr_ls -lparcsr_mv -lseq_mv -lIJ_mv -lkrylov -lHYPRE_utilities -lm -fopenmp -lmpi

Zstd Compression

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

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 3, Long Mode - Compression SpeedRyzen 7 5800X3DRyzen 7 5800XRyzen 9 5950X2004006008001000SE +/- 2.20, N = 3SE +/- 8.19, N = 3SE +/- 11.64, N = 31008.8985.8907.71. (CC) gcc options: -O3 -pthread -lz -llzma

GEGL

GEGL is the Generic Graphics Library and is the library/framework used by GIMP and other applications like GNOME Photos. This test profile times how long it takes to complete various GEGL operations on a static set of sample JPEG images. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: AntialiasRyzen 7 5800XRyzen 7 5800X3DRyzen 9 5950X714212835SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 327.2628.7930.25

Operation: Antialias

Epyc 7702-retest: The test quit with a non-zero exit status. E: ./gegl: 4: gegl: not found

GIMP

GIMP is an open-source image manipulaton program. This test profile will use the system-provided GIMP program otherwise on Windows relys upon a pre-packaged Windows binary from upstream GIMP.org. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.30Test: auto-levelsRyzen 7 5800XRyzen 7 5800X3DRyzen 9 5950X3691215SE +/- 0.02, N = 3SE +/- 0.02, N = 4SE +/- 0.01, N = 311.8012.1613.02

Test: auto-levels

Epyc 7702-retest: The test quit with a non-zero exit status. E: ./gimp: 26: gimp: not found

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 7 5800X3DRyzen 9 5950XRyzen 7 5800X70140210280350SE +/- 0.26, N = 3SE +/- 0.26, N = 3SE +/- 0.36, N = 3295.49302.38324.621. (CC) gcc options: -shared -fwrapv -O2 -lxc -lblas -lmpi

Selenium

OpenBenchmarking.orgScore, Fewer Is BetterSeleniumBenchmark: PSPDFKit WASM - Browser: Google ChromeRyzen 7 5800XRyzen 7 5800X3DRyzen 9 5950X7001400210028003500SE +/- 5.36, N = 3SE +/- 17.67, N = 3SE +/- 22.19, N = 32783282230541. chrome 100.0.4896.127

AOM AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.3Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 4KRyzen 9 5950XRyzen 7 5800X3DRyzen 7 5800X3691215SE +/- 0.06, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 312.2811.5211.221. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

Darktable

Darktable is an open-source photography / workflow application this will use any system-installed Darktable program or on Windows will automatically download the pre-built binary from the project. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 3.8.1Test: Masskrug - Acceleration: CPU-onlyRyzen 7 5800X3DRyzen 9 5950XRyzen 7 5800X1.19992.39983.59974.79965.9995SE +/- 0.004, N = 7SE +/- 0.003, N = 3SE +/- 0.005, N = 34.8775.0275.333

Test: Masskrug - Acceleration: CPU-only

Epyc 7702-retest: The test quit with a non-zero exit status. E: ./darktable: 5: darktable-cli: not found

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 3.8.1Test: Server Room - Acceleration: CPU-onlyRyzen 7 5800X3DRyzen 7 5800XRyzen 9 5950X1.08022.16043.24064.32085.401SE +/- 0.005, N = 7SE +/- 0.009, N = 3SE +/- 0.003, N = 34.3914.5104.801

Test: Server Room - Acceleration: CPU-only

Epyc 7702-retest: The test quit with a non-zero exit status. E: ./darktable: 5: darktable-cli: not found

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPURyzen 7 5800X3DRyzen 7 5800XRyzen 9 5950X6001200180024003000SE +/- 6.84, N = 3SE +/- 5.85, N = 3SE +/- 11.16, N = 32721.402800.552966.02MIN: 2698.96MIN: 2780.99MIN: 2931.471. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl

Ngspice

Ngspice is an open-source SPICE circuit simulator. Ngspice was originally based on the Berkeley SPICE electronic circuit simulator. Ngspice supports basic threading using OpenMP. This test profile is making use of the ISCAS 85 benchmark circuits. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterNgspice 34Circuit: C7552Ryzen 7 5800X3DRyzen 9 5950XRyzen 7 5800X20406080100SE +/- 0.05, N = 3SE +/- 0.93, N = 3SE +/- 0.12, N = 377.1079.3184.021. (CC) gcc options: -O0 -fopenmp -lm -lstdc++ -lfftw3 -lXaw -lXmu -lXt -lXext -lX11 -lXft -lfontconfig -lXrender -lfreetype -lSM -lICE

VP9 libvpx Encoding

This is a standard video encoding performance test of Google's libvpx library and the vpxenc command for the VP9 video format. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.10.0Speed: Speed 5 - Input: Bosphorus 4KRyzen 7 5800X3DRyzen 7 5800XRyzen 9 5950X612182430SE +/- 0.21, N = 3SE +/- 0.10, N = 3SE +/- 0.16, N = 324.3123.6022.351. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPURyzen 7 5800X3DRyzen 7 5800XRyzen 9 5950X6001200180024003000SE +/- 4.12, N = 3SE +/- 6.39, N = 3SE +/- 9.02, N = 32734.372807.742971.54MIN: 2717.38MIN: 2789.56MIN: 2944.831. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl

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.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100, LosslessRyzen 7 5800XRyzen 9 5950XRyzen 7 5800X3D48121620SE +/- 0.05, N = 3SE +/- 0.13, N = 6SE +/- 0.01, N = 413.0813.1614.171. (CC) gcc options: -fvisibility=hidden -O2 -lm -ljpeg -lpng16 -ltiff

InfluxDB

This is a benchmark of the InfluxDB open-source time-series database optimized for fast, high-availability storage for IoT and other use-cases. The InfluxDB test profile makes use of InfluxDB Inch for facilitating the benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgval/sec, More Is BetterInfluxDB 1.8.2Concurrent Streams: 64 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000Ryzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D400K800K1200K1600K2000KSE +/- 5310.01, N = 3SE +/- 339.60, N = 3SE +/- 4181.25, N = 31850267.01757043.31709606.9

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPURyzen 7 5800X3DRyzen 7 5800XRyzen 9 5950X6001200180024003000SE +/- 2.65, N = 3SE +/- 1.50, N = 3SE +/- 1.23, N = 32735.692812.702960.05MIN: 2721.54MIN: 2802.04MIN: 2940.71. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl

Darktable

Darktable is an open-source photography / workflow application this will use any system-installed Darktable program or on Windows will automatically download the pre-built binary from the project. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 3.8.1Test: Boat - Acceleration: CPU-onlyRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D1.09762.19523.29284.39045.488SE +/- 0.013, N = 3SE +/- 0.006, N = 3SE +/- 0.004, N = 74.5264.8364.878

Test: Boat - Acceleration: CPU-only

Epyc 7702-retest: The test quit with a non-zero exit status. E: ./darktable: 5: darktable-cli: not found

AOM AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.3Encoder Mode: Speed 6 Realtime - Input: Bosphorus 1080pRyzen 7 5800XRyzen 7 5800X3DRyzen 9 5950X3691215SE +/- 0.09, N = 3SE +/- 0.06, N = 3SE +/- 0.03, N = 310.8910.6010.111. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

InfluxDB

This is a benchmark of the InfluxDB open-source time-series database optimized for fast, high-availability storage for IoT and other use-cases. The InfluxDB test profile makes use of InfluxDB Inch for facilitating the benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgval/sec, More Is BetterInfluxDB 1.8.2Concurrent Streams: 4 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000Ryzen 7 5800XRyzen 7 5800X3DRyzen 9 5950X400K800K1200K1600K2000KSE +/- 2583.53, N = 3SE +/- 1731.08, N = 3SE +/- 4060.22, N = 31644844.71565473.91528176.3

Zstd Compression

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

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 8 - Decompression SpeedRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D10002000300040005000SE +/- 23.10, N = 3SE +/- 11.87, N = 15SE +/- 26.65, N = 34845.24749.64519.71. (CC) gcc options: -O3 -pthread -lz -llzma

VP9 libvpx Encoding

This is a standard video encoding performance test of Google's libvpx library and the vpxenc command for the VP9 video format. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.10.0Speed: Speed 5 - Input: Bosphorus 1080pRyzen 7 5800XRyzen 7 5800X3DRyzen 9 5950X1020304050SE +/- 0.12, N = 3SE +/- 0.02, N = 4SE +/- 0.14, N = 341.8541.3239.131. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11

GEGL

GEGL is the Generic Graphics Library and is the library/framework used by GIMP and other applications like GNOME Photos. This test profile times how long it takes to complete various GEGL operations on a static set of sample JPEG images. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: Wavelet BlurRyzen 7 5800XRyzen 7 5800X3DRyzen 9 5950X1020304050SE +/- 0.07, N = 3SE +/- 0.01, N = 3SE +/- 0.62, N = 343.3345.5246.28

Operation: Wavelet Blur

Epyc 7702-retest: The test quit with a non-zero exit status. E: ./gegl: 4: gegl: not found

ONNX Runtime

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

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: yolov4 - Device: CPU - Executor: StandardRyzen 7 5800X3DRyzen 7 5800X90180270360450SE +/- 0.60, N = 3SE +/- 1.80, N = 34243971. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

Chia Blockchain VDF

Chia is a blockchain and smart transaction platform based on proofs of space and time rather than proofs of work with other cryptocurrencies. This test profile is benchmarking the CPU performance for Chia VDF performance using the Chia VDF benchmark. The Chia VDF is for the Chia Verifiable Delay Function (Proof of Time). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIPS, More Is BetterChia Blockchain VDF 1.0.1Test: Square Plain C++Ryzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D50K100K150K200K250KSE +/- 1049.34, N = 3SE +/- 351.19, N = 3SE +/- 264.58, N = 32166672129002029001. (CXX) g++ options: -flto -no-pie -lgmpxx -lgmp -lboost_system -pthread

GEGL

GEGL is the Generic Graphics Library and is the library/framework used by GIMP and other applications like GNOME Photos. This test profile times how long it takes to complete various GEGL operations on a static set of sample JPEG images. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: Rotate 90 DegreesRyzen 7 5800XRyzen 7 5800X3DRyzen 9 5950X918273645SE +/- 0.11, N = 3SE +/- 0.04, N = 3SE +/- 0.23, N = 334.7936.8237.15

Operation: Rotate 90 Degrees

Epyc 7702-retest: The test quit with a non-zero exit status. E: ./gegl: 4: gegl: not found

Darktable

Darktable is an open-source photography / workflow application this will use any system-installed Darktable program or on Windows will automatically download the pre-built binary from the project. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 3.8.1Test: Server Rack - Acceleration: CPU-onlyRyzen 7 5800X3DRyzen 9 5950XRyzen 7 5800X0.04880.09760.14640.19520.244SE +/- 0.001, N = 13SE +/- 0.001, N = 3SE +/- 0.002, N = 30.2040.2160.217

Test: Server Rack - Acceleration: CPU-only

Epyc 7702-retest: The test quit with a non-zero exit status. E: ./darktable: 5: darktable-cli: not found

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-TLSRyzen 7 5800XRyzen 9 5950XRyzen 7 5800X3D70K140K210K280K350KSE +/- 2197.04, N = 3SE +/- 1682.93, N = 3SE +/- 1346.67, N = 33260643202913065641. (CC) gcc options: -pedantic -O3

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.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100, Lossless, Highest CompressionRyzen 7 5800XRyzen 9 5950XRyzen 7 5800X3D714212835SE +/- 0.03, N = 3SE +/- 0.05, N = 3SE +/- 0.08, N = 327.5927.6229.321. (CC) gcc options: -fvisibility=hidden -O2 -lm -ljpeg -lpng16 -ltiff

LuaRadio

LuaRadio is a lightweight software-defined radio (SDR) framework built atop LuaJIT. LuaRadio provides a suite of source, sink, and processing blocks, with a simple API for defining flow graphs, running flow graphs, creating blocks, and creating data types. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterLuaRadio 0.9.1Test: Complex PhaseRyzen 7 5800XRyzen 9 5950XRyzen 7 5800X3D2004006008001000SE +/- 4.96, N = 3SE +/- 2.42, N = 3SE +/- 2.13, N = 3810.9807.2763.7

OpenBenchmarking.orgMiB/s, More Is BetterLuaRadio 0.9.1Test: Hilbert TransformRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D306090120150SE +/- 0.66, N = 3SE +/- 0.37, N = 3SE +/- 0.10, N = 3129.0128.9121.6

FinanceBench

FinanceBench is a collection of financial program benchmarks with support for benchmarking on the GPU via OpenCL and CPU benchmarking with OpenMP. The FinanceBench test cases are focused on Black-Sholes-Merton Process with Analytic European Option engine, QMC (Sobol) Monte-Carlo method (Equity Option Example), Bonds Fixed-rate bond with flat forward curve, and Repo Securities repurchase agreement. FinanceBench was originally written by the Cavazos Lab at University of Delaware. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterFinanceBench 2016-07-25Benchmark: Repo OpenMPRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D6K12K18K24K30KSE +/- 68.83, N = 3SE +/- 74.27, N = 3SE +/- 385.48, N = 327120.8727436.2328746.901. (CXX) g++ options: -O3 -march=native -fopenmp

Radiance Benchmark

This is a benchmark of NREL Radiance, a synthetic imaging system that is open-source and developed by the Lawrence Berkeley National Laboratory in California. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRadiance Benchmark 5.0Test: SMP ParallelRyzen 7 5800XRyzen 9 5950XRyzen 7 5800X3D306090120150138.10139.62146.30

Selenium

OpenBenchmarking.orgms, Fewer Is BetterSeleniumBenchmark: WASM collisionDetection - Browser: Google ChromeRyzen 7 5800XRyzen 9 5950XRyzen 7 5800X3D60120180240300SE +/- 1.22, N = 3SE +/- 2.09, N = 3SE +/- 0.29, N = 3252.63253.13267.331. chrome 100.0.4896.127

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 1.21Ryzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D8001600240032004000SE +/- 27.66, N = 12SE +/- 28.52, N = 12SE +/- 25.48, N = 123624.53587.03425.61. (CXX) g++ options: -O3 -march=native -rdynamic

Google SynthMark

SynthMark is a cross platform tool for benchmarking CPU performance under a variety of real-time audio workloads. It uses a polyphonic synthesizer model to provide standardized tests for latency, jitter and computational throughput. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgVoices, More Is BetterGoogle SynthMark 20201109Test: VoiceMark_100Ryzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D2004006008001000SE +/- 3.07, N = 3SE +/- 1.36, N = 3SE +/- 0.37, N = 3959.69949.52907.131. (CXX) g++ options: -lm -lpthread -std=c++11 -Ofast

GEGL

GEGL is the Generic Graphics Library and is the library/framework used by GIMP and other applications like GNOME Photos. This test profile times how long it takes to complete various GEGL operations on a static set of sample JPEG images. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: Color EnhanceRyzen 7 5800XRyzen 9 5950XRyzen 7 5800X3D1020304050SE +/- 0.06, N = 3SE +/- 0.08, N = 3SE +/- 0.00, N = 340.4040.9242.72

Operation: Color Enhance

Epyc 7702-retest: The test quit with a non-zero exit status. E: ./gegl: 4: gegl: not found

srsRAN

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

OpenBenchmarking.orgeNb Mb/s, More Is BettersrsRAN 21.10Test: 4G PHY_DL_Test 100 PRB SISO 64-QAMRyzen 7 5800XRyzen 9 5950XRyzen 7 5800X3D110220330440550SE +/- 3.92, N = 3SE +/- 0.74, N = 3SE +/- 0.51, N = 4516.9512.6489.71. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lmbedcrypto -lconfig++ -lsctp -lbladeRF -lpthread -lm -lfftw3f

Liquid-DSP

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

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 8 - Buffer Length: 256 - Filter Length: 57Ryzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D120M240M360M480M600MSE +/- 693717.84, N = 3SE +/- 3152845.28, N = 3SE +/- 3064486.54, N = 35826466675742800005523566671. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

Zstd Compression

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

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 8, Long Mode - Decompression SpeedRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D11002200330044005500SE +/- 28.80, N = 3SE +/- 43.26, N = 3SE +/- 20.17, N = 35066.95020.04804.71. (CC) gcc options: -O3 -pthread -lz -llzma

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 TimeRyzen 9 5950XRyzen 7 5800X3DRyzen 7 5800X1122334455SE +/- 0.07, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 347.2548.9849.791. RawTherapee, version 5.8, command line.

Total Benchmark Time

Epyc 7702-retest: The test run did not produce a result.

dav1d

Dav1d is an open-source, speedy AV1 video decoder. This test profile times how long it takes to decode sample AV1 video content. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is Betterdav1d 1.0Video Input: Summer Nature 1080pRyzen 7 5800X3DRyzen 9 5950XRyzen 7 5800X2004006008001000SE +/- 0.60, N = 9SE +/- 8.52, N = 3SE +/- 2.75, N = 31051.701022.54998.341. (CC) gcc options: -pthread -lm

Selenium

OpenBenchmarking.orgms, Fewer Is BetterSeleniumBenchmark: Kraken - Browser: Google ChromeRyzen 7 5800XRyzen 9 5950XRyzen 7 5800X3D110220330440550SE +/- 1.37, N = 3SE +/- 3.35, N = 3SE +/- 1.10, N = 3479.8492.8504.61. chrome 100.0.4896.127

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.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: DefaultRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D0.26120.52240.78361.04481.306SE +/- 0.011, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 121.1041.1131.1611. (CC) gcc options: -fvisibility=hidden -O2 -lm -ljpeg -lpng16 -ltiff

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 6.0.9Test: SETRyzen 7 5800XRyzen 7 5800X3DRyzen 9 5950X600K1200K1800K2400K3000KSE +/- 25751.93, N = 3SE +/- 10148.30, N = 4SE +/- 28822.75, N = 152905516.002857092.312765545.481. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

srsRAN

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

OpenBenchmarking.orgeNb Mb/s, More Is BettersrsRAN 21.10Test: 4G PHY_DL_Test 100 PRB SISO 256-QAMRyzen 7 5800XRyzen 9 5950XRyzen 7 5800X3D120240360480600SE +/- 0.78, N = 3SE +/- 3.28, N = 3SE +/- 0.62, N = 4560.2558.6533.31. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lmbedcrypto -lconfig++ -lsctp -lbladeRF -lpthread -lm -lfftw3f

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.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100Ryzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D0.40930.81861.22791.63722.0465SE +/- 0.023, N = 3SE +/- 0.005, N = 3SE +/- 0.001, N = 111.7321.7421.8191. (CC) gcc options: -fvisibility=hidden -O2 -lm -ljpeg -lpng16 -ltiff

OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100, Highest CompressionRyzen 7 5800XRyzen 9 5950XRyzen 7 5800X3D1.26472.52943.79415.05886.3235SE +/- 0.025, N = 3SE +/- 0.025, N = 3SE +/- 0.008, N = 75.3575.4135.6211. (CC) gcc options: -fvisibility=hidden -O2 -lm -ljpeg -lpng16 -ltiff

srsRAN

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

OpenBenchmarking.orgeNb Mb/s, More Is BettersrsRAN 21.10Test: 5G PHY_DL_NR Test 52 PRB SISO 64-QAMRyzen 7 5800XRyzen 9 5950XRyzen 7 5800X3D4080120160200SE +/- 0.18, N = 3SE +/- 0.64, N = 3SE +/- 0.30, N = 4165.2163.6157.51. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lmbedcrypto -lconfig++ -lsctp -lbladeRF -lpthread -lm -lfftw3f

LuaRadio

LuaRadio is a lightweight software-defined radio (SDR) framework built atop LuaJIT. LuaRadio provides a suite of source, sink, and processing blocks, with a simple API for defining flow graphs, running flow graphs, creating blocks, and creating data types. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterLuaRadio 0.9.1Test: FM Deemphasis FilterRyzen 7 5800XRyzen 9 5950XRyzen 7 5800X3D100200300400500SE +/- 2.93, N = 3SE +/- 0.61, N = 3SE +/- 2.02, N = 3471.2469.3449.6

srsRAN

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

OpenBenchmarking.orgUE Mb/s, More Is BettersrsRAN 21.10Test: 5G PHY_DL_NR Test 52 PRB SISO 64-QAMRyzen 7 5800XRyzen 9 5950XRyzen 7 5800X3D20406080100SE +/- 0.15, N = 3SE +/- 0.10, N = 3SE +/- 0.13, N = 480.880.477.11. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lmbedcrypto -lconfig++ -lsctp -lbladeRF -lpthread -lm -lfftw3f

OpenBenchmarking.orgeNb Mb/s, More Is BettersrsRAN 21.10Test: 4G PHY_DL_Test 100 PRB MIMO 256-QAMRyzen 7 5800XRyzen 9 5950XRyzen 7 5800X3D120240360480600SE +/- 0.58, N = 3SE +/- 0.60, N = 3SE +/- 0.26, N = 3560.3555.6534.91. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lmbedcrypto -lconfig++ -lsctp -lbladeRF -lpthread -lm -lfftw3f

OpenBenchmarking.orgeNb Mb/s, More Is BettersrsRAN 21.10Test: 4G PHY_DL_Test 100 PRB MIMO 64-QAMRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D110220330440550SE +/- 2.05, N = 3SE +/- 1.13, N = 3SE +/- 0.25, N = 3512.9511.4489.81. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lmbedcrypto -lconfig++ -lsctp -lbladeRF -lpthread -lm -lfftw3f

OpenBenchmarking.orgSamples / Second, More Is BettersrsRAN 21.10Test: OFDM_TestRyzen 7 5800XRyzen 9 5950XRyzen 7 5800X3D40M80M120M160M200MSE +/- 1519137.18, N = 3SE +/- 1550037.38, N = 15SE +/- 1205892.94, N = 151731666671718066671655133331. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lmbedcrypto -lconfig++ -lsctp -lbladeRF -lpthread -lm -lfftw3f

OpenBenchmarking.orgUE Mb/s, More Is BettersrsRAN 21.10Test: 4G PHY_DL_Test 100 PRB SISO 64-QAMRyzen 7 5800XRyzen 9 5950XRyzen 7 5800X3D4080120160200SE +/- 0.81, N = 3SE +/- 1.07, N = 3SE +/- 0.61, N = 4185.9184.5177.71. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lmbedcrypto -lconfig++ -lsctp -lbladeRF -lpthread -lm -lfftw3f

Liquid-DSP

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

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 1 - Buffer Length: 256 - Filter Length: 57Ryzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D16M32M48M64M80MSE +/- 684551.19, N = 3SE +/- 723050.33, N = 3SE +/- 40370.51, N = 37659300075001333732593331. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

Zstd Compression

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

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19, Long Mode - Decompression SpeedRyzen 7 5800XRyzen 9 5950XRyzen 7 5800X3D9001800270036004500SE +/- 51.55, N = 3SE +/- 24.51, N = 3SE +/- 4.34, N = 34190.34156.44009.51. (CC) gcc options: -O3 -pthread -lz -llzma

srsRAN

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

OpenBenchmarking.orgUE Mb/s, More Is BettersrsRAN 21.10Test: 4G PHY_DL_Test 100 PRB SISO 256-QAMRyzen 7 5800XRyzen 9 5950XRyzen 7 5800X3D4080120160200SE +/- 1.19, N = 3SE +/- 1.13, N = 3SE +/- 0.46, N = 4193.9193.5185.61. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lmbedcrypto -lconfig++ -lsctp -lbladeRF -lpthread -lm -lfftw3f

LZ4 Compression

This test measures the time needed to compress/decompress a sample file (an Ubuntu ISO) using LZ4 compression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 3 - Compression SpeedRyzen 7 5800XRyzen 9 5950XRyzen 7 5800X3D1632486480SE +/- 0.47, N = 15SE +/- 0.64, N = 3SE +/- 0.81, N = 470.8070.0867.801. (CC) gcc options: -O3

srsRAN

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

OpenBenchmarking.orgUE Mb/s, More Is BettersrsRAN 21.10Test: 4G PHY_DL_Test 100 PRB MIMO 256-QAMRyzen 7 5800XRyzen 9 5950XRyzen 7 5800X3D4080120160200SE +/- 0.18, N = 3SE +/- 0.38, N = 3SE +/- 0.12, N = 3182.3182.2174.71. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lmbedcrypto -lconfig++ -lsctp -lbladeRF -lpthread -lm -lfftw3f

OpenBenchmarking.orgUE Mb/s, More Is BettersrsRAN 21.10Test: 4G PHY_DL_Test 100 PRB MIMO 64-QAMRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D4080120160200SE +/- 1.14, N = 3SE +/- 0.69, N = 3SE +/- 0.24, N = 3173.1171.2165.91. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lmbedcrypto -lconfig++ -lsctp -lbladeRF -lpthread -lm -lfftw3f

Liquid-DSP

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

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 4 - Buffer Length: 256 - Filter Length: 57Ryzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D60M120M180M240M300MSE +/- 494873.72, N = 3SE +/- 684178.34, N = 3SE +/- 1277197.45, N = 32980600002960200002861600001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

Selenium

OpenBenchmarking.orgms, Fewer Is BetterSeleniumBenchmark: WASM imageConvolute - Browser: Google ChromeRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D510152025SE +/- 0.16, N = 3SE +/- 0.14, N = 3SE +/- 0.04, N = 321.2621.4022.111. chrome 100.0.4896.127

Radiance Benchmark

This is a benchmark of NREL Radiance, a synthetic imaging system that is open-source and developed by the Lawrence Berkeley National Laboratory in California. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRadiance Benchmark 5.0Test: SerialRyzen 7 5800XRyzen 9 5950XRyzen 7 5800X3D100200300400500433.99435.70450.72

Selenium

OpenBenchmarking.orgRuns Per Minute, More Is BetterSeleniumBenchmark: Speedometer - Browser: Google ChromeRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D50100150200250SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.67, N = 32452432361. chrome 100.0.4896.127

Zstd Compression

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

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 3, Long Mode - Decompression SpeedRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D11002200330044005500SE +/- 32.87, N = 3SE +/- 26.25, N = 3SE +/- 21.72, N = 34903.44887.54732.41. (CC) gcc options: -O3 -pthread -lz -llzma

LZ4 Compression

This test measures the time needed to compress/decompress a sample file (an Ubuntu ISO) using LZ4 compression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 9 - Compression SpeedRyzen 7 5800XRyzen 9 5950XRyzen 7 5800X3D1530456075SE +/- 0.73, N = 5SE +/- 0.52, N = 10SE +/- 0.58, N = 868.4668.0266.121. (CC) gcc options: -O3

Liquid-DSP

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

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 2 - Buffer Length: 256 - Filter Length: 57Ryzen 7 5800XRyzen 9 5950XRyzen 7 5800X3D30M60M90M120M150MSE +/- 1210633.44, N = 3SE +/- 1256940.64, N = 8SE +/- 521738.55, N = 31502300001495762501453033331. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

Selenium

OpenBenchmarking.orgScore, More Is BetterSeleniumBenchmark: Jetstream 2 - Browser: Google ChromeRyzen 7 5800XRyzen 9 5950XRyzen 7 5800X3D50100150200250SE +/- 0.88, N = 3SE +/- 2.37, N = 3SE +/- 1.29, N = 3212.66210.38206.341. chrome 100.0.4896.127

GEGL

GEGL is the Generic Graphics Library and is the library/framework used by GIMP and other applications like GNOME Photos. This test profile times how long it takes to complete various GEGL operations on a static set of sample JPEG images. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: ReflectRyzen 7 5800X3DRyzen 7 5800XRyzen 9 5950X612182430SE +/- 0.15, N = 15SE +/- 0.26, N = 3SE +/- 0.04, N = 324.1424.1924.85

Operation: Reflect

Epyc 7702-retest: The test quit with a non-zero exit status. E: ./gegl: 4: gegl: not found

SQLite Speedtest

This is a benchmark of SQLite's speedtest1 benchmark program with an increased problem size of 1,000. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSQLite Speedtest 3.30Timed Time - Size 1,000Ryzen 7 5800XRyzen 9 5950XRyzen 7 5800X3D1020304050SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 342.3043.4343.521. (CC) gcc options: -O2 -lz

Zstd Compression

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

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19 - Decompression SpeedRyzen 7 5800XRyzen 9 5950XRyzen 7 5800X3D9001800270036004500SE +/- 33.78, N = 3SE +/- 4.19, N = 3SE +/- 5.78, N = 34145.54096.44036.61. (CC) gcc options: -O3 -pthread -lz -llzma

LZ4 Compression

This test measures the time needed to compress/decompress a sample file (an Ubuntu ISO) using LZ4 compression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 1 - Compression SpeedRyzen 7 5800XRyzen 9 5950XRyzen 7 5800X3D3K6K9K12K15KSE +/- 39.63, N = 3SE +/- 31.84, N = 3SE +/- 90.23, N = 312299.3912138.7212002.311. (CC) gcc options: -O3

FinanceBench

FinanceBench is a collection of financial program benchmarks with support for benchmarking on the GPU via OpenCL and CPU benchmarking with OpenMP. The FinanceBench test cases are focused on Black-Sholes-Merton Process with Analytic European Option engine, QMC (Sobol) Monte-Carlo method (Equity Option Example), Bonds Fixed-rate bond with flat forward curve, and Repo Securities repurchase agreement. FinanceBench was originally written by the Cavazos Lab at University of Delaware. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterFinanceBench 2016-07-25Benchmark: Bonds OpenMPRyzen 7 5800XRyzen 9 5950XRyzen 7 5800X3D9K18K27K36K45KSE +/- 122.13, N = 3SE +/- 310.73, N = 3SE +/- 72.38, N = 340833.9141209.8441821.021. (CXX) g++ options: -O3 -march=native -fopenmp

VP9 libvpx Encoding

This is a standard video encoding performance test of Google's libvpx library and the vpxenc command for the VP9 video format. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.10.0Speed: Speed 0 - Input: Bosphorus 1080pRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D510152025SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.08, N = 318.3318.2617.901. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11

LZ4 Compression

This test measures the time needed to compress/decompress a sample file (an Ubuntu ISO) using LZ4 compression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 9 - Decompression SpeedRyzen 7 5800XRyzen 9 5950XRyzen 7 5800X3D3K6K9K12K15KSE +/- 14.40, N = 5SE +/- 14.44, N = 10SE +/- 17.41, N = 813316.113218.813029.11. (CC) gcc options: -O3

VP9 libvpx Encoding

This is a standard video encoding performance test of Google's libvpx library and the vpxenc command for the VP9 video format. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.10.0Speed: Speed 0 - Input: Bosphorus 4KRyzen 7 5800XRyzen 7 5800X3DRyzen 9 5950X3691215SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.10, N = 38.968.948.791. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11

LZ4 Compression

This test measures the time needed to compress/decompress a sample file (an Ubuntu ISO) using LZ4 compression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 3 - Decompression SpeedRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D3K6K9K12K15KSE +/- 50.92, N = 3SE +/- 9.86, N = 15SE +/- 25.51, N = 413267.513264.813023.01. (CC) gcc options: -O3

Selenium

OpenBenchmarking.orgRuns / Minute, More Is BetterSeleniumBenchmark: StyleBench - Browser: Google ChromeRyzen 7 5800X3DRyzen 9 5950XRyzen 7 5800X1326395265SE +/- 0.12, N = 3SE +/- 0.21, N = 3SE +/- 0.25, N = 358.757.957.71. chrome 100.0.4896.127

GIMP

GIMP is an open-source image manipulaton program. This test profile will use the system-provided GIMP program otherwise on Windows relys upon a pre-packaged Windows binary from upstream GIMP.org. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.30Test: rotateRyzen 7 5800XRyzen 9 5950XRyzen 7 5800X3D3691215SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 411.6511.8411.84

Test: rotate

Epyc 7702-retest: The test quit with a non-zero exit status. E: ./gimp: 26: gimp: not found

LZ4 Compression

This test measures the time needed to compress/decompress a sample file (an Ubuntu ISO) using LZ4 compression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 1 - Decompression SpeedRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D3K6K9K12K15KSE +/- 7.33, N = 3SE +/- 17.97, N = 3SE +/- 30.81, N = 313608.713559.613467.01. (CC) gcc options: -O3

GraphicsMagick

This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample 6000x4000 pixel JPEG image. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: RotateRyzen 7 5800XRyzen 7 5800X3DRyzen 9 5950X2004006008001000SE +/- 6.17, N = 3SE +/- 9.71, N = 3SE +/- 4.91, N = 31033102910281. (CC) gcc options: -fopenmp -O2 -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lxml2 -lz -lm -lpthread

CPU Temperature Monitor

OpenBenchmarking.orgCelsiusCPU Temperature MonitorPhoronix Test Suite System MonitoringRyzen 7 5800X3D20406080100Min: 28.63 / Avg: 77.48 / Max: 91.75

ONNX Runtime

MinAvgMaxRyzen 7 5800X3D51.090.591.8OpenBenchmarking.orgCelsius, Fewer Is BetterONNX Runtime 1.11CPU Temperature Monitor20406080100

OpenBenchmarking.orgCelsius, Fewer Is BetterONNX Runtime 1.11CPU Temperature MonitorRyzen 7 5800X3D20406080100Min: 50.63 / Avg: 90.13 / Max: 91

MinAvgMaxRyzen 7 5800X3D48.090.491.8OpenBenchmarking.orgCelsius, Fewer Is BetterONNX Runtime 1.11CPU Temperature Monitor20406080100

Natron

MinAvgMaxRyzen 7 5800X3D42.083.490.8OpenBenchmarking.orgCelsius, Fewer Is BetterNatron 2.4CPU Temperature Monitor20406080100

NCNN

MinAvgMaxRyzen 7 5800X3D48.473.483.0OpenBenchmarking.orgCelsius, Fewer Is BetterNCNN 20210720CPU Temperature Monitor20406080100

GEGL

MinAvgMaxRyzen 7 5800X3D40.164.472.1OpenBenchmarking.orgCelsius, Fewer Is BetterGEGLCPU Temperature Monitor20406080100

TensorFlow Lite

MinAvgMaxRyzen 7 5800X3D49.088.590.8OpenBenchmarking.orgCelsius, Fewer Is BetterTensorFlow Lite 2020-08-23CPU Temperature Monitor20406080100

oneDNN

MinAvgMaxRyzen 7 5800X3D51.878.590.0OpenBenchmarking.orgCelsius, Fewer Is BetteroneDNN 2.6CPU Temperature Monitor20406080100

MinAvgMaxRyzen 7 5800X3D51.579.690.1OpenBenchmarking.orgCelsius, Fewer Is BetteroneDNN 2.6CPU Temperature Monitor20406080100

MinAvgMaxRyzen 7 5800X3D42.983.389.9OpenBenchmarking.orgCelsius, Fewer Is BetteroneDNN 2.6CPU Temperature Monitor20406080100

AOM AV1

MinAvgMaxRyzen 7 5800X3D39.859.166.9OpenBenchmarking.orgCelsius, Fewer Is BetterAOM AV1 3.3CPU Temperature Monitor20406080100

MinAvgMaxRyzen 7 5800X3D41.960.468.3OpenBenchmarking.orgCelsius, Fewer Is BetterAOM AV1 3.3CPU Temperature Monitor20406080100

MinAvgMaxRyzen 7 5800X3D43.868.176.1OpenBenchmarking.orgCelsius, Fewer Is BetterAOM AV1 3.3CPU Temperature Monitor20406080100

MinAvgMaxRyzen 7 5800X3D45.570.576.9OpenBenchmarking.orgCelsius, Fewer Is BetterAOM AV1 3.3CPU Temperature Monitor20406080100

MinAvgMaxRyzen 7 5800X3D49.075.080.4OpenBenchmarking.orgCelsius, Fewer Is BetterAOM AV1 3.3CPU Temperature Monitor20406080100

NAMD

MinAvgMaxRyzen 7 5800X3D44.188.190.4OpenBenchmarking.orgCelsius, Fewer Is BetterNAMD 2.14CPU Temperature Monitor20406080100

Rodinia

MinAvgMaxRyzen 7 5800X3D50.675.082.3OpenBenchmarking.orgCelsius, Fewer Is BetterRodinia 3.1CPU Temperature Monitor20406080100

ONNX Runtime

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

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: ArcFace ResNet-100 - Device: CPU - Executor: StandardRyzen 7 5800X3DRyzen 7 5800X400800120016002000SE +/- 2.78, N = 3SE +/- 61.04, N = 12191412601. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: fcn-resnet101-11 - Device: CPU - Executor: StandardRyzen 7 5800X3DRyzen 7 5800X20406080100SE +/- 4.66, N = 10SE +/- 0.17, N = 3100561. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: bertsquad-12 - Device: CPU - Executor: StandardRyzen 7 5800X3DRyzen 7 5800X2004006008001000SE +/- 11.93, N = 4SE +/- 52.77, N = 129877341. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

Natron

Natron is an open-source, cross-platform compositing software for visual effects (VFX) and motion graphics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterNatron 2.4Input: SpaceshipRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D0.74251.4852.22752.973.7125SE +/- 0.10, N = 15SE +/- 0.03, N = 3SE +/- 0.03, N = 53.33.33.2

Input: Spaceship

Epyc 7702-retest: The test quit with a non-zero exit status. E: Natron-2.4.0-Linux-64-no-installer/bin/Natron: error while loading shared libraries: libGLU.so.1: cannot open shared object file: No such file or directory

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 20210720Target: CPU - Model: regnety_400mRyzen 7 5800X3DRyzen 7 5800XRyzen 9 5950X3691215SE +/- 0.01, N = 3SE +/- 0.08, N = 15SE +/- 0.05, N = 35.165.199.62MIN: 5.1 / MAX: 6.39MIN: 4.96 / MAX: 106.17MIN: 9.43 / MAX: 10.161. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: squeezenet_ssdRyzen 7 5800X3DRyzen 9 5950XRyzen 7 5800X48121620SE +/- 0.01, N = 3SE +/- 0.07, N = 3SE +/- 0.82, N = 1512.4014.9115.88MIN: 12.08 / MAX: 19.53MIN: 14.14 / MAX: 17.25MIN: 14.39 / MAX: 132.751. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: resnet50Ryzen 7 5800X3DRyzen 7 5800XRyzen 9 5950X612182430SE +/- 0.01, N = 3SE +/- 0.34, N = 15SE +/- 0.06, N = 317.9519.7024.53MIN: 17.8 / MAX: 19.64MIN: 18.91 / MAX: 131.81MIN: 24.23 / MAX: 25.11. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

GEGL

GEGL is the Generic Graphics Library and is the library/framework used by GIMP and other applications like GNOME Photos. This test profile times how long it takes to complete various GEGL operations on a static set of sample JPEG images. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: ScaleRyzen 7 5800XRyzen 7 5800X3DRyzen 9 5950X246810SE +/- 0.018, N = 3SE +/- 0.010, N = 7SE +/- 0.121, N = 155.3015.5376.797

Operation: Scale

Epyc 7702-retest: The test quit with a non-zero exit status. E: ./gegl: 4: gegl: not found

TensorFlow Lite

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

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: NASNet MobileRyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3DEpyc 7702Epyc 7702-retest40K80K120K160K200KSE +/- 18.44, N = 3SE +/- 310.20, N = 3SE +/- 322.16, N = 3SE +/- 8683.82, N = 12SE +/- 4535.02, N = 12101346135737140472175457187589

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPURyzen 7 5800XRyzen 7 5800X3DRyzen 9 5950X0.40520.81041.21561.62082.026SE +/- 0.000352, N = 3SE +/- 0.001055, N = 4SE +/- 0.163086, N = 150.8061400.8260851.800976MIN: 0.76MIN: 0.79MIN: 0.591. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPURyzen 7 5800X3DRyzen 9 5950XRyzen 7 5800X0.58221.16441.74662.32882.911SE +/- 0.001189, N = 4SE +/- 0.158158, N = 15SE +/- 0.000391, N = 31.0657101.4785602.587430MIN: 1.02MIN: 0.83MIN: 2.491. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPURyzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D246810SE +/- 0.16613, N = 15SE +/- 0.14031, N = 15SE +/- 0.13247, N = 124.684157.537197.67542MIN: 3.55MIN: 5.03MIN: 5.161. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl

AOM AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.3Encoder Mode: Speed 10 Realtime - Input: Bosphorus 1080pRyzen 7 5800X3DRyzen 7 5800XRyzen 9 5950X50100150200250SE +/- 2.73, N = 15SE +/- 3.15, N = 15SE +/- 1.43, N = 3211.35176.16159.361. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.3Encoder Mode: Speed 9 Realtime - Input: Bosphorus 1080pRyzen 7 5800X3DRyzen 7 5800XRyzen 9 5950X4080120160200SE +/- 3.52, N = 15SE +/- 1.78, N = 3SE +/- 2.63, N = 12203.04171.61147.951. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.3Encoder Mode: Speed 10 Realtime - Input: Bosphorus 4KRyzen 7 5800X3DRyzen 7 5800XRyzen 9 5950X20406080100SE +/- 2.22, N = 15SE +/- 1.44, N = 15SE +/- 1.77, N = 1274.7261.2756.891. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.3Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4KRyzen 7 5800X3DRyzen 9 5950XRyzen 7 5800X1632486480SE +/- 1.83, N = 15SE +/- 1.09, N = 14SE +/- 1.30, N = 1572.0556.1756.041. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.3Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4KRyzen 7 5800X3DRyzen 9 5950XRyzen 7 5800X1224364860SE +/- 0.32, N = 4SE +/- 0.69, N = 15SE +/- 0.55, N = 1555.3844.2642.551. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -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.orgdays/ns, Fewer Is BetterNAMD 2.14ATPase Simulation - 327,506 AtomsEpyc 7702-retestEpyc 7702Ryzen 9 5950XRyzen 7 5800XRyzen 7 5800X3D0.41760.83521.25281.67042.088SE +/- 0.02413, N = 15SE +/- 0.01734, N = 15SE +/- 0.00542, N = 3SE +/- 0.00255, N = 3SE +/- 0.00231, N = 30.761130.767381.106361.820011.85586

Rodinia

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

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP HotSpot3DRyzen 7 5800XRyzen 9 5950XRyzen 7 5800X3D1632486480SE +/- 0.71, N = 15SE +/- 1.03, N = 15SE +/- 0.97, N = 1565.8166.5170.141. (CXX) g++ options: -O2 -lOpenCL

303 Results Shown

ASKAP
Blender:
  Classroom - CPU-Only
  Pabellon Barcelona - CPU-Only
  BMW27 - CPU-Only
  Fishy Cat - CPU-Only
OpenCV
Blender
KTX-Software toktx
oneDNN
OSPray:
  particle_volume/scivis/real_time
  gravity_spheres_volume/dim_512/pathtracer/real_time
  gravity_spheres_volume/dim_512/ao/real_time
ASKAP
TensorFlow Lite
Appleseed
TensorFlow Lite
ASKAP
Zstd Compression
TensorFlow Lite
Mobile Neural Network
TensorFlow Lite:
  SqueezeNet
  Mobilenet Float
OpenFOAM
KTX-Software toktx
NCNN:
  CPU - shufflenet-v2
  CPU-v2-v2 - mobilenet-v2
  CPU-v3-v3 - mobilenet-v3
ACES DGEMM
NAS Parallel Benchmarks
NCNN
Appleseed
OSPray Studio:
  2 - 1080p - 32 - Path Tracer
  1 - 1080p - 32 - Path Tracer
Java JMH
Mobile Neural Network
ASKAP
NAS Parallel Benchmarks
N-Queens
toyBrot Fractal Generator
m-queens
OpenSSL
toyBrot Fractal Generator
OpenSSL
Rodinia
toyBrot Fractal Generator
GraphicsMagick
Numpy Benchmark
toyBrot Fractal Generator
GraphicsMagick
OpenSSL
OSPray Studio:
  1 - 1080p - 1 - Path Tracer
  2 - 1080p - 1 - Path Tracer
  3 - 1080p - 1 - Path Tracer
  2 - 1080p - 16 - Path Tracer
  1 - 1080p - 16 - Path Tracer
  3 - 1080p - 16 - Path Tracer
Stargate Digital Audio Workstation
LeelaChessZero
Stockfish
KTX-Software toktx
Facebook RocksDB
ASTC Encoder
Stargate Digital Audio Workstation
NCNN
Stargate Digital Audio Workstation
IndigoBench
OSPray Studio
x265
Stargate Digital Audio Workstation
GraphicsMagick
Embree
IndigoBench
NCNN
Embree
Rodinia
x264
LeelaChessZero
NCNN
Facebook RocksDB
SVT-HEVC
POV-Ray
Mobile Neural Network
KTX-Software toktx
Embree
PHPBench
oneDNN
GraphicsMagick
NCNN
Embree
oneDNN
Liquid-DSP
libavif avifenc
Appleseed
Timed MPlayer Compilation
ONNX Runtime
Rodinia
Mobile Neural Network
GraphicsMagick
oneDNN
dav1d
Coremark
SVT-HEVC
Timed LLVM Compilation
oneDNN:
  Deconvolution Batch shapes_3d - u8s8f32 - CPU
  IP Shapes 1D - u8s8f32 - CPU
SVT-AV1
OSPray
ASKAP
SVT-AV1
Timed LLVM Compilation
libavif avifenc
Timed Godot Game Engine Compilation
oneDNN
Rodinia
libavif avifenc
Zstd Compression
SVT-VP9
NCNN
PyBench
libavif avifenc
Java Gradle Build
SVT-AV1
dav1d
ASTC Encoder
Facebook RocksDB
AOM AV1
NCNN
Timed Mesa Compilation
KTX-Software toktx
Timed ImageMagick Compilation
oneDNN
SVT-AV1
oneDNN:
  Recurrent Neural Network Inference - f32 - CPU
  Recurrent Neural Network Inference - bf16bf16bf16 - CPU
Zstd Compression
NCNN
oneDNN
Timed Wasmer Compilation
Xcompact3d Incompact3d
rays1bench
oneDNN
GEGL
SVT-HEVC
Facebook RocksDB
OCRMyPDF
SVT-AV1:
  Preset 10 - Bosphorus 1080p
  Preset 4 - Bosphorus 1080p
Timed PHP Compilation
Zstd Compression
Google Draco
NAS Parallel Benchmarks
GROMACS
Chia Blockchain VDF
SVT-VP9
Mobile Neural Network:
  SqueezeNetV1.0
  resnet-v2-50
SVT-VP9
Zstd Compression
Redis
AOM AV1
x265
AOM AV1
dav1d
libavif avifenc
LULESH
ONNX Runtime
NAS Parallel Benchmarks
NCNN
ASKAP:
  tConvolve MT - Degridding
  tConvolve MT - Gridding
OpenCV
Mobile Neural Network
NAS Parallel Benchmarks
LuaRadio
SVT-AV1
Google Draco
GIMP:
  unsharp-mask
  resize
SVT-AV1
ASTC Encoder
GEGL
OpenCV
GraphicsMagick
GEGL
Ngspice
Algebraic Multi-Grid Benchmark
Zstd Compression
GEGL
GIMP
GPAW
Selenium
AOM AV1
Darktable:
  Masskrug - CPU-only
  Server Room - CPU-only
oneDNN
Ngspice
VP9 libvpx Encoding
oneDNN
WebP Image Encode
InfluxDB
oneDNN
Darktable
AOM AV1
InfluxDB
Zstd Compression
VP9 libvpx Encoding
GEGL
ONNX Runtime
Chia Blockchain VDF
GEGL
Darktable
SecureMark
WebP Image Encode
LuaRadio:
  Complex Phase
  Hilbert Transform
FinanceBench
Radiance Benchmark
Selenium
QuantLib
Google SynthMark
GEGL
srsRAN
Liquid-DSP
Zstd Compression
RawTherapee
dav1d
Selenium
WebP Image Encode
Redis
srsRAN
WebP Image Encode:
  Quality 100
  Quality 100, Highest Compression
srsRAN
LuaRadio
srsRAN:
  5G PHY_DL_NR Test 52 PRB SISO 64-QAM
  4G PHY_DL_Test 100 PRB MIMO 256-QAM
  4G PHY_DL_Test 100 PRB MIMO 64-QAM
  OFDM_Test
  4G PHY_DL_Test 100 PRB SISO 64-QAM
Liquid-DSP
Zstd Compression
srsRAN
LZ4 Compression
srsRAN:
  4G PHY_DL_Test 100 PRB MIMO 256-QAM
  4G PHY_DL_Test 100 PRB MIMO 64-QAM
Liquid-DSP
Selenium
Radiance Benchmark
Selenium
Zstd Compression
LZ4 Compression
Liquid-DSP
Selenium
GEGL
SQLite Speedtest
Zstd Compression
LZ4 Compression
FinanceBench
VP9 libvpx Encoding
LZ4 Compression
VP9 libvpx Encoding
LZ4 Compression
Selenium
GIMP
LZ4 Compression
GraphicsMagick
CPU Temperature Monitor:
  Phoronix Test Suite System Monitoring
  CPU Temp Monitor
  CPU Temp Monitor
  CPU Temp Monitor
  CPU Temp Monitor
  CPU Temp Monitor
  CPU Temp Monitor
  CPU Temp Monitor
  CPU Temp Monitor
  CPU Temp Monitor
  CPU Temp Monitor
  CPU Temp Monitor
  CPU Temp Monitor
  CPU Temp Monitor
  CPU Temp Monitor
  CPU Temp Monitor
  CPU Temp Monitor
  CPU Temp Monitor
ONNX Runtime:
  ArcFace ResNet-100 - CPU - Standard
  fcn-resnet101-11 - CPU - Standard
  bertsquad-12 - CPU - Standard
Natron
NCNN:
  CPU - regnety_400m
  CPU - squeezenet_ssd
  CPU - resnet50
GEGL
TensorFlow Lite
oneDNN:
  Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPU
  Matrix Multiply Batch Shapes Transformer - f32 - CPU
  Deconvolution Batch shapes_1d - f32 - CPU
AOM AV1:
  Speed 10 Realtime - Bosphorus 1080p
  Speed 9 Realtime - Bosphorus 1080p
  Speed 10 Realtime - Bosphorus 4K
  Speed 9 Realtime - Bosphorus 4K
  Speed 8 Realtime - Bosphorus 4K
NAMD
Rodinia